Rough terrain mapping and classification for foothold selection in a walking robot

• DOI: 10.1002/rob.20397
• Publication Date: 2011-06-21T13:53:47Z
• Authors: Dominik Belter; Piotr Skrzypczyński
• Keywords: Traverse; Legged robot; Hexapod; Raised-relief map

Abstract Although legged locomotion over a moderately rugged terrain can be accomplished by employing simple reactions to the ground contact information, more effective approach, which allows predictively avoiding obstacles, requires model of environment and control algorithm that takes this into account when planning footsteps leg movements. This article addresses issues perception modeling foothold selection in walking robot. An integrated system is presented robot traverse previously unseen, uneven using only onboard perception, provided reasonable general path known. efficient method for real‐time building local elevation map from sparse two‐dimensional (2D) range measurements miniature 2D laser scanner described. The mapping module supports algorithm, employs unsupervised learning create an adaptive decision surface. learn realistic simulations; therefore no priori expert‐given rules or parameters are used. usefulness our approach demonstrated experiments with six‐legged Messor. We discuss lessons learned field tests modifications turned out essential successful operation under real‐world conditions. © 2011 Wiley Periodicals, Inc.