模型预测控制
可解释性
初始化
强化学习
计算机科学
稳健性(进化)
控制理论(社会学)
适应性
残余物
灵活性(工程)
人工智能
控制工程
集合(抽象数据类型)
约束满足
航程(航空)
约束(计算机辅助设计)
控制(管理)
机器学习
数学优化
简单(哲学)
最优控制
期限(时间)
鲁棒控制
自适应控制
适应(眼睛)
训练集
控制系统
作者
Se Hwan Jeon,Ho Jae Lee,Seungwoo Hong,Sangbae Kim
标识
DOI:10.1109/tro.2026.3721669
摘要
Model Predictive Control (MPC) provides interpretable, tunable locomotion controllers grounded in physical models, but its robustness depends on frequent replanning and is limited by model mismatch and real-time computational constraints. Reinforcement Learning (RL), by contrast, can produce highly robust behaviors through stochastic training but often lacks interpretability, suffers from out-of-distribution failures, and requires intensive reward engineering. This work presents a GPU-parallelized residual architecture that tightly integrates MPC and RL by blending their outputs at the torque-control level. We develop a kinodynamic whole-body MPC formulation evaluated across thousands of agents in parallel at 100 Hz for RL training. The residual policy learns to make targeted corrections to the MPC outputs, combining the interpretability and constraint handling of model-based control with the adaptability of RL. The model-based control prior acts as a strong bias, initializing and guiding the policy towards desirable behavior with a simple set of rewards. Compared to standalone MPC or end-to-end RL, our approach achieves higher sample efficiency, converges to greater asymptotic rewards, expands the range of trackable velocity commands, and enables zero-shot adaptation to unseen gaits and uneven terrain.
科研通智能强力驱动
Strongly Powered by AbleSci AI