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

arXiv: https://arxiv.org/abs/2307.10041 · HTML: https://mlsanity.com/paper/2307.10041/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2023.

## Built on by (most cited first, 5 of 5)

- [H3DFact: Heterogeneous 3D Integrated CIM for Factorization with Holographic Perceptual Representations](https://mlsanity.com/paper/2404.04173/) (2024)
- [FLARE: One-Shot PE-Level Fault Localization in Systolic Arrays via Algebraic Test Vectors](https://mlsanity.com/paper/2605.08594/) (2026)
- [MAPS: Energy-Reliability Tradeoff Management in Autonomous Vehicles Through LLMs Penetrated Science](https://mlsanity.com/paper/2409.06558/) (2024)
- [Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors](https://mlsanity.com/paper/2507.18804/) (2025)
- [Vector Symbolic Policy Gradient](https://mlsanity.com/paper/2608.18404/) (2026)

## Abstract (arXiv)

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.