Kaige of University of Waterloo

Abstract: 

Cooperative perception (CP) is a key technology to facilitate consistent and accurate situational awareness for connected and autonomous vehicles (CAVs). To tackle the network resource inefficiency issue in traditional broadcast-based CP, unicast-based CP has been proposed to associate CAV pairs for cooperative perception via vehicle-to-vehicle transmission. In this work, we investigate unicast-based CP among CAV pairs. With the consideration of dynamic perception workloads and channel conditions due to vehicle mobility and dynamic radio resource availability, we propose an adaptive cooperative perception scheme for CAV pairs in a mixed-traffic autonomous driving scenario with both CAVs and human-driven vehicles. We aim to determine when to switch between cooperative perception and local perception for each CAV pair, and allocate communication and computing resources to cooperative CAV pairs for maximizing the computing efficiency gain under perception task delay requirements. A model-assisted distributed learning solution is developed, which integrates multi-agent reinforcement learning for adaptive CAV cooperation decision and a model-based approach for communication and computing resource allocation. Simulation results demonstrate the effectiveness of the proposed scheme in achieving high computing efficiency gain, as compared with benchmark schemes.

Biography:

Kaige Qu (S’19−M’21) received the Ph.D. degree in electrical and computer Engineering from the University of Waterloo, Waterloo, ON,
Canada, in 2021. She received the B.Sc. degree in communication engineering from Shandong University, Jinan, China, in 2013, and M.Sc. degrees in integrated circuits engineering and electrical engineering from Tsinghua University, Beijing, China, and KU Leuven, Leuven, Belgium, respectively, in 2016. Since February 2021, she has been a Post-doctoral Fellow and then a Research Associate with the Department of Electrical and Computer Engineering, University of Waterloo. Her research interests include connected and autonomous vehicles, network intelligence, network virtualization, and digital twin assisted network automation.

Email:

Address:200 Univ. Ave. West, University of Waterloo, Waterloo, Canada, N2L 3G1