D3dlo: Deep 3d Lidar Odometry

Abstract

LiDAR odometry (LO) describes the task of finding an alignment of subsequent LiDAR point clouds. This alignment can be used to estimate the motion of the platform where the LiDAR sensor is mounted on. Currently, on the well-known KITTI Vision Benchmark Suite state-of-the-art algorithms are non-learning approaches. We propose a network architecture that learns LO by directly processing 3D point clouds. It is trained on the KITTI dataset in an end-to-end manner without the necessity of pre-defining corresponding pairs of points. An evaluation on the KITTI Vision Benchmark Suite shows similar performance to a previously published work, DeepCLR [1], even though our model uses only around 3.56% of the number of network parameters thereof. Furthermore, a plane point extraction is applied which leads to a marginal performance decrease while simultaneously reducing the input size by up to 50%.

An Attention-Based Odometry Framework for Multisensory Unmanned Ground Vehicles (UGVs)

“…They projected 3D lidar point clouds into 2D images using cylindrical projection and then converted them into normal images to ensure geometric consistency. In contrast, Adis et al [14] did not project 3D lidar point clouds but instead utilized mini-PointNet to directly handle point clouds, taking full advantage of point clouds. However, obtaining local point cloud features with PointNet in this method proved challenging, making the analysis of complex scenes difficult.…”