High-definition Maps Research Articles

A Base-Map-Guided Global Localization Solution for Heterogeneous Robots Using a Co-View Context Descriptor

With the continuous advancement of autonomous driving technology, an increasing number of high-definition (HD) maps have been generated and stored in geospatial databases. These HD maps can provide strong localization support for mobile robots equipped with light detection and ranging (LiDAR) sensors. However, the global localization of heterogeneous robots under complex environments remains challenging. Most of the existing point cloud global localization methods perform poorly due to the different perspective views of heterogeneous robots. Leveraging existing HD maps, this paper proposes a base-map-guided heterogeneous robots localization solution. A novel co-view context descriptor with rotational invariance is developed to represent the characteristics of heterogeneous point clouds in a unified manner. The pre-set base map is divided into virtual scans, each of which generates a candidate co-view context descriptor. These descriptors are assigned to robots before operations. By matching the query co-view context descriptors of a working robot with the assigned candidate descriptors, the coarse localization is achieved. Finally, the refined localization is done through point cloud registration. The proposed solution can be applied to both single-robot and multi-robot global localization scenarios, especially when communication is impaired. The heterogeneous datasets used for the experiments cover both indoor and outdoor scenarios, utilizing various scanning modes. The average rotation and translation errors are within 1° and 0.30 m, indicating the proposed solution can provide reliable localization support despite communication failures, even across heterogeneous robots.

An Indoor-Outdoor Layered HD Map Construction for Unmanned Ground Vehicles

Abstract. High-Definition Maps (HD Maps) are lane-level 3-dimensional road network models that ensure the safe operation of autonomous vehicles and drive the continuous advancement of autonomous driving technology to higher levels. However, HD Maps currently face challenges regarding limited coverage and description of indoor environments (e.g. underground parking), as well as the lack of uniformity between indoor and outdoor map formats. Therefore, this paper proposes a Layered HD Map model for both indoor and outdoor environments. The map model consists of 6 layers, allowing effective representation of indoor and outdoor environments, as well as transitional areas. The paper also establishes an Unmanned Ground Vehicle (UGV) to collect and update map data using LiDAR (Light Detection and Ranging) SLAM (Simultaneous Localization and Mapping) and autonomous exploration technology, aiming to enhance the efficiency and automation of HD Map acquisition. In order to verify the validity of the proposed map model, this paper conducted a navigation experiment in a double decker parking lot containing entrances and exits. The results of the experiments demonstrate that the Layered HD Map generated through autonomous LiDAR SLAM can effectively describe the indoor and outdoor environments, and enable successful navigation of UGVs.

Efficient micro-mobility path planning without using high-definition maps

Efficient path planning is crucial for the safe autonomous operation of micro-mobility vehicles in unknown environments. When planning paths for micro-mobility, factors, such as the changes in the user's intended destination and user comfort, must be considered. Moreover, for driving in unknown areas, the path planner should not rely on predetermined detailed information like High-Definition maps (HD maps). In this paper, we propose an innovative path planning algorithm for automated driving that solely uses basic perception data from RGB camera, IMU and GPS, thereby eliminating the dependency on HD maps. We initially convert perception data into an occupancy grid map. Subsequently, a global path planner, based on a modified A* algorithm, computes an efficient trajectory, particularly adept to navigation in unknown environments and to scenarios where goal position moves. Additionally, we developed a local planner that optimize multi-clothoid curves using designed constraints to predict the best trajectory. Our experiments, conducted in both simulated and real-world environments, validate the effectiveness of our approach for micro-mobility path planning using only perception data.

Organizing planning knowledge for automated vehicles and intelligent transportation systems

AbstractIntelligent Transportation Systems (ITS) are crucial for developing fully automated vehicles. While significant progress has been made with advanced driver assistance systems and automation technology, challenges remain, such as improving traffic information, enhancing planning and control systems, and developing better decision‐making capabilities. Despite these hurdles, the potential benefits of ITS are so many that its challenges have attracted substantial industrial investment and research groups interested in the automated driving field. In this work, a methodology based on state space search for planning knowledge integration is proposed. The main goal of the proposal is to provide a planning system with the necessary information to perform properly any task related to lateral and longitudinal control, path following, trajectory generation, arbitration and behavior execution by localizing the vehicle with respect to a high‐level road plan. To this end, this research compares cutting‐edge methods for rapidly finding the K nearest neighbor in relatively high dimensional road plans constructed from the traffic information stored in a high definition map. During the experimentation phase, promising real‐time results have been obtained for fast KNN algorithms, leading to a robust tree index‐based methodology for decision making in self‐driving vehicles combining path planning, trajectory tracking, trajectory creation, knowledge aggregation and precise vehicle control.

Three-Dimensional Reconstruction of Zebra Crossings in Vehicle-Mounted LiDAR Point Clouds

In the production of high-definition maps, it is necessary to achieve the three-dimensional instantiation of road furniture that is difficult to depict on traditional maps. The development of mobile laser measurement technology provides a new means for acquiring road furniture data. To address the issue of traffic marking extraction accuracy in practical production, which is affected by degradation, occlusion, and non-standard variations, this paper proposes a 3D reconstruction method based on energy functions and template matching, using zebra crossings in vehicle-mounted LiDAR point clouds as an example. First, regions of interest (RoIs) containing zebra crossings are obtained through manual selection. Candidate point sets are then obtained at fixed distances, and their neighborhood intensity features are calculated to determine the number of zebra stripes using non-maximum suppression. Next, the slice intensity feature of each zebra stripe is calculated, followed by outlier filtering to determine the optimized length. Finally, a matching template is selected, and an energy function composed of the average intensity of the point cloud within the template, the intensity information entropy, and the intensity gradient at the template boundary is constructed. The 3D reconstruction result is obtained by solving the energy function, performing mode statistics, and normalization. This method enables the complete 3D reconstruction of zebra stripes within the RoI, maintaining an average planar corner accuracy within 0.05 m and an elevation accuracy within 0.02 m. The matching and reconstruction time does not exceed 1 s, and it has been applied in practical production.

Global Localization using OpenStreetMap and Elevation Offsets

Localization is a critical component in autonomous vehicle navigation stacks. While GNSS-only localization cannot be fully reliable and available all the time, localization based on 3D high-definition (HD) maps have to be robust to world changes, which is still a challenging issue. Added to that, in general, HD maps are expensive and difficult to construct and maintain.In this paper, we propose a particle filter-based 2D global pose estimation method that can use the crowdsourced OpenStreetMap (OSM) API, a digital surface map, or both. The main contributions of the proposed approach are: that it is lightweight, does not require the vehicle to map the environment, does not require a GPU (can be used with low-power computing resources), is agnostic to the odometry source, and achieved relatively low position and orientation errors for this localization modality using the KITTI dataset sequences. The proposed method's implementation is open source and is available with the experimental results on our GitHub page.

Vehicle Localization Using Crowdsourced Data Collected on Urban Roads.

Vehicle localization using mounted sensors is an essential technology for various applications, including autonomous vehicles and road mapping. Achieving high positioning accuracy through the fusion of low-cost sensors is a topic of considerable interest. Recently, applications based on crowdsourced data from a large number of vehicles have received significant attention. Equipping standard vehicles with low-cost onboard sensors offers the advantage of collecting data from multiple drives over extensive road networks at a low operational cost. These vehicle trajectories and road observations can be utilized for traffic surveys, road inspections, and mapping. However, data obtained from low-cost devices are likely to be highly inaccurate. On urban roads, unlike highways, complex road structures and GNSS signal obstructions caused by buildings are common. This study proposes a reliable vehicle localization method using a large amount of crowdsourced data collected from urban roads. The proposed localization method is designed with consideration for the high inaccuracy of the data, the complexity of road structures, and the partial use of high-definition (HD) maps that account for environmental changes. The high inaccuracy of sensor data affects the reliability of localization. Therefore, the proposed method includes a reliability assessment of the localized vehicle poses. The performance of the proposed method was evaluated using data collected from buses operating in Seoul, Korea. The data used for the evaluation were collected 18 months after the creation of the HD maps.

An Object-Centric Hierarchical Pose Estimation Method Using Semantic High-Definition Maps for General Autonomous Driving.

To achieve Level 4 and above autonomous driving, a robust and stable autonomous driving system is essential to adapt to various environmental changes. This paper aims to perform vehicle pose estimation, a crucial element in forming autonomous driving systems, more universally and robustly. The prevalent method for vehicle pose estimation in autonomous driving systems relies on Real-Time Kinematic (RTK) sensor data, ensuring accurate location acquisition. However, due to the characteristics of RTK sensors, precise positioning is challenging or impossible in indoor spaces or areas with signal interference, leading to inaccurate pose estimation and hindering autonomous driving in such scenarios. This paper proposes a method to overcome these challenges by leveraging objects registered in a high-precision map. The proposed approach involves creating a semantic high-definition (HD) map with added objects, forming object-centric features, recognizing locations using these features, and accurately estimating the vehicle's pose from the recognized location. This proposed method enhances the precision of vehicle pose estimation in environments where acquiring RTK sensor data is challenging, enabling more robust and stable autonomous driving. The paper demonstrates the proposed method's effectiveness through simulation and real-world experiments, showcasing its capability for more precise pose estimation.

Tightly coupled integration of vector HD map, LiDAR, GNSS, and INS for precise vehicle navigation in GNSS-challenging environment

ABSTRACT High-precision positioning and navigation are necessary for autonomous driving. GNSS RTK and INS integrated system is commonly used in vehicular navigation. But it suffers from severe signal reflections and blockages of GNSS signals and error accumulation of INS with MEMS-IMU in GNSS-challenging environment. In addition, high-definition (HD) maps in vector format and light detection and ranging (LiDAR) are two common options for intelligent vehicles. A tightly coupled localization method with vector HD map, LiDAR, GNSS RTK, and INS is proposed to take advantage of their complementary characteristics to accurately navigate a vehicle in a GNSS-challenging environment. The method is based on a particle filter (PF) framework. Lateral positions of particles are constrained by LiDAR measurements and lane information in the vector HD map. A constrained and damped LAMBDA searching method is proposed to update particle weights, aiming to find accurate longitudinal localization. Experimental results prove that our method can maintain sub-meter level horizontal positioning accuracy in GNSS-challenging environment, with improvements of (77%, 75%, 64% and 65%), regarding to three-dimensional position and yaw, compared to traditional GNSS-RTK/INS integration, while the improvement of the popular GNSS-RTK/INS/LiDAR integrated framework LIO-SAM is (16%, 53%, 48% and 51%).

Ultra-fast semantic map perception model for autonomous driving

Autonomous driving relies on real-time perception of environmental semantic maps to make decisions, accurate and real-time perception of environmental semantics is crucial for safe navigation, as well as for efficient construction of high-definition maps in the backend. Our research found that when the output space of the semantic map perception model is an orthogonal projection subspace of the input perception space, it significantly improves the accuracy and real-time performance of map semantic segmentation while reducing learning pressure on deep network models. Based on this, we propose a simple yet efficient semantic map segmentation network that aims to achieve extremely fast speed and precision. Furthermore, we implement a semantic map fusion process using a Bayesian framework that promotes global semantic information accumulation in local semantics over time and space. Our experimental results demonstrate the superiority of our method, achieving state-of-the-art performance in network speed and mIoU metrics. At the same spatial resolution of semantic maps, our method reaches over 350+ frames per second, which is at least 15 times faster than the previous state-of-the-art method. Code released at https://github.com/xzx-ai/MDSegMap.

A Comprehensive Survey on High-Definition Map Generation and Maintenance

The automotive industry has experienced remarkable growth in recent decades, with a significant focus on advancements in autonomous driving technology. While still in its early stages, the field of autonomous driving has generated substantial research interest, fueled by the promise of achieving fully automated vehicles in the foreseeable future. High-definition (HD) maps are central to this endeavor, offering centimeter-level accuracy in mapping the environment and enabling precise localization. Unlike conventional maps, these highly detailed HD maps are critical for autonomous vehicle decision-making, ensuring safe and accurate navigation. Compiled before testing and regularly updated, HD maps meticulously capture environmental data through various methods. This study explores the vital role of HD maps in autonomous driving, delving into their creation, updating processes, and the challenges and future directions in this rapidly evolving field.

Information System Model and Key Technologies of High-Definition Maps in Autonomous Driving Scenarios.

Background: High-definition maps can provide necessary prior data for autonomous driving, as well as the corresponding beyond-line-of-sight perception, verification and positioning, dynamic planning, and decision control. It is a necessary element to achieve L4/L5 unmanned driving at the current stage. However, currently, high-definition maps still have problems such as a large amount of data, a lot of data redundancy, and weak data correlation, which make autonomous driving fall into difficulties such as high data query difficulty and low timeliness. In order to optimize the data quality of high-definition maps, enhance the degree of data correlation, and ensure that they better assist vehicles in safe driving and efficient passage in the autonomous driving scenario, it is necessary to clarify the information system thinking of high-definition maps, propose a complete and accurate model, determine the content and functions of each level of the model, and continuously improve the information system model. Objective: The study aimed to put forward a complete and accurate high-definition map information system model and elaborate in detail the content and functions of each component in the data logic structure of the system model. Methods: Through research methods such as the modeling method and literature research method, we studied the high-definition map information system model in the autonomous driving scenario and explored the key technologies therein. Results: We put forward a four-layer integrated high-definition map information system model, elaborated in detail the content and functions of each component (map, road, vehicle, and user) in the data logic structure of the model, and also elaborated on the mechanism of the combined information of each level of the model to provide services in perception, positioning, decision making, and control for autonomous driving vehicles. This article also discussed two key technologies that can support autonomous driving vehicles to complete path planning, navigation decision making, and vehicle control in different autonomous driving scenarios. Conclusions: The four-layer integrated high-definition map information model proposed by this research institute has certain application feasibility and can provide references for the standardized production of high-definition maps, the unification of information interaction relationships, and the standardization of map data associations.

Global Navigation Satellite System/Inertial Measurement Unit/Camera/HD Map Integrated Localization for Autonomous Vehicles in Challenging Urban Tunnel Scenarios

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.

A Review on End-to-End High-Definition Map Generation

Abstract. Autonomous driving offers benefits such as congestion mitigation, increased productivity through the reallocation of driving time, and decreased energy waste. However, achieving Level 4 and 5 autonomous driving remains a significant challenge for both academia and industry. Among the various modules of autonomous driving, High-Definition (HD) maps have become a crucial component due to their high precision in map elements, enabling accurate localization, scene interpretation, navigation, vehicle control and motion forecasting of trajectory of surrounding objects. Several map providers, including TomTom, HERE, Waymo, and NVIDIA, create HD maps for their specific purposes. However, most HD map datasets are not publicly available for individual researchers and companies to investigate the current trends in HD map generation. Furthermore, recent survey papers on HD map generation have tended to focus only on specific aspects, such as road topology or boundary extraction, rather than considering the overall end-to-end HD map generation process. Therefore, we begin with a brief definition, standards, and functionality of HD maps, followed by an exploration of different types of HD maps, including offline and online variants, highlighting their respective advantages and disadvantages. Finally, we will discuss the most recent end-to-end HD map generation architectures, along with various types of open-source HD map datasets and compare their performances.

Semi-automated approach towards efficient HD Maps generation and verification with Lanelet2 formats

Abstract. HD Maps (High-Definition Maps) serve as crucial resources for the domain of autonomous vehicle. Because HD Maps can provide detailed and accurate road information, the generation of HD Maps has been a labour-intensive and high cost. This research presents an innovative and semi-automated approach for efficient HD Maps generation by using assure mapping tool with deep learning techniques and mobile laser scanned point cloud geometry. The proposed method starts with data collection from various sources such as images, LiDAR point clouds, and integrated INS/GNSS trajectory data. These data are labelled by using a pre-trained model. After finishing post-labelling, these data are subjected to deep learning training by using VoxelNet and Yolact++ framework and leading to the generation of an AI model. The tool effectively recognizes and categorizes features such as road surface markings, traffic signs, and traffic lights, which can be further expanded as per requirements. Finally, the output format can be converted to OpenDRIVE, Lanelet2, and other else. Hence, the extracted lane lines can compare to the manual mapping data for verifying the accuracy. This study demonstrates that the proposed approach can be instrumental in streamlining the HD Maps generation procedure, reducing manual labour, and enhancing efficiency. The assure mapping tool proves to be an effective instrument, particularly when powered by deep learning algorithms and point cloud geometries, in the creation of reliable, comprehensive, and application-ready HD Maps.

Automated Lane Centering: An Off-the-Shelf Computer Vision Product vs. Infrastructure-Based Chip-Enabled Raised Pavement Markers.

Safe autonomous vehicle (AV) operations depend on an accurate perception of the driving environment, which necessitates the use of a variety of sensors. Computational algorithms must then process all of this sensor data, which typically results in a high on-vehicle computational load. For example, existing lane markings are designed for human drivers, can fade over time, and can be contradictory in construction zones, which require specialized sensing and computational processing in an AV. But, this standard process can be avoided if the lane information is simply transmitted directly to the AV. High definition maps and road side units (RSUs) can be used for direct data transmission to the AV, but can be prohibitively expensive to establish and maintain. Additionally, to ensure robust and safe AV operations, more redundancy is beneficial. A cost-effective and passive solution is essential to address this need effectively. In this research, we propose a new infrastructure information source (IIS), chip-enabled raised pavement markers (CERPMs), which provide environmental data to the AV while also decreasing the AV compute load and the associated increase in vehicle energy use. CERPMs are installed in place of traditional ubiquitous raised pavement markers along road lane lines to transmit geospatial information along with the speed limit using long range wide area network (LoRaWAN) protocol directly to nearby vehicles. This information is then compared to the Mobileye commercial off-the-shelf traditional system that uses computer vision processing of lane markings. Our perception subsystem processes the raw data from both CEPRMs and Mobileye to generate a viable path required for a lane centering (LC) application. To evaluate the detection performance of both systems, we consider three test routes with varying conditions. Our results show that the Mobileye system failed to detect lane markings when the road curvature exceeded ±0.016 m-1. For the steep curvature test scenario, it could only detect lane markings on both sides of the road for just 6.7% of the given test route. On the other hand, the CERPMs transmit the programmed geospatial information to the perception subsystem on the vehicle to generate a reference trajectory required for vehicle control. The CERPMs successfully generated the reference trajectory for vehicle control in all test scenarios. Moreover, the CERPMs can be detected up to 340 m from the vehicle's position. Our overall conclusion is that CERPM technology is viable and that it has the potential to address the operational robustness and energy efficiency concerns plaguing the current generation of AVs.

Compact HD Map Construction via Douglas-Peucker Point Transformer

High-definition (HD) map construction requires a comprehensive understanding of traffic environments, encompassing centimeter-level localization and rich semantic information. Previous works face challenges in redundant point representation or high-complexity curve modeling. In this paper, we present a flexible yet effective map element detector that synthesizes hierarchical information with a compact Douglas-Peucker (DP) point representation in a transformer architecture for robust and reliable predictions. Specifically, our proposed representation approximates class-agnostic map elements with DP points, which are sparsely located in crucial positions of structures and can get rid of redundancy and complexity. Besides, we design a position constraint with uncertainty to avoid potential ambiguities. Moreover, pairwise-point shape matching constraints are proposed to balance local structural information of different scales. Experiments on the public nuScenes dataset demonstrate that our method overwhelms current SOTAs. Extensive ablation studies validate each component of our methods. Codes will be released at https://github.com/sweety121/DPFormer.

A Review of Crowdsourcing Update Methods for High-Definition Maps

High-definition (HD) maps serve as crucial infrastructure for autonomous driving technology, facilitating vehicles in positioning, environmental perception, and motion planning without being affected by weather changes or sensor-visibility limitations. Maintaining precision and freshness in HD maps is paramount, as delayed or inaccurate information can significantly impact the safety of autonomous vehicles. Utilizing crowdsourced data for HD map updating is widely recognized as a superior method for preserving map accuracy and freshness. Although it has garnered considerable attention from researchers, there remains a lack of comprehensive exploration into the entire process of updating HD maps through crowdsourcing. For this reason, it is imperative to review and discuss crowdsourcing techniques. This paper aims to provide an overview of the overall process of crowdsourced updates, followed by a detailed examination and comparison of existing methodologies concerning the key techniques of data collection, information extraction, and change detection. Finally, this paper addresses the challenges encountered in crowdsourced updates for HD maps.

A comprehensive research of deep learning approaches for High Definition map construction in autonomous driving

In the realm of autonomous driving, High Definition Maps (HD maps) are indispensable for safe and precise navigation. Traditional HD map construction methods involving point cloud capture and SLAM have proven effective but labor-intensive. This paper addresses the growing interest in leveraging deep learning techniques to streamline HD map creation. This paper presents a systematic exploration of deep learning methodologies for HD map construction. It categorizes these approaches into two core components: Feature Extraction and Feature Decoding. Feature Extraction involves the transformation of input data, comprising images and LiDAR point clouds, into Bird's Eye View (BEV) representations. Feature Decoding is dissected into rasterized map objectives and vector map objectives. Detailed analysis is conducted on prominent methodologies. The paper provides a nuanced evaluation of these deep learning techniques, highlighting their respective strengths and limitations. Factors such as precision, computational efficiency, and the preservation of fine-grained details are considered when selecting the most suitable method. This comprehensive review summarizes and prospects the research in related fields.

Unraveling Spatial–Temporal Patterns and Heterogeneity of On-Ramp Vehicle Merging Behavior: Evidence from the exiD Dataset

Understanding the spatiotemporal characteristics of merging behavior is crucial for the advancement of autonomous driving technology. This study aims to analyze on-ramp vehicle merging patterns, and investigate how various factors, such as merging scenarios and vehicle types, influence driving behavior. Initially, a framework based on a high-definition (HD) map is developed to extract trajectory information in a meticulous manner. Subsequently, eight distinct merging patterns are identified, with a thorough examination of their behavioral characteristics from both temporal and spatial perspectives. Merging behaviors are examined temporally, encompassing the sequence of events from approaching the on-ramp to completing the merge. This study specifically analyzes the target lane’s spatial characteristics, evaluates the merging distance (ratio), investigates merging speed distributions, compares merging patterns and identifies high-risk situations. Utilizing the latest aerial dataset, exiD, which provides HD map data, the study presents novel findings. Specifically, it uncovers patterns where the following vehicle in the target lane chooses to accelerate and overtake rather than cutting in front of the merging vehicle, resulting in Time-to-Collision (TTC) values of less than 2.5 s, indicating a significantly higher risk. Moreover, the study finds that differences in merging speed, distance, and duration can be disregarded in patterns where vehicles are present both ahead and behind, or solely ahead, suggesting these patterns could be integrated for simulation to streamline analysis and model development. Additionally, the practice of truck platooning has a significant impact on vehicle merging behavior. Overall, this study enhances the understanding of merging behavior, facilitating autonomous vehicles’ ability to comprehend and adapt to merging scenarios. Furthermore, this research is significant in improving driving safety, optimizing traffic management, and enabling the effective integration of autonomous driving systems with human drivers.