视觉引导的无限时域规划框架，让四足、双足机器人在复杂地形中稳定行走
VIP-Loco: A Visually Guided Infinite Horizon Planning Framework for Legged Locomotion
- 用深度图像和本体感知生成紧凑特征，驱动强化学习策略
- 部署时结合学习模型与无限时域MPC，实现动态适应与结构化规划
- 支持多种机器人形态，在坡道、台阶、跳跃等任务中表现稳健
腿式机器人在复杂动态环境中的感知行走需要提前预测并适应变化。模型预测控制（MPC）虽能提供可解释的运动规划并满足约束，但对高维感知输入和快速变化地形适应能力弱。而无模型强化学习（RL）虽能应对视觉挑战，却缺乏规划能力。为此，我们提出VIP-Loco：将视觉场景理解与强化学习及规划相结合。训练阶段，内部模型将本体状态与深度图像映射为紧凑的运动动力学特征，供RL策略使用；部署时，利用学习模型构建无限时域MPC，融合适应性与结构化规划。我们在模拟环境中验证了该框架在斜坡、台阶、爬行、倾斜、跨空跳、攀爬等挑战性任务上的性能，涵盖三种机器人形态：四足（Unitree Go1）、双足（Cassie）和轮足混合（TronA1-W）。通过消融实验和与前沿方法对比，证明VIP-Loco统一了感知与规划，实现了多样环境中鲁棒且可解释的运动能力。
原文摘要 · Abstract (English)
Perceptive locomotion for legged robots requires anticipating and adapting to complex, dynamic environments. Model Predictive Control (MPC) serves as a strong baseline, providing interpretable motion planning with constraint enforcement, but struggles with high-dimensional perceptual inputs and rapidly changing terrain. In contrast, model-free Reinforcement Learning (RL) adapts well across visually challenging scenarios but lacks planning. To bridge this gap, we propose VIP-Loco, a framework that integrates vision-based scene understanding with RL and planning. During training, an internal model maps proprioceptive states and depth images into compact kinodynamic features used by the RL policy. At deployment, the learned models are used within an infinite-horizon MPC formulation, combining adaptability with structured planning. We validate VIP-Loco in simulation on challenging locomotion tasks, including slopes, stairs, crawling, tilting, gap jumping, and climbing, across three robot morphologies: a quadruped (Unitree Go1), a biped (Cassie), and a wheeled-biped (TronA1-W). Through ablations and comparisons with state-of-the-art methods, we show that VIP-Loco unifies planning and perception, enabling robust, interpretable locomotion in diverse environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。