The Ultimate Solution for L4 Autonomous Driving: Cooperative Perception

[CFAR Outstanding PhD Student Seminar Series]
The Ultimate Solution for L4 Autonomous Driving: Cooperative Perception by Xu Runsheng
12 Apr 2023 | 10.00am (Singapore Time)

Autonomous driving perception systems are faced with significant challenges, such as occlusion and sparse sensor observations at a distance. Cooperative perception presents a promising solution to these challenges as it utilises vehicle-to-everything (V2X) communication that enables autonomous vehicles to share visual information with each other.

In this seminar, Xu Runsheng from the University of California, Los Angeles will explore the state-of-the-art technologies in cooperative perception and present his recent research on the topic, including three published papers: (1) V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer (ECCV2022), (2) CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers (CoRL2022) and (3) V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception (CVPR2023 Highlight). He will also share insights into the current developments and future directions in autonomous driving perception.

Xu Runsheng
Ph.D. Candidate
University of California, Los Angeles (UCLA)
Xu Runsheng is a Ph.D. candidate at the University of California, Los Angeles (UCLA), specialising in autonomous driving research. Having worked as a Senior Deep Learning Engineer at Mercedes-Benz R&D North America and as a Computer Vision Engineer at OPPO Mobile R&D US, he brings extensive industry experience. Runsheng has made significant contributions to several high-impact commercial projects, including OPPO Reno2 Low-Light Imaging and Mercedes-Benz Autopilot systems. As the first author, he has published numerous articles in top-tier vision and robotics conferences and journals, such as CVPR, ECCV, CoRL, ICRA, and IROS. Additionally, Runsheng has developed a widely recognised coding framework in the connected autonomous driving domain, garnering thousands of GitHub stars for its popularity and utility.