Multi-robot Coordination
Distributed decision-making for aerial-ground teams under communication constraints.
Research Overview
My work blends multi-agent reinforcement learning, distributed robotics, and embedded autonomy, focusing on reliable coordination strategies for autonomous robot teams.
Focus Areas
Research Interests
Multi-agent Reinforcement Learning
Centralised training with decentralised execution for pursuit-evasion and exploration tasks.
Vision-Language Navigation
Linking high-level instructions with onboard perception for autonomous mobility.
Embedded Autonomy
Deployable autonomy stacks on resource-limited edge hardware.
Experience
Research Experience
- 2024 – 2026
Intelligent Swarm Pursuit-Evasion under Incomplete Information · Core Researcher
Prof. Yuanshi Zheng · National Natural Science Foundation of China
- Studied MARL policies for aerial swarms that adapt between local exploration and burst communication under incomplete information.
- Raised pursuit success to 91% in the NP-1E pursuit-evasion environment.
- Filed multiple published invention patents on UAV coordination and sparse-reward exploration.
- 2025
Autonomous UAV–Ground Vehicle Navigation · Research Engineer
Meituan Academy of Robotics Shenzhen · Industry Collaboration
- Developing navigation stack combining RGB, LiDAR, odometry for indoor logistics.
- Implemented dual control modes with constraint-aware planning.
- Achieved 10 cm arrival accuracy in dynamic test arenas.
- 2022 – 2023
Visual-Inertial SLAM for Autonomous UAVs · Team Lead
Assoc. Prof. Li Jun · Undergraduate Thesis
- Integrated IMU and vision for warehouse-scale SLAM and obstacle-aware planning.
- Maintained <0.3 m drift over 10-minute flights.
- Automated waypoint navigation through cluttered aisles.
Interested in collaboration? Feel free to reach out via the Contact page.