学习可泛化特征场用于移动操作
Learning Generalizable Feature Fields for Mobile Manipulation
AI总结：
针对移动操作中物体与场景统一表示的问题，提出可实时运行的场景级可泛化神经特征场GeFF，通过新视角合成预训练与CLIP特征蒸馏实现导航与操作统一，在四足机器人上验证其优于基线的性能。
摘要：
移动操作中的一个开放问题是如何以统一方式表示物体和场景，使机器人能同时用于导航和操作。后者需要捕捉复杂几何结构并理解细粒度语义，而前者则涉及捕捉广阔物理尺度下的固有复杂性。在本研究中，我们提出GeFF（可泛化特征场），一种场景级可泛化神经特征场，作为实时运行的导航和操作统一表示。为此，我们将生成式新视角合成作为预训练任务，然后通过CLIP特征蒸馏将生成的丰富场景先验与自然语言对齐。我们通过在配备操作器的四足机器人上部署GeFF来证明该方法的有效性。我们定量评估了GeFF的开放词汇物体/部件级操作能力，结果显示GeFF在运行时和存储-精度权衡方面优于基于点的基线，同时提供了语义感知导航和铰接物体操作的定性示例。
英文摘要：
An open problem in mobile manipulation is how to represent objects and scenes in a unified manner so that robots can use both for navigation and manipulation. The latter requires capturing intricate geometry while understanding fine-grained semantics, whereas the former involves capturing the complexity inherent at an expansive physical scale. In this work, we present GeFF (Generalizable Feature Fields), a scene-level generalizable neural feature field that acts as a unified representation for both navigation and manipulation that performs in real-time. To do so, we treat generative novel view synthesis as a pre-training task, and then align the resulting rich scene priors with natural language via CLIP feature distillation. We demonstrate the effectiveness of this approach by deploying GeFF on a quadrupedal robot equipped with a manipulator. We quantitatively evaluate GeFF's ability for open-vocabulary object-/part-level manipulation and show that GeFF outperforms point-based baselines in runtime and storage-accuracy trade-offs, with qualitative examples of semantics-aware navigation and articulated object manipulation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
