KINO: A Keyframe Interface for VLM Planning and Whole-Body Control in Humanoid Loco-Manipulation

2026-09-16

AI Summary

该研究通过结合视觉-语言模型规划和强化学习控制，使用关键帧接口解决人形机器人在执行任务时的全身协调运动问题。

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.

Problem

• humanoid loco-manipulation
• whole-body control
• vision-language model
• reinforcement learning

Innovation

• motion keyframes
• hierarchical framework
• saliency-based keyframe sampling