BEACON: 语言条件下的遮挡区域导航可行性预测
BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion
AI总结：
BEACON通过融合视觉语言模型与深度信息，提升遮挡区域导航可行性预测的准确性。
摘要：
语言条件的局部导航需要机器人根据当前观察和开放词汇、关系性指令推断附近的可通行目标位置。现有视觉语言空间定位方法通常依赖视觉语言模型（VLMs）在图像空间进行推理，产生与可见像素相关的2D预测。因此，它们在遮挡区域推断目标位置时表现不佳，通常由家具或移动人类引起。为了解决这个问题，我们提出了BEACON，它在有限的局部区域内预测以自身为中心的鸟瞰图（BEV）可行性热图，包括遮挡区域。给定一条指令和来自机器人周围四个方向的RGB-D观测数据，BEACON通过将空间线索注入VLM并融合VLM的输出与基于深度的BEV特征来预测BEV热图。使用在Habitat模拟器中构建的遮挡感知数据集，我们进行了详细的实验分析，以验证我们的BEV空间公式和每个模块的设计选择。我们的方法在验证子集上，对遮挡目标位置的平均精度提高了22.74个百分点，优于最先进的图像空间基线。我们的项目页面是：https://xin-yu-gao.github.io/beacon。
英文摘要：
Language-conditioned local navigation requires a robot to infer a nearby traversable target location from its current observation and an open-vocabulary, relational instruction. Existing vision-language spatial grounding methods usually rely on vision-language models (VLMs) to reason in image space, producing 2D predictions tied to visible pixels. As a result, they struggle to infer target locations in occluded regions, typically caused by furniture or moving humans. To address this issue, we propose BEACON, which predicts an ego-centric Bird's-Eye View (BEV) affordance heatmap over a bounded local region including occluded areas. Given an instruction and surround-view RGB-D observations from four directions around the robot, BEACON predicts the BEV heatmap by injecting spatial cues into a VLM and fusing the VLM's output with depth-derived BEV features. Using an occlusion-aware dataset built in the Habitat simulator, we conduct detailed experimental analysis to validate both our BEV space formulation and the design choices of each module. Our method improves the accuracy averaged across geodesic thresholds by 22.74 percentage points over the state-of-the-art image-space baseline on the validation subset with occluded target locations. Our project page is: https://xin-yu-gao.github.io/beacon.
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。
