Feasible control of complex systems using automatic learning
Feasible control of complex systems using automatic learning
- Neue Suche nach: Agostini, Alejandro
- Neue Suche nach: Celaya, Enric
- Neue Suche nach: Agostini, Alejandro
- Neue Suche nach: Celaya, Enric
International Conference on Informatics in Control, Automation and Robotics (ICINCO), 2005, Barcelona (España) ; Robotic applications often involve dealing with complex dynamic systems. In these cases coping with control requirements with conventional techniques is hard to achieve and a big effort has to be done in the design and tuning of the control system. An alternative to conventional control techniques is the use of automatic learning systems that could learn control policies automatically, by means of the experience. But the amount of experience required in complex problems is intractable unless some generalization is performed. Many learning techniques have been proposed to deal with this challenge but the applicability of them in a complex control task is still difficult because of their bad learning convergence or insufficient generalization. In this work a new learning technique, that exploits a kind of generalization called categorization, is used in a complex control task. The results obtained show that it is possible to learn, in short time and with good convergence, a control policy that outperforms a classical PID control tuned for the specific task of controlling a manipulator with high inertia and variable load. ; This work was supported by the project 'Sistema reconfigurable para la navegación basada en visión de robots caminantes y rodantes en entornos naturales.' (00). ; Peer Reviewed
Dokumentinformationen
Feasible control of complex systems using automatic learning
2005-01-01
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Robot control , Reinforcement learning , Categorization , Control theory , Cybernetics: Artificial intelligence: Generalisation (artificial intelligence) , Automation: Robots: Intelligent robots , Cybernetics: Artificial intelligence: Learning (artificial intelligence) , Automatic theorem proving , Intelligent robots and autonomous agents , Machine learning
| DDC: | 629 |
Ähnliche Titel
Methods and systems for balanced feasible and stable control
| Europäisches Patentamt | 2020
Methods and Systems for Balanced Feasible and Stable Control
| Europäisches Patentamt | 2019
Feasible Controller Design for Stochastic Systems
| Online Contents | 1997
Automatic driving feasible region control method and system based on roadside fusion perception
| Europäisches Patentamt | 2021