Title :
Learning control of underactuated robots by using discrete event model
Author :
Sakurai, Toshiaki ; Fujimoto, Yasutaka
Author_Institution :
Dept. of Electr. & Comput. Eng., Yokohama Nat. Univ., Yokohama
Abstract :
This paper proposes a new learning method based on a state machine using 2-link manipulator robot. The motion symbols, which decide the robot motion, are generated by the state machine as the time series data. Using this method, the robot can achieve complicated tasks, for example, underactuated robots are controlled. This method is verified by the simulation.
Keywords :
discrete event systems; learning systems; manipulators; motion control; time series; 2-link manipulator robot; discrete event model; learning control; learning method; robot control; robot motion; state machine; time series data; underactuated robots; Animals; Control systems; Electronic mail; Hidden Markov models; Learning systems; Machine learning; Mechanical systems; Robot control; Service robots; State-space methods; Motion symbol; Optimization; State machine; State symbol;
Conference_Titel :
SICE Annual Conference, 2008
Conference_Location :
Tokyo
Print_ISBN :
978-4-907764-30-2
Electronic_ISBN :
978-4-907764-29-6
DOI :
10.1109/SICE.2008.4654915
