OverlapNet: Loop Closing for LiDAR-based SLAM

TL;DR

OverlapNet introduces a deep learning approach for loop closure detection in LiDAR-based SLAM, improving accuracy and generalization across different datasets and environments.

Contribution

The paper presents a novel neural network that estimates image overlap and yaw angle from LiDAR data for robust loop closure detection in SLAM.

Findings

Outperforms state-of-the-art loop closure detection methods

Demonstrates strong generalization to unseen environments

Enhances SLAM mapping accuracy with integrated loop closure detection

Abstract

Simultaneous localization and mapping (SLAM) is a fundamental capability required by most autonomous systems. In this paper, we address the problem of loop closing for SLAM based on 3D laser scans recorded by autonomous cars. Our approach utilizes a deep neural network exploiting different cues generated from LiDAR data for finding loop closures. It estimates an image overlap generalized to range images and provides a relative yaw angle estimate between pairs of scans. Based on such predictions, we tackle loop closure detection and integrate our approach into an existing SLAM system to improve its mapping results. We evaluate our approach on sequences of the KITTI odometry benchmark and the Ford campus dataset. We show that our method can effectively detect loop closures surpassing the detection performance of state-of-the-art methods. To highlight the generalization capabilities of our approach, we evaluate our model on the Ford campus dataset while using only KITTI for training. The experiments show that the learned representation is able to provide reliable loop closure candidates, also in unseen environments.