时间：3月26日（周二）9:00
地点：正阳会议中心2号楼报告厅
主讲人：庄卫华Zhuang Weihua
摘要：Artificial intelligence (Al) models will continue to be pervasively deployed to support diverse applications in the 5G/6G era. In this presentation, we investigate Al for cooperative perception to achieve reliable situation awareness of connected and autonomous vehicles (CAvs), We discuss the key challenges and present an accuracy-aware and resource-efficient raw-level cooperative sensing and computing scheme among CAvs and road-side infrastructure. 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, object classification task placement, and resource allocation, 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. Numerical results demonstrate the accuracy awareness and resource efficiency achieved by the proposed cooperative sensing and computing scheme, in comparison with benchmark solutions.
