USA-Net：面向机器人记忆的统一语义与可供性表示
USA-Net: Unified Semantic and Affordance Representations for Robot Memory
AI总结：
本文提出 USA-Net，在单一可微隐式地图中统一编码场景语义与空间可供性，并据此构建基于梯度的开放式词汇导航规划器，生成更短且更贴近 CLIP 目标查询的轨迹。
摘要：
为了使机器人能够遵循诸如“去打开水槽上方的棕色橱柜”这类开放式指令，它们需要同时理解场景几何结构和环境语义。机器人系统通常通过相互分离的流水线来处理这些问题，有时还会使用差异很大的表示空间；当这两个目标发生冲突时，这种做法可能并非最优。在本工作中，我们提出了 USA-Net，这是一种构建世界表示的简单方法，可在一个可微地图中同时编码场景的语义和空间可供性。这使我们能够构建一个基于梯度的规划器，它可以导航到场景中由开放式词汇指定的位置。我们使用该规划器持续生成轨迹；与不利用梯度信息的同类基于网格的规划器所给出的路径相比，这些轨迹长度缩短了 5%–10%，并且在 CLIP 嵌入空间中距离目标查询近 10%–30%。据我们所知，这是首个在单一隐式地图中同时优化语义和可供性的端到端可微规划器。代码和可视化内容可在我们的网站获取：https://usa.bolte.cc/。
英文摘要：
In order for robots to follow open-ended instructions like "go open the brown cabinet over the sink", they require an understanding of both the scene geometry and the semantics of their environment. Robotic systems often handle these through separate pipelines, sometimes using very different representation spaces, which can be suboptimal when the two objectives conflict. In this work, we present USA-Net, a simple method for constructing a world representation that encodes both the semantics and spatial affordances of a scene in a differentiable map. This allows us to build a gradient-based planner which can navigate to locations in the scene specified using open-ended vocabulary. We use this planner to consistently generate trajectories which are both shorter 5-10% shorter and 10-30% closer to our goal query in CLIP embedding space than paths from comparable grid-based planners which don't leverage gradient information. To our knowledge, this is the first end-to-end differentiable planner optimizes for both semantics and affordance in a single implicit map. Code and visuals are available at our website: https://usa.bolte.cc/
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。
