Swinging up the Acrobot: an example of intelligent control

In our approach, intelligent control integrates the symbolic reasoning of artificial intelligence (AI) into the control procedure. We describe how this can be accomplished by a straightforward abstraction of the conventional notion of the control model. We apply the techniques to the problem of swing-up control of the Acrobot. The resulting explanation-based control strategy is compared with two more-conventionally-derived control strategies. We briefly discuss the strengths and weaknesses of the new approach.

[1]  Kenneth D. Forbus.  Qualitative Process Theory , 1984, Artif. Intell..

[2]  Michael R. Genesereth,et al.  Logical foundations of artificial intelligence , 1987 .

[3]  Mark W. Spong,et al.  Robot dynamics and control , 1989 .

[4]  Benjamin J. Kaipers,et al.  Qualitative Simulation , 1989, Artif. Intell..

[5]  G. DeJong,et al.  A machine learning approach to intelligent adaptive control , 1990, 29th IEEE Conference on Decision and Control.

[6]  M. W. Spong,et al.  Pseudolinearization of the acrobot using spline functions , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[7]  I. Kanellakopoulos,et al.  Backstepping to passivity: recursive design of adaptive systems , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[8]  Mark W. Spong,et al.  Swing up control of the Acrobot , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[9]  Gerald DeJong,et al.  Learning to Plan in Continuous Domains , 1994, Artif. Intell..