BERRY: Bit Error Robustness for Energy-Efficient Reinforcement Learning-Based Autonomous Systems

TL;DR

BERRY is a framework that enhances the robustness and energy efficiency of reinforcement learning-based autonomous UAVs operating under low-voltage conditions prone to bit errors, enabling safer and longer missions.

Contribution

It introduces a novel robust learning framework supporting offline and onboard training, demonstrating practical low-voltage operation with significant energy savings and improved mission success.

Findings

Up to 15.62% reduction in flight energy

18.51% increase in successful missions

3.43x reduction in processing energy

Abstract

Autonomous systems, such as Unmanned Aerial Vehicles (UAVs), are expected to run complex reinforcement learning (RL) models to execute fully autonomous position-navigation-time tasks within stringent onboard weight and power constraints. We observe that reducing onboard operating voltage can benefit the energy efficiency of both the computation and flight mission, however, it can also result in on-chip bit failures that are detrimental to mission safety and performance. To this end, we propose BERRY, a robust learning framework to improve bit error robustness and energy efficiency for RL-enabled autonomous systems. BERRY supports robust learning, both offline and on-board the UAV, and for the first time, demonstrates the practicality of robust low-voltage operation on UAVs that leads to high energy savings in both compute-level operation and system-level quality-of-flight. We perform extensive experiments on 72 autonomous navigation scenarios and demonstrate that BERRY generalizes well across environments, UAVs, autonomy policies, operating voltages and fault patterns, and consistently improves robustness, efficiency and mission performance, achieving up to 15.62% reduction in flight energy, 18.51% increase in the number of successful missions, and 3.43x processing energy reduction.