用单个全景摄像头实现腿式机器人360°语义占位感知，解决行走抖动问题。
OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera
- 融合环形全景与球面展开图，保持360°连续性与网格对齐
- 在笛卡尔与柱坐标空间推理，减少离散化偏差，边界更清晰
- 轻量级设计适配腿式机器人，支持无额外传感器的运动补偿
稳健的3D语义占位对于腿式/人形机器人至关重要，但多数语义场景补全（SSC）系统针对前向传感器的轮式平台。本文提出OneOcc，一种仅依赖视觉的全景式SSC框架，专为步态引起的体位抖动和360°连续性设计。OneOcc结合：(i) 双投影融合（DP-ER），利用环形全景及其等距展开图，保留360°连续性与网格对齐；(ii) 双网格体素化（BGV），在笛卡尔与柱面极坐标空间中推理，降低离散化偏差并锐化自由/占据边界；(iii) 轻量级解码器搭配分层AMoE-3D，实现动态多尺度融合，提升长距离与遮挡推理能力；(iv) 即插即用的步态位移补偿（GDC），在特征层面学习运动校正，无需额外传感器。我们还发布了两个全景占位基准：QuadOcc（真实四足机器人，第一人称360°）和Human360Occ（H3O，CARLA中人类视角360°，含RGB、深度、语义占位；标准划分城市内/跨城市）。OneOcc在QuadOcc上达到新最优，超越强视觉基线且媲美经典激光雷达基线；在H3O上，城市内提升+3.83 mIoU，跨城市提升+8.08。模块轻量，可部署于腿式/人形机器人实现全向感知。数据集与代码将公开于https://github.com/MasterHow/OneOcc。
原文摘要 · Abstract (English)
Robust 3D semantic occupancy is crucial for legged/humanoid robots, yet most semantic scene completion (SSC) systems target wheeled platforms with forward-facing sensors. We present OneOcc, a vision-only panoramic SSC framework designed for gait-introduced body jitter and 360° continuity. OneOcc combines: (i) Dual-Projection fusion (DP-ER) to exploit the annular panorama and its equirectangular unfolding, preserving 360° continuity and grid alignment; (ii) Bi-Grid Voxelization (BGV) to reason in Cartesian and cylindrical-polar spaces, reducing discretization bias and sharpening free/occupied boundaries; (iii) a lightweight decoder with Hierarchical AMoE-3D for dynamic multi-scale fusion and better long-range/occlusion reasoning; and (iv) plug-and-play Gait Displacement Compensation (GDC) learning feature-level motion correction without extra sensors. We also release two panoramic occupancy benchmarks: QuadOcc (real quadruped, first-person 360°) and Human360Occ (H3O) (CARLA human-ego 360° with RGB, Depth, semantic occupancy; standardized within-/cross-city splits). OneOcc sets a new state of the art on QuadOcc, outperforming strong vision baselines and remaining competitive with classical LiDAR baselines; on H3O it gains +3.83 mIoU (within-city) and +8.08 (cross-city). Modules are lightweight, enabling deployable full-surround perception for legged/humanoid robots. Datasets and code will be publicly available at https://github.com/MasterHow/OneOcc.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。