Max Robotics — Global Service Robot Directory + US Certification

About

Yibiao Zhao is a leading researcher in human-robot interaction, computer vision, and cognitive robotics, with a focus on enabling machines to understand and anticipate human behavior. His most influential work, “Inferring Forces and Learning Human Utilities from Videos” (83 citations), introduces a groundbreaking framework that models physical affordances and human utilities—quantifying the forces and preferences that drive human-object interactions. This work provides a deeper, more granular account of how people engage with their environment, moving beyond simple action recognition to infer underlying goals and physical constraints. Zhao also developed algorithms for detecting potential falling objects by inferring human action and natural disturbance (31 citations), enhancing robot safety in dynamic settings. His method for inferring hierarchical human intent from video (28 citations) allows robots to predict future actions by sampling possible plans, a critical capability for collaborative robotics. Additionally, Zhao’s work on representing human theory of mind for human-robot interaction and his PODDP framework for planning under uncertainty (5 citations) push the boundaries of autonomous agents’ ability to reason about unobservable states. Through these contributions, Zhao has established himself as a key figure in creating socially aware, physically grounded robots.