← 研踪 PaperTrailarXiv:2611.25656 · v1
A$^2$-VLA: Adapting Vision-Language-Action Policies to New Tools through Agentic Affordance Discovery
首次提交 2026-11-19 15:38
版本更新 2026-11-19 15:38
雷达观测 2026-11-20 19:58
摘要
Tools with different shapes can have similar functions, but transferring manipulation skills across tools requires understanding how tool geometry relates to the specific task and adjusting the manipulation strategy accordingly. The key challenge is to discover the common affordances that contribute to task completion across different tools and verify whether they support new tools in performing similar work. We present A-VLA, a tool-adaptation framework that combines an embodied agent with a VLA policy. It treats tool affordances as hypotheses the agent can construct, test, and revise. Given teleoperated demonstrations with a few source tools, the agent reconstructs the scenes in simulation and autonomously determines task-relevant affordance features: functional regions and their key geometric properties. It develops affordance-extraction skills and refines both the features and skills through autonomous experiments in the reconstructed scenes. Validated extraction skills accumulate in a reusable skill library for unseen tools. Finally, A-VLA uses encoded functional-region features as conditioning inputs to a backbone during training and inference. Evaluation examines affordance reliability in reconstructed scenes and real-robot task success on unseen tools. Our method achieves 86.1% success in simulated cross-tool trajectory retargeting based on affordances. On three real-robot tool-use tasks, A-VLA improves task success by 30.7 percentage points over .
作者备注:16 pages, 6 figures. Includes appendices
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-19 15:38 · 最新观测版本
A$^2$-VLA: Adapting Vision-Language-Action Policies to New Tools through Agentic Affordance Discovery
Tools with different shapes can have similar functions, but transferring manipulation skills across tools requires understanding how tool geometry relates to the specific task and adjusting the manipulation strategy accordingly. The key challenge is to discover the common affordances that contribute to task completion across different tools and verify whether they support new tools in performing similar work. We present A-VLA, a tool-adaptation framework that combines an embodied agent with a VLA policy. It treats tool affordances as hypotheses the agent can construct, test, and revise. Given teleoperated demonstrations with a few source tools, the agent reconstructs the scenes in simulation and autonomously determines task-relevant affordance features: functional regions and their key geometric properties. It develops affordance-extraction skills and refines both the features and skills through autonomous experiments in the reconstructed scenes. Validated extraction skills accumulate in a reusable skill library for unseen tools. Finally, A-VLA uses encoded functional-region features as conditioning inputs to a backbone during training and inference. Evaluation examines affordance reliability in reconstructed scenes and real-robot task success on unseen tools. Our method achieves 86.1% success in simulated cross-tool trajectory retargeting based on affordances. On three real-robot tool-use tasks, A-VLA improves task success by 30.7 percentage points over .
查看此版本解读 →查看此版本原文 ↗