Analyzing and Improving Fault Tolerance of Learning-Based Navigation Systems
This addresses safety-critical issues in autonomous applications like robotics and drones, but it is incremental as it builds on existing fault tolerance methods.
The paper tackled the problem of hardware faults in learning-based navigation systems, which can cause safety violations, by evaluating their resilience and proposing two efficient mitigation techniques that achieved a 2x success rate and 39% quality-of-flight improvement.
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.