Papers
2
Total Citations
39
H-Index
2
About
Le Mao is a rising researcher at the forefront of socially-aware multi-robot navigation, tackling the critical challenge of enabling robots to move safely and intuitively alongside humans. His work centers on fusing multi-agent reinforcement learning with advanced transformer architectures to model complex human-robot interactions. In his highly-cited 2024 paper (21 citations), he introduced a multi-agent reinforcement learning framework that allows robot teams to cooperatively navigate crowded public spaces without collisions, even under limited communication—a key step toward real-world deployment. His 2023 work on NaviSTAR (18 citations) broke new ground by combining a hybrid spatio-temporal graph transformer with preference learning, enabling robots to infer pedestrian intentions and adapt their behavior to social norms. These contributions directly address the "freezing robot" problem in dense crowds, where autonomous systems struggle to predict human motion. With nearly 40 citations in just two years, Le Mao’s research is rapidly shaping the future of human-robot coexistence, offering scalable solutions for service robots, autonomous delivery fleets, and assistive technologies in shared spaces.
Research Focus
Key Achievements
Top Papers
- 1
- 2