Accuracy-Aware Cooperative Sensing and Computing for Connected Autonomous Vehicles

TL;DR

An optimization problem for joint sensing data selection, subtask placement and resource allocation among multiple object classification subtasks is formulated, to minimize the total resource cost while satisfying the delay and accuracy requirements.

Abstract

To maintain high perception performance among connected and autonomous vehicles (CAVs), in this paper, we propose an accuracy-aware and resource-efficient raw-level cooperative sensing and computing scheme among CAVs and road-side infrastructure. The scheme enables fined-grained partial raw sensing data selection, transmission, fusion, and processing in per-object granularity, by exploiting the parallelism among object classification subtasks associated with each object. A supervised learning model is trained to capture the relationship between the object classification accuracy and the data quality of selected object sensing data, facilitating accuracy-aware sensing data selection. We formulate an optimization problem for joint sensing data selection, subtask placement and resource allocation among multiple object classification subtasks, to minimize the total resource cost while satisfying the delay and accuracy requirements. A genetic algorithm based iterative solution is proposed for the optimization problem. Simulation results demonstrate the accuracy awareness and resource efficiency achieved by the proposed cooperative sensing and computing scheme, in comparison with benchmark solutions.

Figures (10)

• Figure 1: An illustration of edge-assisted autonomous driving scenario.
• Figure 2: The simulated LiDAR 3D point clouds of two CAVs. (a) Provided by the ego CAV. (b) Provided by an assisting CAV.
• Figure 3: An illustration of 3D bounding box partition with $K=2$.
• Figure 4: A flowchart of the proposed algorithm.
• Figure 5: Object classification accuracy for object $0$. (a) Using data from ego CAV $0$. (b) Using data from assisting CAV $1$.