论文信息 - Optimal regulation and reinforcement learning for the nonholonomic integrator

Optimal regulation and reinforcement learning for the nonholonomic integrator

Reinforcement learning methods based on the Hamilton-Jacobi-Bellman equation have proven to be effective for linear systems. We consider the extension of these methods to a class of nonlinear systems whose linearizations are not controllable. Optimal values for a discounted, infinite horizon cost function based on a smooth homogeneous norm are proposed and validated both for the continuous-time and for the discrete-time three-dimensional nonholonomic integrator.

Roger W. Brockett | Kristi A. Morgansen

[1] S. Lyshevski. Optimization of a class of nonholonomic dynamic systems , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[2] Richard Colbaugh,et al. Learning Control for Nonholonomic Mechanical Systems , 1998 .

[3] Olav Egeland,et al. Exponential stabilization of a nonholonomic underwater vehicle with constant desired configuration , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[4] R. W. Brockett. Asymptotic stability and feed back stabilization , 1983 .

[5] Roger W. Brockett,et al. Characteristic Phenomena and Model Problems in Nonlinear Control , 1996 .

[6] Andrew G. Barto,et al. Adaptive linear quadratic control using policy iteration , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[7] S. Sastry,et al. Adaptive Control: Stability, Convergence and Robustness , 1989 .

[8] George M. Siouris,et al. Applied Optimal Control: Optimization, Estimation, and Control , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[9] Richard Colbaugh,et al. Adaptive control of nonholonomic robotic systems , 1998 .

[10] Graham C. Goodwin,et al. Adaptive filtering prediction and control , 1984 .

[11] Joao P. Hespanha,et al. Logic-based switching control of a nonholonomic system with parametric modeling uncertainty , 1999 .