外观
论文arXiv 2603.143452 个月前
VIP-Loco：用于腿式运动的视觉引导无限时域规划框架
原文链接：VIP-Loco: A Visually Guided Infinite Horizon Planning Framework for Legged Locomotion（arXiv 2603.14345 · 发布日期：2026-08-01）
VIP-Loco: A Visually Guided Infinite Horizon Planning Framework for Legged Locomotion
VIP-Loco面向复杂动态环境中的腿式感知运动，结合视觉场景理解、RL与无限时域MPC，并在多形态机器人仿真任务中验证。
核心要点
- 腿式机器人感知运动需预判复杂动态环境，MPC难处理高维视觉与快速地形变化。
- 训练时内部模型将本体状态和深度图映射为紧凑运动动力学特征，供RL策略使用。
- 部署时将学习模型用于无限时域MPC，将适应性与结构化规划结合起来。
- 在坡道、楼梯、爬行、倾斜、跳沟和攀爬等仿真任务中，与先进方法及消融进行比较。
验证范围与局限：验证范围为仿真环境，覆盖Unitree Go1、Cassie和TronA1-W三种机器人形态及所列运动任务。
英文摘要 (Abstract)
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.
作者：Aditya Shirwatkar, Satyam Gupta, Shishir Kolathaya
来源
本页事实对应的公开页面，以原文为准。