Title :
Fall avoidance of bipedalwalking robot by profit sharing that can learn deterministic policy for POMDPs environments
Author :
Suzuki, Takumi ; Osana, Yuko
Author_Institution :
Sch. of Comput. Sci., Tokyo Univ. of Technol., Tokyo, Japan
fDate :
July 30 2014-Aug. 1 2014
Abstract :
In this paper, fall avoidance of bipedal walking robot is realized by the Profit Sharing that can learn deterministic policy for POMDPs environments. In this research, the Profit Sharing that can learn deterministic policy for POMDPs environments which can obtain the deterministic policy by using the history of observations is employed. We carried out a series of experiments using bipedal walking robot, and confirmed that attitude control can be realized by the Profit Sharing that can learn deterministic policy for POMDPs environments.
Keywords :
attitude control; learning (artificial intelligence); legged locomotion; POMDP environments; attitude control; bipedal walking robot; deterministic policy; fall avoidance; observation history; profit sharing; Accelerometers; Robots; Bipedal Walking Robot; Fall Avoidance; Reinforcement Learning;
Conference_Titel :
Nature and Biologically Inspired Computing (NaBIC), 2014 Sixth World Congress on
Conference_Location :
Porto
Print_ISBN :
978-1-4799-5936-5
DOI :
10.1109/NaBIC.2014.6921875
