Gait-Net-augmented Implicit Kino-dynamic MPC for Dynamic Variable-frequency Humanoid Locomotion over Discrete Terrains

TL;DR

This paper introduces a Gait-Net-augmented implicit kino-dynamic MPC that enables humanoid robots to adapt step timing and placement dynamically over discrete terrains, improving responsiveness and stability in challenging conditions.

Contribution

It presents a novel Gait-Net-augmented MPC framework that optimizes step location, duration, and contact forces simultaneously for natural variable-frequency humanoid locomotion.

Findings

Successful simulation validation of variable-frequency locomotion.

Effective real-world implementation on humanoid hardware.

Capability to handle 3-D discrete terrains with minimal terrain data.

Abstract

Reduced-order-model-based optimal control techniques for humanoid locomotion struggle to adapt step duration and placement simultaneously in dynamic walking gaits due to their reliance on fixed-time discretization, which limits responsiveness to various disturbances and results in suboptimal performance in challenging conditions. In this work, we propose a Gait-Net-augmented implicit kino-dynamic model-predictive control (MPC) to simultaneously optimize step location, step duration, and contact forces for natural variable-frequency locomotion. The proposed method incorporates a Gait-Net-augmented Sequential Convex MPC algorithm to solve multi-linearly constrained variables by iterative quadratic programs. At its core, a lightweight Gait-frequency Network (Gait-Net) determines the preferred step duration in terms of variable MPC sampling times, simplifying step duration optimization to the parameter level. Additionally, it enhances and updates the spatial reference trajectory within each sequential iteration by incorporating local solutions, allowing the projection of kinematic constraints to the design of reference trajectories. We validate the proposed algorithm in high-fidelity simulations and on small-size humanoid hardware, demonstrating its capability for variable-frequency and 3-D discrete terrain locomotion with only a one-step preview of terrain data.