Analyzing and Improving Fault Tolerance of Learning-Based Navigation Systems

TL;DR

This paper evaluates the fault tolerance of learning-based navigation systems and introduces two mitigation techniques that significantly improve their resilience against hardware faults.

Contribution

It provides an experimental analysis of fault impacts and proposes novel mitigation methods tailored for resource-constrained autonomous navigation systems.

Findings

Fault mitigation techniques achieve 2x success rate

39% improvement in quality-of-flight

Enhanced resilience of navigation systems to hardware faults

Abstract

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.