Learning to Drive and Simulate Autonomous Mobile Robots

We show how to apply learning methods to two robotics problems, namely the optimization of the on-board controller of an omnidirectional robot, and the derivation of a model of the physical driving behavior for use in a simulator. We show that optimal control parameters for several PID controllers can be learned adaptively by driving an omni directional robot on a field while evaluating its behavior, using an reinforcement learning algorithm. After training, the robots can follow the desired path faster and more elegantly than with manually adjusted parameters. Secondly, we show how to learn the physical behavior of a robot. Our system learns to predict the position of the robots in the future according to their reactions to sent commands. We use the learned behavior in the simulation of the robots instead of adjusting the physical simulation model whenever the mechanics of the robot changes. The updated simulation reflects then the modified physics of the robot.

[1]  Sven Behnke,et al.  Predicting Away Robot Control Latency , 2003, RoboCup.

[2]  Sven Behnke,et al.  Robust Real Time Color Tracking , 2000, RoboCup.

[3]  Peter Stone,et al.  Policy gradient reinforcement learning for fast quadrupedal locomotion , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[4]  Rodney A. Brooks,et al.  Real Robots, Real Learning Problems , 1993 .

[5]  Tore Hägglund,et al.  Automatic Tuning and Adaptation for PID Controllers - A Survey , 1992 .

[6]  J. G. Ziegler,et al.  Optimum Settings for Automatic Controllers , 1942, Journal of Fluids Engineering.

[7]  Tore Hägglund,et al.  Automatic Tuning and Adaptation for PID Controllers—A Survey , 1992 .

[8]  Bernhard Nebel,et al.  Towards a Life-Long Learning Soccer Agent , 2002, RoboCup.

[9]  Tore Hägglund,et al.  Advances in Pid Control , 1999 .

[10]  John R. Koza,et al.  Genetic Programming IV: Routine Human-Competitive Machine Intelligence , 2003 .

[11]  Sven Behnke,et al.  Predicting away the Delay , 2003 .

[12]  Peter Stone,et al.  Reinforcement Learning for 3 vs. 2 Keepaway , 2000, RoboCup.

[13]  Karl Johan Åström,et al.  PID Controllers: Theory, Design, and Tuning , 1995 .

[14]  Alexander Gloye,et al.  Plug & Play : Fast Automatic Geometry and Color Calibration for Cameras Tracking Mobile Robots , 2004 .

[15]  Martin A. Riedmiller,et al.  Self-learning neural control of a mobile robot , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[16]  Sven Behnke,et al.  Using Hierarchical Dynamical Systems to Control Reactive Behavior , 1999, RoboCup.

[17]  Sridhar Mahadevan,et al.  Robot Learning , 1993 .