发表机构
EmPACT Lab, NTU Singapore Institute for Infocomm Research, A*STAR Singapore（EmPACT实验室，南洋理工大学信息与通信研究所，A*STAR新加坡）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对现有视觉语言模型在处理360°观测时方向估计不一致的问题，提出无需训练的几何感知框架EAGOR，将方向推理表述为球面上的递归贝叶斯估计，引入球谐信念场，实验证明其性能优于现有方法。
AI 中文摘要
全方位（360°）相机为具身智能体提供周围环境的全景视图，适用于导航和物体搜索等任务中的方向推理。现有视觉语言模型（VLMs）将360°观测投影到2D等距矩形投影（ERP）图像并使用针对透视图像设计的架构处理，忽略了360°观测的球形性质，导致方向估计在相机视图变换下不一致。我们提出EAGOR，一个无需训练、几何感知的具身360°方向推理框架。它将方向推理直接在球面上表述为递归贝叶斯估计，通过引入球谐信念场（SH-BF）消除ERP接缝不连续、纬度扭曲和插值误差。在两个基准数据集和腿部机器人的真实世界实验中评估，EAGOR始终优于现有方法，在HOS和OSR-Bench上分别实现平均相对增益+34.4%和+45.6%，同时提高导航成功率+14.6%，减少步数17.7%，降低平均角度误差24.5%。
英文摘要
Omni-directional (360°) cameras provide embodied agents with a holistic view of their surroundings, making them suited for directional reasoning in tasks such as navigation and object search. Existing Vision Language Models (VLMs) project 360° observations to 2D equirectangular projection (ERP) images and process them using architectures designed for perspective images. However, they ignore the spherical nature of 360° observations, where each pixel represents a viewing direction relative to the agent. Consequently, their direction estimates often become inconsistent under camera view transformations caused by agent motion. This limitation is particularly critical for map-free navigation, where the agent must continuously estimate the target direction in its egocentric frame. We propose EAGOR, a training-free, geometry-aware framework for embodied 360° directional reasoning. Instead of predicting target directions as ERP image coordinates, EAGOR formulates directional reasoning as recursive Bayesian estimation directly on the sphere. It maintains a continuous belief over target directions and propagates it equivariantly under agent motion without training the backbone VLMs. To achieve this, we introduce the Spherical Harmonic Belief Field (SH-BF), whose spherical harmonic representation provides a globally defined, rotation-aware basis for directional estimation on the spherical manifold. This formulation eliminates ERP seam discontinuities, latitude distortions, and interpolation errors. We evaluate EAGOR on two benchmark datasets and real-world experiments with a legged robot across directional reasoning tasks. EAGOR consistently outperforms existing methods, achieving average relative gains of +34.4% and +45.6% on HOS and OSR-Bench, respectively, while improving navigation success by +14.6%, reducing step count by 17.7%, and lowering mean angular error by 24.5%.
Comments12 Pages, 7 Figures, 4 Tables
