用学习的世界模型实现人形机器人实时接触规划，提升复杂环境下的自主能力。
Ego-Vision World Model for Humanoid Contact Planning
- 基于离线数据训练压缩空间中的世界模型，结合采样式MPC进行规划
- 在无演示数据下实现墙支撑、挡物、过低拱门等多任务接触行为
- 仅需本体感知和自视角深度图，部署于真实机器人并实现实时响应
让人形机器人利用物理接触而非单纯避让碰撞，是其在非结构化环境中实现自主的关键。传统基于优化的规划器难以处理接触复杂性，而在线策略强化学习（RL）样本效率低且多任务能力有限。本文提出一种结合学习型世界模型与采样式模型预测控制（MPC）的框架，基于无演示的离线数据集，在压缩潜在空间中预测未来状态。为应对稀疏接触奖励与传感器噪声，MPC采用学习的代理价值函数以实现密集、鲁棒的规划。该单一可扩展模型支持多种接触感知任务，包括扰动后墙支撑、拦截来物及穿越高度受限拱门，相比在线策略RL显著提升样本效率与多任务能力。系统已在真实人形机器人上部署，仅依赖本体感知和自视角深度图像，实现稳健、实时的接触规划。代码与数据集见：https://ego-vcp.github.io/
原文摘要 · Abstract (English)
Enabling humanoid robots to exploit physical contact, rather than simply avoid collisions, is crucial for autonomy in unstructured environments. Traditional optimization-based planners struggle with contact complexity, while on-policy reinforcement learning (RL) is sample-inefficient and has limited multi-task ability. We propose a framework combining a learned world model with sampling-based Model Predictive Control (MPC), trained on a demonstration-free offline dataset to predict future outcomes in a compressed latent space. To address sparse contact rewards and sensor noise, the MPC uses a learned surrogate value function for dense, robust planning. Our single, scalable model supports contact-aware tasks, including wall support after perturbation, blocking incoming objects, and traversing height-limited arches, with improved sample efficiency and multi-task capability over on-policy RL. Deployed on a physical humanoid, our system achieves robust, real-time contact planning from proprioception and ego-centric depth images. Code and dataset are available at our website: https://ego-vcp.github.io/
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。