Variable-Frequency Model Learning and Predictive Control for Jumping Maneuvers on Legged Robots

TL;DR

This paper introduces a novel variable-frequency learning-based model predictive control method for legged robots, significantly improving accuracy and robustness in dynamic jumping maneuvers with long flight phases.

Contribution

The paper presents a new learning-based control approach with variable-frequency model predictive control that accounts for model errors and unknown dynamics, enhancing jump accuracy.

Findings

Outperforms fixed-frequency MPC in jumping distance accuracy, reducing errors 2-8 times.

Achieves less than 3% error in continuous jumps on uneven terrain with perturbations.

Attains 1-2 cm error in diverse jumps with different targets and uncertainties.

Abstract

Achieving both target accuracy and robustness in dynamic maneuvers with long flight phases, such as high or long jumps, has been a significant challenge for legged robots. To address this challenge, we propose a novel learning-based control approach consisting of model learning and model predictive control (MPC) utilizing a variable-frequency scheme. Compared to existing MPC techniques, we learn a model directly from experiments, accounting not only for leg dynamics but also for modeling errors and unknown dynamics mismatch in hardware and during contact. Additionally, learning the model with variable-frequency allows us to cover the entire flight phase and final jumping target, enhancing the prediction accuracy of the jumping trajectory. Using the learned model, we also design variable-frequency to effectively leverage different jumping phases and track the target accurately. In a total of 92 jumps on Unitree A1 robot hardware, we verify that our approach outperforms other MPCs using fixed frequency or nominal model, reducing the jumping distance error 2 to 8 times. We also achieve jumping distance errors of less than 3 percent during continuous jumping on uneven terrain with randomly placed perturbations of random heights (up to 4 cm or 27 percent the robot standing height). Our approach obtains distance errors of 1 to 2 cm on 34 single and continuous jumps with different jumping targets and model uncertainties. Code is available at https://github.com/DRCL-USC/Learning MPC Jumping.