Low-Latency Edge Video Analytics for On-Road Perception of Autonomous Ground Vehicles

To improve the transportation efficiency of advanced manufacturing, cameras have been extensively deployed to enhance the on-road perception of autonomous ground vehicles in smart industrial parks. Considering the informative yet substantial data volume of contents generated by those cameras, we employ vehicle-to-everything links to deliver the captured video frames to neighboring vehicles, road-side units, or base stations, in order to respond to vehicle-control-related video queries. To help vehicles obtain low-latency and high-accuracy on-road information for autonomous driving, an optimization problem is formulated, taking into account the impact of vehicle mobility and diverse resource demands of different video queries. Then, a two-stage algorithm is proposed to determine the frame rate of video cameras, as well as the destination of the associated video frames based on matching theory. Extensive simulation results show that this approach can improve the accuracy by up to 18% and reduce the response delay by 13.2%.

I. Introduction

Autonomous driving plays an important role in achieving safe and efficient transportation, and improving economic efficiency [1]. However, it has not yet been deployed at scale, since it is difficult to rely on current offline-trained vehicle control algorithms to achieve absolute driving safety under complex and dynamic road conditions. In contrast, autonomous driving has already been applied extensively in smart industrial parks in the form of autonomous ground vehicle (AGV) [2], as smart industrial parks are relatively isolated compared with urban or highway scenarios, which are ideal testbeds of autonomous driving techniques. For instance, AGVs are applied in mine clearing, firefighting, and smart ports [3] for precise positioning and delivering heavy/bulky pieces between manufacturing stations [4].