Perceptive Mixed-Integer Footstep Control for Underactuated Bipedal Walking on Rough Terrain

2025-01-31

AI Summary

This work addresses the challenge of real-time balance control and safe gait planning for bipedal robots traversing discontinuous, rugged terrain. We propose an end-to-end perception–planning–control closed-loop framework. Our key contributions are: (1) the first online convex polygonal terrain decomposition method, enabling efficient, time-consistent real-time terrain segmentation; (2) the first single-shot mixed-integer quadratic programming (MIQP) formulation that jointly optimizes footstep selection, placement, ankle torque, template dynamic parameters, and gait timing; and (3) a decoupled perception module separating semantic classification from geometric fitting to ensure both accuracy and real-time performance. Evaluated on the Cassie robot, the framework achieves outdoor walking at >100 Hz, significantly improving perceptual accuracy and gait robustness. It establishes new state-of-the-art performance in bipedal locomotion over complex unstructured terrain.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Traversing rough terrain requires dynamic bipeds to stabilize themselves through foot placement without stepping in unsafe areas. Planning these footsteps online is challenging given non-convexity of the safe terrain, and imperfect perception and state estimation. This paper addresses these challenges with a full-stack perception and control system for achieving underactuated walking on discontinuous terrain. First, we develop model-predictive footstep control (MPFC), a single mixed-integer quadratic program which assumes a convex polygon terrain decomposition to optimize over discrete foothold choice, footstep position, ankle torque, template dynamics, and footstep timing at over 100 Hz. We then propose a novel approach for generating convex polygon terrain decompositions online. Our perception stack decouples safe-terrain classification from fitting planar polygons, generating a temporally consistent terrain segmentation in real time using a single CPU thread. We demonstrate the performance of our perception and control stack through outdoor experiments with the underactuated biped Cassie, achieving state of the art perceptive bipedal walking on discontinuous terrain. Supplemental Video: https://youtu.be/eCOD1bMi638

Problem

• Bipedal Robot
• Terrain Perception
• Gait Control

Innovation

• MPFC Method
• Real-time Terrain Recognition
• Bipedal Robot Gait Planning