We present a novel algorithm for learning-based loop-closure for SLAM (simultaneous localization and mapping) applications. Our approach is designed for general 3D point cloud data, including those from lidar, and is used to prevent accumulated drift over time for autonomous driving. We voxelize the point clouds into coarse voxels and calculate the overlap to estimate if the vehicle drives in a loop. We perform point-level registration to compute the current pose accurately. We have evaluated our approach on well-known datasets KITTI, KITTI-360, Nuscenes, Complex Urban, NCLT, and MulRan. We show at most 2 times improvement in accuracy estimation of translation and rotation. On some challenging sequences, our method is the first approach that can obtain a 100% success rate.

翻译：我们提出了一种新颖的基于学习的环路闭合算法，用于同时定位与地图构建（SLAM）应用。该方法针对一般三维点云数据（包括激光雷达数据）设计，旨在防止自动驾驶中随时间累积的漂移误差。我们通过将点云体素化为粗粒度体素并计算重叠度来估计车辆是否行驶于闭环路径中，同时执行点级配准以精确计算当前位姿。我们在KITTI、KITTI-360、Nuscenes、Complex Urban、NCLT和MulRan等知名数据集上评估了该方法。结果表明，在平移和旋转精度估计上实现了最高2倍的提升。在某些具有挑战性的序列中，我们的方法是首个能够达到100%成功率的方案。