Max Robotics — Global Service Robot Directory + US Certification

About

Zhitao Song is a robotics researcher specializing in legged locomotion, motion planning, and control systems for quadrupedal robots. His work sits at the intersection of optimization, model predictive control, and agile robot motion, with a particular focus on pushing the boundaries of what four-legged robots can physically achieve. Song's most recognized contribution is his optimal motion planning framework for quadrupedal jumping, which garnered 23 citations and introduced a 12-dimensional black-box optimization approach to automatically generate energy-efficient and versatile jumping motions — including flips and spins — using centroidal dynamics. His involvement in GenLoco (17 citations) demonstrated his commitment to generalized locomotion controllers capable of operating across diverse commercially available quadrupedal platforms, addressing a critical scalability challenge in the field. Beyond dynamic jumping, Song has advanced adaptive control through a data-driven error model integrated with Model Predictive Control, tackling the persistent gap between simplified robot models and real-world performance. His 2024 work on omnidirectional jumping further demonstrates his drive toward real-time, agile motion execution. Collectively, Song's research meaningfully advances the agility, adaptability, and generalizability of legged robotic systems.