Industrial & Academic Positions

  • 2015 2011

    R&D of Educational Apps

    INP APPS

  • 2011 2005

    Lecturer of Computer Science

    University of Essex

  • 2000 1999

    Principal designer of Data acquisition systems

  • 1999 1998

    Research and Development of Medical Electronic Equipment

    LOGOS Research, Greece

Education & Training

  • Ph.D. Present

    Ph.D. in BioRobotics

    School of Informatics,
    University of Edinburgh

  • M.Sc. 2001

    Artificial Intelligence (Robotics)

    Department of Artificial Intelligence,
    University of Edinburgh

  • B.Eng. 1999

    Electronics Engineering

    Electronics Department, TEI of Piraeus, Greece

Honors, Awards and Grants

  • 2016-2019
    Principal's Career Development Scholarship
    image
    The Principal of the University of Edinburgh very kindly gave me the privilige to award me with this full scholarship to cover the cost of my studies towards a Ph.D.
  • 2003
    ESA Student Participation Program of the IAF’03 Congress
    image
    I had the privilege to be one of the 100 European young scientists selected by the European Space Agency (ESA) to participate and present their scientific papers at the “Student Participation Program of the IAF’03 Congress” for a second time.
  • 2003
    IEE Young Members Presentation Competition
    image
    I won the second prize of IEE's annual “Young Members Presentation Competition” in June 2003.
  • 2002
    ESA Student Participation Program of the IAF’02 Congress
    image
    I had the privilege to be one of the 100 European young scientists selected by the European Space Agency (ESA) to participate in the “Student Participation Program of the IAF’02 Congress”.
  • 2000
    Hellenic Scholarships Institute (IKY) Award
    image
    The Hellenic government kindly gave me the privilege to award me this highly competitive and prestigious scholarship for postgraduate studies.
  • 1997-1999
    Hellenic Scholarship Foundation (IKY) Award
    image
    The Hellenic government kindly awarded me this scholarship for each year of my undergraduate studies as one of the top three students at the Department of Electronics of the TEI of Piraeus, Greece.

Filter by type:

Sort by year:

Experiments in Subsymbolic Action Planning with Mobile Robots

Pisokas, J. and Nehmzow, U.
Conference Papers AISB 2003 Convention: Cognition in Machines and Animals, 2003.

Abstract

The ability to determine a sequence of actions in order to reach a particular goal is of utmost importance to mobile robots. One major problem with symbolic planning approaches regards assumptions made by the designer while introducing externally specified world models, preconditions and postconditions. To bypass this problem, it would be desirable to develop mechanisms for action planning that are based on the agent's perceptual and behavioural space, rather than on externally supplied symbolic representations. We present a subsymbolic planning mechanism that uses a non-symbolic representation of sensor-action space, learned through the agent's autonomous interaction with the environment. In this paper, we present experiments with two autonomous mobile robots, which use autonomously learned subsymbolic representations of perceptual and behavioural space to determine goal-achieving sequences of actions. The experimental results we present illustrate that such an approach results in an embodied robot planner that produces plans which are grounded in the robot's perception-action space.

Experiments with Sensors for Urban Search and Rescue Robots

Pissokas, J. and Malcolm, C.
Conference Papers International Symposium on Robotics and Automation, 2002.

Abstract

Subsymbolic Action Planning for Mobile Robots: Do plans need to be precise?

Pisokas, J. and Nehmzow, U.
Conference Papers 4th British Conference on Mobile Robots: Towards Intelligent Mobile Robots, 2003.

Abstract

Prediction of Perception for Subsymbolic Action Planning in Mobile Robots

Nehmzow, U. and Pisokas, J.
Conference Papers European Conference on Mobile Robotics, 2003.

Abstract

Experiments in subsymbolic action planning with mobile robots

Pisokas, J. and Nehmzow, U.
Book Chapter In Lecture Notes in Computer Science, Adaptive Agents and Multi-Agent Systems II: Adaptation and Multi-Agent Learning, Volume 3394 LNAI, Pages 216–229, 2005, Springer-Verlag.

Abstract

The ability to determine a sequence of actions in order to reach a particular goal is of utmost importance to mobile robots. One major problem with symbolic planning approaches regards assumptions made by the designer while introducing externally specified world models, preconditions and postconditions. To bypass this problem, it would be desirable to develop mechanisms for action planning that are based on the agent's perceptual and behavioural space, rather than on externally supplied symbolic representations. We present a subsymbolic planning mechanism that uses a non-symbolic representation of sensor-action space, learned through the agent's autonomous interaction with the environment. In this paper, we present experiments with two autonomous mobile robots, which use autonomously learned subsymbolic representations of perceptual and behavioural space to determine goal-achieving sequences of actions. The experimental results we present illustrate that such an approach results in an embodied robot planner that produces plans which are grounded in the robot's perception-action space.

Global navigation through local reference frames

Pisokas, J.
Conference Papers From Animals to Animats 9: 9th International Conference on Simulation of Adaptive Behavior, Volume 4095 LNAI,Pages 274–285, 2006.

Abstract

The contribution of this paper is that illustrates the use of funneling actions in combination with local deictic reference frames for forming consistent and useful large scale maps. These maps do not rely on any geodetic sensors. Indications for the feasibility of such representations in humans, and other species, can be found in studies of spatial cognition. However, such implementations or applications in robotics have not been illustrated until now.

Learning to plan for robots using generalized representations

Pisokas, J. and Gu, D. and Hu, H.
Journal Article Industrial Robot, Volume 33, Issue 4, Pages 270–277, 2006.

Abstract

Robots operating in the real world should be able to make decisions and plan ahead their actions. We argue that learning using generalized representations of the robot's experience can assist such a ability. Design/methodology/approach: We present results from our research on methods for enabling mobile robots to plan their actions using generalized representations of their experience. Such generalized representations are acquired through a learning phase during which the robot explores its environment and builds subsymbolic (connectionist) representations of the result that its actions have to its sensory perception. Then these representations are employed by the robot for autonomously determining task-achieving sequences of actions (plans),for attaining assigned tasks. Findings: Such subsymbolic mechanisms can employ generalization techniques in order to pursue plans through unexplored regions of the robot's environment. Originality/value: Subsymbolic motion planning can autonomously determine task-achieving sequences of actions in real environments, without using presupplied symbolic knowledge, but instead generating novel plans using previously acquired subsymbolic representations.

Frequency shift for position estimation in mobile robots

Pisokas, J.
Conference Papers IEEE International Conference on Systems, Man and Cybernetics, Volume 4,Pages 3516–3521, 2005.

Abstract

The ability of a robot to estimate its location in the environment is crucial for variety of tasks. Several approaches have been developed offering either low cost solutions with low accuracy or high accuracy solutions at high cost. This paper presents a displacement sensor, for mobile robots, which exploits the frequency shift caused to a signal due to the robot's motion. This method offers a low cost solution combined with higher accuracy than other approaches of similar cost. The achieved accuracy level in combination with the relatively low power consumption and weight make this sensor a reasonable choice for mobile robotics applications.

Performance comparison of three subsymbolic action planners for mobile robots

Pisokas, J. and Nehmzow, U.
Journal Article Robotics and Autonomous Systems, Volume 51, Issue 1, Pages 55–67, 2005.

Abstract

In this paper, we investigate the feasibility of building action-planning mechanisms capable of autonomously determining task-achieving sequences of actions (plans), using previously acquired subsymbolic representations. These subsymbolic representations are acquired by the robot autonomously during an exploration phase. Furthermore, we investigate whether such subsymbolic mechanisms can employ generalisation techniques in order to pursue plans through unexplored regions of the robot's environment. Performance comparison of three subsymbolic action-planning mechanisms on different tasks conclude the paper.

Subsymbolic action planning for robots: Generalised representations of experience

Pisokas, J. and Nehmzow, U.
Conference Papers 8th Conference on Intelligent Autonomous Systems, Pages 666–673, 2004.

Abstract

Subsymbolic path-planning for space and planetary exploration robots

Pisokas, J.
Conference Papers 55th International Astronautical Congress, Volume 5, 2004.

Abstract

Space and planetary exploration and construction can be significantly facilitated by the use of robotic technology, which can provide low risk and low cost means. Especially for remote missions, it seems necessary to use robots able to autonomously pursue mission goals specified beforehand by humans. One key competence that such an autonomous robotic agent should possess is the ability to plan sequences of activities for achieving mission goals. Current technologies base such planning skills on human intervention and/or a priori obtained maps of the operation environment. However, missions to remote unexplored planetary objects will not always have these privileges of pre-supplied maps of the landing and operation terrain and of frequent communication with human operators on earth. On the contrary we need robots able, after landing, to adapt to their environment and learn how to successfully operate in it autonomously for achieving pre-specified mission goals. Achieving such degrees of autonomy requires two capabilities of the robots: first, to be able to learn how to operate in a new environment and second, to be able to generalize over their experience in order to behave properly in novel situations by exploiting previous experience.

Teaching History

  • 2011 2005

    Computer Programming (C)

    An introduction to basic concepts, structures, and methodologies of computer programming. The fundamentals of procedural programming were introduced using the C computer programming language.
  • 2011 2009

    Introduction to Programming (Python)

    An introductory course for first year students. The different types of programming languages were introduced and contrasted as well as basic programming concepts and algorithms. Procedural and Object-Oriented programming principles were introduced using Python 3 as the programming language.
  • 2011 2009

    Quantitative Methods

    I taught part of this course.
  • 2011 2009

    Computer Systems

    Introductory course to computer systems, architectures and principles.

At My Office

You can find me at my office located at the Informatics Forum of the University of Edinburgh.

I am at my office every day from 9:00 until 18:00, but you may consider emailing me to fix an appointment.

@inproceedings{Pisokas2003a,
     author = {Pisokas, J. and Nehmzow, U.},
     booktitle = {AISB 2003 Convention: Cognition in Machines and Animals},
     title = {Experiments in Subsymbolic Action Planning with Mobile Robots},
     year = {2003}
}
@inproceedings{Pisokas2002,
     author = {Pissokas, J. and Malcolm, C.},
     booktitle = {International Symposium on Robotics and Automation},
     title = {Experiments with Sensors for Urban Search and Rescue Robots},
     year = {2002}
}
@inproceedings{Pisokas2003c,
     author = {Pisokas, J. and Nehmzow, U.},
     booktitle = {4th British Conference on Mobile Robots: Towards Intelligent Mobile Robots},
     publisher = {Springer-Verlag & IEE},
     title = {Subsymbolic Action Planning for Mobile Robots: Do plans need to be precise?},
     year = {2003}
}
@inproceedings{Pisokas2003b,
     author = {Nehmzow, U. and Pisokas, J.},
     booktitle = {European Conference on Mobile Robotics},
     title = {Prediction of Perception for Subsymbolic Action Planning in Mobile Robots},
     year = {2003}
}
@inbook{Pisokas2005a,
     author = {Pisokas, J. and Nehmzow, U.},
     booktitle = {Lecture Notes in Computer Science, Adaptive Agents and Multi-Agent Systems II: Adaptation and Multi-Agent Learning},
     editor = {[{u'name': {u'name': u'Kudenko, Daniel', u'ID': u'KudenkoDaniel'}}, {u'name': {u'name': u'Kazakov, Dimitar', u'ID': u'KazakovDimitar'}}, {u'name': {u'name': u'Alonso, Eduardo', u'ID': u'AlonsoEduardo'}}]},
     pages = {216--229},
     publisher = {Springer-Verlag},
     title = {Experiments in subsymbolic action planning with mobile robots},
     volume = {3394 LNAI},
     year = {2005}
}
@inproceedings{Pisokas2006b,
     author = {Pisokas, J.},
     booktitle = {From Animals to Animats 9: 9th International Conference on Simulation of Adaptive Behavior},
     editor = {[{u'name': {u'name': u'Nolfi, Stefano', u'ID': u'NolfiStefano'}}, {u'name': {u'name': u'Baldassare, Gianluca', u'ID': u'BaldassareGianluca'}}, {u'name': {u'name': u'Calabretta, Raffaele', u'ID': u'CalabrettaRaffaele'}}, {u'name': {u'name': u'Hallam, John', u'ID': u'HallamJohn'}}, {u'name': {u'name': u'Marocco, Davide', u'ID': u'MaroccoDavide'}}, {u'name': {u'name': u'Miglino, Orazio', u'ID': u'MiglinoOrazio'}}, {u'name': {u'name': u'Meyer, Jean-Arcady', u'ID': u'MeyerJean-Arcady'}}, {u'name': {u'name': u'Parisi, Domenico', u'ID': u'ParisiDomenico'}}]},
     pages = {274--285},
     publisher = {Springer-Verlag Berlin Heidelberg},
     title = {Global navigation through local reference frames},
     volume = {4095 LNAI},
     year = {2006}
}
@article{Pisokas2006a,
     author = {Pisokas, J. and Gu, D. and Hu, H.},
     journal = {{u'pages': u'270--277', u'name': u'Industrial Robot', u'number': u'4', u'volume': u'33'}},
     title = {Learning to plan for robots using generalized representations},
     year = {2006}
}
@inproceedings{Pisokas2005c,
     author = {Pisokas, J.},
     booktitle = {IEEE International Conference on Systems, Man and Cybernetics},
     pages = {3516--3521},
     publisher = {IEEE},
     title = {Frequency shift for position estimation in mobile robots},
     volume = {4},
     year = {2005}
}
@article{Pisokas2005b,
     author = {Pisokas, J. and Nehmzow, U.},
     journal = {{u'pages': u'55--67', u'name': u'Robotics and Autonomous Systems', u'number': u'1', u'volume': u'51'}},
     title = {Performance comparison of three subsymbolic action planners for mobile robots},
     year = {2005}
}
@inproceedings{pisokas2004b,
     author = {Pisokas, J. and Nehmzow, U.},
     booktitle = {8th Conference on Intelligent Autonomous Systems},
     pages = {666--673},
     title = {Subsymbolic action planning for robots: Generalised representations of experience},
     year = {2004}
}
@inproceedings{Pisokas2004a,
     author = {Pisokas, J.},
     booktitle = {55th International Astronautical Congress},
     publisher = {International Astronautical Federation},
     title = {Subsymbolic path-planning for space and planetary exploration robots},
     volume = {5},
     year = {2004}
}