Jianshuo Zhao
Papers
2
Total Citations
25
H-Index
2
About
Jianshuo Zhao is a leading researcher in the field of autonomous robotics, with a primary focus on intelligent path planning and navigation for mobile robots operating in unknown environments. His major contributions center on the innovative integration of reinforcement learning—specifically Q-learning—with potential field methods to solve the critical challenge of enabling robots to reach their destinations safely and efficiently without prior environmental maps. Zhao’s work directly addresses the trade-off between path length and safety, a persistent problem in robotics. His two most cited papers, both from 2022, have garnered 13 and 12 citations respectively, establishing a strong foundation for his emerging impact. In his first notable work, he proposed the Potential and Dynamic Q-Learning (PDQL) approach, which synergizes Q-learning with artificial potential fields to improve exploration and convergence. His second key paper introduced the "short and safe Q-learning" method, designed to produce optimal routes that are both minimal in distance and collision-free. Through these contributions, Zhao is advancing the practical deployment of autonomous systems in complex, real-world settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2A path planning approach for mobile robots using short and safe Q-learning12 citations · 2022