可供性场干预：使视觉-语言-动作模型摆脱机器人操作中的记忆陷阱
Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation
把 3D 空间可供性场当作 VLA 的按需插件：用本体感知检测记忆陷阱、重定位到高可供性区域、以可供性路径点锚定动作并做轨迹打分，为视觉研究者提供了一个可复用的「显式 3D 几何先验补足端到端策略空间推理」的框架。
原文依据 uses SAFs as an on-demand plug-in to guide VLA behavior
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉-语言-动作（VLA）模型通过将视觉观测与语言指令直接映射为动作，在机器人操作中展现出优异性能。然而，它们在分布偏移下依然脆弱：当测试场景发生变化时，VLA 往往复现记忆中的轨迹，而非适应更新后的场景，我们将这一失效模式称为「记忆陷阱」。该局限源于端到端设计，其缺乏显式的三维空间推理，导致在陌生环境中无法可靠识别可操作区域。为弥补这一缺失的空间理解，三维空间可供性场（SAF）能够提供一种几何表示，突出物理上可行的交互位置，从而就机器人应当接近或避开的区域给出显式线索。为此，我们提出可供性场干预（AFI），一种轻量级混合框架，将 SAF 作为按需插件来引导 VLA 行为。我们的系统通过本体感知检测记忆陷阱，将机器人重新定位至近期的高可供性区域，并提出可供性驱动的路径点以锚定 VLA 生成的动作。随后，基于 SAF 的打分器选择累积可供性最高的轨迹。大量实验表明，在真实机器人平台的分布外场景下，我们的方法在不同 VLA 骨干（pi-0 与 pi-0.5）上平均提升 23.5%，在 LIBERO-Pro 基准上提升 20.2%，验证了其在增强 VLA 对分布偏移的鲁棒性方面的有效性。项目主页：https://vla-afi.github.io/。
英文原文摘要 1633 字符
Vision-Language-Action (VLA) models have shown great performance in robotic manipulation by mapping visual observations and language instructions directly to actions. However, they remain brittle under distribution shifts: when test scenarios change, VLAs often reproduce memorized trajectories instead of adapting to the updated scene, which is a failure mode we refer to as the "Memory Trap". This limitation stems from the end-to-end design, which lacks explicit 3D spatial reasoning and prevents reliable identification of actionable regions in unfamiliar environments. To compensate for this missing spatial understanding, 3D Spatial Affordance Fields (SAFs) can provide a geometric representation that highlights where interactions are physically feasible, offering explicit cues about regions the robot should approach or avoid. We therefore introduce Affordance Field Intervention (AFI), a lightweight hybrid framework that uses SAFs as an on-demand plug-in to guide VLA behavior. Our system detects memory traps through proprioception, repositions the robot to recent high-affordance regions, and proposes affordance-driven waypoints that anchor VLA-generated actions. A SAF-based scorer then selects trajectories with the highest cumulative affordance. Extensive experiments demonstrate that our method achieves an average improvement of 23.5% across different VLA backbones (pi-0 and pi-0.5) under out-of-distribution scenarios on real-world robotic platforms, and 20.2% on the LIBERO-Pro benchmark, validating its effectiveness in enhancing VLA robustness to distribution shifts. Project page: https://vla-afi.github.io/.