Spatio-Temporal Case-Based Reasoning*

This paper presents an approach to leaming an optimal behavioral Parameterization in the framework of a Case-Based Reasoning methodology for autonomous navigation tasks. It is based on our previous work on a behavior-based robotic system that also employed spatio-temporal case-based reasoning 131 in the selection of behavioral parameters but was not capable of leaming new parameterimtions. The present method extends the case-based reasoning module by making it capable of leaming new and optimizing the existing cases where each case is a set of behavioral parameters. The leaming process can either be a separate training process or be part of the mission execution. In either case, the robot leams an optimal parameterization of its behavior for different environments it encounters. The goal of this research is not only to automatically optimize the performance of the robot but also to avoid the manual configuration of behavioral parameters and the initial configuration of a case library, both of which require the user to possess good knowledge of robot behavior and the performance of numerous experiments. The presented method was integrated within a hybrid robot architecture and evaluated in extensive computer simulations, showing a significant increase in the performance over a non- adaptive system and a performance comparable to a non-leaming CBR system that uses a hand-coded case library.

[1]  Russell J. Clark,et al.  Case-based reactive navigation: a method for on-line selection and adaptation of reactive robotic control parameters , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[2]  Pat Langley,et al.  Case-Based Acquisition of Place Knowledge , 1995, ICML.

[3]  John Hallam,et al.  A Learning Mobile Robot: Theory, Simulation and Practice , 1997, EWLR.

[4]  Ashwin Ram,et al.  A Multistrategy Case-Based and Reinforcement Learning Approach to Self-Improving Reactive Control Systems for Autonomous Robotic Navigation , 1993 .

[5]  K. Ganesan,et al.  Case-based path planning for autonomous underwater vehicles , 1994, Auton. Robots.

[6]  Rajesh P. N. Rao,et al.  Hierarchical Learning of Navigational Behaviors in an Autonomous Robot using a Predictive Sparse Distributed Memory , 1998, Machine Learning.

[7]  Ronald C. Arkin,et al.  Using Genetic Algorithms to Learn Reactive Control Parameters for Autonomous Robotic Navigation , 1994, Adapt. Behav..

[8]  Ronald C. Arkin,et al.  Spatio-temporal case-based reasoning for behavioral selection , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[9]  Ronald C. Arkin,et al.  Multiagent Mission Specification and Execution , 1997, Auton. Robots.

[10]  Tucker R. Balch,et al.  AuRA: principles and practice in review , 1997, J. Exp. Theor. Artif. Intell..

[11]  Kay Schröter,et al.  AT Humboldt in RoboCup-98 (Team description) , 1998, RoboCup.

[12]  Jaime G. Carbonell,et al.  Derivational Analogy in PRODIGY: Automating Case Acquisition, Storage, and Utilization , 1993, Machine Learning.

[13]  Seth Hutchinson,et al.  A case-based approach to robot motion planning , 1992, [Proceedings] 1992 IEEE International Conference on Systems, Man, and Cybernetics.

[14]  Sridhar Mahadevan,et al.  Automatic Programming of Behavior-Based Robots Using Reinforcement Learning , 1991, Artif. Intell..

[15]  Ronald C. Arkin,et al.  Motor Schema — Based Mobile Robot Navigation , 1989, Int. J. Robotics Res..