Backend
From Temperature-Limited to Battery-Limited Legged Locomotion
arXiv eess.SY0 views
arXiv:2611.22231v1 Announce Type: cross Abstract: On legged robots, sustained locomotion often ends in thermal shutdown rather than battery depletion: the heat of walking concentrates in a few joint motors, which overheat long before the battery is empty. We train thermally aware locomotion policies by reinforcement learning without ever observing temperature, and demonstrate this on a Unitree Go2 quadruped. We first identify a coupled 13-node lumped RC thermal network, fitted on two runs of a single robot and calibrated against the measured electrical power, that predicts all twelve motor temperatures with a mean RMSE below 1 $^\circ$C across different robot instances, gaits, payloads, and speeds. Under a sustained gait, the temperatures the motors will settle at follow directly from the gait-averaged squared torques and joint speeds. Our core contribution is a reward that drives down the hottest predicted asymptotes: thermal time constants exceed the credit-assignment horizon of reinforcement learning by orders of magnitude, but predicted asymptotes respond to torque and joint speed within a single gait cycle, so the policy learns to lower and spread heat with no temperature input. On the robot, the policy turns sustained locomotion from temperature-limited to battery-limited: with a 5 kg payload at 1 m/s, a learned baseline reaches thermal shutdown after 19 minutes (1.1 km), whereas our policy runs the battery down after 174 minutes (10.0 km) with its hottest motor 14 $^\circ$C below the shutdown threshold in a 26 $^\circ$C room; on an unloaded factory circuit with stairs and ramps, the baseline overheats after 25 laps (6.2 km), while our policy completes 47 (11.2 km) on one battery with 22 $^\circ$C of margin.
Source:https://arxiv.org/abs/2611.22231PreviousWhen does deep reinforcement learning pay off in HVAC supervisory control? Four small Modelica case studies trained directly on FMUsNextLearning Regions of Attraction for Transverse Feedback Linearization under Controller Singularities
Related posts
Right Goal, Wrong Body: Re-grounding Frozen VLAs under Actuation Shift
0arXiv cs.RO
DAPPT: Domain-Aware Policies from Procedural Trajectories for Sim-to-Real Dexterous Tool Use
0arXiv cs.RO
Prompt Re-Specification and Target-Mask Availability in Mask-Conditioned Visual Reinforcement Learning for Moving-Platform Landing
0arXiv cs.RO
Drone Navigation for Fast, Safe Emergency Response
0arXiv cs.RO
Why Your Enterprise Needs Digital Transformation Strategy Consulting Now!
0dev.to AI
How do I get a receipt when one AI researches and another writes the final work?
0dev.to AI