CAOM: Change-aware online 3D mapping with heterogeneous multi-beam and push-broom LiDAR point clouds

A high-definition (HD) map is becoming an integral component of future mobility systems such as autonomous and connected vehicles. Advances in computing systems, LiDAR technologies, and vehicle communication technologies have enabled the HD map to directly treat a point cloud map (PCM), modeling road environments as LiDAR signal-level data. However, if actual road environments are changed, the PCM, modeling the environments before changes, can not be used for vehicle applications. Accordingly, the PCM has to stay up-to-date states by reflecting the environment changes continuously. This paper presents a crowd-sourcing framework to update the PCM from environment changes continuously using LiDAR and vehicle communication. Multiple intelligent vehicles installed with the LiDAR sensors download the PCM from a map server via wireless vehicle communication. To minimize the effects of environment changes, a robust localization based on a hierarchical Simultaneous Localization and Mapping (SLAM) estimates the pose (position and direction). The estimated pose is used to detect the differences between the PCM and environments, which are defined as map changes. The map changes are detected by the probabilistic and evidential theory considering the LiDAR characteristics, such as beam divergence and multi-echo. The detected map changes are uploaded to the map cloud server and merged into the PCM. The proposed crowd-sourcing framework to keep the PCM up-to-date is verified and evaluated via simulations and experiments in sites with road environment changes.

Review and challenge: High definition map technology for intelligent connected vehicle

Deploying fully autonomous vehicles has been a subject of intense research in both industry and academia. However, the majority of these efforts have relied heavily on High Definition (HD) prior maps. These are necessary to provide the planning and control modules a rich model of the operating environment. While this approach has shown success, it drastically limits both the scale and scope of these deployments as creating and maintaining HD maps for very large areas can be prohibitive. In this work, we present a new method for building the HD map online by starting with a Standard Definition (SD) prior map such as a navigational road map, and incorporating onboard sensors to infer the local HD map. We evaluate our method extensively on 100 sequences of real-world vehicle data and demonstrate that it can infer a highly structured HD map-like model of the world accurately using only SD prior maps and onboard sensors.

In this paper, we studied a SLAM method for vector-based road structure mapping using multi-beam LiDAR. We proposed to use the polyline as the primary mapping element instead of grid cell or point cloud, because the vector-based representation is precise and lightweight, and it can directly generate vector-based High-Definition (HD) driving map as demanded by autonomous driving systems. We explored: 1) the extraction and vectorization of road structures based on local probabilistic fusion. 2) the efficient vector-based matching between frames of road structures. 3) the loop closure and optimization based on the pose-graph. In this study, we took a specific road structure, the road boundary, as an example. We applied the proposed matching method in three different scenes and achieved the average absolute matching error of 0.07 m. We further applied the vector-based mapping system to a road with the length of 860 meters and achieved an average global accuracy of 0.466 m without the aid of GPS.

Navigation system for orchard spraying robot based on 3D LiDAR SLAM with NDT_ICP point cloud registration

High Definition (HD) maps are necessary for many applications of automated driving (AD), but their manual creation and maintenance is very costly. Vehicle fleet data from series production vehicles can be used to automatically generate HD maps, but the data is often incomplete and noisy. We propose a system for the generation of HD maps from vehicle fleet data, which is tolerant to missing or misclassified detections and can handle drives with multiple routes, generating a single complete map, model-free and without prior reference lines. Using randomly selected drives as pivot drives, a step-wise lateral sampling of detections is performed. These sampled points are then clustered and aligned using Expectation Maximization (EM), estimating a lateral offset for each drive to compensate localization errors. The clustered points are replaced with the maxima of their probability density function (PDF) and connected to form polylines using a modified rectangular linear assignment algorithm. The data from vehicles on varying routes is then fused into a hierarchical singular map graph. The proposed approach achieves an average accuracy below 0.5 meters compared to a hand annotated ground truth map, as well as correctly resolving lane splits and merges, proving the feasibility of the use of vehicle fleet data for the generation of highway HD maps.

Smart cities are emerging and under development worldwide. As one of the core components for achieving the goal of smart transportation, autonomous vehicles are undoubtedly on the blueprint for smart cities. The development of autonomous driving cars leads to the demand for highly accurate and detailed machine-readable maps. To meet this demand, the high-definition (HD) maps are being developed. The HD maps are extended three-dimensional maps that tend to contain enough detailed information in the driving environment to be consumed by machines. Both commercial companies and research communities got a recent interest in building and are exploring research problems on this kind of mapping data. Several companies have already defined their commercial HD map formats, but there are arguments that the existing HD map formats are not research-friendly enough. In this paper, we propose to define a research-friendly HD map data model by extending the popular node-edge model that is widely used by researchers. Our model considers both on-road and off-road data to be extensible for future use cases and information that will be available on various three-dimensional objects in the outdoor space. This is partially motivated by several use cases that will benefit from HD mapping data other than the self-driving technology. We give a brief discussion for such potential use cases and how our model will fit their requirements. We also discuss that our model can be still used for human-machine interactions for compatibility with existing techniques and applications.

Autonomous vehicle technology has been advancing over the past decade with many challenges and obstacles. One obstacle to achieving fully autonomous driving is the feasibility of efficiently producing robust high definition (HD) maps of existing road infrastructure in a sustainable manner. HD maps are digital twins of road infrastructure that include 3-D representation of road features critical to a vehicle’s ability to navigate a road and maintain a consistent trajectory. This includes lane markings, barriers, and road edges. HD maps are often produced by first surveying roads using remote sensing technology. The collected data are then segmented using computer vision and machine learning algorithms to produce an HD map of the features of concern. One common challenge that is specific to extracting lane marking information is that the markings are occasionally occluded or degraded by high traffic volumes. This results in failure to detect lane markings and the existence of significant gaps in the extracted information. These gaps are manually filled in by quality control staff in a tedious and time-consuming process. To help overcome such challenges, this paper proposes a novel algorithm through which Kalman filtering is combined with Bézier curve fitting to automatically refine lane marking information. The proposed algorithm is tested on multiple roads where mobile lidar data were collected and segmentation was first applied using deep learning technology. The proposed algorithm was then used to refine the lane marking information which helped close all the gaps and recreate missing portions of the extracted lane markings.

High-Definition (HD) maps are needed for robust navigation of autonomous vehicles, limited by the on-board storage capacity. To solve this, we propose a novel framework, Environment-Aware Normal Distributions Transform (EA-NDT), that significantly improves compression of standard NDT map representation. The compressed representation of EA-NDT is based on semantic-aided clustering of point clouds resulting in more optimal cells compared to grid cells of standard NDT. To evaluate EA-NDT, we present an open-source implementation that extracts planar and cylindrical primitive features from a point cloud and further divides them into smaller cells to represent the data as an EA-NDT HD map. We collected an open suburban environment dataset and evaluated EA-NDT HD map representation against the standard NDT representation. Compared to the standard NDT, EA-NDT achieved consistently at least 1.5x higher map compression while maintaining the same descriptive capability. Moreover, we showed that EA-NDT is capable of producing maps with significantly higher descriptivity score when using the same number of cells than the standard NDT.

Three-dimensional (3D) mapping deals with the problem of building a map of the unknown environments explored by a mobile robot. In contrast to 2D maps, 3D maps contain richer information of the visited places. Besides enabling robot navigation in 3D, a 3D map of the robot surroundings could be of great importance for higher-level robotic tasks, like scene interpretation and object interaction or manipulation, as well as for visualization purposes in general, which are required in surveillance, urban search and rescue, surveying, and others. Hence, the goal of this thesis is to develop a system which is capable of reconstructing the surrounding environment of a mobile robot as a three-dimensional map. Microsoft Kinect camera is a novel sensing sensor that captures dense depth images along with RGB images at high frame rate. Recently, it has dominated the stage of 3D robotic sensing, as it is low-cost, low-power. For this work, it is used as the exteroceptive sensor and obtains 3D point clouds of the surrounding environment. Meanwhile, the wheel odometry of the robot is used to initialize the search for correspondences between different observations. As a single 3D point cloud generated by the Microsoft Kinect sensor is composed of many tens of thousands of data points, it is necessary to compress the raw data to process them efficiently. The method chosen in this work is to use a feature-based representation which simplifies the 3D mapping procedure. The chosen features are planar surfaces and orthogonal corners, which is based on the fact that indoor environments are designed such that walls, ground floors, pillars, and other major parts of the building structures can be modeled as planar surface patches, which are parallel or perpendicular to each other. While orthogonal corners are presented as higher features which are more distinguishable in indoor environment. In this thesis, the main idea is to obtain spatial constraints between pairwise frames by building correspondences between the extracted vertical plane features and corner features. A plane matching algorithm is presented that maximizes the similarity metric between a pair of planes within a search space to determine correspondences between planes. The corner matching result is based on the plane matching results. The estimated spatial constraints form the edges of a pose graph, referred to as graph-based SLAM front-end. In order to build a map, however, a robot must be able to recognize places that it has previously visited. Limitations in sensor processing problem, coupled with environmental ambiguity, make this difficult. In this thesis, we describe a loop closure detection algorithm by compressing point clouds into viewpoint feature histograms, inspired by their strong recognition ability. The estimated roto-translation between detected loop frames is added to the graph representing this newly discovered constraint. Due to the estimation errors, the estimated edges form a non-globally consistent trajectory. With the aid of a linear pose graph optimizing algorithm, the most likely configuration of the robot poses can be estimated given the edges of the graph, referred to as SLAM back-end. Finally, the 3D map is retrieved by attaching each acquired point cloud to the corresponding pose estimate. The approach is validated through different experiments with a mobile robot in an indoor environment

Statistical learning techniques and increased computational power have facilitated the development of self-driving car technology. However, a limiting factor has been the high expense of scaling and maintaining high-definition (HD) maps. These maps are a crucial backbone for many approaches to self-driving technology. In response to this challenge, we present an approach that fuses pre-built point cloud map data with images to automatically and accurately identify static landmarks such as roads, sidewalks, and crosswalks. Our pipeline utilizes semantic segmentation of 2D images, associates semantic labels with points in point cloud maps to pinpoint locations in the physical world, and employs a confusion matrix formulation to generate a probabilistic bird's-eye view semantic map from semantic point clouds. The approach has been tested in an urban area with different segmentation networks to generate a semantic map with road features. The resulting map provides a rich context of the environment that is valuable for downstream tasks such as trajectory generation and intent prediction. Moreover, it has the potential to be extended to the automatic generation of HD maps for semantic features. The entire software pipeline is implemented in the robot operating system (ROS), a widely used robotics framework, and made available.

Lane-level localization is critical for autonomous vehicles (AVs). However, complex urban scenarios, particularly tunnels, pose significant challenges to AVs’ localization systems. In this paper, we propose a fusion localization method that integrates multiple mass-production sensors, including Global Navigation Satellite Systems (GNSSs), Inertial Measurement Units (IMUs), cameras, and high-definition (HD) maps. Firstly, we use a novel electronic horizon module to assess GNSS integrity and concurrently load the HD map data surrounding the AVs. This map data are then transformed into a visual space to match the corresponding lane lines captured by the on-board camera using an improved BiSeNet. Consequently, the matched HD map data are used to correct our localization algorithm, which is driven by an extended Kalman filter that integrates multiple sources of information, encompassing a GNSS, IMU, speedometer, camera, and HD maps. Our system is designed with redundancy to handle challenging city tunnel scenarios. To evaluate the proposed system, real-world experiments were conducted on a 36-kilometer city route that includes nine consecutive tunnels, totaling near 13 km and accounting for 35% of the entire route. The experimental results reveal that 99% of lateral localization errors are less than 0.29 m, and 90% of longitudinal localization errors are less than 3.25 m, ensuring reliable lane-level localization for AVs in challenging urban tunnel scenarios.

In recent years, high-definition (HD) maps are considered to be significant complements to the on-board sensors of autonomous vehicles. Due to the highly dynamic characteristic of HD map, how to update HD maps fast and efficiently has become the pivotal issue which attracts great attentions. Currently, most of the research on this issue focuses on the crowdsourcing protocol design or specific updating method meanwhile disregarding the need of communication and computing resource in HD map update. Therefore, in this paper, we propose an integrated update framework including both an adaptive data transmission scheme and an adaptive task scheduling scheme to realize fast data collection and fast data processing for HD map update. To the best of our knowledge, this is the first work that addresses the problem of HD map update which takes the need of communication and computing resource into consideration. In this paper, we firstly illustrate the system architecture of our HD map update framework. Based on that, to realize fast data collection, we propose an adaptive data transmission scheme, which optimizes the transmission rate on different links of each vehicle considering the wireless channel capacity and fronthaul link capacity of the access points. Besides, to realize fast data processing, we propose an adaptive task scheduling scheme, which enables cooperative computing between the edge nodes and cloud computing server, considering the constraints of computing capacity and backhaul link capacity. To the end, we carry out simulations to verify the effectiveness of our proposed policies.

A training dataset for semantic segmentation of urban point cloud map for intelligent vehicles

Most existing Simultaneous Localization and Mapping (SLAM) systems rely on the assumption of static environments to achieve reliable and efficient mapping. However, such methods often suffer from degraded localization accuracy and mapping consistency in dynamic settings, as they lack explicit mechanisms to distinguish between static and dynamic elements. To overcome this limitation, we present BMP-SLAM, a vision-based SLAM approach that integrates semantic segmentation and Bayesian motion estimation to robustly handle dynamic indoor scenes. To enable real-time dynamic object detection, we integrate YOLOv5, a semantic segmentation network that identifies and localizes dynamic regions within the environment, into a dedicated dynamic target detection thread. Simultaneously, the data association Bayesian mobile probability proposed in this paper effectively eliminates dynamic feature points and successfully reduces the impact of dynamic targets in the environment on the SLAM system. To enhance complex indoor robotic navigation, the proposed system integrates semantic keyframe information with dynamic object detection outputs to reconstruct high-fidelity 3D point cloud maps of indoor environments. The evaluation conducted on the TUM RGB-D dataset indicates that the performance of BMP-SLAM is superior to that of ORB-SLAM3, with the trajectory tracking accuracy improved by 96.35%. Comparative evaluations demonstrate that the proposed system achieves superior performance in dynamic environments, exhibiting both lower trajectory drift and enhanced positioning precision relative to state-of-the-art dynamic SLAM methods.