TY - GEN
T1 - RL-Compensated Model Predictive Control for Quadruped Robot Locomotion on Challenging Terrains
AU - Xiao, Zhefeng
AU - Zheng, Dongdong
AU - Sun, Zeyuan
AU - Zeng, Yi
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.
PY - 2026
Y1 - 2026
N2 - Model Predictive Control (MPC) has been widely applied in quadruped robot locomotion. However, the method relies heavily on accuracy of the system model and the feasibility of the pre-planned desired trajectory. Reinforcement learning (RL) improves the performance of the target policy through continuous interaction between the robot and the environment. However, it cannot guarantee the safety of the robot’s actions, and the design of the reward function is a cumbersome process. In this paper, An RL-compensated MPC algorithm framework is proposed. We simplify the quadruped robot into a single rigid body (SRB) dynamic model and train an RL policy to compensate for the linear acceleration, angular acceleration, gait frequency and foothold location of the robot. Comparative experiments against the MPC algorithm in simulation verify that the proposed framework can improve the robot’s locomotion performance on irregular terrains.
AB - Model Predictive Control (MPC) has been widely applied in quadruped robot locomotion. However, the method relies heavily on accuracy of the system model and the feasibility of the pre-planned desired trajectory. Reinforcement learning (RL) improves the performance of the target policy through continuous interaction between the robot and the environment. However, it cannot guarantee the safety of the robot’s actions, and the design of the reward function is a cumbersome process. In this paper, An RL-compensated MPC algorithm framework is proposed. We simplify the quadruped robot into a single rigid body (SRB) dynamic model and train an RL policy to compensate for the linear acceleration, angular acceleration, gait frequency and foothold location of the robot. Comparative experiments against the MPC algorithm in simulation verify that the proposed framework can improve the robot’s locomotion performance on irregular terrains.
KW - Locomotion control
KW - Model predictive control
KW - Quadruped robots
KW - Reinforcement learning
UR - https://www.scopus.com/pages/publications/105042426838
U2 - 10.1007/978-981-92-1599-7_18
DO - 10.1007/978-981-92-1599-7_18
M3 - Conference contribution
AN - SCOPUS:105042426838
SN - 9789819215980
T3 - Communications in Computer and Information Science
SP - 209
EP - 219
BT - Neuromorphic Computing - 4th International Conference, ICNC 2025, Revised Selected Papers
A2 - Li, Chuandong
A2 - Zhou, Qi
A2 - Liang, Hongjing
A2 - Lai, Jingang
A2 - Li, Bin
A2 - Shi, Kaibo
PB - Springer Science and Business Media Deutschland GmbH
T2 - 4th International Conference on Neuromorphic Computing, ICNC 2025
Y2 - 12 December 2025 through 14 December 2025
ER -