Robot Control Optimization Using Reinforcement Learning

Conventional robot control schemes are basically model-based methods. However, exact modeling of robot dynamics poses considerable problems and faces various uncertainties in task execution. This paper proposes a reinforcement learning control approach for overcoming such drawbacks. An artificial ne...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of intelligent & robotic systems Ročník 21; číslo 3; s. 221 - 238
Hlavní autoři: Song, Kai-Tai, Sun, Wen-Yu
Médium: Journal Article
Jazyk:angličtina
Vydáno: Dordrecht Kluwer 01.03.1998
Springer Nature B.V
Témata:
Applied sciences
Artificial intelligence
Artificial neural networks
Computer science; control theory; systems
Computer simulation
Connectionism. Neural networks
Control theory. Systems
Dynamic models
Exact sciences and technology
Learning
Learning theory
Machine learning
Mathematical models
Neural networks
Reinforcement
Robot arms
Robot control
Robot dynamics
Robot learning
Robotics
Robots
Studies
Tracking
Tracking control
Learning
Experimental result
Simulation
Reinforcement learning
Control synthesis
Tracking task
Neural network
Trajectory
Artificial intelligence
Robotics
ISSN:0921-0296, 1573-0409
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Conventional robot control schemes are basically model-based methods. However, exact modeling of robot dynamics poses considerable problems and faces various uncertainties in task execution. This paper proposes a reinforcement learning control approach for overcoming such drawbacks. An artificial neural network (ANN) serves as the learning structure, and an applied stochastic real-valued (SRV) unit as the learning method. Initially, force tracking control of a two-link robot arm is simulated to verify the control design. The simulation results confirm that even without information related to the robot dynamic model and environment states, operation rules for simultaneous controlling force and velocity are achievable by repetitive exploration. Hitherto, however, an acceptable performance has demanded many learning iterations and the learning speed proved too slow for practical applications. The approach herein, therefore, improves the tracking performance by combining a conventional controller with a reinforcement learning strategy. Experimental results demonstrate improved trajectory tracking performance of a two-link direct-drive robot manipulator using the proposed method.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISSN:0921-0296
1573-0409
DOI:10.1023/A:1007904418265