Home /Research /Generation of obstacle avoidance behaviors for quadruped robots using finite automaton
LOCOMOTION

Generation of obstacle avoidance behaviors for quadruped robots using finite automaton

Kiyotaka Izumi, Ryoichi Sato, Keigo Watanabe

Year
2008
Citations
3

Abstract

An obstacle avoidance method is proposed for quadruped robots by using the combination or switching of fundamental actions, which are composed of four, such as go-straight-on action, detour action, striding action, and climbing-over action. The transition of these actions is described in a finite automaton that is understandable visually in two-dimensional plane for our designer compared to any logical description. The external sensor information, provided by a monocular camera, some ultrasonic sensors and some force sensors, are utilized to change the fundamental actions. The effectiveness of the proposed method is demonstrated with some experiments.

Keywords

Action (physics)ObstacleComputer scienceRobotAutomatonClimbingFinite-state machineObstacle avoidanceCellular automatonArtificial intelligence

Related papers

Browse all LOCOMOTION papers