Real-Time Gait Adaptation for Quadrupeds using Model Predictive Control and Reinforcement Learning

2025/10/23 by Kotecha, Prakrut, B, Ganga Nair, Kolathaya, Shishir · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2510.20706

Abstract

Model-free reinforcement learning (RL) has enabled adaptable and agile quadruped locomotion; however, policies often converge to a single gait, leading to suboptimal performance. Traditionally, Model Predictive Control (MPC) has been extensively used to obtain task-specific optimal policies but lacks the ability to adapt to varying environments. To address these limitations, we propose an optimization framework for real-time gait adaptation in a continuous gait space, combining the Model Predictive Path Integral (MPPI) algorithm with a Dreamer module to produce adaptive and optimal policies for quadruped locomotion. At each time step, MPPI jointly optimizes the actions and gait variables using a learned Dreamer reward that promotes velocity tracking, energy efficiency, stability, and smooth transitions, while penalizing abrupt gait changes. A learned value function is incorporated as terminal reward, extending the formulation to an infinite-horizon planner. We evaluate our framework in simulation on the Unitree Go1, demonstrating an average reduction of up to 36.48 % in energy consumption across varying target speeds, while maintaining accurate tracking and adaptive, task-appropriate gaits.

Citations

• PIP-Loco: A Proprioceptive Infinite Horizon Planning Framework for Quadrupedal Robot Locomotion
• TD-MPC2: Scalable, Robust World Models for Continuous Control
• ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots
• Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior
• Monte Carlo Tree Search Gait Planner for Non-Gaited Legged System Control
• Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
• Fast and Efficient Locomotion via Learned Gait Transitions
• Learning Off-Policy with Online Planning
• Dream to Control: Learning Behaviors by Latent Imagination
• Highly Dynamic Quadruped Locomotion via Whole-Body Impulse Control and Model Predictive Control
• Proximal Policy Optimization Algorithms

Cited by

• Learning to Plan, Planning to Learn: Adaptive Hierarchical RL-MPC for Sample-Efficient Decision Making

Related

• Learning to Adapt through Bio-Inspired Gait Strategies for Versatile Quadruped Locomotion
• Combining model-predictive control and predictive reinforcement learning for stable quadrupedal robot locomotion
• PIP-Loco: A Proprioceptive Infinite Horizon Planning Framework for Quadrupedal Robot Locomotion
• SYNLOCO: Synthesizing Central Pattern Generator and Reinforcement Learning for Quadruped Locomotion
• Fast and Efficient Locomotion via Learned Gait Transitions