A hybrid adaptive architecture for mobile robots based on reactive behaviors

It is desirable that mobile robots applied to real world applications perform their tasks in previously unknown environments. Thus, a mobile robot architecture capable of adaptation is very suitable. This work presents a hybrid adaptive architecture for mobile robots called AAREACT that has the ability of learning how to coordinate primitive behaviors codified by the potential fields method by using reinforcement learning. The proposed architecture is evaluated in terms of its performance curve when the robot is moved from a scenario to another. Experiments were performed on a Pioneer robot simulator, from ActivMedia Robotics/spl reg/. Results suggest that AAREACT has good adaptation skills for specific environment and task.

[1]  E. Gat.  On Three-Layer Architectures , 1997 .

[2]  Julio Rosenblatt,et al.  DAMN: a distributed architecture for mobile navigation , 1997, J. Exp. Theor. Artif. Intell..

[3]  J. Ota,et al.  Acceleration of reinforcement learning by a mobile robot using generalized rules , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[4]  Hiroshi Ishiguro,et al.  A robot architecture based on situated modules , 1999, Proceedings 1999 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human and Environment Friendly Robots with High Intelligence and Emotional Quotients (Cat. No.99CH36289).

[5]  Robin R. Murphy,et al.  Introduction to AI Robotics , 2000 .

[6]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[7]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[8]  András Lörincz,et al.  Module-Based Reinforcement Learning: Experiments with a Real Robot , 1998, Machine Learning.

[9]  Erann Gat,et al.  Integrating Planning and Reacting in a Heterogeneous Asynchronous Architecture for Controlling Real-World Mobile Robots , 1992, AAAI.

[10]  Kian Hsiang Low,et al.  A hybrid mobile robot architecture with integrated planning and control , 2002, AAMAS '02.

[11]  Antonio Henrique Pinto Selvatici.  AAREACT: uma arquitetura comportamental adaptativa para robôs móveis que integra visão, sonares e odometria. , 2005 .

[12]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[13]  Hideaki Takeda,et al.  A cognitive robot architecture based on tactile and visual information , 1998, Adv. Robotics.

[14]  Maja J. Mataric,et al.  Reward Functions for Accelerated Learning , 1994, ICML.

[15]  Esther Luna Colombini,et al.  An analysis of feature-based and state-based representations for module-based learning in mobile robots , 2005, Fifth International Conference on Hybrid Intelligent Systems (HIS'05).

[16]  Sven Koenig,et al.  A reactive robot architecture with planning on demand , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[17]  Alex M. Andrew,et al.  Reinforcement Learning: : An Introduction , 1998 .

[18]  Ronald C. Arkin,et al.  An Behavior-based Robotics , 1998 .