OverlapNet: Loop Closing for LiDAR-based SLAM

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.

Accepted by RSS 2020. Code: https://github.com/PRBonn/OverlapNet

References in corpus (4)

• SuMa++: Efficient LiDAR-based Semantic SLAM
• Learning to Localize Using a LiDAR Intensity Map
• OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios
• Localising Faster: Efficient and precise lidar-based robot localisation in large-scale environments

Cited by in corpus (16)

• OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition
• Range Image-based LiDAR Localization for Autonomous Vehicles
• Intensity-SLAM: Intensity Assisted Localization and Mapping for Large Scale Environment
• BoW3D: Bag of Words for Real-Time Loop Closing in 3D LiDAR SLAM
• Globally Consistent 3D LiDAR Mapping with GPU-accelerated GICP Matching Cost Factors
• MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions, spherical coordinates, and intensity
• Contour Context: Abstract Structural Distribution for 3D LiDAR Loop Detection and Metric Pose Estimation
• Learning an Overlap-based Observation Model for 3D LiDAR Localization
• Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning
• Online Range Image-based Pole Extractor for Long-term LiDAR Localization in Urban Environments
• Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots
• ROLO-SLAM: Rotation-Optimized LiDAR-Only SLAM in Uneven Terrain with Ground Vehicle
• Spherical Multi-Modal Place Recognition for Heterogeneous Sensor Systems
• RaLF: Flow-based Global and Metric Radar Localization in LiDAR Maps
• TSCM: A Teacher-Student Model for Vision Place Recognition Using Cross-Metric Knowledge Distillation
• Efficiently Closing Loops in LiDAR-Based SLAM Using Point Cloud Density Maps