发表机构
University of Illinois Chicago; University of California, Los Angeles（伊利诺伊大学芝加哥分校; 加州大学洛杉矶分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对开放世界投递操作，提出利用预训练流动匹配VLA作为低层控制，以接地输出为空间线索，通过轻量适配器预测对角仿射变换引导策略，在桌面和移动场景中显著提升指令遵循与操作成功率。
AI 中文摘要
开放世界货物投递要求移动操作机器人遵循自由形式的用户指令并操作可能新颖的物体。现有的双系统方法使用高层接地模型将语言转换为接地视觉提示，但其低层控制器在嘈杂感知、动态场景和接触丰富的交互下可能仍然脆弱。我们转而使用预训练的流动匹配视觉-语言-动作模型作为低层控制接口，利用其对环境变化的响应性和鲁棒性，同时将接地输出视为策略引导的空间线索。我们的关键见解是，预训练的VLA已经提供了强大的操作先验，而空间线索则提供了在新型语言-物体映射下引导动作所需的缺失目标信息。具体而言，我们引入了一个轻量级的线索条件适配器。该适配器首先通过对比目标进行训练，以产生显著且空间可区分的线索表示，然后被监督以预测生成动作块上的对角仿射变换，使策略引导与线索目标对齐。在桌面和移动基座设置中，我们的方法在域内和域外物体上均提高了指令遵循和操作成功率，平均任务成功率提升近2倍，且推理开销可忽略不计。
英文摘要
Open-world goods delivery requires mobile manipulators to follow free-form user instructions and manipulate potentially novel objects. Existing dual-system approaches use high-level grounding models to convert language into grounded visual prompts, but their low-level controllers can remain brittle under noisy perception, dynamic scenes, and contact-rich interactions. We instead use a pretrained flow-matching vision-language-action model as the low-level control interface, leveraging its reactivity and robustness to environmental changes while treating the grounding output as a spatial cue for policy steering. Our key insight is that the pretrained VLA already provides a strong manipulation prior, while the spatial cue supplies the missing target information needed to guide actions under novel language--object mappings. Concretely, we introduce a lightweight cue-conditioned adapter. The adapter is first trained with contrastive objectives to produce salient and spatially discriminative cue representations, and is then supervised to predict a diagonal affine transformation over the generated action chunk, aligning policy steering with the cued target. Across tabletop and mobile-base settings, our method improves instruction following and manipulation success on both in-domain and out-of-domain objects, achieving up to near $2\times$ improvement in average task success rate with negligible inference overhead.
CommentsCoRL 2026. Project page at https://hatchetproject.github.io/delivery_steer/
