MAGICIAN: 通过想象高斯分布实现高效的长期规划用于主动建图
MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping
AI总结:
MAGICIAN通过想象高斯分布实现高效长期规划,提升主动建图的探索效率与重建完整性,适用于不同动作空间的室内和室外基准测试。
摘要:
主动建图旨在确定智能体如何移动以高效重建未知环境。现有方法多依赖贪心的下一步最佳视角预测,导致探索效率低和重建不完整。为此,我们引入MAGICIAN,一种新的长期规划框架,通过想象高斯分布最大化累积表面覆盖增益,该分布基于3D高斯点划法的场景表示,源自具有强结构先验的预训练占用网络。该表示通过快速体渲染实现对任何新视角的高效覆盖增益计算,可集成到树搜索算法中进行长视距规划。我们通过闭环更新想象高斯分布并优化轨迹。我们的方法在不同动作空间的室内和室外基准测试中均取得最佳性能,凸显了长期规划在主动建图中的优势。
英文摘要:
Active mapping aims to determine how an agent should move to efficiently reconstruct unknown environments. Most existing approaches rely on greedy next-best-view prediction, resulting in inefficient exploration and incomplete reconstruction. To address this, we introduce MAGICIAN, a novel long-term planning framework that maximizes accumulated surface coverage gain through Imagined Gaussians, a scene representation based on 3D Gaussian Splatting, derived from a pre-trained occupancy network with strong structural priors. This representation enables efficient coverage gain computation for any novel viewpoint via fast volumetric rendering, allowing its integration into a tree-search algorithm for long-horizon planning. We update Imagined Gaussians and refine the trajectory in a closed loop. Our method achieves state-of-the-art performance across indoor and outdoor benchmarks with varying action spaces, highlighting the advantage of long-term planning in active mapping.
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。