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.

翻译：自主系统（例如无人机）需在严格的机载重量和功率约束下运行复杂的强化学习模型，以执行完全自主的定位-导航-定时任务。我们观察到，降低机载工作电压可提升计算与飞行任务的能效，但同时也可能导致片上比特故障，威胁任务安全与性能。为此，我们提出BERRY——一种增强基于强化学习的自主系统在比特错误鲁棒性与能效方面的鲁棒学习框架。BERRY同时支持离线与无人机机载的鲁棒学习，并首次证明了无人机在低电压下实现鲁棒运行的实用性，从而在计算级操作与系统级飞行质量中均实现高能耗节省。我们在72个自主导航场景中进行了大量实验，结果表明BERRY在不同环境、无人机型号、自主策略、工作电压及故障模式下均具有良好的泛化能力，并能持续提升鲁棒性、效率与任务性能：飞行能耗最高降低15.62%，成功任务数量增加18.51%，处理能耗降低3.43倍。