Past/Current Research Projects

Fine-tuning vision-language models with reinforcement learning to enable efficient visual active search in the real world.

Distributed reinforcement learning for scalable, decentralized multi-agent path finding in highly-structured environments (e.g., Amazon fulfillment centers)

Communication learning for simultaneous communication and action policy learning.

Reinforcement learning method to solve multi-robot combinatorial optimization problem with specific objective and constraints

Deployment of robots to conduct efficient exploration and search in complex environments

Multi-robot search and monitor an area to locate potentially evasive targets, by learning strategies in a mixed cooperative-competitive environment.

Decentralised multi-robot exploration in communication-constraint environments, ensuring appropriate connectivity and adaptability in real-world conditions.

Distributed RL for junction-level traffic light phase control, as well as for decentralized CAVs control via communication learning.

The project’s aim is to exploit this manipulative prowess in order to boost the performance of legged robots in both industrial and real-world situations.