Papers
6
Total Citations
124
H-Index
6
About
Kai Cai is a leading researcher at the intersection of discrete-event systems, multi-robot coordination, and warehouse automation. His work centers on developing formal, provably correct control methods for robotic networks operating in complex, safety-critical environments. A major contribution is the application of supervisory control theory (SCT) to multi-robot warehouse automation, as demonstrated in his highly cited 2018 paper (43 citations), which provides a cyber-physical control approach for safe, deadlock-free, and efficient goods-to-person systems. Cai has also advanced the field of Multi-Agent Pickup and Delivery (MAPD), proposing a TSP-based online algorithm (2023, 23 citations) and an anytime solution under energy constraints (2024, 10 citations). Notably, he integrates deep reinforcement learning with supervisory control to achieve both efficiency and formal safety guarantees (2022, 15 citations). His work on obstacle-avoidance path planning for bending robots (2023, 17 citations) further showcases his versatility in robot control. With a consistent focus on bridging formal methods and practical robotics, Cai’s research is shaping the future of safe, scalable automation in logistics and manufacturing.
Research Focus
Key Achievements
Top Papers
- 1
- 2A TSP-Based Online Algorithm for Multi-Task Multi-Agent Pickup and Delivery23 citations · 2023
- 3
- 4
- 5
- 6Anytime Multi-Task Multi-Agent Pickup and Delivery Under Energy Constraint10 citations · 2024