Diffusion Based Robust LiDAR Place Recognition

• URL: http://arxiv.org/abs/2504.12412v1
• Date: Wed, 16 Apr 2025 18:23:17 GMT
• Title: Diffusion Based Robust LiDAR Place Recognition
• Authors: Benjamin Krummenacher, Jonas Frey, Turcan Tuna, Olga Vysotska, Marco Hutter,
• Abstract summary: Mobile robots on construction sites require accurate pose estimation to perform autonomous surveying and inspection missions.<n>In this paper, we focus on the global re-positioning of a robot with respect to an accurate scanned mesh of the building solely using LiDAR data.<n>We train a diffusion model with a PointNet++ backbone, which allows us to model multiple position candidates from a single LiDAR point cloud.<n>The resulting model can successfully predict the global position of LiDAR in confined and complex sites despite the adverse effects of perceptual aliasing.
• Score: 7.703398598907747
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mobile robots on construction sites require accurate pose estimation to perform autonomous surveying and inspection missions. Localization in construction sites is a particularly challenging problem due to the presence of repetitive features such as flat plastered walls and perceptual aliasing due to apartments with similar layouts inter and intra floors. In this paper, we focus on the global re-positioning of a robot with respect to an accurate scanned mesh of the building solely using LiDAR data. In our approach, a neural network is trained on synthetic LiDAR point clouds generated by simulating a LiDAR in an accurate real-life large-scale mesh. We train a diffusion model with a PointNet++ backbone, which allows us to model multiple position candidates from a single LiDAR point cloud. The resulting model can successfully predict the global position of LiDAR in confined and complex sites despite the adverse effects of perceptual aliasing. The learned distribution of potential global positions can provide multi-modal position distribution. We evaluate our approach across five real-world datasets and show the place recognition accuracy of 77% +/-2m on average while outperforming baselines at a factor of 2 in mean error.

Related papers

• LPRnet: A self-supervised registration network for LiDAR and photogrammetric point clouds [38.42527849407057]
  LiDAR and photogrammetry are active and passive remote sensing techniques for point cloud acquisition, respectively. Due to the fundamental differences in sensing mechanisms, spatial distributions and coordinate systems, their point clouds exhibit significant discrepancies in density, precision, noise, and overlap. This paper proposes a self-supervised registration network based on a masked autoencoder, focusing on heterogeneous LiDAR and photogrammetric point clouds.
  arXiv  Detail & Related papers  (2025-01-10T02:36:37Z)
• LiDAR-based Registration against Georeferenced Models for Globally Consistent Allocentric Maps [16.335109366948473]
  Modern unmanned aerial vehicles (UAVs) are irreplaceable in search and rescue (SAR) missions to obtain a situational overview or provide closeups without endangering personnel.<n>However, UAVs heavily rely on global navigation satellite system (GNSS) for localization which works well in open spaces, but the precision drastically degrades in the vicinity of buildings.<n>In contrast, CityGML models provide approximate building shapes with accurate georeferenced poses.
  arXiv  Detail & Related papers  (2024-12-03T16:25:08Z)
• RING#: PR-by-PE Global Localization with Roto-translation Equivariant Gram Learning [20.688641105430467]
  Global localization is crucial in autonomous driving and robotics applications when GPS signals are unreliable. Most approaches achieve global localization by sequential place recognition (PR) and pose estimation (PE) We introduce a new paradigm, PR-by-PE localization, which bypasses the need for separate place recognition by directly deriving it from pose estimation. We propose RING#, an end-to-end PR-by-PE localization network that operates in the bird's-eye-view (BEV) space, compatible with both vision and LiDAR sensors.
  arXiv  Detail & Related papers  (2024-08-30T18:42:53Z)
• JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds [79.00975648564483]
  Trajectory forecasting models, employed in fields such as robotics, autonomous vehicles, and navigation, face challenges in real-world scenarios. This dataset provides comprehensive data, including the locations of all agents, scene images, and point clouds, all from the robot's perspective. The objective is to predict the future positions of agents relative to the robot using raw sensory input data.
  arXiv  Detail & Related papers  (2023-11-05T18:59:31Z)
• Analyzing Infrastructure LiDAR Placement with Realistic LiDAR Simulation Library [22.077414016647516]
  Infrastructure sensors play a critical role in Vehicle-to-Everything(V2X) cooperative perception.<n>How to find the optimal placement of infrastructure sensors is rarely studied.<n>We propose a pipeline that can efficiently and effectively find optimal installation positions for infrastructure sensors in a realistic simulated environment.
  arXiv  Detail & Related papers  (2022-11-29T07:18:32Z)
• PCGen: Point Cloud Generator for LiDAR Simulation [10.692184635629792]
  Existing methods generate data which are more noisy and complete than the real point clouds. We propose FPA raycasting and surrogate model raydrop. With minimal training data, the surrogate model can generalize to different geographies and scenes. Results show that object detection models trained by simulation data can achieve similar result as the real data trained model.
  arXiv  Detail & Related papers  (2022-10-17T04:13:21Z)
• IR-MCL: Implicit Representation-Based Online Global Localization [31.77645160411745]
  In this paper, we address the problem of estimating the robots pose in an indoor environment using 2D LiDAR data. We propose a neural occupancy field (NOF) to implicitly represent the scene using a neural network. We show that we can accurately and efficiently localize a robot using our approach surpassing the localization performance of state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-10-06T17:59:08Z)
• iSDF: Real-Time Neural Signed Distance Fields for Robot Perception [64.80458128766254]
  iSDF is a continuous learning system for real-time signed distance field reconstruction. It produces more accurate reconstructions and better approximations of collision costs and gradients.
  arXiv  Detail & Related papers  (2022-04-05T15:48:39Z)
• Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling [67.75095378830694]
  We develop a two-stage odometry estimation network, where we obtain the ego-motion by estimating a set of sub-region transformations. In this paper, we aim to alleviate the influence of unreliable structures in training, inference and mapping phases. Our two-frame odometry outperforms the previous state of the arts by 16%/12% in terms of translational/rotational errors.
  arXiv  Detail & Related papers  (2022-02-27T12:52:27Z)
• Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems [92.26462290867963]
  Kimera-Multi is the first multi-robot system that is robust and capable of identifying and rejecting incorrect inter and intra-robot loop closures. We demonstrate Kimera-Multi in photo-realistic simulations, SLAM benchmarking datasets, and challenging outdoor datasets collected using ground robots.
  arXiv  Detail & Related papers  (2021-06-28T03:56:40Z)
• ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation [111.56730703473411]
  Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotations. Simulation-to-real domain adaptation (SRDA) trains a DNN using unlimited synthetic data with automatically generated labels. ePointDA consists of three modules: self-supervised dropout noise rendering, statistics-invariant and spatially-adaptive feature alignment, and transferable segmentation learning.
  arXiv  Detail & Related papers  (2020-09-07T23:46:08Z)
• Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds [76.52448276587707]
  We propose Reconfigurable Voxels, a new approach to constructing representations from 3D point clouds. Specifically, we devise a biased random walk scheme, which adaptively covers each neighborhood with a fixed number of voxels. We find that this approach effectively improves the stability of voxel features, especially for sparse regions.
  arXiv  Detail & Related papers  (2020-04-06T15:07:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.