Max Robotics — Global Service Robot Directory + US Certification

About

Guoyi Chi is at the forefront of advancing human-robot interaction and multi-robot coordination, with a research portfolio that bridges theoretical optimization and practical robotic dexterity. His work centers on three key areas: human-guided robotic comanipulation, distributed optimization for multi-robot systems, and learning-based dynamic manipulation. A major contribution is his pioneering development of distributed deep reinforcement learning frameworks for multi-robot formation control, achieving 22 citations for its bi-objective approach that balances task efficiency and coordination. Chi has also made significant strides in cooperative transportation, introducing discrete-time distributed optimization algorithms (16 citations) that enable multiple robots to collaboratively move objects without centralized control—a critical capability for disaster response and warehouse logistics. His most cited work (38 citations) explores human-guided robotic comanipulation, demonstrating how robots can leverage human expertise during physical tasks. Notably, Chi is advancing robotic dexterity through the creation of the first large-scale multi-view, multi-modal dataset of human throw-and-catch actions, published in 2024, which promises to unlock new levels of dynamic manipulation in robots. His inertial neural network approach for loco-manipulation trajectory tracking (17 citations) further showcases his ability to integrate neural computation with real-time control. With a growing citation impact exceeding 97 total citations, Chi’s research is shaping the next generation of collaborative and physically adept robots.