Peide Cai
Ph.D. candidate, Department of Electronic & Computer Engineering, HKUST

I am a fourth-year Ph.D. student at the Robotics and Multi-perception Lab in Robotics Institute, Hong Kong Univerisity of Science and Technology, under the supervision of Prof. Ming Liu. Before that, I received my bachelor’s degree in Control Science & Engineering at Zhejiang University in 2018.
My research interests mainly include deep reinforcement learning (DRL), imitation learning (IL), autonomous driving, and robotics.
Complex and various traffic scenarios are hard to model manually, therefore, learning to drive from data is a promising solution. My research focus is to develop stronger AI for autonomous driving, which can automatically learn (end-to-end) control policies with deep learning techniques such as DRL and IL. My ultimate goal is to make the AI driving agent more applicable to daily life and deploy it to complex and challenging driving scenarios.
News
Our work on “DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks” is accepted by IEEE Transactions on Intelligent Transportation Systems.
Our work on “Vision-based Autonomous Car Racing Using Deep Imitative Reinforcement Learning” is accepted by RA-L & IROS 2021.
Our work on “Learning Scalable Self-Driving Policies for Generic Traffic Scenarios with Graph Neural Networks” is accepted by IROS 2021.
Selected publications
Service
Reviewer for IEEE Robotics and Automation Letters (RA-L)Reviewer for IEEE International Conference on Robotics and Automation (ICRA)
Reviewer for IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)