HorizonNav：用于 anticipatory 3D 机器人导航的几何引导视频扩散框架
HorizonNav: Geometry-Guided Video Diffusion for Anticipatory 3D Robot Navigation
AI总结：
HorizonNav 是几何引导视频扩散的机器人导航框架，通过对齐阶段提升 3D 环境几何一致性，实验显示其规划可行场景、RRT 成功率均提升，可暴露无激光雷达时的重建失败模式。
摘要：
我们提出了 HorizonNav，一种基于视频扩散的 anticipatory 机器人导航框架，可将单张 RGB 图像和文本提示转换为几何对齐的合理周围 3D 空间表示。给定初始观测和重建目标的文本描述，视觉语言模型在设计指令的引导下解释场景，并为视频扩散模型构建结构化提示。生成的视频序列提供环境的合理未来观测，随后使用单目 ORB-SLAM3 进行相机位姿估计，使用 Video Depth Anything 进行密集深度预测。我们的核心贡献是几何引导的深度对齐阶段，该阶段结合估计的相机位姿和三角化视觉地标，以约束多视图的密集深度预测。这种对齐提高了重建 3D 环境的几何一致性，解决了仅生成视频的时间一致性无法解决的不一致性。对想象 3D 环境中导航的实验评估显示，在 19 个场景的 horizon 研究中，规划可行场景从 P20 时的 13/19 增加到 P81 时的 15/19，成功的 RRT 试验从 62/90 增加到 75/90。在单独的走廊研究中，25 条可评估的生成相机轨迹中有 6 条违反重建的碰撞约束；RRT 规划器在这 6 条中的 5 条中恢复了可行替代方案。更大的档案包含 67 次尝试中的 58 个可用重建，其中 36 个支持下游规划，22 个不支持，在没有激光雷达的情况下暴露了重建和自由空间的失败模式而非隐藏它们。在 15 个走廊重建中，匹配结构地标的平均重建误差约为 0.30 m。
英文摘要：
We present HorizonNav, a video diffusion-based framework for anticipatory robot navigation that transforms a single RGB image and a text prompt into a geometrically aligned representation of plausible surrounding 3D space. Given the initial observation and a textual description of the reconstruction objective, a vision-language model, guided by designed instructions, interprets the scene and constructs structured prompts for a video diffusion model. The resulting video sequence provides plausible future observations of the environment, which are subsequently processed using monocular ORB-SLAM3 for camera pose estimation and Video Depth Anything for dense depth prediction. Our central contribution is a geometry-guided depth alignment stage that combines the estimated camera poses with triangulated visual landmarks to constrain dense depth predictions across multiple views. This alignment improves the geometric consistency of the reconstructed 3D environment, addressing inconsistencies that temporal coherence of the generated video alone cannot resolve. The experimental evaluation of navigation in imagined 3D environment shows that across a 19-scene horizon study, planning-feasible scenes increase from 13/19 at P20 to 15/19 at P81, while successful RRT trials increase from 62/90 to 75/90. In a separate corridor study, 6 of 25 evaluable generated-camera trajectories violate the reconstructed collision constraints; RRT planner recovers feasible alternatives in 5 of those 6 cases. A larger archive contains 58 usable reconstructions from 67 attempted cases, of which 36 support a downstream plan and 22 do not, exposing reconstruction and free-space failure modes rather than hiding them without lidar. Across 15 corridor reconstructions, the mean reconstruction error is approximately 0.30 m at matched structural landmarks.
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。
