The problem of finding thermally minimizing configurations of a humanoid robot to recover its actuators from unsafe thermal states is addressed. A first-order, data-driven, effort-based, thermal model of the robot's actuators is devised, which is used to predict future thermal states. Given this predictive capability, a map between configurations and future temperatures is formulated to find what configurations, subject to valid contact constraints, can be taken now to minimize future thermal states. Effectively, this approach is a realization of a contact-constrained thermal inverse-kinematics (IK) process. Experimental validation of the proposed approach is performed on the NASA Valkyrie robot hardware.
@article{arxiv.1902.00187,
title = {Thermal Recovery of Multi-Limbed Robots with Electric Actuators},
author = {Steven Jens Jorgensen and James Holley and Frank Mathis and Joshua S. Mehling and Luis Sentis},
journal= {arXiv preprint arXiv:1902.00187},
year = {2019}
}
Comments
8 pages, 7 figures, Published to IEEE Robotics and Automation Letters on January 18, 2019. Corrections on Arxiv Version Added on May, 2019