Shengduo Chen
Papers
4
Total Citations
224
H-Index
4
About
Shengduo Chen is a leading researcher in multi-robot navigation and collision avoidance, whose work bridges reinforcement learning and real-world robotics. His key contributions focus on developing intelligent, distributed systems that enable robots to navigate safely through complex, dynamic environments. Chen’s most influential work, "Reinforcement Learned Distributed Multi-Robot Navigation With Reciprocal Velocity Obstacle Shaped Rewards" (2022, 144 citations), introduces a novel approach that combines deep reinforcement learning with reciprocal velocity obstacles to achieve adaptive, collision-free navigation in crowded spaces. He further advanced the field with "Cooperative Multi-Robot Navigation in Dynamic Environment with Deep Reinforcement Learning" (2020, 57 citations), which addresses the critical challenge of transferring policies from simulation to real-world deployment. Chen has also pioneered adaptive environment modeling for collision avoidance in complex scenes (2022, 18 citations) and developed distributed, range-only collision avoidance frameworks for low-cost, large-scale multi-robot systems (2020). His work is distinguished by its practical focus on overcoming real-world constraints like noisy sensors and partial observability, making his algorithms suitable for cost-sensitive applications. With over 220 total citations, Chen’s research is shaping the future of autonomous multi-robot coordination, from warehouse logistics to search-and-rescue operations.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4