# Digit验证捕获感知MPC步态规划，轴对齐安全走廊保障递归可行性

> 原文链接：https://robotics.hellobike.com/papers/2026-11-10-2611-10169-4f747490
> 频道：papers | 更新日期：2026-11-10 | 标签：auto, arxiv
> 核心摘要：提出面向LIP模型的捕获感知序列MPC框架，利用轴对齐安全走廊融合避障与稳定性约束。在Digit高保真仿真中验证，具备递归可行性与低算力开销，支持狭窄空间自适应原地踏步切换。

# Digit验证捕获感知MPC步态规划，轴对齐安全走廊保障递归可行性

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[Capturability-Aware Footstep Planning in Cluttered Environments: A Recursively Feasible Sequential MPC on Axis-Aligned Safe Corridors](https://arxiv.org/abs/2611.10169)（arXiv 2611.10169）

## 核心内容

针对人形机器人在 cluttered 环境中兼顾避障与行走稳定性的难题，研究提出一种基于线性倒立摆（LIP）模型的捕获感知序列模型预测控制（MPC）步态规划框架。该方法通过构建相交矩形序列形成的轴对齐安全走廊，将障碍物规避与捕获能力约束统一建模，从理论上保证了规划层的递归可行性。在高保真仿真环境中使用 Agility Digit 机器人进行验证，结果表明该方案能有效应对复杂地形约束。

技术核心在于利用轴对齐安全走廊将非凸避障问题转化为凸约束，使MPC求解效率大幅提升且性能独立于预测 horizon 长度。系统具备环境自适应机制，当执行阶段遭遇规划时未预见的封闭门等阻塞物时，可自动切换至原地踏步模式以维持平衡。相比传统方法，该框架在保持高成功率的同时显著降低了计算负载，为人形机器人在动态受限空间中的实时步态规划提供了工程化解决路径。

## 关键看点

- **安全走廊建模**：采用相交矩形序列构建轴对齐安全走廊，将避障与LIP捕获能力约束融合为凸优化问题
- **递归可行性**：理论证明序列MPC框架在满足安全走廊约束下具备递归可行性，避免规划器在线失效
- **自适应容错**：执行期遇突发阻塞（如门关闭）时自动切换原地踏步模式，保障LIP模型动态稳定性
- **计算效率**：规划成功率与性能对预测horizon不敏感，在Digit高保真仿真中实现低算力高鲁棒性

## 工程与产业观察

该工作解决了LIP步态规划中避障与稳定性耦合导致的递归不可行痛点，轴对齐安全走廊为实时MPC提供了高效凸近似范式。其对环境突变的原地踏步降级策略，增强了具身智能体在非结构化场景中的部署鲁棒性，对人形机器人运动控制算法的工程落地具有直接参考价值。

## 英文摘要 (Abstract)

A fundamental aspect of humanoid footstep planning is to jointly guarantee obstacle avoidance and locomotion stability. This paper presents a capturability-aware sequential Model Predictive Control (MPC) framework for Linear Inverted Pendulum (LIP)-based humanoid footstep planning in the presence of obstacles. The proposed method combines obstacle avoidance with capturability constraints through safe corridors constructed as sequences of intersecting rectangles, yielding a sequential MPC framework with recursive feasibility guarantees for the LIP-based planning layer. The planner autonomously adapts to constrained scenarios, switching to in-place walking when obstructions---such as doors assumed to be open during planning but unexpectedly found to be closed during execution---block forward motion. Performance is largely independent of the prediction horizon, allowing high success rates while keeping the computational cost low. The approach is validated in high-fidelity simulations with the humanoid robot Digit, demonstrating a practical solution for capturable humanoid footstep planning in cluttered environments.

作者：Athanasios Kyriakopoulos, Shubham S. Kumbhar, Kunal S. Narkhede, Abhijeet M. Kulkarni, Ioannis Poulakakis
:::

## 原始参考来源 (Sources)

- [arXiv 2611.10169：Capturability-Aware Footstep Planning in Cluttered Environments: A Recursively Feasible Sequential MPC on Axis-Aligned Safe Corridors](https://arxiv.org/abs/2611.10169)