Improving Map Re-localization with Deep 'Movable' Objects Segmentation on 3D LiDAR Point Clouds

by   Victor Vaquero, et al.

Localization and Mapping is an essential component to enable Autonomous Vehicles navigation, and requires an accuracy exceeding that of commercial GPS-based systems. Current odometry and mapping algorithms are able to provide this accurate information. However, the lack of robustness of these algorithms against dynamic obstacles and environmental changes, even for short time periods, forces the generation of new maps on every session without taking advantage of previously obtained ones. In this paper we propose the use of a deep learning architecture to segment movable objects from 3D LiDAR point clouds in order to obtain longer-lasting 3D maps. This will in turn allow for better, faster and more accurate re-localization and trajectoy estimation on subsequent days. We show the effectiveness of our approach in a very dynamic and cluttered scenario, a supermarket parking lot. For that, we record several sequences on different days and compare localization errors with and without our movable objects segmentation method. Results show that we are able to accurately re-locate over a filtered map, consistently reducing trajectory errors between an average of 35.1 and of 47.9


page 1

page 3


Robust Lifelong Indoor LiDAR Localization using the Area Graph

Lifelong indoor localization in a given map is the basis for navigation ...

Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation

We present a self-supervised learning approach for the semantic segmenta...

SROM: Simple Real-time Odometry and Mapping using LiDAR data for Autonomous Vehicles

In this paper, we present SROM, a novel real-time Simultaneous Localizat...

An Experimental Evaluation of Robustness and Precision for Long-term LiDAR-based Localization in Highly Changing Environments

One of the hardest challenges to face in the development of a non GPS-ba...

A Robust and Rapidly Deployable Waypoint Navigation Architecture for Long-Duration Operations in GPS-Denied Environments

For long-duration operations in GPS-denied environments, accurate and re...

Automatic Map Update Using Dashcam Videos

Autonomous driving requires 3D maps that provide accurate and up-to-date...

CMSG Cross-Media Semantic-Graph Feature Matching Algorithm for Autonomous Vehicle Relocalization

Relocalization is the basis of map-based localization algorithms. Camera...

Please sign up or login with your details

Forgot password? Click here to reset