Information-Efficient Model Identification for Tensegrity Robot Locomotion

TitleInformation-Efficient Model Identification for Tensegrity Robot Locomotion
Publication TypeReport
Year of Publication2018
AuthorsZhu, S, Surovik, D, Bekris, KE, Boularias, A
Series TitleAAAI Spring Symposium Series 2018
Date Published03/2018
CityStanford University, CA, USA
TypeSymposium on Integrating Representation, Reasoning, Learning, and Execution for Goal Directed Autonomy
Abstract

This paper aims to identify in a practical manner unknown physical parameters, such as mechanical models of actuated robot links, which are critical in dynamical robotic tasks. Key features include the use of an off-the-shelf physics engine and the data-efficient adaptation of a black-box Bayesian optimization framework. The task being considered is locomotion with a high-dimensional, compliant tensegrity robot. A key insight in this case is the need to project the system identification challenge into an appropriate lower dimensional space. Comparisons with alternatives indicate that the proposed method can identify the parameters more accurately within the given time budget, which also results in more precise locomotion control.