Max Robotics — Global Service Robot Directory + US Certification

About

Xu Chang is a robotics researcher whose work centers on the locomotion control and dynamics of legged robots, with a particular focus on quadruped systems. His research bridges classical control theory and modern machine learning, exploring how model predictive control (MPC) and reinforcement learning (RL) can be integrated to achieve robust, agile robot movement in complex environments. Among his most influential contributions is his 2022 paper "Model Predictive Control of Quadruped Robot Based on Reinforcement Learning," which has garnered 20 citations and proposes a hybrid framework combining MPC's structured environmental understanding with RL's adaptive learning capabilities — a compelling solution to the longstanding challenge of transferring high-level tasks to precise joint-level control. His complementary work on MPC with PD compensation (2021, 16 citations) further refines real-world quadruped control performance. Beyond control strategies, Xu has made foundational contributions to robot modeling, developing a decoupling identification method for legged robot base parameters that simplifies dynamic parameter estimation. His 2022 work on agile and robust locomotion skills reflects his broader mission to overcome the limitations of conventional controllers in highly nonlinear robotic systems. Across his portfolio, Xu's research offers meaningful advances toward practical, intelligent legged robots.