Sethu Vijayakumar
Professor of Robotics & Microsoft-RAEng Senior Research Fellow

Home
Research
Publications
Videos
Teaching
Outreach
Contact

IPAB
Informatics
U. Edinburgh

 

Professor Sethu Vijayakumar holds a Personal Chair in Robotics and is the Director of the Institute of Perception, Action & Behavior (IPAB) in the School of Informatics at the University of Edinburgh.  Since 2007, he is the Microsoft/Royal Academy of Engineering Senior Research Fellow in Learning Robotics. He also holds additional appointments as an Adjunct Faculty of the University of Southern California(USC), Los Angeles, a Visiting Research Scientist at the ATR Computational Neuroscience Labs, Kyoto-Japan and the RIKEN Brain Science Institute, Tokyo. He has a Ph.D.('98) in Computer Science and Engineering from the Tokyo Institute of Technology. Prof. Vijayakumar previously held the position of Reader (2007-2010) and Lecturer (2003-2007) at the University of Edinburgh, a Research Assistant Professor ('01-'03) at USC and a Staff Scientist ('98-'00) at the RIKEN Brain Science Institute. His research interest spans a broad interdisciplinary curriculum involving basic research in the fields of statistical machine learning, motor control, planning and optimization in autonomous systems and computational neuroscience. See here for a list of his publications. Sethu is a keen science communicator and in recent years, has been active in conceptualising, producing and presenting several public  outreach events to engage with the general public and children on all things science and engineering. He is a Fellow of the Royal Society of Edinburgh.
 

Winter 2012: I delivered the Alan Turing Centenary Lecture as part of Science Alive Hong Kong organized by British Council, Hong Kong Education Bureau and Hong Kong Science Museum. [link]
 Conferences: We hosted the International Conference on Machine Leaning (ICML 2012) in Edinburgh. I am the Area Chair for Robotics: Science and Systems  (R:SS 2013) in Berlin (June 24-28), having served as the Area Chair last year for the previous edition (R:SS 2012) held in Sydney and the Silver Jubilee Edition of the Neural Information Processing Systems (NIPS 2012) in Lake Tahoe.
Recent Invited Talks / Tutorials: I delivered keynote lectures at the Summer School on Variable Impedance in Germany and the CMCW motor control meeting in Ben-Gurion University, Israel. Jul 2012: I also gave a tutorial on Machine Learning for Robotics in the Robotics: Science and Systems (R:SS 2012) conference in Sydney.
 2012: Our research has been featured on the EPSRC website, on the BBC Bang Goes the Theory programme and on the British Council Research webpages. More on media coverage and the outreach activities here including the inaugural lecture of Edinburgh International Science Festival 2009 with ASIMO! 
Projects: Our active projects include an EU FP6 STREP project STIFF (on variable impedance actuation) and
     a FP7 STREP project TOMSY and an EPSRC project TBMS on the topics of Topology Based Motion Synthesis.
                    What is this about...a short clip can be found here.
 2007: I have been awarded the Microsoft/Royal Academy of Engineering Senior Research Fellowship.
Check out our new home since June 2008: The Informatics Forum, in the Edinburgh Inspiring Capital video.
Details of my research group, the Statistical Learning & Motor Control (SLMC) lab can be accessed here.

  IPAB/Institute for Perception, Action & Behavior School of Informatics/UoESLMC group/IPAB/UoE   UoE/University of Edinburgh    USC / University of Southern California


Selected Publications (for full list, see here)

  • Konrad Rawlik, Marc Toussaint and Sethu Vijayakumar, On Stochastic Optimal Control and Reinforcement Learning by Approximate Inference, Proc. Robotics: Science and Systems (R:SS 2012), Sydney, Australia (2012). [pdf] [R:SS 2012 Best Paper Award Runner-up]

  • Sethu Vijayakumar, Aaron D'Souza and Stefan Schaal, Incremental Online Learning in High Dimensions, Neural Computation, vol. 17, no. 12, pp. 2602-2634 (2005). [pdf] [LWPR software] [see next for usage guide]

  • Stefan Klanke, Sethu Vijayakumar and Stefan Schaal, A Library for Locally Weighted Projection Regression, Journal of Machine Learning Research (JMLR), vol. 9, pp. 623--626 (2008). [pdf][DOI]

  • Djordje Mitrovic, Stefan Klanke and Sethu Vijayakumar,  Learning Impedance Control of Antagonistic Systems based on Stochastic Optimisation Principles, International Journal of Robotic Research (IJRR), Vol. 30, No. 5, pp. 556-573 (2011). [pdf][DOI]

  • Sethu Vijayakumar and Hidemitsu Ogawa, A Functional Analytic Approach to Incremental Learning in Optimally Generalizing Neural Networks, Proc. IEEE International Conference on Neural Networks (ICNN '95), Australia, vol. 2, pp.777-782 (1995).[DOI] [ICNN 1995 Best Student Paper Award]

  • Dmitry Zarubin, Vladimir Ivan, Marc Toussaint, Taku Komura and Sethu Vijayakumar, Heirachical Motion Planning in Topological Representations,Proc. Robotics: Science and Systems (R:SS 2012), Sydney, Australia (2012). [pdf] [video]

  • Sethu Vijayakumar, Timothy Hospedales and Adrian Haith, Generative Probabilistic Modeling: Understanding Causal Sensorimotor Integration, In: Trommershauser, Kording & Landy (Eds), Sensory Cue Integration, pp. 63-81, Oxford University Press (2011) [OUP][preprint]

  • Timothy Hospedales and Sethu Vijayakumar, Bayesian Structure Inference for Multisensory Scene Understanding, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 30, no. 12, pp. 2140-2157 (2008). [pdf][DOI]

  • Sebastian Bitzer and Sethu Vijayakumar, Latent Spaces for Dynamic Movement Primitives, Proc. 9th IEEE RAS International Conference on Humanoid Robots (Humanoids ’09), Paris, France (2009). [pdf]

  • Djordje Mitrovic, Stefan Klanke, Rieko Osu, Mitsuo Kawato and Sethu Vijayakumar, A Computational Model of Limb Impedance Control based on Principles of Internal Model Uncertainty, PLoS ONE, Vol. 5, No. 10 (2010). [pdf][DOI]

  • Sethu Vijayakumar, Aaron D'Souza, Tomohiro Shibata, Jorg Conradt and Stefan Schaal, Statistical Learning for Humanoid Robots, Autonomous Robots , Vol. 12, No.1, pp. 55-69 (2002). [pdf]

  • Djordje Mitrovic, Stefan Klanke and Sethu Vijayakumar,  Adaptive Optimal Feedback Control with Learned Internal Dynamics Models, In: O. Sigaud and J. Peters (eds.): From Motor Learning to Interaction Learning in Robots, SCI 264, pp. 65-84, Springer-Verlag (2010). [pdf]

  • Graham McNeill and Sethu Vijayakumar, Part-based Probabilistic Point Matching Using Equivalence Constraints, Proc. Advances in Neural Information Processing Systems (NIPS '06), Vancouver (2006). [pdf]

  • Sethu Vijayakumar and Hidemitsu Ogawa, RKHS based Functional Analysis for Exact Incremental Learning
    Neurocomputing, Vol.29, No.1-3, pp.85-113, Elsevier Science(1999). [pdf]

  • Jo-Anne Ting, Aaron D'Souza, Sethu Vijayakumar and Stefan Schaal,  Efficient Learning and Feature Selection in High Dimensional Regression, Neural Computation, vol. 22, no. 4, pp. 831-886 (2010). [pdf]

  • Ian Saunders and Sethu Vijayakumar, The Role of Feed-Forward and Feedback Processes for Closed-Loop Prosthesis Control, Journal of Neuroengineering and Rehabilitation (JNER), 8:60 (2011). [pdf][DOI]

  • Stefan Schaal, Chris Atkeson and Sethu Vijayakumar, Real time robot learning with locally weighted statistical learning, Proc. International Conference on Robotics and Automation (ICRA2000), San Francisco, USA, vol.1, pp.288-293,(2000). [pdf] [ICRA 2000 Best Paper Award Finalist]