Learning from History for Behavior-Based Mobile Robots in Non-Stationary Conditions

Autonomous Robots

Volumn 5, Issue 3-4, 1998, Pages 335-354

  Michaud, François ^a,c,d   Matarić, Maja J ^b,c,e,f,g,h  

^a UNIVERSITÉ DE SHERBROOKE   (Canada)

^b University of Southern California ^*  (United States)

^c BRANDEIS UNIVERSITY   (United States)

^d LABORIUS   (Canada)

^e USC Robotics Research Lab   (United States)

^f USC   (United States)

^g MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^h CALIFORNIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

History based learning; Multirobot learning; Nonstationary conditions; Self evaluation

Indexed keywords

LEARNING ALGORITHMS; MOTION PLANNING; ROBOT LEARNING; ROBOT PROGRAMMING;

HISTORY-BASED LEARNING; MULTIROBOT LEARNING; NONSTATIONARY CONDITIONS;

MOBILE ROBOTS;

EID: 0032117054     PISSN: 09295593     EISSN: None     Source Type: Journal    
DOI: 10.1023/a:1008814507256     Document Type: Article

References (29)

1. Agre, P.E. 1988. The dynamic structure of everyday life. Ph.D. Thesis, Massachusetts Institute of Technology, Cambridge, MA.
2. Albus, J.S. 1991. Outline for a theory of intelligence. IEEE Trans. on Systems, Man, and Cybernetics, 21(3):473-509.
3. Asada, M., Uchibe, E., Noda, S., Tawaratsumida, S., and Hosoda, K. 1994. Coordination of multiple behaviors acquired by a vision-based reinforcement learning. In Proc. IEEE/RSJ/GI Int'l Conf. on Intelligent Robots and Systems, Munich, Germany.
4. Brooks, R.A. 1986. A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, RA-2(1):14-23.
5. Brooks, R.A. 1991. Intelligence without representation. Artificial Intelligence, 47:139-159.
6. Brooks, R.A. 1996. MARS: Multiple agency reactivity system. Technical Report IS Robotics, Cambridge, MA.
7. del R. Millán, J. 1996. Rapid, safe, and incremental learning of navigation strategies, IEEE Trans. on Systems, Man, and Cybernetics - Part B: Cybernetics, 26(3):408-420.
8. Dorigo, M. and Colombetti, M. 1994. Robot shaping: Developing autonomous agents through learning. Artificial Intelligence, 71(4):321-370.
9. Floreano, D. and Mondada, F. 1996. Evolution of homing navigation in a real mobile robot. IEEE Trans. on Systems, Man, and Cybernetics - Part B: Cybernetics, 26(3):396-407.
10. Fontán, M.S. and Matarić, M.J. 1996. A study of territoriality: the role of critical mass in adaptive task division. In From Animals to Animats: Proc. 4th Int'l Conf. on Simulation of Adaptive Behavior, P. Maes, M.J. Matarić, J.-A. Meyer, J. Pollack, and S. Wilson (Eds.), Cape Cod, The MIT Press.
11. Goldberg, D. and Matarić, M.J. 1997. Interference as a tool for designing and evaluating multirobot controllers. In Proc. National Conf. on Artificial Intelligence (AAAI), Providence, RI, pp. 637-642.
12. Kaelbling, L.P., Liftman, M.L., and Moore, A.W. 1996. Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4:237-285.
13. Maes, P. 1989. The dynamics of action selection. In Proc. Int'l Joint Conf. on Artificial Intelligence (UCAI), Detroit, MI, pp. 991-997.
14. Maes, P. and Brooks, R.A. 1990. Learning to coordinate behaviors. In Proc. Nat'l Conf. on Artificial Intelligence (AAAI), vol. 2, pp. 796-802.
15. Mahadevan, S. and Connell, J. 1992. Automatic programming of behavior-based robots using reinforcement learning. Artificial Intelligence, 55:311-365.
16. Mahadevan, S. and Kaelbling, L.P. 1996. The NSF workshop on reinforcement learning: Summary and observations. AI Magazine.
17. Matarić, M.J. 1992a. Integration of representation into goal-driven behavior-based robots. IEEE Transactions on Robotics and Automation, 8(3):46-54.
18. Matarić, M.J. 1992b. Behavior-based systems: Key properties and implications. In Proc. IEEE Int'l Conf. on Robotics and Automation, Workshop on Architectures for Intelligent Control Systems, Nice, France, pp. 46-54.
19. Matarić, M.J. 1994a. Interaction and intelligent behavior. MIT AI Lab AI-TR 1495, Massachusetts Institute of Technology, Cambridge, MA.
20. Matarić, M.J. 1994b. Reward functions for accelerated learning. In Proc. 11th Int'l Conf. on Machine Learning, W.W. Cohen and H. Hirsh (Eds.), New Brunswick, NJ, Morgan Kauffman Publishers, pp. 181-189.
21. Matarić, M.J. 1997. Reinforcement learning in the multi-robot domain. Autonomous Robots, 4(1).
22. McCallum, A.K. 1996a. Hidden state and reinforcement learning with instance-based state identification. IEEE Trans. on Systems, Man, and Cybernetics - Part B: Cybernetics, 26(3):464-473.
23. McCallum, A.K. 1996b. Learning to use selective attention and short-term memory in sequential tasks. In From Animals to Animats: Proc. 4th Int'l Conf. on Simulation of Adaptive Behavior, P. Maes, M.J. Matarić, J.-A. Meyer, J. Pollack, and S.W. Wilson (Eds.), Cape Cod, The MIT Press, pp. 315-324.
24. McCallum, A.K. 1996c. Reinforcement learning with selective perception and hidden state. Ph.D. Thesis, Department of Computer Science, University of Rochester, USA.
25. Michaud, F. 1996. Nouvelle architecture unifiée de contrôle intelligent par sélection intentionnelle de comportements. Ph.D. Thesis, Department of Electrical and Computer Engineering, Université de Sherbrooke, Québec, Canada.
26. Michaud, F. 1997. Adaptability by behavior selection and observation for mobile robots. In Soft Computing in Engineering Design and Manufacturing, R. Roy, P. Chawdry, and P. Pants (Eds.), Springer-Verlag.
27. Michaud, F., Lachiver, G., and Dinh, C.T.L. 1996. A new control architecture combining reactivity, deliberation and motivation for situated autonomous agent. In From Animals to Animats: Proc. 4th Int'l Conf. on Simulation of Adaptive Behavior, P. Maes, M.J. Matarić, J.-A. Meyer, J. Pollack, and S.W. Wilson (Eds.), Cape Cod, The MIT Press, pp. 247-254.
28. Michaud, F. and Matarić, M.J. 1997. A history-based learning approach for adaptive robot behavior selection. Technical Report CS-97-192, Computer Science Department, Volen Center for Complex System, Brandeis University, Waltham, MA, USA.
29. Ram, A. and Santamaria, J.C. 1993. Multistrategy learning in reactive control systems for autonomous robotic navigation. Informatica, 17(4):347-369.