Name
Abstract | ||
|---|---|---|
A model, predictor, or error estimator is often used by a feedback controller to control a plant. Creating such a model is difficult when the plant exhibits nonlinear behavior. In this paper, a novel online learning control framework is proposed that does not require explicit knowledge about the plant. This framework uses two learning modules, one for creating an inverse model, and the other for actually controlling the plant. Except for their inputs, they are identical. The inverse model learns by the exploration performed by the not yet fully trained controller, while the actual controller is based on the currently learned model. The proposed framework allows fast online learning of an accurate controller. The controller can be applied on a broad range of tasks with different dynamic characteristics. We validate this claim by applying our control framework on several control tasks: 1) the heating tank problem (slow nonlinear dynamics); 2) flight pitch control (slow linear dynamics); and 3) the balancing problem of a double inverted pendulum (fast linear and nonlinear dynamics). The results of these experiments show that fast learning and accurate control can be achieved. Furthermore, a comparison is made with some classical control approaches, and observations concerning convergence and stability are made. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/TNNLS.2012.2208655 | Neural Networks and Learning Systems, IEEE Transactions |
Keywords | Field | DocType |
control engineering computing,feedback,learning (artificial intelligence),nonlinear control systems,stability,balancing problem,double inverted pendulum,dynamic characteristic,feedback control,flight pitch control,heating tank problem,inverse model,nonlinear behavior,online learning control,slow linear dynamics,slow nonlinear dynamics,Adaptive control,feedback control,heating tank,inverted pendulum,neural network,pitch control,reservoir computing | Control theory,Inverted pendulum,Nonlinear system,Control theory,Computer science,Reservoir computing,Adaptive control,Artificial neural network,Double inverted pendulum,Pitch control | Journal |
Volume | Issue | ISSN |
23 | 10 | 2162-237X |
Citations | PageRank | References |
17 | 0.86 | 20 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Waegeman, T. | 1 | 17 | 0.86 |
| Francis Wyffels | 2 | 17 | 0.86 |
| Francis Schrauwen | 3 | 17 | 0.86 |