Papers
6
Total Citations
61
H-Index
4
About
Shiguang Wu is a leading researcher in multi-robot systems, specializing in the intersection of deep reinforcement learning, distributed control, and cooperative autonomy. His work addresses fundamental challenges in multi-target coverage, connectivity maintenance, and dynamic task allocation for robot teams operating under real-world constraints. Wu's most impactful contribution is a deep-reinforcement-learning-based framework for multi-target coverage with guaranteed connectivity, which has garnered 20 citations and provides a time-efficient, distributed policy for robots with limited communication and sensing. He further advanced the field with a knowledge-incorporated policy framework (11 citations) that enables efficient multi-target coverage while preserving network links, and a distributed transferable policy for cooperative target encirclement with collision avoidance (13 citations). Wu has also developed an improved auction algorithm for dynamic multi-robot task allocation (9 citations) and explored multi-robot coverage path planning using deep reinforcement learning. His work consistently bridges theoretical reinforcement learning with practical multi-robot coordination, offering scalable solutions for applications in search-and-rescue, environmental monitoring, and autonomous exploration.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Multi-robot Dynamic Task Allocation Based on Improved Auction Algorithm9 citations · 2021
- 5Multi-Robot Coverage Path Planning based on Deep Reinforcement Learning4 citations · 2021
- 6