Papers
9
Total Citations
264
H-Index
7
About
Zhen Ni is a leading researcher at the intersection of reinforcement learning, adaptive optimal control, and human-robot interaction (HRI), with a particular focus on crowd safety and autonomous navigation. Their most significant contributions lie in developing robot-assisted pedestrian regulation systems that leverage deep reinforcement learning to prevent crowd disasters in densely populated areas. Ni's pioneering work demonstrates how mobile robots can passively influence pedestrian flow through HRI, effectively mitigating dangerous phenomena like the "faster-is-slower" effect in emergency evacuations. Their highly cited 2018 paper on robot-assisted pedestrian regulation using deep reinforcement learning (80 citations) established a new paradigm for crowd management, while their 2023 work on safe reinforcement learning for obstacle avoidance (71 citations) introduced innovative barrier function techniques into adaptive optimal control. Ni has also advanced the field through data-driven heuristic dynamic programming and event-triggered adaptive dynamic programming methods. Their research portfolio, spanning from foundational theory to practical implementations with Turtlebot robots and virtual reality systems, has garnered over 260 citations, demonstrating substantial impact on both the robotics and control systems communities.
Research Focus
Key Achievements
Top Papers
- 1Robot-Assisted Pedestrian Regulation Based on Deep Reinforcement Learning80 citations · 2018
- 2
- 3
- 4Robot-assisted pedestrian regulation in an exit corridor20 citations · 2016
- 5
- 6Data-driven heuristic dynamic programming with virtual reality17 citations · 2015
- 7
- 8
- 9