Thermal Recovery of Multi-Limbed Robots with Electric Actuators
This addresses thermal management for humanoid robots in real-world applications, representing an incremental improvement in robot safety and endurance.
The paper tackles the problem of finding robot configurations that minimize future thermal states of actuators to enable recovery from overheating, achieving a 40% reduction in peak actuator temperature during experimental validation on the NASA Valkyrie robot.
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.