eduzhai > Applied Sciences > Engineering >

Lessons Learned from Accident of Autonomous Vehicle Testing An Edge Learning-aided Offloading Framework

  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: This letter proposes an edge learning-based offloading framework forautonomous driving, where the deep learning tasks can be offloaded to the edgeserver to improve the inference accuracy while meeting the latency constraint.Since the delay and the inference accuracy are incurred by wirelesscommunications and computing, an optimization problem is formulated to maximizethe inference accuracy subject to the offloading probability, the pre-brakingprobability, and data quality. Simulations demonstrate the superiority of theproposed offloading framework.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×