Poisson Surface Reconstruction for LiDAR Odometry and Mapping

Abstract

Robots can assist humans in a multitude of ways. For example, robots can handle tedious tasks that humans prefer not to do, such as vacuum cleaning daily to keep a house clean. They can tackle challenging problems that, when attempted by humans, might result in fatal errors, such as driving a car. Furthermore, robots can perform tasks we already do but with greater efficiency and accuracy. An example of this could be a robot that constantly scans large warehouses, providing insights on optimizing logistics worldwide. Additionally, robots can be deployed to foreign planets like Mars, where rovers can traverse the terrain, collect data, and send it back to Earth, giving us insights into the potential viability of human habitation there.Addressing these tasks effectively is a significant challenge due to the complex nature of each component that constitutes a robotics system. A robot without prior knowledge about its environment must simultaneously create a map, determine its location within that map, analyze its surroundings, and devise an efficient route to explore an unfamiliar environment. Often, a map serves as the robot's foundational understanding of its surroundings and provides a spatial representation of the area, identifying obstacles, paths, and other significant features. This knowledge is essential for the robot to effectively navigate, avoid collisions, and perform the aforementioned tasks strategically and safely.In addition to these challenges, robots exist and navigate within a threedimensional world. Consequently, using and exploiting modern sensors, such as 3D LiDARs, become essential in tackling real-world robot applications. By relying on 3D data, we can expand mobile robots capabilities and potential applications, pushing the boundaries of what they can accomplish.The central question of this thesis is: "Can we estimate what the world looks like based on sensor data from 3D LiDARs?" To answer this question, we develop a comprehensive 3D mapping pipeline. We first propose a reliable mechanism to collect data from the real world. Second, we introduce a method to understand the spatial movement of the sensors within the world. Finally, we investigate diverse world representations for different downstream robotic tasks, such as navigation, localization, scene understanding, and others. The ideas presented in this v I also want to thank all my colleagues and lab mates. I am incredibly fortunate to be surrounded by such remarkable individuals, each unique, who provide unconditional support and motivation in my professional and personal life. Although the list of names should be longer, I would like to mainly express my gratvii itude for the moments I have shared with

3D Point Cloud Reconstruction and SLAM as an Input

“…After SuMa was proposed, Puma [14] known as oisson Surface Reconstruction for LiDAR Odometry and Mapping was proposed to handle the outdoor scene. It also uses the implicit method and adds a post-processing step to handle large scenes after Poisson reconstruction was first invented.…”

Range Image-based LiDAR Localization for Autonomous Vehicles

“…The PSR algorithm provides a global solution that considers the whole input data at once without resorting to heuristic partitioning [4] or blending [1], [22]. Therefore, instead of building the map incrementally [28], we aggregate all the oriented point clouds into a global reference frame using map poses, then, this oriented point cloud map is directly fed to the PSR algorithm, yielding a globally consistent triangular mesh of the environment.…”

GLPU: A Geometric Approach For Lidar Pointcloud Upsampling

“…Light detection and ranging (LiDAR) pointclouds are vital for 3D perception and geometrical understanding of a surrounding environment for autonomous vehicles. Numerous tasks are dependent on 3D information from lidar, such as 3D object detection [1][2][3][4][5], 3D semantic segmentation [6], localization [7], mapping [8] and path planning [9]. Mounted on the vehicle, lidar rotates around a vertical axis and emits pulses of infrared light waves to retrieve accurate 3D measurements.…”