Xubin Ping
Papers
3
Total Citations
14
H-Index
3
About
Xubin Ping is a researcher advancing the frontiers of multi-agent robotics and intelligent manipulation. His work centers on two key areas: the coordinated control of multi-robot systems and the application of deep reinforcement learning to robotic grasping. In the domain of formation control, Ping has tackled the challenge of maneuvering non-holonomic wheeled mobile robots into precise, rigid formations, a critical capability for applications like search-and-rescue and automated logistics. His 2020 paper on distance-based formation maneuvering, with 6 citations, provides a finite-time control solution for leader-follower configurations. Simultaneously, Ping is pioneering more efficient training methods for robotic manipulators. His 2021 work introduced a policy guidance mechanism to overcome the slow convergence and low sample quality that plague deep reinforcement learning, while his 2023 paper explores transfer learning with neural networks featuring lateral connections to accelerate skill acquisition. These contributions, each garnering 4 citations, address fundamental bottlenecks in robot learning, making his research highly relevant for students and engineers seeking to build more capable, autonomous robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3