论文/arXiv 2610.18194·15 天前

用于机器人操作的跨具身可供性迁移

为解决人类可供性标注与机器人约束不匹配，框架结合点云和机器人描述符预测可执行区域，并在家用物体数据集验证。

AI 整理

• 感知与导航
• 仿真与训练
• 数据与采集

Universal Robots UR5e

原文链接：Cross-Embodiment Affordance Transfer for Robotic Manipulation（arXiv 2610.18194 · 发布日期：2026-10-13）

Cross-Embodiment Affordance Transfer for Robotic Manipulation

为解决人类可供性标注与机器人约束不匹配，框架结合点云和机器人描述符预测可执行区域，并在家用物体数据集验证。

核心要点

• 人类标注反映人手交互，可能与机器人几何可达性和机械可行性不一致。
• 方法输入物体3D点云与机器人几何和约束描述符，预测机器人可执行表面区域。
• 训练结合人类标注和仿真中多次采样接近试验得到的机器人执行结果。
• 在家用物体数据集和UR5e两种平行夹爪配置上，优于不含机器人信息的模型。

验证范围与局限：验证范围为家用物体数据集和UR5e两种平行夹爪配置，执行结果来自仿真试验。

英文摘要 (Abstract)

Robotic manipulation systems commonly learn object affordances from human-annotated datasets, which reflect interaction possibilities for a human hand rather than the physical constraints of a specific robot. For example, a surface region of an object identified as graspable by a human annotator may be geometrically unreachable or mechanically infeasible for a robot, yet this mismatch is rarely addressed explicitly. To tackle this challenge, we proposed a framework that translates human affordance annotations into robot-executable affordance predictions conditioned on the physical properties of the robot. The network predicts which surface regions of an object are physically executable by the robot, given a 3D point cloud of an object and a descriptor encoding the robot's geometry and constraints. The model was trained using human-annotated affordances together with robotic execution outcomes from multiple sampled approach trials in simulation, where execution outcomes determined which regions are executable for the robot. The evaluation was performed on a household objects dataset using two parallel-jaw gripper configurations on a UR5e robot arm. The framework outperformed a model that does not receive information about the robot. The experimental results demonstrated that affordance prediction must be conditioned on the robot and that human annotations alone are insufficient for learning robot-executable affordance representations.

作者：Sawera Yaseen, Serge Thill, Rekha Raja

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.18194：Cross-Embodiment Affordance Transfer for Robotic Manipulation访问 2026-10-21