Max Robotics — Global Service Robot Directory + US Certification

About

Lixing Liu is pioneering advanced control and motion planning for snake-like robots, a domain where high redundancy and complex ground interactions pose formidable challenges. Their core research focuses on reinforcement learning, unified motion modeling, and dense control strategies to enable these flexible robots to navigate unpredictable environments. Liu’s most impactful work, a 2024 paper on a reinforcement learning path-following strategy for snake robots, has already garnered 11 citations, demonstrating immediate resonance in the field. This work introduces a transferable constrained-residual gait generator, overcoming the limitations of traditional controllers by allowing the robot to adapt its undulating motion to follow complex paths accurately. Another key contribution is a unified motion modeling approach that decomposes snake robot movement into predictable components, enabling motion prediction for all gaits generated by the backbone curve method. Most recently, Liu has tackled the critical issue of state sparse sensing, developing a representation reinforcement learning framework for dense point-following control even when environmental data is intermittent. These achievements mark Liu as a rising leader in bio-inspired robotics, pushing the boundaries of what serpentine robots can achieve in real-world, sensor-limited conditions.