OccPlanner：面向像素目标导航的目标感知占用条件扩散规划器
OccPlanner: Goal-Aware Occupancy-Conditioned Diffusion Planner for PixelGoal Navigation
- Changhong Intelligent Robot（长虹智能机器人）
- University of Electronic Science and Technology of China（电子科技大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
该研究针对像素目标导航的3D目标定位与无碰撞规划难题，提出OccPlanner模型，引入L3ROcc生成监督，在仿真中大幅提升导航成功率，还验证了其仿真到真实的迁移适配性。
中文摘要 AI 辅助
像素目标导航直接在智能体的相机视图中指定目标，但目标像素既不提供度量深度也不提供可通行性，这使得3D目标定位和无碰撞的连续规划颇具挑战性。我们提出了OccPlanner，一种目标感知的占用条件扩散规划器，它将像素目标定位在以自我为中心的度量空间中，并依次将目标表示与时间视觉上下文以及学习到的局部3D占用特征相关联。为了大规模提供占用监督，我们引入了L3ROcc，它通过几何重建和基于射线的可见性推理，将单目RGB导航视频转换为以机器人为中心的局部3D占用标注。我们在InternData-N1上训练OccPlanner，并在闭环仿真中针对InternScenes的四个未见场景类别和两个目标距离范围进行评估。在5-8米的设置下，OccPlanner在四个类别中将平均成功率（SR）较NavDP从20.81%提升至71.55%，在杂乱简单场景和杂乱困难场景中分别达到86.20%和84.92%。在Unitree Go2上进行的真实世界开环实验进一步提供了利用L3ROcc生成的监督实现仿真到真实迁移与适配的初步证据。
英文摘要
PixelGoal navigation specifies targets directly in the agent's camera view, providing a natural interface between high-level visual reasoning and low-level navigation. Depth can lift a visible target pixel into a metric PointGoal, but this estimate becomes unreliable under occlusion or sensor noise. Moreover, a PointGoal alone does not encode traversability or feasible paths around obstacles. We present OccPlanner, a goal-aware occupancy-conditioned diffusion planner that learns complementary egocentric goal and planning-oriented 3D representations through metric target and occupancy prediction, respectively. These representations condition a diffusion trajectory module to generate target-directed, obstacle-aware trajectories. For scalable geometric supervision, we introduce L3ROcc, which converts monocular RGB navigation videos into aligned 3D occupancy and trajectory annotations. We train OccPlanner on L3ROcc-processed InternData-N1 and evaluate it in closed-loop simulation across four unseen InternScenes categories and two goal-distance ranges. Across all eight settings, OccPlanner substantially outperforms existing open-source PixelGoal approaches and achieves competitive performance against PointGoal planners with direct metric-goal inputs.
