# Analyzing and Improving Fault Tolerance of Learning-Based Navigation Systems

arXiv: https://arxiv.org/abs/2111.04957 · HTML: https://mlsanity.com/paper/2111.04957/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2021.

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

- [Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AI](https://mlsanity.com/paper/2401.01040/) (2024)
- [Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecture](https://mlsanity.com/paper/2409.13153/) (2024)
- [ReaLM: Reliable and Efficient Large Language Model Inference with Statistical Algorithm-Based Fault Tolerance](https://mlsanity.com/paper/2503.24053/) (2025)
- [ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parameters](https://mlsanity.com/paper/2407.04964/) (2024)
- [FRL-FI: Transient Fault Analysis for Federated Reinforcement Learning-Based Navigation Systems](https://mlsanity.com/paper/2203.07276/) (2022)

## Abstract (arXiv)

Learning-based navigation systems are widely used in autonomous applications, such as robotics, unmanned vehicles and drones. Specialized hardware accelerators have been proposed for high-performance and energy-efficiency for such navigational tasks. However, transient and permanent faults are increasing in hardware systems and can catastrophically violate tasks safety. Meanwhile, traditional redundancy-based protection methods are challenging to deploy on resource-constrained edge applications. In this paper, we experimentally evaluate the resilience of navigation systems with respect to algorithms, fault models and data types from both RL training and inference. We further propose two efficient fault mitigation techniques that achieve 2x success rate and 39% quality-of-flight improvement in learning-based navigation systems.