VIP-Loco：一种基于视觉的无限 horizon 规划框架用于腿部运动
VIP-Loco: A Visually Guided Infinite Horizon Planning Framework for Legged Locomotion
AI总结：
VIP-Loco结合视觉感知与强化学习，实现腿部机器人在复杂动态环境中的鲁棒运动规划，通过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，结合无限 horizon MPC提升适应性与结构化规划能力。
摘要：
对于腿部机器人而言，感知运动需要预测并适应复杂动态环境。模型预测控制（MPC）作为基准，提供可解释的运动规划和约束执行，但难以处理高维感知输入和快速变化的地形。相比之下，无模型强化学习（RL）在视觉挑战场景中适应性好，但缺乏规划能力。为此，我们提出VIP-Loco框架，整合基于视觉的场景理解与RL和规划。在训练期间，内部模型将本体状态和深度图像映射为紧凑的运动动力学特征，用于RL策略。在部署期间，学习的模型用于无限 horizon MPC公式中，结合适应性与结构化规划。我们在模拟中验证了VIP-Loco在挑战性运动任务中的有效性，包括斜坡、台阶、爬行、倾斜、跳跃间隙和攀爬，涵盖了三种机器人形态：四足（Unitree Go1）、双足（Cassie）和轮式双足（TronA1-W）。通过消融实验和与最新方法的比较，我们表明VIP-Loco统一了规划与感知，使机器人在多样化环境中实现稳健且可解释的运动。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
