外观
论文arXiv 2609.188691 个月前
KINO：用于人形机器人移动操作中 VLM 规划与全身控制的关键帧接口
提出以运动关键帧连接 VLM 规划与 RL 全身控制，并在仿真和 Unitree G1 上验证物体操作任务。
宇树 G1原文链接：KINO: A Keyframe Interface for VLM Planning and Whole-Body Control in Humanoid Loco-Manipulation（arXiv 2609.18869 · 发布日期：2026-09-16）
KINO: A Keyframe Interface for VLM Planning and Whole-Body Control in Humanoid Loco-Manipulation
提出以运动关键帧连接 VLM 规划与 RL 全身控制，并在仿真和 Unitree G1 上验证物体操作任务。
核心要点
- 面向人形移动操作中理解指令、场景语义并协调全身运动的需求。
- VLM 根据语言、场景和反馈从预定义库选择关键帧，并按场景重定向。
- 关键帧条件全身策略生成关节动作，到达目标机器人姿态和物体姿态。
- 显著性关键帧采样将稀疏 VLM 关键帧下任务成功率从 44% 提升到 92%。
验证范围与局限：验证限于仿真及一台 Unitree G1 上的物体拾取、搬运和放置任务。
英文摘要 (Abstract)
Humanoid loco-manipulation requires robots to interpret task instructions and scene semantics while executing coordinated whole-body motions. We propose a hierarchical framework that uses motion keyframes as an intermediate representation between Vision-Language Model (VLM) planning and Reinforcement Learning (RL) control. Each keyframe specifies a target whole-body robot pose and, when applicable, an object pose. Given a language instruction, scene observations, and execution feedback, the VLM selects successive task-relevant keyframes from a predefined library. The selected keyframes are retargeted to the current scene to account for object poses and dimensions. A keyframe-conditioned whole-body policy then generates joint-level actions to reach these goals. We introduce a saliency-based keyframe sampling strategy for low-level policy training that improves end-to-end task success rate from 44% to 92% when using sparse VLM keyframes. We evaluate our framework on object pickup, transport, and placement tasks in simulation and on a Unitree G1 humanoid. The system successfully performs both one- and two-handed manipulation and generalises to placement locations beyond the training reference data.
作者：Sitong Chen, Fatemeh Zargarbashi, Jin Cheng, Tianxu An, Stelian Coros
来源
本页事实对应的公开页面，以原文为准。