We introduce a novel framework for multiway point cloud mosaicking (named Wednesday)
designed to co-align sets of partially overlapping point clouds--typically obtained from 3D …

LiDAR mapping is important yet challenging in self-driving and mobile robotics. To tackle
such a global point cloud registration problem, DeepMapping converts the complex map …

We propose a direct monocular SLAM algorithm based on the Normalised Information
Distance (NID) metric. In contrast to current state-of-the-art direct methods based on …

An approach for LIDAR-based localization at high speeds is presented. In the proposed
framework, the laser pose estimation is treated as a parallel redundant information, which is …

Publicly available satellite imagery can be an ubiquitous, cheap, and powerful tool for
vehicle localisation when a prior sensor map is unavailable. However, satellite images are …

The ability to navigate from visual observations in unfamiliar environments is a core
component of intelligent agents and an ongoing challenge for Deep Reinforcement …

Lidar mapping plays a crucial role in self-driving and mobile robotics. DeepMapping2 is a
large-scaled LiDAR global optimization method. However, it increases parameter usage …

Autonomous vehicles such as UAVs and AGVs have received increasing attentions over the
past decades due to a wide range of applications in many areas. To accomplish robotic …

Pose estimation is a fundamental building block for robotic applications such as
autonomous vehicles, UAV, and large scale augmented reality. It is also a prohibitive factor …

Abstract 1 1 Introduction 3 1.1 Anatomy of a Modern SLAM System.................... 5 1.2
Leveraging Geometric Properties for Improving SLAM.......... 7 1.2. 1 Minimizing Surface …