DMCA
A unified motion planning method for a multifunctional underwater robot
BibTeX
@MISC{Shiraishi_aunified,
author = {Koichiro Shiraishi and Hajime Kimura},
title = {A unified motion planning method for a multifunctional underwater robot},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper deals with motion planning for a mul-tifunctional underwater robot which can accomplish various missions, e.g., swimming, walking and grasp-ing objects. Authors have developed a unified motion planning method which can generate motion planning for a variety of task by a single algorithm. In this method, motion planning problems are modeled as fi-nite horizon Markov decision processes. The optimum motion planning is obtained by Dynamic Program-ming, however　 Dynamic Programming is sometimes thought to be of limited applicability because of the curse of dimensionality. To avoid the curse of dimen-sionality, authors applied a random network as a state transition network. The explosion of the number of states can be suppressed by using the random network. The effectiveness of the proposed method is demon-strated through numerical simulations of two types of tasks for multifunctional robots. One is a reaching task, the other is a generating thrust force task.
Keyphrases
unified motion planning method multifunctional underwater robot motion planning random network dynamic program-ming dynamic programming fi-nite horizon markov decision various mission optimum motion planning single algorithm motion planning problem multifunctional robot numerical simulation thrust force task grasp-ing object state transition network limited applicability mul-tifunctional underwater robot
