Zikang Xiong

Papers

Total Citations

H-Index

About

Zikang Xiong is an emerging researcher specializing in safe reinforcement learning, robot navigation, and neural control systems. His work sits at the critical intersection of deep reinforcement learning and safety-critical robotics, addressing one of the most pressing challenges in autonomous systems: ensuring provable safety guarantees without sacrificing performance. His most notable contribution, "Model-free Neural Lyapunov Control for Safe Robot Navigation" (2022), tackles the fundamental limitation of model-free deep reinforcement learning controllers — their inherent lack of safety assurance. By integrating neural Lyapunov functions with model-free DRL frameworks, Xiong developed a principled approach that encodes safety constraints directly into the learning process, enabling robots to navigate complex, dynamic environments while maintaining formal stability guarantees. This work has garnered 10 citations since its publication, reflecting growing community interest in bridging theoretical control-theoretic foundations with practical deep learning methodologies. Xiong's research addresses a timely and consequential problem as autonomous robots and AI-driven systems are increasingly deployed in real-world settings where safety failures carry significant consequences, positioning him as a promising contributor to the next generation of trustworthy autonomous systems research.