Real-time Whole-body Model Predictive Control for Bipedal Locomotion with a Novel Kino-dynamic Model and Warm-start Method

2025-05-26

AI Summary

Bipedal robots face significant challenges in real-time whole-body model predictive control (WB-MPC), including high computational latency and poor stability due to high degrees of freedom and frequent contact transitions. To address these issues, this work proposes a lightweight kino-dynamic dynamical model that replaces conventional contact moment modeling with ZMP-driven dynamics. We further design a modular multi-layer perceptron (MLP)-based warm-starting strategy to accelerate convergence of the nonlinear MPC solver. Additionally, we introduce a novel whole-body controller with explicit, real-time regulation of impact dynamics and ZMP trajectories. The proposed framework achieves ≥50 Hz real-time control on both simulation and physical robot platforms. It significantly reduces contact transition latency, enhances disturbance rejection, and improves walking robustness—outperforming state-of-the-art WB-MPC approaches in both efficiency and performance.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Advancements in optimization solvers and computing power have led to growing interest in applying whole-body model predictive control (WB-MPC) to bipedal robots. However, the high degrees of freedom and inherent model complexity of bipedal robots pose significant challenges in achieving fast and stable control cycles for real-time performance. This paper introduces a novel kino-dynamic model and warm-start strategy for real-time WB-MPC in bipedal robots. Our proposed kino-dynamic model combines the linear inverted pendulum plus flywheel and full-body kinematics model. Unlike the conventional whole-body model that rely on the concept of contact wrenches, our model utilizes the zero-moment point (ZMP), reducing baseline computational costs and ensuring consistently low latency during contact state transitions. Additionally, a modularized multi-layer perceptron (MLP) based warm-start strategy is proposed, leveraging a lightweight neural network to provide a good initial guess for each control cycle. Furthermore, we present a ZMP-based whole-body controller (WBC) that extends the existing WBC for explicitly controlling impulses and ZMP, integrating it into the real-time WB-MPC framework. Through various comparative experiments, the proposed kino-dynamic model and warm-start strategy have been shown to outperform previous studies. Simulations and real robot experiments further validate that the proposed framework demonstrates robustness to perturbation and satisfies real-time control requirements during walking.

Problem

• Achieving real-time whole-body control for bipedal robots
• Reducing computational costs in bipedal locomotion models
• Ensuring robustness and low latency in control cycles

Innovation

• Novel kino-dynamic model with ZMP
• MLP-based warm-start strategy
• ZMP-based whole-body controller