Perception Simplex: Verifiable Collision Avoidance in Autonomous Vehicles Amidst Obstacle Detection Faults

arXiv:2209.01710v2 Announce Type: replace-cross
Abstract: Advances in deep learning have revolutionized cyber-physical applications, including the development of Autonomous Vehicles. However, real-world collisions involving autonomous control of vehicles have raised significant safety concerns regarding the use of Deep Neural Networks (DNN) in safety-critical tasks, particularly Perception. The inherent unverifiability of DNNs poses a key challenge in ensuring their safe and reliable operation.
In this work, we propose Perception Simplex (PS), a fault-tolerant application architecture designed for obstacle detection and collision avoidance. …

abstract advances applications arxiv autonomous autonomous vehicles collision concerns control cs.lg cs.ro cs.sy cyber deep learning detection development dnn eess.sy however networks neural networks perception safety safety-critical tasks type vehicles world