Comparison of behavior-based and planning techniques on the small robot maze exploration problem

Neural Networks

Volumn 23, Issue 4, 2010, Pages 560-567

  Slušný, Stanislav ^a   Neruda, Roman ^a   Vidnerová, Petra ^a  

^a INSTITUTE OF COMPUTER SCIENCE   (Czech Republic)

Author keywords

Evolutionary robotics; Localization; Neural networks; Reinforcement learning

Indexed keywords

BEHAVIOR-BASED; CONTROL ARCHITECTURE; EVOLUTIONARY ROBOTICS; LOCALIZATION; MOBILE ROBOTIC; PLANNING TECHNIQUES; RADIAL BASIS FUNCTION NEURAL NETWORKS; REACTIVE CONTROL; ROBOT CONTROLS; SENSORY ABILITIES; SMALL ROBOTS; STATE SPACE;

EVOLUTIONARY ALGORITHMS; LEARNING ALGORITHMS; MOBILE AGENTS; RADIAL BASIS FUNCTION NETWORKS; REINFORCEMENT; REINFORCEMENT LEARNING; ROBOT PROGRAMMING; ROBOTICS; ROBOTS; WIRELESS NETWORKS;

NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; BEHAVIOR; COMPARATIVE STUDY; CONTROLLED STUDY; MATHEMATICAL ANALYSIS; PLANNING; PRIORITY JOURNAL; RADIAL BASED FUNCTION; REINFORCEMENT; ROBOTICS;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; EXPLORATORY BEHAVIOR; MAZE LEARNING; MOTOR ACTIVITY; NEURAL NETWORKS (COMPUTER); REINFORCEMENT (PSYCHOLOGY); ROBOTICS; SPATIAL BEHAVIOR;

EID: 77950252122     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2010.02.001     Document Type: Article

References (35)

1. E-puck, Online documentation. http://www.e-puck.org.
2. Webots. http://www.cyberbotics.com/.
3. Arkin Ronald C. Behavior-based robotics 1998, The MIT Press.
4. Brooks Rodney A. Integrated systems based on behaviors. SIGART Bulletin 1991, 2(4):46-50.
5. Brooks, Rodney A. (1991). Intelligence without reason. Technical report. Massachusetts Institute of Technology.
6. Chen Gang, Yang Zhonghua, He Hao, Goh Kiah Mok Coordinating multiple agents via reinforcement learning. Autonomous Agents and Multi-Agent Systems 2005, 10(3):273-328.
7. Fogel David B. Evolutionary computation: The fossil record 1998, Wiley-IEEE Press.
8. Ghavamzadeh Mohammad, Mahadevan Sridhar, Makar Rajbala Hierarchical multi-agent reinforcement learning. Autonomous Agents and Multi-Agent Systems 2006, 13(2):197-229.
9. Haykin Simon Neural networks: A comprehensive foundation 1998, Prentice Hall. 2 ed.
10. Holland J.H. Adaptation in natural and artificial systems 1992, MIT Press, Cambridge, MA.
11. Kalman R.E. A new approach to linear filtering and prediction problems. Transactions of the ASME. Series D, Journal of Basic Engineering 1960, 82. 45, 35.
12. Konidaris G.D., Hayes G.M. An architecture for behavior-based reinforcement learning. Adaptive Behavior-Animals, Animats, Software Agents, Robots, Adaptive Systems 2005, 13(1):5-32.
13. LaValle Steven M. Planning algorithms 2006, Cambridge University Press.
14. Matarić Maja J. Reinforcement learning in the multi-robot domain. Autonomous Robots 1997, 4(1):73-83.
15. Mataric M., Cliff D. Challenges in evolving controllers for physical robots. Robotics and Autonomous Systems 1997, 19(1):67-84.
16. Mitchell Tom M. Machine learning 1997, McGraw-Hill Science/Engineering/Math. 1 ed.
17. Moody John, Darken Christian J. Fast learning in networks of locally-tuned processing units. Neural Computation 1989, 1(2):281-294.
18. Moriarty D.E., Schultz A.C., Grefenstette J.J. Evolutionary algorithms for reinforcement learning. Journal of Artificial IntelligenceResearch 1999, 11:241-276.
19. Nolfi Stefano, Floreano Dario Evolutionary robotics: The biology, intelligence, and technology of self-organizing machines 2004, The MIT Press.
20. Pfeifer Rolf, Scheier Christian Understanding intelligence 1999, The MIT Press.
21. Poggio, Tomaso, & Girosi, Federico (1989). A theory of networks for approximation and learning. Technical report. Massachusetts Institute of Technology.
22. Powell M.J.D. Radial basis functions for multivariable interpolation: A review. Algorithms for approximation 1987, 143-167. Clarendon Press.
23. Rubinstein Reuven Y. Simulation and the Monte Carlo method 1981, Wiley-Interscience.
24. Rumelhart D.E., Hinton G.E., Williams R.J. Learning internal representations by error propagation. Parallel distributed processing: Explorations in the microstructure of cognition, Vol. 1: Foundations 1986, 318-362. MIT Press, Cambridge, MA, USA.
25. Schmidhuber, J. (2000). Evolutionary computation versus reinforcement learning. In Industrial electronics society, 2000. IECON 2000. 26th annual conference of the IEEE. Vol. 4, (pp. 2992-2997).
26. Slušný Stanislav, Neruda Roman, Vidnerová Petra Evolution of simple behavior patterns for autonomous robotic agent. System science and simulation in engineering 2007, 411-417. WSEAS Press.
27. Slušný, Stanislav, Neruda, Roman, & Vidnerová, Petra (2007b). Evolving controllers for a homogeneous system of physical robots. Evolving controllers for a homogeneous system of physical robots.
28. Slušný Stanislav, Neruda Roman, Vidnerová Petra Rule-based analysis of behaviour learned by evolutionary and reinforcement algorithms. Proceedings of the 4th international conference on intelligent computing: Advanced intelligent computing theories and applications-With aspects of artificial intelligence 2008, 284-291. Springer-Verlag, Shanghai, China.
29. Slušný Stanislav, Neruda Roman, Vidnerová Petra Comparison of RBF network learning and reinforcement learning on the maze exploration problem. LNCS 2008, 720-729. Springer Verlag.
30. Sutton Richard S., Barto Andrew G. Reinforcement learning: An introduction 1998, The MIT Press.
31. Thrun Sebastian, Burgard Wolfram, Fox Dieter Probabilistic robotics 2005, The MIT Press.
32. Vidnerová, Petra, Slušný, Stanislav, & Neruda, Roman (2008). Evolutionary trained radial basis function networks for robot control. In Control, automation, robotics and vision, 2008, ICARCV 2008, 10th international conference on (pp. 833-838).
33. Watkins, C. (1989). Learning from Delayed Rewards. Ph.D. Thesis. University of Cambridge, England.
34. Whiteson Shimon, Taylor Matthew E., Stone Peter Empirical studies in action selection with reinforcement learning. Adaptive Behavior 2007, 15(1):33-50.
35. Zhou Changjiu Robot learning with GA-based fuzzy reinforcement learning agents. Information Sciences 2002, 145(1-2):45-68.