Topological local-metric framework for mobile robots navigation: a long term perspective

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

et al. 2019

Self Cite

Visual localization has attracted considerable attention due to its low-cost and stable sensor, which is desired in many applications, such as autonomous driving, inspection robots and unmanned aerial vehicles. However, current visual localization methods still struggle with environmental changes across weathers and seasons, as there is significant appearance variation between the map and the query image. The crucial challenge in this situation is that the percentage of outliers, i.e. incorrect feature matches, is high. In this paper, we derive minimal closed form solutions for 3D-2D localization with the aid of inertial measurements, using only 2 point matches or 1 point match and 1 line match. These solutions are further utilized in the proposed 2-entity RANSAC, which is more robust to outliers as both line and point features can be used simultaneously and the number of matches required for pose calculation is reduced. Furthermore, we introduce three feature sampling strategies with different advantages, enabling an automatic selection mechanism. With the mechanism, our 2-entity RANSAC can be adaptive to the environments with different distribution of feature types in different segments. Finally, we evaluate the method on both synthetic and realworld datasets, validating its performance and effectiveness in inter-session scenarios.

Section: Introductionmentioning

confidence: 99%

2-Entity RANSAC for robust visual localization in changing environment

Jiao

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

et al. 2019

Self Cite

“…In the experiment sections, we first use the multi-session dataset, called YQ, which is self-collected on a mobile robot platform in a university campus during three days [36], in which the LiDAR scans are captured by Velodyne VLP-16. The original full map M o is generated by using SLAM, shown in Fig.…”

Section: A Dataset and Implementationmentioning

confidence: 99%

3D LiDAR Map Compression for Efficient Localization on Resource Constrained Vehicles

Yin

IEEE Trans. Intell. Transport. Syst.

Tang

et al. 2021

Self Cite

Large scale 3D maps constructed via LiDAR sensor are widely used on intelligent vehicles for localization in outdoor scenes. However, loading, communication and processing of the original dense maps are time consuming for onboard computing platform, which calls for a more concise representation of maps to reduce the complexity but keep the performance of localization. In this paper, we propose a teacher-student learning paradigm to compress the 3D point cloud map. Specifically, we first find a subset of LiDAR points with high number of observations to preserve the localization performance, which is regarded as the teacher of map compression. An efficient optimization strategy is proposed to deal with the massive data in original map. With the supervision of compressed map, a student model is built by training a random forest model fed with geometric feature descriptors of each point. As a result, the student model is able to compress the map without referring to the expensive numerical optimization. Additionally, by incorporating the features, the innovative student model can be generalized to other new maps while no re-training is required. We conduct thorough experiments on multi-session dataset and KITTI dataset to demonstrate the effectiveness and efficiency of the proposed learning paradigm, and the comparison with other map compression methods. The final results show that the learned student model can achieve efficient map compression with comparable LiDAR based localization performance to the original map at the same time.

“…A perception system that employs only one sensor will not be robust. For example, LiDAR-based odometry [1] will fail when working in a long corridor, and the camera-based algorithm [2] , [3], [4] cannot be applied to a textureless scene [5]. Fusing the visual and laser information can eliminate the outliers from the algorithm, and solve various limitations for the algorithms imposed by the single sensor.…”

Section: Lidarcamera Calibration Under Arbitrary Configurations: Obsementioning

confidence: 99%

LiDAR-Camera Calibration Under Arbitrary Configurations: Observability and Methods

IEEE Trans. Instrum. Meas.

Ding

et al. 2020

Self Cite

LiDAR-camera calibration is a precondition for many heterogeneous systems that fuse data from LiDAR and camera. However, the constraint from common field of view and the requirement for strict time synchronization make the calibration a challenging problem. In this paper, we propose a novel LiDAR-camera calibration method aiming to eliminate these two constraints. Specifically, we capture a scan of 3D LiDAR when both the environment and the sensors are stationary, then move the camera to reconstruct the 3D environment using the sequentially obtained images. Finally, we align 3D visual points to the laser scan based on tightly couple graph optimization method to calculate the extrinsic parameters between LiDAR and camera. Under this design, the configuration of these two sensors are free from the common field of view constraint owing to the extended view from the moving camera. And we also eliminate the requirement for strict time synchronization as we only use the single scan of laser data when the sensors are stationary. We theoretically derive the conditions of minimal observability for our method and prove that the accuracy of calibration is improved by collecting more observations from multiple scattered calibration targets. We validate our method on both simulation platform and real-world datasets. Experiments show that our method achieves higher accuracy than other comparable methods, which is in accordance with our theoretical analysis. In addition, the proposed method is beneficial to not only plane measurement error based chessboard, but also other point measurement error based calibration targets, such as boxes and polygonal boards.