Papers
6
Total Citations
135
H-Index
4
About
Yang Mo’s research lies at the intersection of multi-robot systems, human-robot interaction (HRI), and intelligent navigation. Their most impactful work, “Transformer-Based Imitative Reinforcement Learning for Multirobot Path Planning” (103 citations), introduces a decentralized, learning-driven approach that enables large-scale robot teams to generate efficient, collision-free paths—a critical step toward real-world coordination. Mo further advances multi-agent navigation with the Spatial-Temporal RetNet (STR) architecture, which tackles dynamic collision avoidance in distributed settings. In HRI, Mo has developed fast-response gesture recognition systems, including a dynamic-static attention GCN for body–hand gestures and a lightweight spatio-temporal transformer for long-distance UAV control, addressing gaps in outdoor, real-time interaction. Their contributions also extend to policy analysis, with a study on China’s intelligent robot chip technology strategy. By combining imitation learning, reinforcement learning, and transformer architectures, Mo bridges the gap between theoretical multi-agent pathfinding and practical, scalable robotic systems, earning recognition as a rising innovator in autonomous coordination and intuitive human-robot interfaces.
Research Focus
Key Achievements
Top Papers
- 1Transformer-Based Imitative Reinforcement Learning for Multirobot Path Planning103 citations · 2023
- 2
- 3STR: Spatial-Temporal RetNet for Distributed Multi-Robot Navigation10 citations · 2025
- 4
- 5
- 6