Efficient Model Identification for Tensegrity Locomotion
This work addresses a domain-specific challenge in robotics for more efficient model-based control of complex systems, representing an incremental improvement.
The paper tackles the problem of identifying unknown physical parameters for a high-dimensional, compliant Tensegrity robot to improve locomotion control, achieving more accurate parameter identification within a set time budget compared to alternatives.
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 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 model identification challenge into an appropriate lower dimensional space for efficiency. 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.