My Curriculum Vitae (CV): (pdf), (ps).
My Research Statement which summarizes my research goals and accomplishments: (pdf), (ps).

My current (and prior) research projects are summarized in the publications listed below. All publications are available for download. Any questions or comments are welcome. If you would like to collaborate on a research project, please contact me.

• Book Chapters
• Journal Articles
• Conference Papers
• Short Papers
• Symposia and Workshops
• Other Papers + Unrefereed Reports

Book Chapters and Monographs:

1. Mohan Sridharan. Integrated Knowledge-based Reasoning and Data-driven Learning for Explainable Agency in Robotics. In David Aha and Silvia Tulli (editors), Explainable Agency in Artificial Intelligence: Research and Practice, CRC Press, 2024.
   (pre-publication pdf) (official version)
2. Mohan Sridharan, Prashanth Devarakonda and Rashmica Gupta. Can I Do That? Discovering Domain Axioms Using Declarative Programming and Relational Reinforcement Learning. In Nardine Osman and Carles Sierra (editors), Visionary Papers of the Autonomous Agents and Multiagent Systems (AAMAS 2016) Workshops, pages 34-49 (196), Springer Lecture Notes in Artificial Intelligence (LNAI), 2016.
   (pre-publication pdf) (book website)
3. Mohan Sridharan. An Integrated Framework for Robust Human-Robot Interaction. In Jose Garcia-Rodriguez and Miguel Cazorla (editors), Robotic Vision: Technologies for Machine Learning and Vision Applications, pages 281-301 (535), IGI Global, 2013 (web: December 28, 2012).
   (pre-publication pdf) (book website)
4. Nick Hawes, Jeremy Wyatt, Mohan Sridharan, Henrik Jacobsson, Richard Dearden, Aaron Sloman and Geert-Jan Kruijff. Architecture and Representations. In Henrik I. Christensen, Geert-Jan M. Kruijff and Jeremy L. Wyatt (editors), Cognitive Systems, volume 8 of Cognitive Systems Monographs, pages 51-93, Springer Berlin Heidelberg, April 2010.
   (pre-publication pdf)
5. Nick Hawes, Jeremy Wyatt, Mohan Sridharan, Marek Kopicki, Somboon Hongeng, Ian Calvert, Aaron Sloman, Geert-Jan Kruijff, Henrik Jacobsson, Michael Brenner, Danijel Skocaj, Alen Vrecko, Nikodem Majer and Michael Zillich. The PlayMate System. In Henrik I. Christensen, Geert-Jan M. Kruijff and Jeremy L. Wyatt (editors), Cognitive Systems, volume 8 of Cognitive Systems Monographs, pages 367-393, Springer Berlin Heidelberg, April 2010.
   (pre-publication pdf)

Journal Articles:

1. Laura Ferrante, Mohan Sridharan, Claudio Zito, and Dario Farina. Toward Impedance Control in Human-Machine Interfaces for Upper-limb Prostheses. In the IEEE Transactions on Biomedical Engineering (TBME), 2024 (to appear).
   (official version) (pdf)
2. Jack Collins, Mark Robson, Jun Yamada, Mohan Sridharan, Karol Janik, and Ingmar Posner. RAMP: A Benchmark for Evaluating Robotics Assembly Manipulation and Planning. In Robotics and Automation Letters (RA-L), 9(1): 9-16, January 2024.
   (official version) (pdf) (arXiv)
3. Hasra Dodampegama and Mohan Sridharan. Knowledge-based Reasoning and Learning under Partial Observability in Ad Hoc Teamwork. In Theory and Practice of Logic Programming, 23(4):696-714, 2023.
   (official version) (pdf)
4. Mohan Sridharan and Tiago Mota. Towards Combining Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning. In Journal of Autonomous Agents and Multi-Agent Systems, 37(4), 2023.
   (official version) (pdf)
5. Shiqi Zhang and Mohan Sridharan. A Survey of Knowledge-based Sequential Decision Making under Uncertainty. In Artificial Intelligence Magazine, 43(2):249-266, 2022.
   (official version) (pdf)
6. Tiago Mota, Mohan Sridharan, and Ales Leonardis. Integrated Commonsense Reasoning and Deep Learning for Transparent Decision Making in Robotics. In Springer Nature Computer Science, 2(242), 2021.
   (official version) (pdf)
7. Daniele Meli, Mohan Sridharan, and Paolo Fiorini. Inductive learning of answer set programs for autonomous surgical task planning: Application to a training task for surgeons. In Machine Learning Journal, special issue on Learning and Reasoning, 110: 1739-1763, July 2021.
   (official version) (pdf)
8. Angel Daruna, Mehul Gupta, Mohan Sridharan, and Sonia Chernova. Continual Learning of Knowledge Graph Embeddings. In Robotics and Automation Letters (RA-L), 6(2): 1128-1135, April 2021.
   (official version) (pdf)
9. Rocio Gomez, Mohan Sridharan and Heather Riley. What do you really want to do? Towards a Theory of Intentions for Human-Robot Collaboration. In Annals of Mathematics and Artificial Intelligence, special issue on Commonsense Reasoning, 89(1): 179-208, February 2021.
   (official version) (pdf)
10. Rivindu Weerasekera, Mohan Sridharan and Prakash Ranjitkar. Implications of Spatio-temporal Data Aggregation on Short-term Traffic Prediction using Machine Learning Algorithms. In Journal of Advanced Transportation, Vol. 2020, Article ID: 7057519, 21 pages, 2020.
    (official version) (pdf)
11. Heather Riley and Mohan Sridharan. Integrating Non-monotonic Logical Reasoning and Inductive Learning With Deep Learning for Explainable Visual Question Answering. In Frontiers in Robotics and AI, special issue on Combining Symbolic Reasoning and Data-Driven Learning for Decision-Making, Volume 6, December 2019.
    (official version) (pdf)
12. Mohan Sridharan and Ben Meadows. Towards a Theory of Explanations for Human-Robot Collaboration. In Künstliche Intelligenz Journal, 33(4):331-342, December 2019.
    (official version) (pdf)
13. Mohan Sridharan, Michael Gelfond, Shiqi Zhang and Jeremy Wyatt. REBA: Refinement-based Architecture for Knowledge Representation and Reasoning in Robotics. In Journal of Artificial Intelligence Research, 65:87-180, May 2019.
    (official version) (pdf)
14. Mohan Sridharan and Ben Meadows. Knowledge Representation and Interactive Learning of Domain Knowledge for Human-Robot Interaction. In Advances in Cognitive Systems Journal, 7:77-96, December 2018.
    (official version) (pdf)
15. Ben Meadows, Mohan Sridharan and Zenon Colaco. Towards an Explanation Generation System for Robots: Analysis and Recommendations. In the Robotics Journal, 5(4):21, December 2016.
    (official version) (pdf)
16. Shiqi Zhang, Mohan Sridharan and Jeremy Wyatt. Mixed Logical Inference and Probabilistic Planning for Robots in Unreliable Worlds. In the IEEE Transactions on Robotics (T-RO), 31(3):699-713, June 2015.
    (official version) (pdf)
17. Daniel Holman, Mohan Sridharan, Prasanna Gowda, Dana Porter, Thomas Marek, Terry Howell and Jerry Moorhead. Gaussian Process Models for Reference ET Estimation from Alternative Meteorological Data Sources. In the Journal of Hydrology, 517: 28-35, September 2014.
    (official version) (pdf)
18. Shiqi Zhang, Mohan Sridharan and Christian Washington. Active Visual Planning for Mobile Robot Teams using Hierarchical POMDPs. In the IEEE Transactions on Robotics (T-RO), 29 (4): 975-985, August 2013.
    (official version) (pdf)
19. William Stone, Bartholomew Hogan, Christopher Flesher, Shilpa Gulati, Kristof Richmond, Aniket Murarka, Greg Kuhlmann, Mohan Sridharan, Victoria Siegel, Rachel Middleton Price, Peter Doran and John Priscu. Design and Deployment of a 4DOF Hovering AUV for Sub-Ice Exploration and Mapping. In the Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 224 (4): 341-361, 2010.
    (official version) (pdf)
20. Mohan Sridharan, Jeremy Wyatt and Richard Dearden. Planning to See: A Hierarchical Approach to Planning Visual Actions on a Robot using POMDPs. Artificial Intelligence Journal, 174 (11): 704-725, July 2010.
    (official version) (pdf)
21. Mohan Sridharan. Bootstrap Learning and Visual Processing Management on Mobile Robots. Advances in Artificial Intelligence (AAI) Special Issue on Artificial Intelligence in Neuroscience and Systems Biology: Lessons Learnt, Open Problems, and the Road Ahead, Vol 2010, Article ID 765876, 20 pages, (doi:10.1155/2010/765876) February 2010.
    (official version) (pdf)
22. Mohan Sridharan and Peter Stone. Color Learning and Illumination Invariance on Mobile Robots: A Survey. Robotics and Autonomous Systems (RAS), 57 (6-7): 629-644, June 2009.
    (official version) (pdf)
23. Mohan Sridharan and Peter Stone. Structure-Based Color Learning on a Mobile Robot under Changing Illumination. Autonomous Robots, 23(3): 161-182, October 2007.
    (official version) (pdf)
24. Mohan Sridharan and Peter Stone. Planning Actions to Enable Color Learning on a Mobile Robot. Information and Systems Sciences (ISS) Special Issue on Visual Information Processing, 3(3): 510-525, 2007.
    (pdf)
25. Peter Stone, Mohan Sridharan, Daniel Stronger, Gregory Kuhlmann, Nate Kohl, Peggy Fidelman and Nick Jong. From Pixels to Multi-Robot Decision-Making: A Study in Uncertainty. Robotics and Autonomous Systems (RAS) Special Issue on Planning Under Uncertainty in Robotics, 54(11): 933-943, November 2006.
    (official version) (pdf) (ps)

Refereed Conferences:

1. Raghav Arora, Shivam Singh, Karthik Swaminathan, Snehasis Banerjee, Brojeshwar Bhowmick, Krishna Murthy Jatavallabhula, Mohan Sridharan, and Madhava Krishna. Anticipate & Act: Integrating LLMs and Classical Planning for Efficient Task Execution in Household Environments. In the IEEE International Conference on Robotics and Automation (ICRA), Yokohoma, Japan, May 13-17, 2024. We describe a framework that leverages the generic knowledge of LLMs based on a small number of prompts to perform high-level task anticipation, using the anticipated tasks as goals in a classical planning system to compute a sequence of finer-granularity actions that jointly achieves these goals.
   (pdf) (project page with video and code)
2. Ayush Agrawal, Raghav Arora, Ahana Datta, Snehasis Banerjee, Brojeshwar Bhowmick, Krishna Murthy Jatavallabhula, Mohan Sridharan, and Madhava Krishna. CLIPGraphs: Multimodal Graph Networks to Infer Object-Room Affinities. In the IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Busan, Korea, August 28-31, 2023. We describe a framework that combines commonsense domain knowledge, data-driven methods, and recent advances in multimodal learning to learn object-room affinities based on embedded vision and language features toward scene rearrangement tasks.
   (pdf) (project page with video and code)
3. Hasra Dodampegama and Mohan Sridharan. Knowledge-based Reasoning and Learning under Partial Observability in Ad Hoc Teamwork. In the International Conference on Logic Programming (ICLP), London, UK, July 9-15, 2023. This paper extends our hybrid architecture for ad hoc teamwork, enabling the ad hoc agent to select and revise the models predicting the behavior of other agents, and to operate under partial observability.
   (pdf)
4. Nandiraju Gireesh, Ayush Agrawal, Ahana Datta, Snehasis Banerjee, Mohan Sridharan, Brojeshwar Bhowmick, and Madhava Krishna. Sequence-Agnostic Multi-Object Navigation. In the IEEE International Conference on Robotics and Automation (ICRA), London, UK, May 29-June 3, 2023. This paper formulates multi-object navigation, which requires a robot to localize an instance of each of a set of object classes, as a deep reinforcement learning problem.
   (pdf) (video demo)
5. Hasra Dodampegama and Mohan Sridharan. Back to the Future: Toward a Hybrid Architecture for Ad Hoc Teamwork. In the AAAI Conference on Artificial Intelligence (AAAI), Washington DC, USA, February 7-14, 2023. This paper describes an architecture for ad hoc teamwork that combines the principles of knowledge-based reasoning (specifically non-monotonic logical reasoning with commonsense knowledge) and ecological rationality (specifically heuristic methods for rapid learning and reasoning).
   (pdf) (AIhub blog)
6. Nandiraju Gireesh, D. A. Sasi Kiran, Snehasis Banerjee, Mohan Sridharan, Brojeshwar Bhowmick, and Madhava Krishna. Object Goal Navigation using Data Regularized Q-Learning. In the IEEE International Conference on Automation Science and Engineering (CASE), Mexico City, Mexico, August 20-24, 2022. This paper formulates object goal navigation as a deep reinforcement learning problem, and introduces new methods for data augmentation and Q-function regularization.
   (pdf) (project page with video and code)
7. D. A. Sasi Kiran, Kritika Anand, Chaitanya Kharyal, Gulshan Kumar, Nandiraju Gireesh, Snehasis Banerjee, Ruddra dev Roychoudhury, Mohan Sridharan, Brojeshwar Bhowmick, and Madhava Krishna. Spatial Relation Graph and Graph Convolutional Network for Object Goal Navigation. In the IEEE International Conference on Automation Science and Engineering (CASE), Mexico City, Mexico, August 20-24, 2022. This paper describes an approach for object goal navigation that learns and uses a spatial relational graph and a Graph Convolutional Network-based embeddings for estimating the likelihood of proximity of different (semantically-labeled) regions and the occurrence of different object classes in these regions..
   (pdf) (project page with video and code)
8. Mark Robson and Mohan Sridharan. A Keypoint-based Object Representation for Generating Task-specific Grasps. In the IEEE International Conference on Automation Science and Engineering (CASE), Mexico City, Mexico, August 20-24, 2022. This paper describes an approach for generating robot grasps by jointly considering safety and other task-specific constraints that are encoded in a three-level representation for each object class.
   (pdf)
9. Pat Langley and Mohan Sridharan. Scaling Challenges in Explanatory Reasoning. In the Annual Conference on Advances in Cognitive Systems (ACS), Online, November 15-18, 2021. This paper describes results of analytically and empirically exploring scaling challenges in explanatory reasoning; this exploration is performed in the context of the PENUMBRA architecture.
   (pdf)
10. Saif Sidhik, Mohan Sridharan, and Dirk Ruiken. Towards a Framework for Changing-Contact Robot Manipulation. In the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic, September 27-October 1, 2021. This paper describes an hybrid variable impedance framework with a transition-phase controller that enables smooth transitions as a robot manipulator makes or breaks contacts during changing-contact manipulation tasks.
    (pdf)
11. Tiago Mota and Mohan Sridharan. Answer me this: Constructing Disambiguation Queries for Explanation Generation in Robotics. In the International Conference on Development and Learning (ICDL), Beijing, China, August 23-26, 2021. This paper extends the earlier work on integrating commonsense reasoning and deep learning for transparency in decision making and learning, to also enable the robot to automatically construct queries that address ambiguities in the human queries.
    (pdf)
12. Keith Jones, Dennis Harris, Barbara Cherry, and Mohan Sridharan. A Qualitative Study of Caregiving in Support of Aging in Place to Inform Analyses of Caregivers’ Work and Design of Robot Caregivers. In the Advances in Human Factors and Ergonomics in Healthcare and Medical Devices (AHFE), New York, USA, July 25-29, 2021. Paper describes methodology to be followed to analyze caregivers' work towards design recommendations for robot caregivers.
    (pdf, official version)
13. Angel Daruna, Mehul Gupta, Mohan Sridharan, and Sonia Chernova. Continual Learning of Knowledge Graph Embeddings. In the International Conference of Robotics and Automation (ICRA), May 30-June 5, 2021. This paper is the conference presentation of the RA-L journal paper (above); it describes the reformulation of continual learning algorithms for knowledge graph embedding in robotics domains.
    (pdf)
14. Daniele Meli, Paolo Fiorini, and Mohan Sridharan. Towards Inductive Learning of Surgical Task Knowledge: A Preliminary Case Study of the Peg Transfer Task. In the International Conference on Knowledge-Based and Intelligent Information and Engineering Systems (KES), September 16-18, 2020. This paper describes the results of a case study on adapting an inductive learning algorithm and non-monotonic logical reasoning for a representative surgical training task.
    (pdf)
15. Saif Sidhik, Mohan Sridharan, and Dirk Ruiken. Learning Hybrid Models for Variable Impedance Control of Changing-Contact Manipulation Tasks. In the Annual Conference on Advances in Cognitive Systems (ACS), Palo Alto, USA, August 10-12, 2020. This paper describes an hybrid force-motion control framework with incrementally learned forward models for variable impedance control of changing-contact robot manipulation tasks.
    (pdf)
16. Heather Riley and Mohan Sridharan. Integrating Deep Learning and Non-monotonic Logical Reasoning for Explainable Visual Question Answering. In the European Conference on Multiagent Systems (EUMAS) (published papers track), Thessaloniki, Greece, July 13-15, 2020. This paper is a condensed version of the Frontiers 2019 special issue article; it describes an architecture that combines the principles of non-monotonic logical reasoning, inductive axiom learning, and deep learning, for reliable and efficient visual question answering and reasoning in robotics and computer vision.
    (pdf)
17. Rocio Gomez, Mohan Sridharan, and Heather Riley. Towards a Theory of Intentions for Human-Robot Collaboration. In the European Conference on Multiagent Systems (EUMAS) (published papers track), Thessaloniki, Greece, July 13-15, 2020. This paper is a condensed version of the AMAI 2020 article; it describes an architecture that combines an adaptive theory of intentions with earlier work on a refinement-based architecture, for reliable and efficient reasoning in robotics.
    (pdf)
18. Tiago Mota and Mohan Sridharan. Commonsense Reasoning and Deep Learning for Transparent Decision Making in Robotics. In the European Conference on Multiagent Systems (EUMAS), Thessaloniki, Greece, July 13-15, 2020. This paper describes an architecture that extends work described in the RSS 2019 paper; it describes an architecture that combines the principles of non-monotonic logical reasoning and deep learning, enabling a robot to provide relational descriptions as "explanations" of its decisions and beliefs.
    (pdf)
19. Michael Mathew, Saif Sidhik, Mohan Sridharan, Morteza Azad, Akinobu Hayashi, and Jeremy Wyatt. Online Learning of Feed-Forward Models for Task-Space Variable Impedance Control. In the International Conference on Humanoid Robots (Humanoids), Toronto, Canada, October 15-17, 2019. This paper describes an approach that uses the prediction errors in a learned forward model for a manipulation task to revise the model and modify the impedance parameters of a feedback controller during task execution; the approach also includes a hybrid force-motion controller to provide compliance in desired directions.
    (pdf)
20. Tiago Mota and Mohan Sridharan. Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning on Robots. In the Robotics Science and Systems Conference (RSS), Freiburg, Germany, June 22-26, 2019. Finalist for Best Paper Award and Finalist for Best Student Paper Award. This paper describes an architecture that combines the principles of non-monotonic logical reasoning (with commonsense knowledge) and inductive learning to guide the construction of deep networks from limited samples for scene understanding problems.
    (pdf)
21. Heather Riley and Mohan Sridharan. Non-monotonic Logical Reasoning and Deep Learning for Explainable Visual Question Answering. In the International Conference on Human Agent Interaction (HAI), Southampton, UK, December 15-18, 2018. This paper describes an architecture that combines the principles of non-monotonic logical reasoning, deep learning, and decision tree induction, to support intuitive explanations for classification output and answers to queries (in the context of visual question answering).
    (pdf)
22. Tiago Mota and Mohan Sridharan. Incrementally Grounding Expressions for Spatial Relations between Objects. In the International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, Sweden, July 13-19, 2018. This paper describes an architecture that combines the principles of interactive learning and declarative programming to incrementally learn and revise the grounding of spatial relations between objects in a scene.
    (pdf)
23. Mohan Sridharan and Ben Meadows.Learning Affordances for Social Robots. In the International Conference on Social Robotics (ICSR), Tsukuba, Japan, November 22-24, 2017. This paper describes an architecture that combines the principles of relational reinforcement learning and declarative programming to enable a robot to learn action capabilities ("affordances") using observations obtained through reactive execution or active exploration.
    (pdf)
24. Lars Kunze, Mohan Sridharan, Christos Dimitrakakis and Jeremy Wyatt. Adaptive Sampling-based View Planning under Time Constraints. In the IEEE European Conference on Mobile Robotics (ECMR), Paris, France, September 6-8, 2017. This paper describes an adaptive sampling-based algorithm for view planning on mobile robots, which poses planning with a constraint on planning time and execution time as an orienteering problem.
    (pdf)
25. Mohan Sridharan and Ben Meadows. A Combined Architecture for Discovering Affordances, Causal Laws, and Executability Conditions. In the International Conference on Advances in Cognitive Systems (ACS), Troy, USA, May 12-14, 2017. This paper describes an architecture that combines principles of non-monotonic logical reasoning and relational reinforcement learning to discover axioms corresponding to action capabilities (aka affordances), and the preconditions and effects of actions.
    (pdf)
26. Mohan Sridharan, Ben Meadows and Rocio Gomez. What can I not do? Towards an Architecture for Reasoning about and Learning Affordances. In the International Conference on Automated Planning and Scheduling (ICAPS), Pittsburgh, USA, June 18-23, 2017. This paper describes an architecture that builds on the principles of non-monotonic logical reasoning and relational reinforcement learning to represent, reason with, and learn action capabilities (aka affordances).
    (pdf)
27. Mohan Sridharan and Ben Meadows. Should I do that? Using Relational Reinforcement Learning and Declarative Programming to Discover Domain Axioms. In the IEEE International Conference on Developmental Learning and Epigenetic Robotics (ICDL-EpiRob), Paris, France, September 19-22, 2016. This paper describes an architecture that combines the capabilities of declarative programming and relational reinforcement learning for incremental and interactive discovery of domain axioms.
    (pdf)
28. Mohan Sridharan, Ben Meadows and Zenon Colaco. A Tale of Many Explanations: Towards An Explanation Generation System for Robots. In the Intelligent Robotics and Multiagent Systems (IRMAS) track of the ACM/SIGAPP Symposium on Applied Computing (SAC), Pisa, Italy, April 4-8, 2016. This paper compares the capabilities and limitations of a representative system from the two broad classes of explanation generation systems in robotics. The results of this study are used to provide insights and recommendations for developing an explanation generation system for robots.
    (pdf)
29. Zenon Colaco and Mohan Sridharan. What Happened and Why? A Mixed Architecture for Planning and Explanation Generation in Robotics. In the Australasian Conference on Robotics and Automation (ACRA), Canberra, Australia, December 2-4, 2015. This paper extends our previous (declarative programming + probabilistic sequential decision making) architecture by: (a) jointly explaining unexpected plan outcomes and partial scene descriptions; and (b) representing and reasoning at a finer resolution with declarative programming for more efficient probabilistic reasoning.
    (pdf)
30. Ranjini Swaminathan, Mohan Sridharan, Gill Dobbie and Katharine Hayhoe. Modeling Ice Storm Climatology. In the 28th Australasian Joint Conference on Artificial Intelligence (AI), Canberra, Australia, November 30-December 4, 2015. This paper describes a novel computational framework comprising classification and feature selection algorithms, which is used to model ice storm climatology.
    (pdf)
31. Batbold Myagmarjav and Mohan Sridharan. Incremental Knowledge Acquisition for Human-Robot Collaboration. In the 24th International Symposium on Robot and Human Interactive Communication (RO-MAN), Kobe, Japan, August 31-September 4, 2015. This paper describes an architecture that enables robots to incrementally acquire domain knowledge from non-expert humans by posing contextual queries that jointly maximize information gain, minimize ambiguity, and minimize human confusion.
    (pdf)
32. Sarah Rainge and Mohan Sridharan. Integrating Reinforcement Learning and Declarative Programming to Learn Causal Laws in Dynamic Domains. In the International Conference on Social Robotics (ICSR 2014), Sydney, Australia, October 27-29, 2014. This paper describes an architecture that uses declarative programming to represent and reason with incomplete domain knowledge, and uses reinforcement learning to incrementally discover the (previously unknown) causal laws describing the domain dynamics.
    (pdf)
33. Shiqi Zhang, Mohan Sridharan, Michael Gelfond and Jeremy Wyatt. Towards An Architecture for Knowledge Representation and Reasoning in Robotics. In the International Conference on Social Robotics (ICSR 2014), Sydney, Australia, October 27-29, 2014. This paper describes a two-layered architecture that enables robots to represent and reason with qualitative and quantitative descriptions of knowledge and uncertainty; it uses an action language for the system descriptions, allows histories with prioritized defaults, and executes tentative plans obtained by commonsense reasoning using probabilistic algorithms.
    (pdf)
34. Kimia Salmani and Mohan Sridharan. Multi-Instance Active Learning with Online Labeling for Object Recognition. In the 27th International Conference of the Florida AI Research Society (FLAIRS 2014), Pensacola Beach, USA, May 21-23, 2014. This paper presents an online multi-instance active learning algorithm for incremental learning of object models using visual cues and limited verbal feedback provided by non-expert human participants. (Best Paper Award)
    (pdf)
35. Xiang Li and Mohan Sridharan. Move and the Robot will Learn: Vision-based Autonomous Learning of Object Models. In the International Conference on Advanced Robotics (ICAR 2013), Montevideo, Uruguay, November 25-29, 2013. This paper presents an algorithm that exploits the complementary strengths of appearance-based and contextual visual cues to support incremental and automatic learning of object models from a small number of images.
    (pdf)
36. Daniel Holman, Mohan Sridharan, Prasanna Gowda, Dana Porter, Thomas Marek, Terry Howell and Jerry Moorhead. Estimating Reference Evapotranspiration for Irrigation Scheduling in the Texas High Plains. In the International Joint Conference on Artificial Intelligence (IJCAI 2013), Beijing, China, August 3-9, 2013. This paper describes the development and use of Gaussian process-based models for analyzing the effect of different weather parameters on reference Evapotranspiration (ET), thus accurately estimating ET for irrigation management in the Texas High plains.
    (pdf)
37. Shiqi Zhang, Mohan Sridharan and Forrest Sheng Bao. ASP+POMDP: Integrating Non-monotonic Logic Programming and Probabilistic Planning on Robots. In the International Conference on Development and Learning (ICDL-EpiRob 2012), San Diego, USA, November 7-9, 2012. This paper describes the integration of Answer Set Programming (for knowledge representation and non-monotonic reasoning) with hierarchical POMDPs (for visual sensing and information processing) on mobile robots. (Paper of Excellence Award)
    (pdf)
38. Shiqi Zhang and Mohan Sridharan. Active Visual Sensing and Collaboration on Mobile Robots using Hierarchical POMDPs. In the International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012), Valencia, Spain, June 4-8, 2012. This paper describes the use of hierarchical POMDPs for active visual search and multirobot collaboration. It also includes implementation based on the ROS framework and evaluation on physical robots.
    (pdf)
39. David South, Mary Shuman, Mohan Sridharan and Susan Urban. Integration of the Alice 3D Programming Environment with Robotics to Stimulate Interest in Computing. In the National Conference on Undergraduate Research (NCUR 2012), Ogden, Utah, March 29-31, 2012. This paper describes the development of a novel educational tool that integrates the Alice 3D (i.e., graphical) programming environment with autonomous wheeled robots to engage school students in computing. This work is based on research performed in Summer 2011 with support from an NSF REU Site project.
    (Student REU poster)
40. Mohan Sridharan. Augmented Reinforcement Learning for Interaction with Non-Expert Humans in Agent Domains. In the International Conference on Machine Learning Applications (ICMLA 2011), Honolulu, Hawaii, December 18-21, 2011. This paper describes an augmented reinforcement learning scheme that incorporates bootstrap learning within a modified reinforcement learning framework to enable robust combination of limited high-level human feedback with environmental feedback (based on sensory inputs) in multiagent simulated game domains.
    (pdf)
41. Barbara Millet, Mohan Sridharan and Yulin Wang. Using Eye Gaze and a Disambiguation Algorithm to Enter Words. In the International Conference on Occupational Ergonomics and Safety (ISOES 2011), Maryland, USA, June 9-10, 2011. This paper describes the use of eye-gaze for text entry and presents an algorithm for disambiguating between eye-swipe patterns. The disambiguation scheme is adapted from the robot vision algorithm described in the ICRA-11 paper.
    (pdf)
42. Xiang Li, Mohan Sridharan and Shiqi Zhang. Autonomous Learning of Vision-based Layered Object Models on Mobile Robots. In the International Conference on Robotics and Automation (ICRA 2011), Shanghai, China, May 9-13, 2011. This paper presents an approach that uses a variety of visual cues (color distributions, local image gradient features) to enable autonomous learning of object models on mobile robots. The learned models are used for recognition in subsequent frames.
    (pdf)
43. Shiqi Zhang, Mohan Sridharan and Xiang Li. To Look or Not to Look: A Hierarchical Representation for Visual Planning on Mobile Robots. In the International Conference on Robotics and Automation (ICRA 2011), Shanghai, China, May 9-13, 2011. This paper presents an approach that uses layered POMDPs for visual search on a mobile robot.
    (pdf)
44. Kshira Nadarajan and Mohan Sridharan. Sensor-based Online Detection of Instabilities for Robust Teamwork in Humanoid Soccer Robots. In the National Conference on Undergraduate Research (NCUR 2011), Ithaca, New York, Mar 31-April 2, 2011. For more information on the technical content of this work, look at the paper presented at the Humanoid Soccer Robots Workshop in December 2010.
    (pdf)
45. Xiang Li and Mohan Sridharan. Safe Navigation on a Mobile Robot using Local and Temporal Visual Cues. In the International Conference on Intelligent Autonomous Systems (IAS 2010), Ottawa, Canada, August 30-September 1, 2010. This paper presents an approach that combines local and temporal visual cues to enable safe navigation on mobile robots in indoor environments.
    (pdf)
46. Shilpa Gulati, Kristof Richmond, Christopher Flesher, Bart Hogan, Aniket Murarka, Gregory Kuhlmann, Mohan Sridharan and William Stone. Towards Autonomous Scientific Exploration of Ice-Covered Lakes: Field Experiments with ENDURANCE AUV in an Antarctic Dry Valley. In the IEEE International Conference on Robotics and Automation (ICRA 2010), Anchorage, USA, May 3-8, 2010. This paper is an overview of the mission conducted by Stone Aerospace in West Lake Bonney in Antarctica, where an autonomous underwater vehicle was used to conduct scientific experiments under the ice shelf.
    (pdf)
47. Mohan Sridharan and Xiang Li. Learning Sensor Models for Robust Information Fusion on a Humanoid Robot. In The IEEE-RAS International Conference on Humanoid Robots (ICHR 2009), Paris, France, December 7-10, 2009. This paper presents a strategy that enables a humanoid robot to autonomously model the expected error of different algorithms that process the information obtained from the different sensors. The learned models are then used to robustly fuse the information obtained from these sensors.
    (pdf) (Videos: 1, 2, 3)
48. Mohan Sridharan, Jeremy Wyatt and Richard Dearden. HiPPo: Hierarchical POMDPs for Planning Information Processing and Sensing Actions on a Robot. In The International Conference on Automated Planning and Scheduling (ICAPS 2008), Sydney, Australia, September 14-18, 2008. One of two papers to win a Distinguished Paper award. This paper presents our hierarchical POMDP planner for the joint planning of information processing and sensing actions. The hierarchical decomposition helps operate in real-time, while still exploiting the probabilistic framework of POMDPs to plan with non-deterministic visual operators. All algorithms are implemented and tested in the playmate scenario of the CoSy project.
    (pdf)
49. Aniket Murarka, Mohan Sridharan and Benjamin Kuipers. Detecting Obstacles and Drop-offs using Stereo and Motion Cues for Safe Local Motion. In The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2008), Nice, France, September 22-26, 2008. This paper presents joint work with Aniket Murarka on using both stereo segmentation algorithms and motion cues (extracted using monocular image data) to detect obstacles and drop-offs. The goal is to enable a robot wheelchair to navigate autonomously.
    (pdf)
50. Mohan Sridharan and Peter Stone. Long-term vs. Greedy Action Planning for Color Learning on a Mobile Robot. In the International Conference on Computer Vision Theory and Applications (VISAPP 2008), Funchal, Madeira-Portugal, January 22-25, 2008. This paper compares greedy/heuristic action selection for color learning on a mobile robot (see ICARCV-06 paper) with a more principled long-term planning approach that maximizes learning opportunities while minimizing localization errors over the action sequence. The action (and error) models are learned autonomously by the robot. See Robot Perception Workshop paper for an extended version.
    (pdf)
51. Mohan Sridharan and Peter Stone. Global Action Selection for Illumination Invariant Color Modeling.. In The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2007), San Diego, USA, October 29-November 2, 2007. This paper presents the combined vision system that performs color learning and illumination adaptation smoothly over a range of illuminations. The robot is able to perform color learning, and detect and adapt to both major and minor illumination changes, without human supervision.
    (pdf)
52. Mohan Sridharan and Peter Stone. Color Learning on a Mobile Robot: Towards Full Autonomy under Changing Illumination. In The International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, January 6-12, 2007. This paper describes an approach that enables a mobile robot to detect illumination changes autonomously and adapt by revising its color knowledge, using the structure inherent in its environment. It extends the planned color learning approach (see ICARCV-06 paper) to handle illumination changes.
    (pdf)
53. Mohan Sridharan and Peter Stone. Autonomous Planned Color Learning on a Mobile Robot Without Labeled Data. In The Ninth International Conference on Control, Automation, Robotics and Vision (ICARCV), Singapore, December 5-8, 2006. This paper describes the planned color learning algorithm that enables a mobile robot to use its knowledge of its environment to suitably plan its motion sequence and learn the desired colors autonomously. It extends the baseline color learning approach (see AAAI-05 paper), where the motion sequence had to be manually provided for each environmental configuration. In addition, it enables the robot to learn colors outside the constrained lab setting.
    (pdf)
54. Mohan Sridharan and Peter Stone. Real-Time Vision on a Mobile Robot Platform. In The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2005), Edmonton, Canada, August 2005. This paper presents the baseline vision system that performs color segmentation, object recognition and line detection in real-time on a mobile robot, and is robust to rapid camera motions. The paper also summarizes a supervised learning approach to detect transitions between known illumination conditions.
    Some videos referenced in the paper.
    (pdf)
55. Mohan Sridharan and Peter Stone. Autonomous Color Learning on a Mobile Robot. In The Twentieth National Conference on Artificial Intelligence (AAAI 2005), Pittsburgh, USA, July 2005. The basic color learning algorithm is described in this paper. The robot uses the structure inherent in its environment, i.e. known positions, shapes, sizes and colors of objects, to learn the desired colors autonomously. The corresponding motion sequence is provided by a human observer, a limitation that is later relaxed (ICARCV-06 paper).
    Some Images and Videos referenced in the paper.
    (pdf)
56. Mohan Sridharan,Gregory Kuhlmann, and Peter Stone. Practical Vision-Based Monte Carlo Localization on a Legged Robot. In IEEE International Conference on Robotics and Automation (ICRA 2005), Barcelona, Spain, April 2005. This paper elaborates on the features that we incorporated in a baseline Monte-Carlo localization algorithm to enable a mobile robot to achieve significant improvement in localization accuracy, in an adversarial environment where the landmarks are frequently occluded.
    (Abstract and Paper)
    
57. Mohan Sridharan and Peter Stone. Towards On-Board Color Constancy on Mobile Robots. In The First Canadian Conference on Computer Vision, London, Canada, May 17-19, 2004. This paper presents a supervised learning approach to detect transitions between known illumination conditions, on a mobile robot. The robot is also able to account for previously unseen illumination conditions.
    (pdf)

Refereed Short Papers/Extended Abstracts:

1. Mohan Sridharan. Toward A Cognitive Architecture for Robots. In the AI and ML Theme of the OR Society's Annual Conference (OR65), Bath, UK, September 12-14, 2023. Summary of architecture that combines the principles of iterative refinement and adaptive satisficing for reliable and efficient knowledge-based and data-driven reasoning, control, and learning on one or more robots working toward a common goal in a dynamic domain.
   (Talk Slides)
2. Tiago Mota, Mohan Sridharan, and Ales Leonardis. Extended Abstract: Non-monotonic Logical Reasoning and Deep Learning for Transparent Decision Making in Robotics. In the Recently Published Research track of the International Conference on Logic Programming (ICLP) and the International Conference on Principles of Knowledge Representation and Reasoning (KR), 2021, Online. Summary of the architecture that combines the principles of non-monotonic logical reasoning and deep learning for providing transparent descriptions of the robot's decisions and beliefs during reasoning and learning in robotics.
   (pdf1, pdf2)
3. Mohan Sridharan. Integrated Commonsense Reasoning and Interactive Learning in Robotics. In the Workshop on Integrating Planning and Learning (WIPL) and the Workshop on Declarative and Neurosymbolic Representations in Robot Learning and Control (DNR-ROB) at Robotics: Science and Systems Conference (R:SS), July 12 and 15, 2021, Online. Summary of the architecture that combines the principles of knowledge-based reasoning and datd-driven learning for explainable reasoning and learning in robotics.
   (pdf1, pdf2)
4. Mohan Sridharan, Michael Gelfond, Shiqi Zhang, and Jeremy Wyatt. REBA: Refinement-based Architecture for Knowledge Representation and Reasoning in Robotics. In the Recently Published Research track of the International Conference on Principles of Knowledge Representation and Reasoning (KR), September 12-18, 2020, Online. Also presented in the Journal Presentation track of the International Conference on Automated Planning and Scheduling. This is a short summary of the REBA architecture described in the JAIR 2019 journal article.
   (pdf)
5. Mohan Sridharan, Rocio Gomez, and Heather Riley. What do you really want to do? Towards a Theory of Intentions for Human-Robot Collaboration. In the Recently Published Research track of the International Conference on Principles of Knowledge Representation and Reasoning (KR), September 12-18, 2020, Online. This is a short summary of the adaptive theory of intentions architecture described in the AMAI journal article.
   (pdf)
6. Mohan Sridharan and Heather Riley. Integrating Non-monotonic Logical Reasoning and Inductive Learning with Deep Learning for Explainable Visual Question Answering. In the Recently Published Research track of the International Conference on Principles of Knowledge Representation and Reasoning (KR), September 12-18, 2020, Online. This is a short summary of the architecture described in the Frontiers 2019 journal article.
   (pdf)
7. Mohan Sridharan. REBA-KRL: Refinement-Based Architecture for Knowledge Representation, Explainable Reasoning, and Interactive Learning in Robotics. In the European Conference on Artificial Intelligence (ECAI), Santiago de Compostela, Spain, August 29-September 2, 2020. This paper is a summary of the refinement-based architecture for knowledge representation, explainable reasoning, and interactive learning in robotics.
   (pdf)
8. Mohan Sridharan. Refinement-Based Architecture for Knowledge Representation, Explainable Reasoning and Interactive Learning in Robotics. In the Workshop on Reasoning about Actions and Processes: Highlights of Recent Advances (RAP) at ICAPS-2019, Berkeley, USA, July 12, 2019. This paper is a brief summary of the refinement-based architecture for knowledge representation, explainable reasoning, and interactive learning in robotics.
   (pdf)
9. Michael Mathew, Saif Sidhik, Mohan Sridharan, Morteza Azad, Jeremy Wyatt, and Akinobu Hayashi. Online Learning of Feed-Forward Models for Variable Impedance Control in Manipulation Tasks. In the Workshop on Emerging paradigms for robotic manipulation: from the lab to the productive world (Emerging Paradigms) at the Robotics Science and Systems Conference (RSS), June 23, 2019, Freiburg, Germany. Best Poster Award. This paper describes an architecture that uses hybrid force-motion control and online learning of feed-forward models for variable impedance control of robot manipulation tasks.
   (pdf)
10. Keith Jones, Barbara Cherry, Dennis Harris and Mohan Sridharan. Formative Analysis of Aging in Place: Implications for the Design of Caregiver Robots. In the Human Factors and Ergonomics Society International Annual Meeting (HFES), Austin, USA, October 9-13, 2017. This paper presents initial results of a formative analysis of the needs of elders being assisted by caregivers, with the objective of identifying key results that will inform the design of caregiver robots of the future.
    (pdf)
11. Pat Langley, Ben Meadows, Mohan Sridharan and Dongkyu Choi. Explainable Agency for Intelligent Autonomous Systems. In the Twenty-Ninth Annual Conference on Innovative Applications of Artificial Intelligence (IAAI), San Francisco, USA, February 4-9, 2017. This paper formulates the problem of enabling an autonomous agent to explain its decisions and the reasoning used to examine the associated choices.
    (pdf)
12. Batbold Myagmarjav and Mohan Sridharan. Incremental Knowledge Acquisition with Selective Active Learning. In the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Istanbul, Turkey, May 4-8, 2015. This paper summarizes an architecture that enables robots to incrementally acquire domain knowledge from non-expert humans by posing contextual queries that maximize information gain, and minimize ambiguity and human confusion.
    (pdf)
13. Keith Jones, Barbara Cherry and Mohan Sridharan. Formative Work Analysis to Design Caregiver Robots. In the International Conference on Human-Robot Interaction (HRI), Portland, USA, March 2-5, 2015. This paper summarizes recent work in analyzing caregiving in elders' homes to create design recommendations for caregiving robots.
    (pdf)
14. Batbold Myagmarjav and Mohan Sridharan. Knowledge Acquisition with Selective Active Learning for Human-Robot Interaction. In the International Conference on Human-Robot Interaction (HRI), Portland, USA, March 2-5, 2015. This paper summarizes the initial version of an architecture for incrementally acquiring domain knowledge from humans by posing contextual queries that maximize information gain and minimize human confusion.
    (pdf)
15. Keith Jones, Mohan Sridharan and Barbara Cherry. Analyzing Elder Care to Guide the Design of Caregiver Robots. In the Social Robotics for Health Innovation Workshop (HI Workshop) at the International Conference on Social Robotics (ICSR), Sydney, Australia, October 27, 2014. This paper proposes a research methodology for analyzing elder care, using the corresponding knowledge to design robots that can assist caregivers.
    (pdf)
16. Xiang Li, Mohan Sridharan and Catherine Meador. Autonomous Learning of Visual Object Models on a Robot Using Context and Appearance Cues. In the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Saint Paul, USA, May 6-10, 2013. This paper describes an algorithm that enables mobile robots to autonomously learn object models using visual context and (local, global and temporal) appearance cues.
    (pdf)
17. Daniel Holman, Mohan Sridharan, Prasanna Gowda, Dana Porter, Thomas Marek, Terry Howell and Jerry Moorhead. Gaussian Processes-based Predictive Models to Estimate Reference ET from Alternative Meteorological Data Sources for Irrigation Scheduling. In the American Society of Agronomy: ASA, CSSA and SSSA International Annual Meeting (ACS 2012), Cincinnati, USA, October 21-24, 2012. This paper describes results of applying Gaussian Processes to predict reference ET measurements based on noisy meteorological measurements from weather stations. (Best Graduate Student Paper Award)
    
18. Shiqi Zhang, Forrest Sheng Bao and Mohan Sridharan. (Student abstract) Combining Probabilistic Planning and Logic Programming on Mobile Robots. In the International Conference on Artificial Intelligence (AAAI), Toronto, Canada, July 22-26, 2012. This short paper summarizes the integration of non-monotonic reasoning and hierarchical POMDPs for active visual sensing on mobile robots. For more details, look at ARMS-12 workshop paper.
    (pdf)

Refereed Symposia and Workshops:

1. Hasra Dodampegama and Mohan Sridharan. Explanation and Knowledge Acquisition in Ad Hoc Teamwork. In the International Symposium on Practical Aspects of Declarative Languages (PADL) at POPL, London, UK, January 15-16, 2024. This paper extends the previous architecture for ad hoc teamwork; it enables the ad hoc agent to provide relational descriptions in response to different types of questions, and incrementally learn and revise axioms governing domain dynamics.
   (pdf)
2. Mohan Sridharan. A Cognitive Architecture for Integrated Robot Systems. In the Workshop on Cognitive AI (CogAI) at IJCLR, Bari, Italy, November 13-15, 2023. This paper describes a robot architecture that supports knowledge-based and data-driven reasoning, control, learning, and collaboration; it combines principles of refinement, ecological rationality, and predictive models.
   (pdf)
3. Pat Langley, Edward Katz and Mohan Sridharan. A Unified Formalism for Embodied Agents. In the AAAI Fall Symposium on Unifying Representations for Robot Application Development (UR-RAD), Arlington, USA, October 25-27, 2023. This paper describes an architecture that seeks to unify representation and processes for reasoning and control .
   (pdf)
4. Hasra Dodampegama and Mohan Sridharan. Collaborate and Explain on the Fly: Nonmonotonic Logical Reasoning and Incremental Learning for Ad Hoc Teamwork. In the Workshop on Nonmonotonic Reasoning (NMR) at KR, Rhodes, Greece, September 2-4, 2023. This paper describes an extension of the previous architecture for ad hoc teamwork (in TPLP 2023) that enables the ad hoc agent to provide relational descriptions as explanations in response to different types of questions.
   (pdf)
5. Hasra Dodampegama and Mohan Sridharan. Back to the Future: Toward a Hybrid Architecture for Ad hoc Teamwork. In the Workshop on Safe and Trustworthy AI (STAI) at ICLP, London, UK, July 9, 2023. This paper describes the capabilities of an architecture for ad hoc teamwork that supports non-monotonic logical reasoning with prior domain knowledge and models learned rapidly to predict the behavior of the other agents .
   (pdf)
6. Laura Ferrante, Mohan Sridharan, Dario Farina, and Claudio Zito. Toward Adaptive Impedance Control of Upper-limb Prostheses. In the Workshop on Compliant Robot Manipulation at ICRA, London, UK, June 2, 2023. Also in Workshop on Emerging Paradigms for Assistive Robotic Manipulation} and Workshop on Neuromechanics Meet Deep Learning. This paper describes a framework for adaptive control of an upper-limb prosthesis that combines a human motor intent predictor and a variable impedance controller to provide the human users three degrees of control (kinematics, stiffness, damping) for each degree of freedom.
   (pdf)
7. Hasra Dodampegama and Mohan Sridharan. Coordination in Ad Hoc Teams using Knowledge-based Reasoning and Learning. In the Workshop on Coordination, Organizations, Institutions, Norms and Ethics for Governance of Multi-Agent Systems (COINE) at AAMAS, London, UK, May 29, 2023. The architecture described in this paper extends our previous architecture for ad hoc teamwork by supporting reasoning under partial observability and communication capabilities.
   (pdf)
8. Michalina Jakubczak, Mohan Sridharan, and Masoumeh Mansouri. Non-monotonic Logical Reasoning and Theory of Mind for Transparency in HRI. In the Workshop on Adaptive Social Interaction based on user~s Mental mOdels and behaVior in HRI (ASIMOV) at ICSR, Florence, Italy, December 13, 2022. This paper describes an architecture that supports non-monotonic logical reasoning with Theory of Mind models to enable transparency and user-specific explanatory descriptions in HRI.
   (pdf)
9. Hasra Dodampegama and Mohan Sridharan. Toward a Reasoning and Learning Architecture for Ad hoc Teamwork. In the AAAI Fall Symposium Series Workshop on AI for HRI (AI-HRI), Arlington, USA, November 17-19, 2022. This paper describes an architecture that combines the principles of non-monotonic logical reasoning, ecological rationality, and incremental learning, to enable a simulated agent to collaborate with others without prior coordination.
   (pdf)
10. Mohan Sridharan, Chloe Benz, Arthur Findelair and Kevin Gloaguen. There and Back Again: Combining Nonmonotonic Logical Reasoning and Deep Learning on an Assistive Robot. In the Workshop on Non-Monotonic Reasoning (NMR), Haifa, Israel, August 7-9, 2022. This paper describes an architecture that combines the principles of non-monotonic logical reasoning and deep learning in simulation and in the physical world in the context of an assistive robot in a restaurant scenario.
    (pdf)
11. Mohan Sridharan. Cognitive Adequacy: Insights from Developing Robot Architectures. In the Workshop on Cognitive Aspects of Knowledge Representation (CAKR) at IJCAI, Vienna, Austria, July 23, 2022. This paper summarizes insights about cognitive adequacy in the context of (assistive) robots by drawing on experience in developing cognitive architectures for robots .
    (pdf)
12. Mohan Sridharan. Towards an Integrated Architecture for Transparent Knowledge-based Reasoning and Data-driven Learning in Robotics. In the Workshop of the UK Planning and Scheduling Special Interest Group (UK PlanSIG), December 20, 2021, Online. Summary of different research strands combining knowledge-based reasoning and data-driven learning in robotics.
    (pdf)
13. Mohan Sridharan. Toward Explainable Reasoning and Learning in Robotics. In the Workshop on Explainable Logic-Based Knowledge Representation (XLoKR) at KR conference, November 2021, Online. Summary of work on architectures that promote transparency regarding the decisions and beliefs during reasoning and learning in robotics.
    (pdf)
14. Shiqi Zhang and Mohan Sridharan. Knowledge-based Sequential Decision Making under Uncertainty: A Survey. In the Workshop on Robust and Reliable Autonomy in the Wild (R2AW) at IJCAI, August 19-26, 2021, Online. An initial draft of the AI Magazine article providing a survey of methods for knowledge-based sequential decision-making under uncertainty.
    (pdf)
15. Tiago Mota and Mohan Sridharan. Non-monotonic Logical Reasoning Guiding Axiom Induction from Deep Networks for Transparent Decision Making in Robotics. In the Workshop on Planning and Robotics (PlanRob) at ICAPS, August 2-6, 2021, Online. This paper summarizes overall architecture that combines non-monotonic logical reasoning, probabilistic reasoning, and deep learning to provide transparent decision-making in robotics; also support construction of disambiguation queries.
    (pdf)
16. Saif Sidhik, Mohan Sridharan, and Dirk Ruiken. Towards a Framework for Changing-Contact Robot Manipulation. In the Workshop on Autonomous Robots and Multirobot Systems (ARMS) at AAMAS, May 3-7, 2021, Online. This paper presents an initial draft of the hybrid framework that supports smooth dynamics and control during changing-contact robot manipulation tasks; please see the IROS-2021 paper for more details>.
    (pdf)
17. Tiago Mota and Mohan Sridharan. Disambiguation Queries for Explanation Generation in Robotics. In the Workshop of the UK Planning & Scheduling Special Interest Group (UK PlanSIG), December 16, 2020, Online. This paper builds on an architecture combining non-monotonic logical reasoning and deep learning; it enables the robot/agent to construct suitable questions (to pose to humans) to remove ambiguity in the questions posed by a human.
    (pdf)
18. Tiago Mota and Mohan Sridharan. Axiom Learning and Belief Tracing for Transparent Decision Making in Robotics. In the AAAI Fall Symposium on Artificial Intelligence for Human-Robot Interaction: Trust and Explainability in Artificial Intelligence for Human-Robot Interaction (AI-HRI), November 13-14, 2020. This paper builds on an architecture combining non-monotonic logical reasoning and deep learning; it supports learning different types of axioms and tracing beliefs for providing relational descriptions of decisions and beliefs.
    (pdf)
19. Four papers accepted for presentation at the Workshop on the scientific foundations of Trustworthy AI, integrating learning, optimisation and reasoning (TAILOR) at the European Conference on Artificial Intelligence (ECAI), Santiago de Compostela, Spain, September 2020. These papers are condensed versions of the papers published at EUMAS 2020 (pdf), AMAI 2020 (pdf), Frontiers in Robotics and AI 2019 (pdf), and JAIR 2019 (pdf) respectively.


20. Heather Riley and Mohan Sridharan. Non-monotonic Logical Reasoning to Guide Deep Learning for Explainable Visual Question Answering. In the Workshop on Robust AI for Neurorobotics (RAI-NR), Edinburgh, UK, August 26-28, 2019. This paper describes an architecture that combines the principles of non-monotonic logical reasoning (with commonsense knowledge) and inductive learning to guide the construction of deep networks from limited samples for visual question answering problems.
    (pdf)
21. Tiago Mota and Mohan Sridharan. Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning for Scene Understanding. In the Workshop on Knowledge Engineering for Planning and Scheduling (KEPS) at the International Conference on Automated Planning and Scheduling (ICAPS), Berkeley, USA, July 11, 2019. This paper describes an architecture that combines the principles of non-monotonic logical reasoning (with commonsense knowledge) and inductive learning to guide the construction of deep networks from limited samples for scene understanding problems.
    (pdf)
22. Mohan Sridharan. Refinement-Based Architecture for Knowledge Representation, Explainable Reasoning, and Interactive Learning in Robotics. In the Workshop on Combining Learning and Reasoning: Towards Human-Level Robot Intelligence (Learn-Reason) at the Robotics Science and Systems Conference (RSS), June 22, 2019, Freiburg, Germany. This paper is a brief summary of the refinement-based architecture for knowledge representation, explainable reasoning, and interactive learning in robotics.
    (pdf)
23. Ermano Arruda, Claudio Zito, Mohan Sridharan, Marek Kopicki, and Jeremy Wyatt. Generative Grasp Synthesis from Demonstration using Parametric Mixtures. In the Workshop on Task-Informed Grasping: From Perception to Physical Interaction (TIG-II) at the Robotics Science and Systems Conference (RSS), June 22, 2019, Freiburg, Germany. This paper describes a generative, parametric approach for grasp synthesis.
    (pdf)
24. Michael Mathew, Saif Sidhik, Mohan Sridharan, Morteza Azad, Akinobu Hayashi, and Jeremy Wyatt. Online Learning of Feed-Forward Models for Variable Impedance Control in Manipulation Tasks. In the Workshop on Task-Informed Grasping: From Perception to Physical Interaction (TIG-II) at the Robotics Science and Systems Conference (RSS), June 22, 2019, Freiburg, Germany. his paper describes an architecture that uses hybrid force-motion control and online learning of feed-forward models for variable impedance control of robot manipulation tasks.
    (pdf)
25. Mohan Sridharan and Ben Meadows. Theory of Explanation for Human-Robot Collaboration. In the AAAI Spring Symposium on Story-Enabled Intelligence, Stanford, USA, March 25-27, 2019. This paper describes a theory of explanations and a cognitive architecture that implements this theory for human-robot collaboration.
    (pdf)
26. Mohan Sridharan and Ben Meadows. Knowledge Representation and Interactive Learning of Domain Knowledge for Human-Robot Interaction. In the Workshop on Integrated Planning, Acting and Execution (IntEx) at the International Conference on Automated Planning and Scheduling (ICAPS), Delft, The Netherlands, June 25, 2018. This paper describes the architecture that uses declarative logic programming, and interactive learning from active observations and reactive action execution, to discover actions and the corresponding axioms.
    (pdf)
27. Rocio Gomez, Mohan Sridharan and Heather Riley. Representing and Reasoning with Intentional Actions on a Robot. In the Workshop on Planning and Robotics (PlanRob) at the International Conference on Automated Planning and Scheduling (ICAPS), Delft, The Netherlands, June 26, 2018. This paper describes the architecture that combines a theory of intentions and a theory of refinement for robots; for any given goal, the robot computes a plan of intentional abstract actions and implements each abstract action as sequence of concrete actions at finer resolution, executing each concrete action using probabilistic models of uncertainty in sensing and actuation.
    (pdf)
28. Tiago Mota and Mohan Sridharan. Learning the Grounding of Expressions for Spatial Relations between Objects. In the Workshop on Perception, Inference and Learning for Joint Semantic, Geometric and Physical Understanding (MRP) at the International Conference on Robotics and Automation (ICRA), Brisbane, Australia, May 21, 2018. This paper describes an architecture that combines the principles of interactive learning and declarative programming to incrementally learn and revise the grounding of spatial relations between objects in a scene.
    (pdf)
29. Pat Langley, Mohan Sridharan, and Ben Meadows. Representation, Use, and Acquisition of Affordances in Cognitive Systems. In the AAAI Spring Symposium on Integrating Representation, Reasoning, Learning, and Execution for Goal Directed Autonomy, Stanford, USA, March 26-28, 2018. This paper proposes key postulates to be implemented in cognitive systems in order to represent, use (i.e., reason with), and learn knowledge of affordances.
    (pdf)
30. Mohan Sridharan and Ben Meadows. Towards an Architecture for Discovering Domain Dynamics: Affordances, Causal Laws, and Executability Conditions. In the Workshop on Planning and Robotics (PlanRob) at the International Conference on Automated Planning and Scheduling (ICAPS), Pittsburgh, USA, June 20, 2017. This paper describes the architecture that combines the complementary strengths of declarative programming and relational reinforcement learning to enable robots to discover axioms corresponding to action capabilities, and the preconditions and effects of actions.
    (pdf)
31. Lars Kunze, Mohan Sridharan, Christos Dimitrakakis and Jeremy Wyatt. View Planning with Time Constraints: An Adaptive Sampling Approach. In the Workshop on AI Planning and Robotics: Challenges and Methods (AIPlanRob) at the International Conference on Robotics and Automation (ICRA), Singapore, May 29, 2017. This paper describes a sampling-based stochastic view planner to search for a desired target object---the planner selects a set of views, and a route through them, in the presence of overlapping views and a constraint on the plan execution time.
    (pdf)
32. Mohan Sridharan. KR³L: An Architecture for Knowledge Representation, Reasoning and Learning in Human-Robot Collaboration. In the Workshop on Knowledge, Data, and Systems for Cognitive Computing (CogComp) at the International Joint Conference on Artificial Intelligence (IJCAI), New York City, USA, July 11, 2016. This paper summarizes an architecture that combines declarative programming, probabilistic graphical models and relational reinforcement learning for non-monotonic logical reasoning, probabilistic reasoning, and incremental and interactive discovery of domain axioms on robots.
    (pdf)
33. Mohan Sridharan and Michael Gelfond. Representing and Reasoning with Logical and Probabilistic Knowledge on Robots. In the Statistical Relational Learning Workshop (StaRAI) at the International Joint Conference on Artificial Intelligence (IJCAI), New York City, USA, July 11, 2016. This paper describes an architecture and the steps in the design of robots capable of non-monotonic logical reasoning and probabilistic reasoning.
    (pdf)
34. Mohan Sridharan and Michael Gelfond. Using Knowledge Representation and Reasoning Tools in the Design of Robots. In the Workshop on Knowledge-based Techniques for Problem Solving and Reasoning (KnowProS) at the International Joint Conference on Artificial Intelligence (IJCAI), New York City, USA, July 10, 2016. This paper reports our experience in the systematic design of a robot capable of representing and manipulating both logical and probabilistic knowledge, using knowledge representation and reasoning tools tailored towards different reasoning tasks.
    (pdf)
35. Mohan Sridharan, Prashanth Devarakonda and Rashmica Gupta. Discovering Domain Axioms Using Relational Reinforcement Learning and Declarative Programming. In the Planning and Robotics Workshop (PlanRob) at the International Conference on Automated Planning and Scheduling (ICAPS), London, UK, June 13-14, 2016. This paper describes initial work on an architecture that combines declarative programming and relational reinforcement learning for incremental and interactive discovery of domain axioms in simulated agent domains.
    (pdf)
36. Mohan Sridharan. Towards An Architecture for Knowledge Representation, Reasoning and Learning in Human-Robot Collaboration. In the AAAI Spring Symposium on Enabling Computing Research in Socially Intelligent Human-Robot Interaction, Stanford, USA, March 21-23, 2016. This paper summarizes the overall architecture for representing and reasoning with commonsense knowledge, and for learning previously unknown rules governing domain dynamics. This paper is a summary of previous papers on knowledge representation and reasoning, and learning, in recent years (e.g., TRO 2015, ACRA 2015, ICSR 2014a, and ICSR 2014b).
    (pdf)
37. Mohan Sridharan, Michael Gelfond, Shiqi Zhang and Jeremy Wyatt. Mixing Non-Monotonic Logical Reasoning and Probabilistic Planning for Robots. In the Hybrid Reasoning Workshop (HR 2015) at the International Joint Conference on Artificial Intelligence (IJCAI), Buenos Aires, Argentina, July 26, 2015. This paper describes the refinement-based architecture for knowledge representation and reasoning in robotics---it summarizes the relationship between a coarse-level qualitative transition diagram and a fine-resolution probabilistic transition diagram, and integrates the previous work meta-reasoning capabilities described in our TRO 2015 paper.
    (pdf)
38. Batbold Myagmarjav and Mohan Sridharan. Incremental Knowledge Acquisition for Human-Robot Collaboration. In the Autonomous Robots and Multirobot Systems Workshop (ARMS 2015) at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Istanbul, Turkey, May 4, 2015. This paper describes an architecture that enables robots to incrementally acquire domain knowledge by posing contextual queries that maximize information gain, minimize ambiguity, and minimize human confusion.
    (pdf)
39. Shiqi Zhang, Mohan Sridharan, Michael Gelfond and Jeremy Wyatt. KR³: An Architecture for Knowledge Representation and Reasoning in Robotics. In the International Workshop on Non-Monotonic Reasoning (NMR 2014), Vienna, Austria, July 17-19, 2014. This paper presents a knowledge representation and reasoning architecture for robots that utilizes the complementary strengths of declarative programming and probabilistic graphical models to represent, reason with, and learn from, qualitative and quantitative descriptions of knowledge and uncertainty.
    (CoRR version)
40. Emilie Featherston, Mohan Sridharan, Susan Urban and Joseph Urban. DOROTHY: Enhancing Bidirectional Communication between a 3D Programming Interface and Mobile Robots. In the Fifth Symposium on Educational Advances in Artificial Intelligence (EAAI 2014), Quebec City, Canada, July 28-29, 2014. This paper describes more recent enhancements in the bidirectional communication and multirobot collaboration capabilities of DOROTHY, an educational tool that integrates the Alice 3D programming environment with autonomous robots to teach computing skills to middle school and high school students.
    (pdf)
41. Shiqi Zhang, Mohan Sridharan, Michael Gelfond and Jeremy Wyatt. Integrating Probabilistic Graphical Models and Declarative Programming for Knowledge Representation and Reasoning in Robotics. In the Planning and Robotics Workshop (PlanRob 2014) at the International Conference on Automated Planning and Scheduling (ICAPS), Portsmouth, USA, June 22-23, 2014. This architecture integrates the complementary strengths of declarative programming and probabilistic graphical models to represent, reason with, and learn from, qualitative and quantitative descriptions of knowledge and uncertainty.
    (pdf)
42. Shiqi Zhang and Mohan Sridharan. Combining Answer Set Programming and POMDPs for Knowledge Representation and Reasoning in Robotics. In the Knowledge Representation and Reasoning in Robotics Workshop (KRR 2013) at the International Conference on Logic Programming (ICLP), Istanbul, Turkey, August 25, 2013. This paper presents a knowledge representation and reasoning architecture for robots, enabling robots to incrementally revise, represent and reason with qualitative and quantitative descriptions of uncertainty and incomplete domain knowledge. We address key limitations of the architecture reported in the ICDL 2012 paper.
    (pdf)
43. David South, Mary Shuman, Kevin Thomas, Austin Ray, Stephanie Graham, Shiloh Huff, Sabyne Peeler, Sarah Rainge, Mohan Sridharan, Susan Urban and Joseph Urban. DOROTHY: Integrating Graphical Programming with Robotics to Stimulate Interest in Computing Careers. In the Alice Symposium, Durham, USA, June 19, 2013. This paper describes our novel educational tool (DOROTHY) that integrates the Alice 3D programming environment with autonomous robots---the tool is designed to stimulate interest in middle school and high school students about computing careers.
    (pdf)
44. Xiang Li, Mohan Sridharan and Catie Meador. Learning Object Models on a Robot using Visual Context and Appearance Cues. In the Autonomous Robots and Multirobot Systems Workshop (ARMS 2013) at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Saint Paul, USA, May 7, 2013. This paper describes an algorithm that enables a mobile robot to autonomously learn object models using local. global, temporal and contextual visual cues.
    (pdf)
45. Mohan Sridharan. Integrating Visual Learning and Hierarchical Planning for Autonomy in Human-Robot Collaboration. In the AAAI Spring Symposium on Designing Intelligent Robots: Reintegrating AI II, Stanford, USA, March 25-27, 2013. This paper describes a framework that integrates learning, planning and high-level human feedback to enable autonomy in human-robot collaboration.
    (pdf)
46. Ranjini Swaminathan, Mohan Sridharan and Katharine Hayhoe. Convolutional Neural Networks for Climate Downscaling. In the Climate Informatics Workshop (CI 2012), Boulder, USA, September 20-21, 2012. This paper presents results of proof of concept experiments that learn convolutional neural networks for downscaling climate models.
    (pdf) (poster)
47. Xiang Li and Mohan Sridharan. Vision-based Autonomous Learning of Object Models on a Mobile Robot. In the Autonomous Robots and Multirobot Systems Workshop (ARMS 2012) at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Valencia, Spain, June 5, 2012. This paper describes an algorithm that enables a mobile robot to autonomously learn object models using local. global and temporal visual cues.
    (pdf)
48. Shiqi Zhang, Forrest Sheng Bao and Mohan Sridharan. ASP-POMDP: Integrating Non-monotonic Logical Reasoning and Probabilistic Planning on Mobile Robots. In the Autonomous Robots and Multirobot Systems Workshop (ARMS 2012) at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Valencia, Spain, June 5, 2012. This paper integrates non-monotonic reasoning and hierarchical POMDPs for active visual sensing on mobile robots.
    (pdf)
49. Ranjini Swaminathan and Mohan Sridharan. Towards Robust Human-Robot Interaction using Multimodal Cues. In the Human-Agent-Robot Teamwork Workshop (HART 2012) at the International Conference on Human-Robot Interaction (HRI), Boston, USA, March 5, 2012. This paper describes a novel algorithm to merge visual and verbal cues to build rich object descriptions and pose natural language queries for human feedback, resulting in more natural human-robot interaction.
    (pdf)
50. Kristof Richmond, Alessandro Febretti, Shilpa Gulati, Christopher Flesher, Bartholomew Hogan, Aniket Murarka, Gregory Kuhlmann, Mohan Sridharan, Andrew Johnson, William Stone, John Priscu and Peter Doran. Sub-ice Exploration of an Antarctic Lake: Results from the ENDURANCE Project. In the International Symposium of Unmanned and Untethered Submersible Technology (UUST 2011), Portsmouth (NH), USA, August 21-24, 2011. This paper describes the recent missions conducted by Stone Aerospace in West Lake Bonney in Antarctica, where an autonomous underwater vehicle was used to conduct scientific experiments under the ice shelf.
    (pdf)
51. Shiqi Zhang and Mohan Sridharan. Visual Search and Multirobot Collaboration on Mobile Robots. In the Workshop on Automated Action Planning for Autonomous Mobile Robots (PAMR), co-located with AAAI-2011, San Francisco, USA, August 7-8, 2011. This paper extends our ICRA-11 paper on using hierarchical POMDPs for visual processing management to handle high-level visual search and multirobot collaboration.
    (pdf)
52. Kshira Nadarajan and Mohan Sridharan. Online Detection of Instability for Robust Teamwork in Humanoid Soccer Robots. In the International Workshop on Humanoid Soccer Robots, co-located with the International Conference on Humanoid Robots (Humanoids 2010), Nashville, USA, December 7, 2010. This paper documents work done with Kshira, a summer intern from Iowa State University. The focus is on developing an online scheme to detect instabilities on humanoid robots, and to use this information for better team coordination.
    (pdf)
53. Akbar Siami Namin and Mohan Sridharan. Position Paper: Bayesian Reasoning for Software Testing. In the Workshop on the Future of Software Engineering Research, co-located with the International Symposium on the Foundations of Software Engineering (FSE 2010), Santa Fe, USA, November 7-8, 2010. A position paper that advocates the use of Bayesian approaches for major challenges in software testing, and software engineering in general.
    (pdf)
54. Mohan Sridharan and Akbar Siami Namin. Prioritizing Mutation Operators based on Importance Sampling. In the International Symposium on Software Reliability Engineering (ISSRE 2010), San Jose, USA, November 1-4, 2010. This paper presents a novel approach based on adaptive sampling for the mutation testing challenge. The appealing aspect of this paper is that the algorithms widely used for localizing a robot or tracking multiple objects in an image sequence, are adapted to address a key challenge in software testing.
    (pdf) (talk slides)
55. Akbar Siami Namin, Barbara Millet and Mohan Sridharan. Fast Abstract: Stochastic Model- based Testing for Human-Robot Interaction.. In the International Symposium on Software Reliability Engineering (ISSRE 2010), San Jose, USA, November 2, 2010. This paper describes some recent work on building probabilistic models for testing the software developed for human-robot interaction systems.
    (pdf)
56. Shiqi Zhang and Mohan Sridharan. Vision-based Scene Analysis on a Mobile Robot using Layered POMDPs. In the POMDP Practitioners Workshop, May 12, 2010 (co-located with ICAPS-2010 and AAMAS-2010). This paper extends our work on hierarchical POMDPs for visual processing management (see AIJ-10 paper above) to handle both high-level scene processing and low-level image processing on a mobile robot.
    (pdf)
57. Akbar Namin, Mohan Sridharan and Pulkit Tomar. Predicting Multi-Core Performance:A Case Study Using Solaris Containers. In the International Workshop on Multicore Software Engineering (IWMSE 2010), May 1, 2010 (co-located with ICSE 2010). This paper compares regression techniques and probabilistic algorithms in terms of their ability to accurately predict the performance of different multi-core architectures on some standard subject programs.
    (pdf)
58. Mohan Sridharan and Xiang Li. Autonomous Information Fusion for Robust Obstacle Localization on a Humanoid Robot. In the Latin American Robotics Symposium (LARS 2009), Valparaiso, Chile, October 29-30, 2009. This paper is the initial version of the work described in the Humanoids-09 paper (see above). It presents an approach for autonomous sensor fusion for the specific goal of combining visual and range information on a humanoid robot.
    (pdf)
59. Mohan Sridharan, Jeremy Wyatt and Richard Dearden. POMDP-based Planning for Visual Processing Management on a Mobile Robot. In The Fifth International Cognitive Vision Workshop (ICVW 2009), which is part of the workshop series at The International Conference on Intelligent Robots and Systems (IROS 2009), St. Louis, USA, October 11, 2009. This paper proposes the use of our hierarchical POMDP architecture for cognitive vision tasks.
    (pdf)
60. Aniket Murarka, Gregory Kuhlmann, Shilpa Gulati, Mohan Sridharan, Chris Flesher and William Stone. Vision-based Frozen Surface Egress: A Docking Algorithm for the ENDURANCE AUV. In the International Symposium of Unmanned and Untethered Submersible Technology (UUST 2009), Durham, USA, August 23-26, 2009. This paper describes an algorithm for an underwater vehicle to safely detect, track and exit from a melthole in the ice, after running autonomous experiments underwater. The algorithm was field-tested in West Lake Bonney in Antarctica. For more information, look at the website of Stone Aerospace.
    (pdf)
61. William Stone, Bart Hogan, Chris Flesher, Kristof Richmond, Aniket Murarka, Gregory Kuhlmann and Mohan Sridharan. Sub-ice Exploration of West Lake Bonney: ENDURANCE 2008 Mission. In the International Symposium of Unmanned and Untethered Submersible Technology (UUST 2009), Durham, USA, August 23-26, 2009. This paper describes the challenging mission conducted by Stone Aerospace in West Lake Bonney in Antarctica, where an autonomous underwater vehicle was used to conduct scientific experiments under the ice shelf.
62. Mohan Sridharan, Richard Dearden and Jeremy Wyatt. E-HiPPo: Extensions to Hierarchical POMDP-based Visual Planning on a Robot. In The Twenty-Seventh PlanSIG Workshop (PlanSIG 2008), Edinburgh, UK, December 11-12, 2008. This paper presents extensions to our ICAPS-08 paper above. We incorporate actions that can change the state of the world, and provide theoretical and experimental bounds on the value-estimation errors incurred by policy-caching. All algorithms are implemented and tested in the playmate scenario of the CoSy project.
    (pdf)
63. Mohan Sridharan and Peter Stone. Comparing Two Action Planning Approaches for Color Learning on a Mobile Robot. In the VISAPP International Workshop on Robotic Perception (VISAPP-RoboPerc 2008), Funchal, Madeira-Portugal, January 22, 2008. This paper compares a long-term planning approach for color learning with the heuristic greedy planning approach for color learning.
    (pdf)
64. Mohan Sridharan and Peter Stone. Autonomous Planned Color Learning on a Mobile Robot Without Labeled Data. In The Fifth International Cognitive Robotics Workshop (The AAAI-2006 Workshop on Cognitive Robotics), July 15-16, 2006, Boston, USA.
    (pdf)
65. Mohan Sridharan and Peter Stone. Robust Autonomous Structure-based Color Learning on a Mobile Robot. In The AAAI/SIGART Doctoral Consortium, AAAI-2006, July 15-16, 2006, Boston, USA.
    (pdf of Talk)
66. Mohan Sridharan and Peter Stone. Autonomous Planned Color Learning on a Legged Robot. In Gerhard Lakemeyer, Elizabeth Sklar, Domenico Sorenti and Tomoichi Takahashi, editors, RoboCup-2006: Robot Soccer World Cup X, Springer Verlag, Berlin, 2007.
    (pdf)
67. Mohan Sridharan and Peter Stone. Towards Eliminating Manual Color Calibration at RoboCup. In Itsuki Noda, Adam Jacoff, Ansgar Bredenfeld and Yasutake Takahashi, editors, RoboCup-2005: Robot Soccer World Cup IX, Springer Verlag, Berlin, 2006.
    (pdf)
68. Mohan Sridharan and Peter Stone. Towards Illumination Invariance in the Legged League. In Daniele Nardi, Martin Riedmiller, and Claude Sammut, editors, RoboCup-2004: Robot Soccer World Cup VIII, Springer Verlag, Berlin, 2005.
    (pdf)
    A few videos referenced in the paper.
    

Courses and Tutorials:

1. Mohan Sridharan. Integrated Knowledge-based and Data-driven Reasoning, Control, and Learning in Robotics: Robustness, Rationality and Explainable Agency. In the European Summer School on Artificial Intelligence (ESSAI), July 15-26, 2024, Athens, Greece.
   (Course slides)
2. Mohan Sridharan. Explainability in Integrated Cognitive Systems Combining Logic-based Reasoning and Data-driven Learning. In the European Summer School in Logic, Language and Information (ESSLLI), August 8-12, 2022, Galway, Ireland. (Course slides)
3. Shiqi Zhang and Mohan Sridharan. Knowledge-based Sequential Decision-Making under Uncertainty. In the AAAI Conference, January 28, 2019, Honolulu, USA.
   (Tutorial slides)
4. Mohan Sridharan and Akbar Siami Namin. Bayesian Methods for Data Analysis in Software Engineering. In The International Conference on Software Engineering (ICSE-2010), May 3, 2010, Cape Town, South Africa.
   (Tutorial slides)

Theses and Dissertations Supervised:

1. Mark Robson. Towards An Holistic Approach for Highly Flexible Robotic Assembly Systems, MPhil Thesis, School of Computer Science, University of Birmingham, UK, May 2024.
   (pdf)
2. Laura Ferrante. Towards Adaptive Impedance Control for Upper-limb Prostheses, Doctoral Dissertation, School of Computer Science, University of Birmingham, UK, December 2023.
   (pdf)
3. Saif Sidhik. An Online Framework for Changing-Contact Robot Manipulation, Doctoral Dissertation, School of Computer Science, University of Birmingham, UK, May 2022.
   (pdf)
4. Tiago Mota. Combining Non-monotonic Logical Reasoning with Data-driven Learning for Scene Understanding and Transparent Decision Making, Doctoral Dissertation, Department of Electrical, Computer, and Software Engineering, The University of Auckland, NZ, December 2021.
   (pdf)
5. Michael Mathew. Learning Forward-Models for Robot Manipulation, Doctoral Dissertation, School of Computer Science, University of Birmingham, UK, May 2020. Co-supervised with Dr.~Jeremy Wyatt.
   (pdf)
6. Ermano Arruda. Generative and Predictive Models for Robust Manipulation, Doctoral Dissertation, School of Computer Science, University of Birmingham, UK, May 2020. Co-supervised with Dr.~Jeremy Wyatt.
   (pdf)
7. Ian Temple. An Exploration of the Use of Auxiliary Tasks for Transfer Learning Using SAC-X, MRes Thesis, Natural Computation, School of Computer Science, University of Birmingham, UK, May 2020.
   (pdf)
8. Maija Filipovica. Representing and Reasoning with Complex Affordances, Masters Thesis, Computational Neuroscience and Cognitive Robotics Program, University of Birmingham, UK, August 2019.
   (pdf)
9. Heather Riley. The Advantages of Non-monotonic Logic in Modular Architectures: High Performance and Interpretable Outputs with Limited Training Data. Masters Thesis, Department of Electrical and Computer Engineering, The University of Auckland, NZ, February 2019.
   (pdf)
10. Han Xu. Integrating Logical Reasoning and Probabilistic Graphical Models for Spoken Dialog System. Masters Thesis, Department of Computer Science, Texas Tech University, May 2017.
    (pdf)
11. Sarah Rainge. Integrating Reinforcement Learning and Declarative Programming to learn Causal Laws in Dynamic Domains. Masters Thesis, Department of Computer Science, Texas Tech University, May 2014.
    (pdf)
12. Xiang Li. Autonomous Learning of Object Models on Mobile Robots using Visual Cues. Doctoral dissertation, Department of Computer Science, Texas Tech University, August 2013.
    (pdf)
13. Shiqi Zhang. Integrating Answer Set Programming and POMDPs for Knowledge Representation and Reasoning in Robotics. Doctoral dissertation, Department of Computer Science, Texas Tech University, August 2013.
    (pdf)
14. Kimia Salmani. Multi-Instance Active Learning with Online Labeling. Masters Thesis, Department of Computer Science, Texas Tech University, August 2013.
    (pdf)
15. Justin Griggs. Intelligent Data Acquisition and Processing for Unmanned Aerial Vehicles. Masters Thesis, Department of Electrical and Computer Engineering, Texas Tech University, August 2012. Co-supervised with Dr. Richard Gale.
    (pdf)
16. Aaron Lee. Online Environment Anticipation using Multivariate Legendre Series. Masters Thesis, Department of Electrical and Computer Engineering, Texas Tech University, December 2011. Co-supervised with Dr. Richard Gale.
    (pdf)
17. Mamatha Aerolla. Incorporating Human and Environmental Feedback for Robust Performance in Agent Domains. Masters Thesis, Department of Computer Science, Texas Tech University, May 2011.
    (pdf)

Unrefereed Reports:

1. Shivam Singh, Karthik Swaminathan, Raghav Arora, Ramandeep Singh, Ahana Datta, Dipanjan Das, Snehasis Banerjee, Mohan Sridharan, and Madhava Krishna. Anticipate & Collab: Data-driven Task Anticipation and Knowledge-driven Planning for Human-robot Collaboration, Technical Report on arXiv, April 2024. This paper describes a framework that leverages the generic knowledge of LLMs to anticipate high-level tasks, using these tasks as goals in a classical planning system to compute a sequence of finer-granularity actions that an agent can execute to jointly achieve these goals in collaboration with a human.
   (arXiv link) (Project web site)
2. Laura Ferrante, Mohan Sridharan, Claudio Zito and Dario Farina. Toward a Framework for Adaptive Impedance Control of an Upper-limb Prosthesis, Technical Report on arXiv, December 2022. This paper describes an architecture that combines principles of human muscle models and variable impedance control for adaptive control of a human-machine interface for an upper-limb prosthesis.
   (arXiv link)
3. Hasra Dodampegama and Mohan Sridharan. Toward a Reasoning and Learning Architecture for Ad hoc Teamwork, Technical Report on arXiv, August 2022. This paper describes an architecture that combines the principles of non-monotonic logical reasoning (with commonsense domain knowledge), ecological rationality, and incremental learning to enable an agent to collaborate with other agents without prior coordination.
   (arXiv link)
4. Martin Rudorfer, Markus Suchi, Mohan Sridharan, Markus Vincze, Ales Leonardis. BURG-Toolkit: Robot Grasping Experiments in Simulation and the Real World, Technical report on arXiv, May 2022. This paper describes the BURG toolkit for benchmarking robot grasping algorithms in simulation and in the physical world.
   (arXiv link)
5. Mark Robson and Mohan Sridharan. Generating Task-specific Robotic Grasps, Technical report on arXiv, March 2022. This paper describes an approach for generating robot grasps that consider both safety and task-specific constraints.
   (arXiv link)
6. Reuth Mirsky, Ignacio Carlucho, Arrasy Rahman, Elliot Fosong, William Macke, Mohan Sridharan, Peter Stone, and Stefano V. Albrecht. A Survey of Ad Hoc Teamwork: Definitions, Methods, and Open Problems, Technical report on arXiv, February 2022. Paper describes a definition for the problem of ad hoc teamwork, summarizes current state of the art in the field, and describes open problems that remain to be solved.
   (arXiv link)
7. Mohan Sridharan and Tiago Mota. Combining Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning in Robotics, Technical report on arXiv, January 2022. Paper describes architecture that enables incremental grounding of spatial relations between objects, and combines knowledge-based reasoning and data-driven learning in robotics.
   (arXiv link)
8. Saif Sidhik, Mohan Sridharan, and Dirk Ruiken. An Adaptive Framework for Reliable Trajectory Following in Changing-Contact Robot Manipulation Tasks, Technical report on arXiv, November 2021. This paper describes a framework that enables a robot manipulator to reliably follow a desired trajectory that requires it to make and break contacts with objects and surfaces .
   (arXiv link)
9. Angel Daruna, Mehul Gupta, Mohan Sridharan, and Sonia Chernova. Continual Learning of Knowledge Graph Embeddings, Technical report on arXiv, May 2021. This is an extended version of the paper that appeared in RA-L 2021) and was presented at ICRA 2021; it presents additional results of reformulating continual learning methods for incremental knowledge graph embedding.
   (arXiv link) (RA-L/ICRA version)
10. Shiqi Zhang and Mohan Sridharan. A Survey of Knowledge-based Sequential Decision Making under Uncertainty. Technical report on arXiv, September 2020. This is a survey of methods for knowledge-based sequential decision-making under uncertainty. A revised version was later published as an article in the Artificial Intelligence Magazine (see above).
    (arXiv link)
11. Heather Riley and Mohan Sridharan. Non-monotonic Logical Reasoning Guiding Deep Learning for Explainable Visual Question Answering. Technical report on arXiv, September 2019. This paper describes an architecture that combines the principles of non-monotonic logical reasoning with commonsense knowledge, and inductive learning, to guide the learning of deep network models in the context of visual question answering. The architecture also supports incremental learning of previously unknown domain knowledge, and adaptation of planning and diagnostics problems.
    (arXiv link)
12. Rocio Gomez, Mohan Sridharan, and Heather Riley. Towards a Theory of Intentions for Human-Robot Collaboration. Technical report on arXiv, July 2019. This paper present an architecture that extends our refinement-based architecture (REBA) by introducing a theory of intentions that enables a robot to represent and reason with intentional actions at the coarse-resolution.
    (arXiv link)
13. Mohan Sridharan, Michael Gelfond, Shiqi Zhang and Jeremy Wyatt. REBA: A Refinement-Based Knowledge Representation and Reasoning Architecture for Robots. Technical report on arXiv, September 2018. This paper presents a general-purpose refinement-based architecture that integrates the complementary strengths of declarative programming and probabilistic graphical models to represent, reason with, and learn from, qualitative and quantitative descriptions of knowledge and uncertainty.
    (arXiv link)
14. Ranjini Swaminathan, Mohan Sridharan and Katharine Hayhoe. A Computational Framework for Modelling and Analyzing Ice Storms. Technical report on arXiv. May 2018. This paper describes a computational architecture for modeling and analyzing ice storms. This architecture adapts algorithms for supervised and unsupervised learning, and reasons with domain knowledge to direct the results of learning.
    (arXiv link)
15. Zenon Colaco and Mohan Sridharan. Mixed Logical and Probabilistic Reasoning for Planning and Explanation Generation in Robotics. CoRR abstract, August 2015. This paper extends the capabilities of our knowledge representation architecture by jointly: (a) explaining unexpected observation by reasoning about exogenous actions; and (b) identifying objects that best explain the partial scene descriptions extracted from sensor inputs.
    (arXiv link)
16. Shiqi Zhang, Mohan Sridharan, Michael Gelfond and Jeremy Wyatt. A Knowledge Representation and Reasoning Architecture for Robots. Technical Report, Department of Computer Science, Texas Tech University, February 2014. This architecture integrates the complementary strengths of declarative programming and probabilistic graphical models to represent, reason with, and learn from, qualitative and quantitative descriptions of knowledge and uncertainty.
    (pdf)
17. Ranjini Swaminathan and Mohan Sridharan. Towards Natural Human-Robot Interaction using Multimodal Cues. Technical Report, Department of Computer Science, Texas Tech University, December 2011. This paper presents a novel approach to learn associations between visual and verbal descriptions of objects. The augmented object description results in robust object recognition.
    (pdf)
18. Mohan Sridharan and Mamatha Aerolla. Bootstrap Learning and Augmented Reinforcement Learning for Robust Performance in Agent Domains. Technical Report, Department of Computer Science, Texas Tech University, May 2011. This is a concise description of Mamatha Aerolla's Masters thesis---also see the ICMLA 2011 conference paper.
    (pdf)
19. Susan Urban, Joseph Urban, Mohan Sridharan and Susan Mengel. Computational Thinking for Middle School Students through the Integration of Graphical Programming and Robotics, Technical report, Department of Computer Science, Texas Tech University, May 2011. This is a description of the use of a novel integrated 3D programming-robotics interface to teach computing to middle-school students. The paper also includes lesson plans and an evaluation framework.
20. Mohan Sridharan and Akbar Siami Namin. A Probabilistic Sampling Model for Effective Mutation Testing. Technical Report, Department of Computer Science, Texas Tech University, May 2010. For a more detailed description of the approach and extensive experimental results, please look at the ISSRE 2010 conference paper.
    (pdf) (online link)
21. Todd Hester, Michael Quinlan, Peter Stone and Mohan Sridharan. TT-UT Austin Villa 2009: Naos across Texas, Technical Report: UT-AI-TR-09-08, The University of Texas at Austin, Department of Computer Science, AI Laboratory, 2009.
    (pdf)
22. Mohan Sridharan, Nick Hawes, Jeremy Wyatt, Richard Dearden and Aaron Sloman. Planning Information Processing and Sensing Actions. Technical Report, University of Birmingham (UK), November 2007.
    (Initial CoSy version) (Updated UBham CS department version)
23. Peter Stone, Peggy Fidelman, Nate Kohl, Gregory Kuhlmann, Tekin Mericli, Mohan Sridharan and Shao-en Yu. The UT Austin Villa 2006 RoboCup Four-Legged Team. AI Lab Technical Report UT-AI-TR-06-337, The University of Texas at Austin, December 2006.
    (pdf)
24. Peter Stone, Kurt Dresner, Peggy Fidelman, Nate Kohl, Gregory Kuhlmann, Mohan Sridharan and Daniel Stronger. The UT Austin Villa 2005 RoboCup Four-Legged Team. AI Lab Technical Report UT-AI-TR-05-325, The University of Texas at Austin, November 2005.
    (pdf)
25. Peter Stone, Kurt Dresner, Peggy Fidelman, Nicholas Jong, Nate Kohl, Gregory Kuhlmann, Mohan Sridharan and Daniel Stronger. The UT Austin Villa 2004 RoboCup Four-Legged Team: Coming of Age. AI Lab Technical Report UT-AI-TR-04-313, The University of Texas at Austin, October 2004.
    (pdf)
26. Peter Stone, Kurt Dresner, Selim Erdogan, Peggy Fidelman, Nicholas Jong, Nate Kohl, Gregory Kuhlmann, Ellie Lin, Mohan Sridharan, Daniel Stronger and Gurushyam Hariharan. UT Austin Villa 2003: A New RoboCup Four-Legged Team. AI Lab Technical Report UT-AI-TR-03-304, The University of Texas at Austin, October 2003.
    (ps.gz)