Zesong Yang
Papers
1
Total Citations
5
H-Index
1
About
Zesong Yang is a rising researcher at the forefront of embodied artificial intelligence and robotic motion planning. His work centers on developing physics-constrained, self-supervised learning frameworks to address fundamental challenges in high-dimensional motion planning. Yang’s most notable contribution is PC-Planner, a novel neural motion planner that integrates a physics-constrained self-supervised learning approach with a shape-aware distance function. This method overcomes the limitations of traditional planners by enabling robust, real-time planning without requiring extensive labeled datasets. By embedding physical constraints directly into the learning process, PC-Planner achieves superior performance in complex, obstacle-dense environments—a critical advancement for autonomous systems. Although early in his career, Yang’s 2024 paper has already garnered 5 citations, signaling growing recognition in the robotics community. His work bridges the gap between classical planning algorithms and modern deep learning, offering a scalable path toward more intelligent and adaptable robots. As interest in embodied AI accelerates, Yang’s contributions are poised to influence both academic research and practical deployment in autonomous navigation and manipulation.
Research Focus
Key Achievements
Top Papers
- 1