Papers
6
Total Citations
70
H-Index
4
About
Xinheng Wang’s research lies at the intersection of multi-robot systems, autonomous navigation, and secure intelligent control, with a strong emphasis on deep reinforcement learning (DRL) and graph neural networks. His most impactful work, “MACNS” (2024, 43 citations), introduces a generic DRL framework integrated with graph neural networks for multi-agent collaborative navigation in dynamic trajectory planning—a breakthrough for coordinating swarms of robots and UAVs. Earlier foundational contributions include a communication model that decouples path planning from connectivity optimization for cooperative sensing (2014, 9 citations), enabling more efficient multi-robot deployments. Wang has also advanced practical robotics by comparing and improving local planners like DWA and TEB for navigating narrow passages (2022, 7 citations), and he explores secure outsourced computations using homomorphic encryption for robot control systems (2022, 6 citations). His recent work extends distributed reinforcement learning to 3D target search (2024) and applies DRL to create autonomous, personalized, and private smart home management (2023). With a career spanning both theoretical algorithms and applied systems, Wang’s research is pivotal for scalable, secure, and intelligent multi-agent coordination.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Comparison and Improvement of Local Planners on ROS for Narrow Passages7 citations · 2022
- 4
- 5
- 6