USING GAIT CHANGE FOR TERRAIN
SENSING BY ROBOTS
In this paper we
examine the interplay between terrain classification accuracy and gait in a
walking robot, and show how changes in walking speed can be used for
terrain-dependent walk optimizations, as well as to enhance terrain
identification. The details of a walking gait have a great influence on the
performance of locomotive systems and their interaction with the terrain. Most
legged robots can benefit from adapting their gait (and specifically walk
speed) to the particular terrain on which they are walking. To achieve this,
the agent should first be capable of identifying the terrain in order to choose
the optimal speed. In this work we are interested in analyzing the performance
of a legged robot on different terrains and with different gait parameters. We
also discuss the effects of gait parameters, such as speed, on the terrain
identification computed by a legged robot. We use an unsupervised
classification algorithm to classify terrains based on inertial measurement
samples and actuator feedback collected over different terrains and operation
speeds. We present the effects of speed on the terrain classification in our
classification results.
Published in:
Date of
Conference:
28-31 May 2013
Page(s):
16 - 22
Print ISBN:
978-1-4673-6409-6
INSPEC Accession
Number:
13683331
Conference
Location :
Regina, SK
Digital Object
Identifier :
Publisher:
IEEE
