Max Robotics — Global Service Robot Directory + US Certification

About

Zi Wang is a robotics and artificial intelligence researcher whose work sits at the intersection of machine learning, task and motion planning, and autonomous manipulation. Wang's primary contributions center on enabling robots to learn and generalize complex, long-horizon behaviors by composing sensorimotor primitives in novel combinations — a capability critical for real-world robotic deployment. Their most influential work, "Learning Compositional Models of Robot Skills for Task and Motion Planning" (2021), has garnered 82 citations and demonstrates how robots can acquire flexible generative planning strategies that extend well beyond their basic trained abilities. This line of research, which Wang pursued across multiple iterations from 2018 through 2021, progressively refined techniques for active model learning and diverse action sampling, allowing robots to intelligently combine primitive skills to tackle previously unseen manipulation challenges. More recently, Wang has expanded into digital twin methodologies, contributing to photogrammetry field-of-view evaluation and 3D layout optimization for reconfigurable manufacturing systems. Spanning both foundational robotics intelligence and applied industrial automation, Wang's research reflects a consistent commitment to bridging learning-based approaches with practical, scalable robotic systems.