Lessons Learned from Accident of Autonomous Vehicle Testing: An Edge Learning-aided Offloading Framework
This addresses safety and efficiency challenges in autonomous vehicles by optimizing task offloading to edge servers, though it appears incremental as it builds on existing edge computing concepts.
The authors tackled the problem of improving inference accuracy for autonomous driving tasks under latency constraints by proposing an edge learning-based offloading framework that optimizes accuracy while considering offloading probability, pre-braking probability, and data quality. Simulations demonstrated the framework's superiority, though no concrete numbers were provided.
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.