Reinforcement Learning Approach to Generate Goal-directed Locomotion of a Snake-Like Robot with Screw-Drive Units

Sromona Chatterjee, Timo Nachstedt, Minija Tamosiunaite, Florentin Wörgötter, Poramate Manoonpong, Yoshihide Enomoto, Ryo Ariizumi, Fumitoshi Matsuno

Publikation: Kapitel i bog/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Abstrakt

Abstract—In this paper we apply a policy improvement algorithm called Policy Improvement using Path Integrals (PI2) to generate goal-directed locomotion of a complex snake-like robot with screw-drive units. PI2 is numerically simple and has an ability to deal with high dimensional systems. Here, this approach is used to find proper locomotion control parameters, like joint angles and screw-drive velocities, of the robot. The learning process was achieved using a simulated robot and the learned parameters were successfully transferred to the real one. As a result the robot can locomote toward a given goal.
OriginalsprogEngelsk
TitelProceedings of the 23rd International Conference on Robotics in Alpe-Adria-Danube Region
ForlagIEEE
Publikationsdato2014
ISBN (Trykt)978-80-227-4219-1
DOI
StatusUdgivet - 2014
Begivenhed23rd International Conference on Robotics in Alpe-Adria-Danube Region - Smolenice Castle, Smolenice, Slovakiet
Varighed: 3. sep. 20145. sep. 2014
Konferencens nummer: 23

Konference

Konference23rd International Conference on Robotics in Alpe-Adria-Danube Region
Nummer23
LokationSmolenice Castle
LandSlovakiet
BySmolenice
Periode03/09/201405/09/2014

Fingeraftryk

Dyk ned i forskningsemnerne om 'Reinforcement Learning Approach to Generate Goal-directed Locomotion of a Snake-Like Robot with Screw-Drive Units'. Sammen danner de et unikt fingeraftryk.

Citationsformater