让机器人听懂用户要做什么，自动避开对方拿东西的区域
Intent-Handover: Grounding Language in Human-Usage Regions for Trustworthy Robot-to-Human Handovers
- 用视觉语言模型识别物体和用户使用区域
- 优化抓取位置，确保用户能舒适接物且不碰撞
- 适合人机协作、服务机器人场景
机器人与人类交接物品时，语音指令可能指物体（如‘杯子’）或用途（如‘倒水’）。成功交接需机器人推断目标物体及用户可握区域。若机器人抓取该区域，会令接收困难，降低可信度；若机械臂过于靠近用户手部，安全感知也会下降。本文提出Intent-Handover，将自然语言与视觉场景结合，生成明确的抓取与交付约束。通过视觉语言模型识别目标物体与用户使用区域，抓取优化模块选择保持该区域可用且避让用户手部的可行抓取点。执行时，机器人追踪上身关键点，估计用户接收姿态，并在人体工程学合理位置完成交付。30名参与者参与的对照实验显示，知晓使用区域可提升信任感，避让手部可增强安全感知，两者同时启用时交互舒适度最高。
原文摘要 · Abstract (English)
Spoken instructions in robot-to-human handovers may specify either an object ("the cup") or an intended use ("pour water"); in both cases, successful handover requires the robot to infer the target object and the region remaining available for the human to hold. If the robot grasps that hold region, the object could become awkward to receive and immediately use, potentially reducing perceived competence and trust; if the gripper approaches too close to the receiving hand during delivery, perceived safety may also suffer. We present Intent-Handover, which grounds unconstrained speech and visual scene context into explicit grasp and delivery constraints. Given a spoken instruction and a scene observation, a vision-language model identifies the target object and the intended human-usage region. A grasp optimization module then selects a feasible grasp keeping this region accessible while enforcing clearance from the predicted receiving hand. During execution, the robot tracks upper-body key points to estimate the user's receiving pose and places the handover at an ergonomically feasible location. In a within-subjects ablation study (n=30), human-usage region awareness increases perceived trust, hand-gripper collision avoidance increases perceived safety, and interaction comfort is highest when both are enabled. Website and code: https://robot-future.github.io/intent-handover/.
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。