Thermal-headroom routing improves robot perception under high heat
Thermal-Headroom Routing for Efficient Robot Perception in Extreme Heat
RoboticsComputer Vision and Pattern RecognitionPerformance
Summary
Robot cameras and sensors need to work well without getting too hot and slowing down. The authors introduce a technique called Thermal-Headroom Routing (THR) that predicts if a robot’s processor will overheat and adjusts how it runs perception tasks to avoid slowing down. Their tests show THR helps keep tasks on time and saves energy when it’s very hot. It works better than methods that don’t predict overheating or use fixed rules. They also checked parts of their model on real hardware but found no actual processor slowing yet.
What this means in practice
- •For robotics engineers: Manage robot perception tasks efficiently in hot environments by predicting processor overheating to meet time and energy constraints.
- •For embedded system developers: Optimize real-time device sensor workloads under varying temperatures to avoid processor slowdowns and energy waste.
Authors
Sparsh Roy, Kevin Zhou, Arhaan Shah, Shreyan Garg, Vihaan Joshi-Apte, Maxim Kudryashov, Nanda Cheruvanthala
Abstract
Adaptive robot perception systems must balance detector accuracy, inference latency, and energy consumption, particularly when high ambient temperatures cause processors to thermally throttle. We propose Thermal-Headroom Routing (THR), a lightweight model-selection policy that forecasts processor temperature using a closed-form RC thermal model and excludes detector configurations predicted to cross a throttling threshold. We evaluate THR with four YOLO11 configurations across seven real-world perception traces, eight ambient temperatures, and 20 randomized seeds, comparing it with latency-aware routing, fixed-threshold thermostats, duty caps, and a matched-compute-budget control. At ambient temperatures of 45-55 degrees C and a tight inference deadline, THR eliminates throttling in simulation, reduces deadline misses by 3.9-7.5 percentage points, and reduces energy per on-time frame by approximately 12-13% relative to a latency-belief router. A separate experiment using deadline-paced, nonoverlapping frame execution yields miss-rate reductions of 6.2-9.5 percentage points. A tuned thermostat or duty cap can match THR at a fixed operating point; predictive routing is most useful when ambient conditions or calibrated thermal parameters differ from those used to tune static policies. Measurements on an Apple M5 support the single-node heating approximation but do not validate hardware throttling. The results characterize the conditions under which thermal forecasting improves the efficiency and timeliness of resource-constrained robot perception.