An adaptive action model for legged navigation planning

Abstract

Navigation planning for legged robots via foot placement planning has enabled several humanoids to traverse interesting environments autonomously. In this paper we explore methods of adapting foot placement actions to the terrain during the search process, allowing for fuller use of the robot's capabilities, and better resulting paths. We show the results of these adaptive action models for both the humanoid HRP-2 and the quadruped LittleDog.