LiftNav: TSDF引导的高斯泼溅中的语义提升路径规划
LiftNav: Path Planning via Semantic Lifting in TSDF-Guided Gaussian Splatting
AI总结：
提出LiftNav混合导航框架，结合TSDF+GS双地图、YOLO检测、TSDF三维提升和B样条轨迹优化，实现无需密集三维嵌入的灵活语义导航，并通过铰链损失碰撞惩罚提升轨迹平滑性和安全性，在Replica数据集仿真中实现100%可行性和更短轨迹。
摘要：
未知室内环境中的自主机器人需要可靠的碰撞避免和对象级理解。经典表示如TSDF支持安全规划但缺乏语义，而像高斯泼溅（GS）这样的逼真方法提供丰富外观但存在软几何问题，限制了精确的障碍物避免。我们提出LiftNav，一个基于GSFusion的TSDF+GS双地图构建的混合导航框架，并增强了基于YOLO的检测、基于TSDF的三维提升和B样条轨迹优化的实时流水线。该设计实现了无需密集三维嵌入的灵活语义导航。我们进一步引入了一种基于铰链损失的碰撞惩罚，提高了轨迹平滑性和安全性。我们在使用Replica数据集的仿真中评估了我们的方法。与最先进的辐射场基线相比，我们展示了100%的可行性和更短的轨迹。
英文摘要：
Autonomous robots in unknown indoor environments require both reliable collision avoidance and object-level understanding. Classical representations such as TSDF support safe planning but lack semantics, while photorealistic methods like Gaussian Splatting (GS) provide rich appearance yet suffer from soft geometry, limiting precise obstacle avoidance. We present LiftNav, a hybrid navigation framework built on GSFusion's TSDF+GS dual map, augmented with a real-time pipeline of YOLO-based detection, TSDF-based 3D lifting, and B-spline trajectory optimization. This design enables flexible semantic navigation without dense 3D embeddings. We further introduce a hinge-loss-based collision penalty that improves trajectory smoothness and safety. We evaluate our approach in a simulation using the Replica dataset. Compared against a state-of-the-art radiance field baseline we show a 100% feasibility rate and shorter trajectories.
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。
