发表机构
Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM); Institute for Advanced Study, Technical University of Munich; Carnegie Mellon University; SIEMENS AG; Huawei-TUM joint laboratory（慕尼黑工业大学慕尼黑机器人与机器智能研究所; 慕尼黑工业大学高级研究所; 卡内基梅隆大学; 西门子公司; 华为-慕尼黑工业大学联合实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对机器人在未知场景快速规划新行为的挑战，提出嵌套运动动力学框架，结合可行性引导树搜索和大语言模型采样策略，能改善搜索过程，生成的轨迹可用强化学习控制器跟踪，质量高可用于实际运动操作场景。
AI 中文摘要
在机器人技术中，在未知场景中快速规划新行为仍是一项基本挑战。人形机器人的运动操作具有高维、混合和欠驱动的特性，这一直阻碍着这一目标的实现。本文提出了一个嵌套的运动动力学框架，用于在给定候选接触序列的情况下进行快速可行性检查和动态一致的轨迹生成，以应对这一挑战。通过将该模块与可行性引导树搜索和基于大语言模型的接触计划采样策略相结合，证明了该框架可显著改善搜索过程。此外，表明生成的轨迹可通过基于强化学习的控制器进行跟踪，且生成的轨迹质量足以在实际运动操作场景中执行。
英文摘要
Fast planning of novel behaviors in unseen scenarios remains a fundamental challenge in robotics. The high-dimensional, hybrid, and underactuated nature of humanoid loco-manipulation continues to hinder the realization of this goal. In this paper, we address this challenge by proposing a nested kino-dynamic framework for rapid feasibility checking and dynamically consistent trajectory generation given a candidate contact sequence. By integrating this module with a feasibility-guided tree search and a Large Language Model (LLM)-based contact plan sampling strategy, we demonstrate that the proposed framework can substantially improve the search process. Furthermore, we show that the generated trajectories can be tracked using a reinforcement learning (RL)-based controller and show that the resulting trajectories are of sufficiently high quality for execution in real-world loco-manipulation scenarios. A supplementary video is available at: https://youtu.be/R6qCHoCormQ.
