Real-Time 6-DOF Pose Estimation of Known Geometries in Point Cloud Data

Abstract

The task of tracking the pose of an object with a known geometry from point cloud measurements arises in robot perception. It calls for a solution that is both accurate and robust, and can be computed at a rate that aligns with the needs of a control system that might make decisions based on it. The Iterative Closest Point (ICP) algorithm is widely used for this purpose, but it is susceptible to failure in practical scenarios. We present a robust and efficient solution for pose-from-point cloud estimation called the Pose Lookup Method (PLuM). PLuM is a probabilistic reward-based objective function that is resilient to measurement uncertainty and clutter. Efficiency is achieved through the use of lookup tables, which substitute complex geometric operations such as raycasting used in earlier solutions. Our results show millimetre accuracy and fast pose estimation in benchmark tests using triangulated geometry models, outperforming state-of-the-art ICP-based methods. These results are extended to field robotics applications, resulting in real-time haul truck pose estimation. By utilising point clouds from a LiDAR fixed to a rope shovel, the PLuM algorithm tracks a haul truck effectively throughout the excavation load cycle at a rate of 20 Hz, matching the sensor frame rate. PLuM is straightforward to implement and provides dependable and timely solutions in demanding environments.

Novel Approaches for Point Cloud Analysis with Evidential Methods: A Multifaceted Approach to Object Pose Estimation, Point Cloud Odometry, and Sensor Registration

“…The Pose Lookup Method [26], or PLuM, is an approximation of the Maximum Sum of Evidence method described in the previous section that is grounded in ERA. PLuM provides a real-time and accurate method for the 6-DOF pose estimation of known geometries in point cloud data, with extensions to kinematic configuration spaces such as estimating the joint angles for an articulated robot similar to the example displayed in Figure 5.…”

SLAMICP Library: Accelerating Obstacle Detection in Mobile Robot Navigation via Outlier Monitoring following ICP Localization

“…The ICP algorithm iteratively estimates the transformation matrix that minimizes an error metric, which is usually the sum of squared differences between the coordinates of the point clouds to be matched. For example, Bhandari et al [ 39 ] proposed using the ICP algorithm to track the position of an object with a known geometry in a six degrees of freedom (DOF) registration problem from point cloud measurements.…”

Point-MDA: Progressive Point Cloud Analysis for Extreme Multi-Scale Detail Activation

“…Point cloud classification has been active in the research fields such as photogrammetry and remote sensing for decades. It has become an important part of intelligent vehicles [1], automatic driving [2], 3D reconstruction [3], forest monitoring [4], robot perception [5], traffic signage extraction [6] and so on. Due to factors like irregularity and disorder, high sensor noise, complex scenes and non-homogeneous density, point cloud classification is still challenging.…”