Lessons Learned From Accident of Autonomous Vehicle Testing: An Edge Learning-Aided Offloading Framework
Bo Yang, Xuelin Cao, Xiangfang Li, Chau Yuen, Lijun Qian
Abstract
This letter proposes an edge learning-based offloading framework for autonomous driving, where the deep learning tasks can be offloaded to the edge server to improve the inference accuracy while meeting the latency constraint. Since the delay and the inference accuracy are incurred by wireless communications and computing, an optimization problem is formulated to maximize the inference accuracy subject to the offloading probability, the pre-braking probability, and data quality. Simulations demonstrate the superiority of the proposed offloading framework.
Topics & Concepts
Computer scienceInferenceEdge computingServerEnhanced Data Rates for GSM EvolutionLatency (audio)WirelessArtificial intelligenceMobile edge computingMachine learningComputer networkTelecommunicationsPrivacy-Preserving Technologies in DataAdvanced Neural Network ApplicationsAge of Information Optimization