Xiaopeng Zong

Papers

Total Citations

H-Index

About

Xiaopeng Zong is a researcher focused on the intersection of reinforcement learning and autonomous vehicle control, with a particular emphasis on dynamic obstacle avoidance. In his most-cited work, "Obstacle Avoidance for Self-Driving Vehicle with Reinforcement Learning" (2017, 24 citations), Zong addresses a critical challenge in self-driving technology: navigating from arbitrary start positions to target positions while safely avoiding both static and moving obstacles of arbitrary shape. This contribution is notable for applying reinforcement learning to a problem traditionally solved with path planning algorithms, offering a more adaptive, learning-based approach to real-time vehicle control. Zong’s work is especially relevant as autonomous vehicles must operate in unpredictable environments with pedestrians, other vehicles, and changing road conditions. By framing obstacle avoidance as a reinforcement learning task, his research opens the door for vehicles that can improve their navigation strategies through experience rather than relying solely on pre-programmed rules. This work has become a reference point for researchers exploring learning-based methods in autonomous driving, demonstrating the potential of AI to handle the complexity and variability of real-world driving scenarios.