Papers
52
Total Citations
401
H-Index
11
About
Hongxu Ma is a prominent robotics researcher whose career spans over fifteen years of sustained contributions to legged robotics, control systems, and autonomous multi-robot coordination. Working primarily on quadruped and humanoid robots, Ma has made significant strides in solving some of the field's most pressing challenges: enabling stable locomotion across unstructured terrain without reliance on expensive sensor arrays. His 2020 work on sensorless contact force estimation (52 citations) demonstrated that high-fidelity force feedback could be achieved through algorithmic innovation alone, lowering hardware barriers for legged robot deployment. Complementing this, Ma pioneered advanced control architectures for electro-hydraulic actuators, combining model predictive control with multi-scale online estimation to handle real-world noise and parameter uncertainty (26 citations). His integration of reinforcement learning with model predictive control frameworks (20 citations) represents a forward-looking hybrid approach increasingly influential in modern locomotion research. Earlier contributions, including position/force control for quadruped legs and trotting gait methods (2013), established foundational techniques still referenced today. From early work in hardware protection circuits for humanoid robots (2010) to particle swarm optimization for multi-robot coordination (2008), Ma's research reflects a uniquely broad yet coherent vision of intelligent, robust robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Model Predictive Control of Quadruped Robot Based on Reinforcement Learning20 citations · 2022
- 4
- 5Quadruped Robot Control through Model Predictive Control with PD Compensator16 citations · 2021
- 6
- 7
- 8Trotting Gait of a Quadruped Robot Based on the Time-Pose Control Method14 citations · 2013
- 9The quadruped robot adaptive control in trotting gait walking on slopes11 citations · 2017
- 10