crest.gif (7669 bytes)

Cognitive Robotics
  

 

Cognitive Robotics II

Murray Shanahan, Mark Witkowski and David Randell

Intelligent and Interactive Systems Section

An EPSRC Funded Research Project at the Department of Electrical and Electronic Engineering at Imperial College, University of London


Contents:

The Cognitive Robotics II Project continued our earlier work on the Cognitive Robotics I project. 

Cognitive Robotics II is now completed, you can read the final report here (pdf). This page is no longer maintained, you can find more recent information here.

Funded Cognitive Robotics research continues at Imperial College with the EPSRC funded project "Spatial Reasoning and Perception in a Humanoid Robot". 

You can view a presentation about our Cognitive Robotics work here (from May 2001).

Aims and Objectives of the Project

The aim of our Cognitive Robotics programme of research is to design and build software for controlling real (as opposed to merely simulated) robots which (i) are based on formal logic and the Event Calculus in particular, a well understood and mathematically rigorous formalism for reasoning about action, change, and space (as described in Murray Shanahan's book "Solving the Frame Problem: A Mathematical Investigation of the Common Sense Law of Inertia"), but which (ii) take account of the lessons learned in twenty five years of Robotics practice, in particular the advantages of tight coupling between sensors and actuators. We combine an Abductive Event Calculus based approach with a framework for qualitative spatial reasoning to create a formalism for reasoning about space, shape, action, and continuous change. Using this formalism, theories are constructed which describe the robot's interaction with its world.

Cognitive Robotics II was a two year research project, started in March 2000. The project was, in large measure, a continuation of previous work on the EPSRC funded projects "Cognitive Robotics I" and  "Logic for Commonsense Reasoning about Continuous Change". The term "cognitive robotics" was first introduced by Ray Reiter and his colleagues, who have a research group on this topic at the University of Toronto.

Our experiments during Cognitive Robotics I  involved a map-building task for a single robot and a logic programming approach to representation and implementation was adopted. The project also developed logic-based control techniques which can exploit abductively constructed maps for planning and navigation. 

We identified three areas leading on from previous project work that we consider merited further substantial research effort. 

  • One of the main achievements of the Cognitive Robotics I project was to demonstrate that the Event Calculus can be used as a viable logic programming language for agent and robot control. We are developing this into an Event Calculus Language Architecture (ECLA), to overcome some of the performance constraints imposed by the current Prolog based meta-interpreter and to integrate our work in abduction, the sense-plan-act cycle and robot interfacing into a robust and efficient system. This will enable us to rapidly extend the scope of our research work and give other researchers easy access to investigate and use the Event Calculus paradigm.
  • The Khepera robots used on the Cognitive Robotics I project inhabited a simple, carefully engineered "model office" environment, and used only short-range (~2cm) infra-red proximity sensors for navigation and map building. We extend the techniques used in the Cognitive Robotics I project to more realistic environments (for instance, a real office environment) with unexpected obstacles, other robots and people, and to use robots with richer sensors, such as sonar and stereoscopic vision. This greatly increased sensory capability enables us to substantially increase the range of reasoning processes that can be used. We already have a larger Nomad scout robot, although our preference for this work was to use "LinuxBot" robots designed and developed in the UK at the Faculty of Engineering at the University of the West of England (UWE). These robots have an on-board Pentium class processor and a wireless Ethernet link.
  • We wish to develop new techniques for robot communication and co-operation, building on the Event Calculus approach, and to demonstrate these on tasks that require co-operation among multiple robots, such as office delivery and co-operative map building. The use of DDE communications during the Cognitive Robotics I project was a partially satisfactory solution to inter-robot communication when using a single computer, but we explore the potential of the Internet based FIPA Agent Communication Language (ACL) in the context of robot to robot communication. We believe that communicative acts should be treated like other sensory events, and so can be assimilated and reasoned about using the methods of abductive reasoning developed during the Cognitive Robotics projects. In this model each robot is (literally) a node on a high bandwidth wireless LAN, each with an Internet IP address.


Stereo photo of the Team (l-r) Mark Witkowski, Murray Shanahan and David Randell
A "robot's eye view" using Videre stereo camera

The IIS Robotics Laboratory

We have recently established a robotics laboratory as a resource for Cognitive Robotics research and teaching within the Department of Electrical and Electronic Engineering. The physical laboratory space is equipped with a small fleet of LinuxBot robots, each with sonar rangefinders and firewire based stereoscopic vision. These robots intercommunicate using a wireless Ethernet LAN, currently established in our office space. We already have a Nomad Scout robot, several Khepera robots from K-Team and a number of LEGO Mindstorms kits, available for research and teaching projects. The group is currently working on LUDWIG, an upper torso, two-armed "humanoid" robot, which was constructed in the department's engineering workshops. Yiannis Demiris has a pair of miniature walking robots, used for research into human-machine and machine-machine imitation.


A LinuxBot robot with stereoscopic vision


LUDWIG, our humanoid upper-torso robot


Flip and Flop, for experiments in walking and imitation

People on the Project

Murray Shanahan was the principal investigator of this project, Mark Witkowski and David Randell were employed on the project as research fellows. Two of Murray Shanahan's Ph.D. students are also engaged in robotics research in the Intelligent and Interactive Systems Group, Paulo Santos and (Ms.) Seçil Özen. Previously, the Cognitive Robotics I project employed Rob Miller as research fellow with Fabio Berti and Hisashi Hayashi as research associates.

Dr. Yiannis Demiris has recently joined the IIS section from the University of Edinburgh Mobile Robots Group. He is known for his work on learning by imitation in robots.

Discussion and correspondence about the work on this project is very welcome. Please contact Murray Shanahan, David Randell or Mark Witkowski directly.

Papers and Publications by the Project Team

This list is no longer maintained, you can find more recent information here.

2003

  • Marcus Santos and Paulo Santos, Sensor Data Assimilation as Database Transactions, in Papers from the 2003 AAAI Spring Symposium, Palo Alto, California, 2003, pages 125-130 [abstract] [postscript] 

2002

  • Paulo Santos and Murray Shanahan, From Regions to Transitions, From Transitions to Objects, in AAAI-02 Cognitive Robotics Workshop, in: Baral, C. and McIlraith, S. (Eds.), Working notes of the AAAI Workshop on Cognitive Robotics, Edmonton, Canada, 2002 [abstract] [postscript]
  • Paulo Santos and Murray Shanahan, Hypothesising Object Relations from Image Transitions, in 15th European Conference on Artificial Intelligence (ECAI-02), in: van Harmelen, F. (Ed.), Proc. Euro. Conf. on Artificial Intelligence (ECAI-02), Lyon, France, July 2002, pages 292-296. [abstract] [postscript]
  • Murray Shanahan, A Logical Account of Perception Incorporating Feedback and Expectation, in Principles of Knowledge Representation and Reasoning: Proceedings of the Eighth International Conference (KR-2002), pages 3-13. [abstract] [postscript]
  • Mark Witkowski, Anticipatory Learning: The Animat as Discovery Engine, in: Proc. Adaptive Behavior in Anticipatory Learning Systems (ABiALS-02), Edinburgh, August 2002 [abstract] [pdf]
  • David Randell and Mark Witkowski, Building Large Composition Tables via Axiomatic Theories, in Principles of Knowledge Representation and Reasoning: Proceedings of the Eighth International Conference (KR-2002), pages 26-35. [abstract] [postscript]

2001

  • John Demiris and Gillian Hayes, Imitation as a Dual-route Process Featuring Predictive and Learning Components: a Biologically-plausible Computational Model, chapter 13, in Imitation in Animals and Artifacts, edited by K. Dautenhahn and C. Nehaniv, MIT Press, 2001 (to appear). [pdf]
  • Paulo Santos and Murray Shanahan, From Stereoscopic Vision to Symbolic Representation, AAAI Fall Symposium on "Anchoring Symbols to Sensor Data in Single and Multiple Robot Systems", North Falmouth, MA, pages 37-43. [abstract] [postscript]
  • David Randell, Mark Witkowski and Murray Shanahan, From Images to Bodies: Modeling and Exploiting Spatial Occlusion and Motion Parallax, Proc. 17th IJCAI-01, pages 57-63. This paper was also presented at the Commonsense 2001 Symposium, New York, May 20-22. [abstract] [postscript]
  • Mark Witkowski, Murray Shanahan, Paulo Santos and David Randell,  Cognitive Robotics: On the Semantic Knife-edge, Proc. TIMR 01 - Towards Intelligent Mobile Robots [abstract] [compressed postscript]
  • Mark Witkowski, David Randell and Murray Shanahan, Deriving Fluents from Sensor Data for Mobile Robots, AAAI Fall Symposium on "Anchoring Symbols to Sensor Data in Single and Multiple Robot Systems", North Falmouth, MA, pages 44-51. [abstract] [postscript]

2000

  • Leliane Nunes de Barros and Paulo E. Santos, The Nature of Knowledge in an Abductive Event Calculus Planner, Proceedings of the European Knowledge Acquisition Workshop (EKAW), Juan les Pins, France. [abstract] [compressed postscript]
  • Murray Shanahan, An Abductive Event Calculus Planner, The Journal of Logic Programming, Vol. 44, pages 207-239. [abstract] [compressed postscript].
  • Murray Shanahan and Mark Witkowski, High-Level Robot Control Through Logic, Proceedings ATAL 2000, pages 100-113 (to appear in the Springer-Verlag LNAI series).  [abstract] [compressed postscript] [electronic appendices]
  • Mark Witkowski, The Role of Behavioral Extinction in Animat Action Selection, Proc 6th Int. Conf. on Simulation of Adaptive Behaviour (SAB-00), [abstract] [postscript]
  • Mark Witkowski, Alexander Artikis and Jeremy Pitt, Trust and Cooperation in a Trading Society of Objective-Trust Based Agents, Proc. Autonomous Agents 2000 Workshop on Deception, Fraud and Trust in Agent Societies, pages 127-136 [abstract] [pdf]. A modified version of this paper is also to appear in Falcone, R., Singh, M. and Tan, Y-H (eds.) Trust in Cyber-Society: Integrating Human and Machine Perspective (Springer LNAI)

1999

1998

  • Hisashi Hayashi, Knowledge Assimilation and Proof Restoration through the Addition of Goals, Proceedings 8th International Conference on Artificial Intelligence: Methodology, Systems, and Applications (AIMSA’98), Lecture Notes in Artificial Intelligence 1480, Springer-Verlag (1998), pages 291–302.
  • A G Cohn, N M Gotts, Z Cui, D A Randell, B Bennet and J M Gooday, Exploiting Temporal Continuity in Qualitative Spatial Calculi, eds M J Egenhofer and R Golledge, Spatial Information Systems, Oxford, 1998.
  • Murray Shanahan, Reinventing Shakey, Working Notes of the 1998 AAAI Fall Symposium on Cognitive Robotics, pages 125–135. [abstract] [compressed postscript]
  • Mark Witkowski, Dynamic Expectancy: An Approach to Behaviour Shaping Using a New Method of Reinforcement Learning, 6th Int. Symp. on Intelligent Robotic Systems (SIRS98), July, 1998, pages 73-81. [abstract] [postscript]

1997

  • Hisashi Hayashi, Language HSimple(R): An Action Language for Representing Concurrent Actions and Continuous Changes, in the Working Notes of the Second Workshop on Practical Reasoning and Rationality, [abstract] [postscript]
  • Murray Shanahan, Solving the Frame Problem: A Mathematical Investigation of the Common Sense Law of Inertia, MIT Press, 1997. [contents]
  • Murray Shanahan, Event Calculus Planning Revisited, in Proceedings of 1997 European Conference on Plannning (ECP 97). An early draft of this paper appears in the Working Notes of the AAAI 97 Workshop on Robots, Softbots, Immobots: Theories of Action, Planning and Control, 1997. [abstract] [compressed postscript]
  • Murray Shanahan, Noise, Non-Determinism and Spatial Uncertainty, Proceedings AAAI 97, pages 153–158 [abstract] [compressed postscript]

1996

  • Rob Miller and Murray Shanahan, Reasoning about Discontinuities in the Event Calculus, in proceedings of the 5th International Conference on Principles of Knowledge Representation and Reasoning (KR 96), 1996. [Abstract] [postscript] [dvi]
  • Murray Shanahan, Noise and the Common Sense Informatic Situation for a Mobile Robot, in the proceedings of AAAI'96, 1996. [Abstract] [compressed postscript]
  • Murray Shanahan, Robotics and the Common Sense Informatic Situation, in the proceedings of ECAI'96, Budapest, Hungary, 1996. [Abstract] [compressed postscript]

Other references, and those before 1996, may be found at the respective author's homepages.

 

Related WWW Sites

This page maintained by Mark Witkowski. Last Change: 4/10/02 (by MW).

 

banner.gif (2541 bytes)