Local Dynamic Map Research Articles

Enhancing Autonomous Driving Robot Systems with Edge Computing and LDM Platforms

The efficient operation and interaction of autonomous robots play crucial roles in various fields, e.g., security, environmental monitoring, and disaster response. For these purposes, processing large volumes of sensor data and sharing data between robots is essential; however, processing such large data in an on-device environment for robots results in substantial computational resource demands, causing high battery consumption and heat issues. Thus, this study addresses challenges related to processing large volumes of sensor data and the lack of dynamic object information sharing among autonomous robots and other mobility systems. To this end, we propose an Edge-Driving Robotics Platform (EDRP) and a Local Dynamic Map Platform (LDMP) based on 5G mobile edge computing and Kubernetes. The proposed EDRP implements the functions of autonomous robots based on a microservice architecture and offloads these functions to an edge cloud computing environment. The LDMP collects and shares information about dynamic objects based on the ETSI TR 103 324 standard, ensuring cooperation among robots in a cluster and compatibility with various Cooperative-Intelligent Transport System (C-ITS) components. The feasibility of operating a large-scale autonomous robot offloading system was verified in experimental scenarios involving robot autonomy, dynamic object collection, and distribution by integrating real-world robots with an edge computing–based offloading platform. Experimental results confirmed the potential of dynamic object collection and dynamic object information sharing with C-ITS environment components based on LDMP.

S-LDM: Server local dynamic map for 5G-based centralized enhanced collective perception

The automotive field is undergoing significant technological advances, which includes making the next generation of autonomous vehicles smarter, greener and safer through vehicular networks, which are often referred to as Vehicle-to-Everything (V2X) communications. Together with V2X, centralized maneuver management services for autonomous vehicles are increasingly gaining importance, as, thanks to their complete view over the road, they can optimally manage even the most complex maneuvers targeting L4 driving and beyond. These services face the challenge of strictly requiring a high reliability and low latency, which are tackled with the deployment at orchestrated Multi-Access Edge Computing (MEC) platforms. In order to properly manage safety-critical maneuvers, these services need to receive a large amount of data from vehicles, even though the useful subset of data is often related to a specific context on the road (e.g., to specific road users or geographical areas). Decoding and post-processing a large amount of raw messages, which are then for the most part filtered, increases the load on safety-critical services, which should instead focus on meeting the deadlines for the actual control and management operations. On this basis, we present an innovative open-source, 5G & MEC enabled service, called Server Local Dynamic Map (S-LDM). The S-LDM is a service that collects information about vehicles and other non-connected road objects using standard-compliant messages. Its primary purpose is to create a centralized dynamic map of the road that can be shared efficiently with other services managing L4 automation, when needed. By doing so, the S-LDM enables these services to widely and precisely understand the current situation of sections of the road, offloading them from the need of quickly processing a large number of messages. After a detailed description of the service architecture, we validate it through extensive laboratory and pilot trials, involving the MEC platforms and production 5G networks of three major European network operations and two Stellantis vehicles equipped with V2X On-Board Units (OBUs). We show how it can efficiently handle high update rates and process each messages in less than few tenths of microseconds. We also provide a complete scalability analysis with details on deployment options, providing insights on where new instances should be created in practical 5G-based V2X scenarios.

Real-Time Object Detection and Tracking Based on Embedded Edge Devices for Local Dynamic Map Generation

This paper proposes a camera system designed for local dynamic map (LDM) generation, capable of simultaneously performing object detection, tracking, and 3D position estimation. This paper focuses on improving existing approaches to better suit our application, rather than proposing novel methods. We modified the detection head of YOLOv4 to enhance the detection performance for small objects and to predict fiducial points for 3D position estimation. The modified detector, compared to YOLOv4, shows an improvement of approximately 5% mAP on the Visdrone2019 dataset and around 3% mAP on our database. We also proposed a tracker based on DeepSORT. Unlike DeepSORT, which applies a feature extraction network for each detected object, the proposed tracker applies a feature extraction network once for the entire image. To increase the resolution of feature maps, the tracker integrates the feature aggregation network (FAN) structure into the DeepSORT network. The difference in multiple objects tracking accuracy (MOTA) between the proposed tracker and DeepSORT is minimal at 0.3%. However, the proposed tracker has a consistent computational load, regardless of the number of detected objects, because it extracts a feature map once for the entire image. This characteristic makes it suitable for embedded edge devices. The proposed methods have been implemented on a system on chip (SoC), Qualcomm QCS605, using network pruning and quantization. This enables the entire process to be executed at 10 Hz on this edge device.

Multi-Layered Local Dynamic Map for a Connected and Automated In-Vehicle System

Automated Driving (AD) has been receiving considerable attention from industry, the public, and researchers for its ability to reduce accidents, emissions, and congestion. The purpose of this study is to extend the standardized Local Dynamic Map (LDM) by adding two new layers, and develop efficient and accurate algorithms designed to enhance AD by exploiting the LDM coupled with Cooperative Perception (CP). The LDM is implemented as a Neo4j graph database and extends the standard four-layer structure by adding a detection layer and a prediction layer. A custom Application Programming Interface (API) manages all incoming data, generates the LDM, and runs the algorithms. Currently, the API can match detected entities coming from different sources, correctly position them on the map even in the presence of high uncertainties in the data, and predict their future actions. We tested the developed LDM with real-world data, which we collected using a prototype vehicle from Centro Ricerche FIAT (CRF) Trento Branch—the supporting research center for this work—in urban, suburban, and highway areas of Trento, Italy. The results show that the developed solution is capable of accurately matching and predicting detected entities, is robust to high uncertainties in the data, and is efficient, achieving real-time performance in all scenarios. From these results we can conclude that the LDM and CP have the potential to be core parts of AD, bringing improvements to the development process.

A Kamm's Circle-Based Potential Risk Estimation Scheme in the Local Dynamic Map Computation Enhanced by Binary Decision Diagrams.

Autonomous vehicles (AV) are a hot topic for safe mobility, which inevitably requires sensors to achieve autonomy, but relying too heavily on sensors will be a risk factor. A high-definition map (HD map) reduces the risk by giving geographical information if it covers dynamic information from moving entities on the road. Cooperative intelligent transport systems (C-ITS) are a prominent approach to solving the issue and local dynamic maps (LDMs) are expected to realize the ideal C-ITS. An actual LDM implementation requires a fine database design to be able to update the information to represent potential risks based on future interactions of vehicles. In the present study, we proposed an advanced method for embedding the geographical future occupancy of vehicles into the database by using a binary decision diagram (BDD). In our method, the geographical future occupancy of vehicles was formulated with Kamm’s circle. In computer experiments, sharing BDD-based occupancy data was successfully demonstrated in the ROS-based simulator with the linked list-based BDD. Algebraic operations in exchanged BDDs effectively managed future interactions such as data insertion and timing of collision avoidance in the LDM. This result opened a new door for the realization of the ideal LDM for safety in AVs.

Online and Predictive Warning System for Forced Lane Changes Using Risk Maps

The survival analysis of driving trajectories allows for holistic evaluations of car-related risks caused by collisions or curvy roads. This analysis has advantages over common Time-To-X indicators, such as its predictive and probabilistic nature. However, so far, the theoretical risks have not been demonstrated in real-world environments. In this paper, we therefore present Risk Maps (RM) for online warning support in situations with forced lane changes, due to the end of roads. For this purpose, we first unify sensor data in a Relational Local Dynamic Map (R-LDM). RM is afterwards able to be run in real-time and efficiently probes a range of situations in order to determine risk-minimizing behaviors. Hereby, we focus on the improvement of uncertainty-awareness and transparency of the system. Risk, utility and comfort costs are included in a single formula and are intuitively visualized to the driver. In the conducted experiments, a low-cost sensor setup with a GNSS receiver for localization and multiple cameras for object detection are leveraged. The final system is successfully applied on two-lane roads and recommends lane change advices, which are separated in gap and no-gap indications. These results are promising and present an important step towards interpretable safety.

Evaluation of LDM (Local Dynamic Map) Service Based on a Role in Cooperative Autonomous Driving with a Road

Evaluation of LDM (Local Dynamic Map) Service Based on a Role in Cooperative Autonomous Driving with a Road

ILDM: An Interoperable Graph-Based Local Dynamic Map

Local dynamic map (LDM) is a key component in the future of autonomous and connected vehicles. An LDM serves as a local database with the necessary tools to have a common reference system for both static data (i.e., map information) and dynamic data (vehicles, pedestrians, etc.). The LDM should have a common and well-defined input system in order to be interoperable across multiple data sources such as sensor detections or V2X communications. In this work, we present an interoperable graph-based LDM (iLDM) using Neo4j as our database engine and OpenLABEL as a common data format. An analysis on data insertion and querying time to the iLDM is reported, including a vehicle discovery service function in order to test the capabilities of our work and a comparative analysis with other LDM implementations showing that our proposed iLDM outperformed in several relevant features, furthering its practical utilisation in advanced driver assistance system development.

An Algorithm for Local Dynamic Map Generation for Safe UAV Navigation

For safe UAV navigation and to avoid collision, it is essential to have accurate and real-time perception of the environment surrounding the UAV, such as free area detection and recognition of dynamic and static obstacles. The perception system of the UAV needs to recognize information such as the position and velocity of all objects in the surrounding local area regardless of the type of object. At the same time, a probability based representation taking into account the noise of the sensor is also essential. In addition, a software design with efficient memory usage and operation time is required in consideration of the hardware limitations of the UAVs. In this paper, we propose a 3D Local Dynamic Map (LDM) generation algorithm for a perception system for UAVs. The proposed LDM uses a circular buffer as a data structure to ensure low memory usage and fast operation speed. A probability based occupancy map is created using sensor data and the position and velocity of each object are calculated through clustering between grid voxels using the occupancy map and velocity estimation based on a particle filter. The objects are predicted using the position and velocity of each object and this is reflected in the occupancy map. This process is continuously repeated and the flying environment of the UAV can be expressed in a three-dimensional grid map and the state of each object. For the evaluation of the proposed LDM, we constructed simulation environments and the UAV for outdoor flying. As an evaluation factor, the occupancy grid is accuracy evaluated and the ground truth velocity and the estimated velocity are compared.

Consistent decentralized cooperative localization for autonomous vehicles using LiDAR, GNSS, and HD maps

AbstractTo navigate autonomously, a vehicle must be able to localize itself with respect to its driving environment and the vehicles with which it interacts. This study presents a decentralized cooperative localization method. It is based on the exchange of local dynamic maps (LDM), which are cyber‐physical representations of the physical driving environment containing poses and kinematic information about nearby vehicles. An LDM acts as an abstraction layer that makes the cooperation framework sensor‐agnostic, and it can even improve the localization of a sensorless communicating vehicle. With this goal in mind, this study focuses on the property of consistency in LDM estimates. Uncertainty in the estimates needs to be properly modeled, so that the estimation error can be statistically bounded for a given confidence level. To obtain a consistent system, we first introduce a decentralized fusion framework that can cope with LDMs whose errors have an unknown degree of correlation. Second, we present a consistent method for estimating the relative pose between vehicles, using a two‐dimensional LiDAR (light detection and ranging) with a point‐to‐line metric within an iterative‐closest‐point approach, combined with communicated polygonal shape models. Finally, we add a bias estimator to reduce position errors when nondifferential GNSS (global navigation satellite system) receivers are used, based on visual observations of features geo‐referenced in a high‐definition map. Real experiments were conducted, and the consistency of our approach was demonstrated on a platooning scenario using two experimental vehicles. The full experimental data set used in this study is publicly available.

Deploying spatial-stream query answering in C-ITS scenarios1

Cooperative Intelligent Transport Systems (C-ITS) play an important role for providing the means to collect and exchange spatio-temporal data via V2X-based communication between vehicles and the infrastructure, which will become a central enabler for road safety of (semi)-autonomous vehicles. The Local Dynamic Map (LDM) is a key concept for integrating static and streamed data in a spatial context. The LDM has been semantically enhanced to allow for an elaborate domain model that is captured by a mobility ontology, and for queries over data streams that cater for semantic concepts and spatial relationships. Our approach for semantic enhancement is in the context of ontology-mediated query answering (OQA) and features conjunctive queries over DL-LiteA ontologies that support window operators over streams and spatial relations between spatial objects. In this paper, we show how this approach can be extended to address a wider range of use cases in the three C-ITS scenarios traffic statistics, traffic events detection, and advanced driving assistance systems. We define for the mentioned use cases requirements derived from necessary domain-specific features and report, based on them, on extensions of our query language and ontology model. The extensions include temporal relations, numeric predictions and trajectory predictions as well as optimization strategies such as caching. An experimental evaluation of queries that reflect the requirements has been conducted using the real-world traffic simulation tool PTV Vissim. It provides evidence for the feasibility/efficiency of our approach in the new scenarios.

Implementation of a Sensor Big Data Processing System for Autonomous Vehicles in the C-ITS Environment

To provide a service that guarantees driver comfort and safety, a platform utilizing connected car big data is required. This study first aims to design and develop such a platform to improve the function of providing vehicle and road condition information of the previously defined central Local Dynamic Map (LDM). Our platform extends the range of connected car big data collection from OBU (On Board Unit) and CAN to camera, LiDAR, and GPS sensors. By using data of vehicles being driven, the range of roads available for analysis can be expanded, and the road condition determination method can be diversified. Herein, the system was designed and implemented based on the Hadoop ecosystem, i.e., Hadoop, Spark, and Kafka, to collect and store connected car big data. We propose a direction of the cooperative intelligent transport system (C-ITS) development by showing a plan to utilize the platform in the C-ITS environment.

Multi-Hop Dynamic Map Data Propagation Algorithm for Clustered Vehicular Networks

To ensure the driving safety in vehicular network, it is necessary to construct a local dynamic map (LDM) for an extended range. Using the standard vehicular communication protocols, however, vehicles can construct the LDM for only one-hop range. Constructing large-scale LDM is highly challenging because vehicles randomly change their position. This paper proposes a dynamic map propagation (DMP) method, which builds a large aggregated LDM data using a multi-hop communication. To reduce the data overhead, we introduce an efficient clustering method based on a half-circle of the forwarder’s wireless range. The DMP elects one forwarder per cluster, which constructs LDM and forwards it to a neighbor cluster. The inter-cluster interference is minimized by allocating a different transmit window to each cluster. DMP copes with a dynamic environment by frequently re-electing the forwarders and their associated transmission windows. Simulation results reveal that DMP enhances the forwarders’ reception ratio by 20%, while extending LDM dissemination range by 29% over a previous work.

Associated Reality: A cognitive Human–Machine Layer for autonomous driving

Advanced Driver Assistance Systems (ADAS) and Automated and Autonomous Vehicles (AV) are cooperative systems and processes that use: artificial intelligence, cognitive methods, cloud technologies, cooperative vehicle-to-everything-communications (V2X), software–hardwareplatforms, sensor platforms and incipient intelligent transport infrastructures, to get self-driving systems and smart connected mobility services. This paper, to support automated driving systems (assisted, semi-autonomous and fully autonomous vehicles), introduces a cognitive layer called Associated Reality to enhance the involved information, knowledge and communication processes. The architecture defined includes an augmented Local Dynamic Map, with complementary layers, and an augmented Graph Database, with complementary semantic–cognitive relations, for the considered purpose, in cooperative human–machine and machine–machine systems. Virtual augmented landmarks are defined to improve the connectivity and intelligence of the involved spatial-information systems. Different structure landmarks and sequence landmarks (which includes regular, repetitive and periodic landmarks) are defined, categorized and used in diverse visual localization and mapping scenarios, for autonomous driving. In this paper, it is also shown, as a proof-of-concept for vehicle localization and mapping in road tunnels, the visual detection of different sequences of periodic luminaires, using YOLO v3 for the corresponding LED lights detection, or a specific alternative procedure developed with very low computational cost.

A Multi-Hop Data Dissemination Algorithm for Vehicular Communication

In vehicular networks, efficient multi-hop message dissemination can be used for various purposes, such a informing the driver about the recent emergency event or propagating the local dynamic map of a predefined region. Dissemination of warning information up to a longer distance can reduce the accidents on the road. It provides a driver additional time to react to the situations adequately and assists in finding a safe route towards the destination. The adopted V2X standards, ETSI TS’s C-ITS and IEEE 1609/IEEE 802.11p, specify only primitive multi-hop message dissemination schemes. IEEE 1609.4 standard disseminates the broadcast messages using the method of flooding, which causes high redundancy, severe congestion, and long delay during multi-hop propagation. To address these problems, we propose an effective broadcast message dissemination method. It introduces a notion of source Lateral Crossing Line (LCL) algorithm, which elects a set of relay vehicles for each hop based on the vehicle locations in a way that reduces the redundant retransmission and congestion, consequently minimizing the delays. Our simulation results demonstrated that the proposed method can achieve about 15% reduction in delays and 2 times the enhancement in propagation distance compared with the previous methods.

도심도로 자율협력주행을 위한 정보 플랫폼 구성 및 평가 방안 연구

최근 C-ITS (CV), 자율주행(AV) 등 외부에서 연계 또는 차량에서 직접 수집한 정보를 이용하여 도로 ‧ 교통의 안전을 증대시키기 위한 연구가 활발히 진행되고 있다. 특히 자율주행 관련 기술은 4차 산업혁명을 선도하는 대표 기술 중 하나로, 우리나라에서도 정부 및 민간 차원의 연구가 매우 활발히 진행되고 있다. 그러나 사망사고를 포함한 자율주행차 관련 인명사고의 발생으로 인해 자율주행 기술에 대한 신임도가 높지 않게 조사되고 있으며, 특히 도심도로 내에서는 예측하기 어려운 변수가 많아 이에 대한 보완이 반드시 필요한 상황이다. 이를 극복하기 위한 방안으로 도로 ‧ 교통 인프라와 자율주행차의 협력기술(CAV)이 도입되고 있으며, 점차 증대하고 있다. 그러나 산발적 연구진행으로 인해 정보 플랫폼에 대한 정립이 미진하고, 적절한 정보 제공 유무에 대한 평가체계가 미흡하다. 이를 극복하기 위해 도심도로에 한정된 자율협력주행 정보 플랫폼의 평가를 위한 효과척도를 신속성, 정확성, 안전성으로 정립하고, 각 척도별 평가지표를 포함한 분석 방안을 수립하였다. 이를 통해 보다 안전한 도로 ‧ 교통 환경의 구성 및 자율주행 관련 기술의 연착을 지원할 수 있을 것으로 기대한다.

Selective local dynamic map construction based on MEC architecture

In view of the rapid increase of data volume in large-scale intelligent connected vehicle scene, this paper proposes a local dynamic map (LDM) construction method based on the mobile edge computing (MEC) architecture. On this basis, we select key nodes from a large number of vehicles to upload data, reducing system computing pressure, data redundancy and system delay. Moreover, the intelligent connected vehicle simulation tool is used to simulate the intersection with large numbers of intelligent connected vehicles, to verify the advantages of the selective local dynamic map construction method.

Towards a Semantically Enriched Local Dynamic Map

With the increasing availability of Cooperative Intelligent Transport Systems, the Local Dynamic Map (LDM) is becoming a key technology for integrating static, temporary, and dynamic information in a geographical context. However, existing ideas do not leverage the full potential of the LDM approach, as an LDM contains streaming data and varying implicit information which are not captured by current models. We aim to provide a semantically enriched LDM that applies Semantic Web technologies, in particular ontologies, in combination with spatial stream databases. This allows us to define an enhanced world model, to derive model properties, to infer new information, and to offer expressive query capabilities over streams. We introduce our envisioned architecture which includes an LDM ontology, an integration and annotation framework, and a stream query answering component. We also sketch three application scenarios that illustrate the usability and benefits of our approach, thus we provide an in-depth validation of the scenarios in an experimental prototype.

Intersection Warning System for Occlusion Risks Using Relational Local Dynamic Maps

This work addresses the task of risk evaluation in traffic scenarios with limited observability due to restricted sensorial coverage. Here, we concentrate on intersection scenarios that are difficult to access visually. To identify the area of sight, we employ ray casting on a local dynamic map providing geometrical information and road infrastructure. Based on the area with reduced visibility, we first model scene entities that pose a potential risk without being visually perceivable yet. Then, we predict a worst-case trajectory in the survival analysis for collision risk estimation. Resulting risk indicators are utilized to evaluate the driver's current behavior, to warn the driver in critical situations, to give suggestions on how to act safely or to plan safe trajectories. We validate our approach by applying the resulting intersection warning system on real world scenarios. The proposed system's behavior reveals to mimic the general behavior of a correctly acting human driver.

On the Interrelation of Security, QoS, and Safety in Cooperative ITS

Cooperative intelligent transport system (C-ITS) is an emerging technology that enables secure and safe road travel using wireless communications. Vehicles regularly share their mobility information with the neighborhood road traffic and infrastructure-based road side units using cooperative awareness messages (CAMs) to develop a local dynamic map for safety applications. Since the applications provided by C-ITS are related to human safety, reliable as well as secure communications are required. To protect the vehicular network from untrusted data of malicious users that could cause network congestion and reduce vehicle safety, ITS standards have proposed various security procedures. In this paper, we analyze the interrelation between security, quality of service (QoS), and safety awareness of vehicles in C-ITS. To formulate an accurate measure of vehicle safety awareness, we first propose novel vehicle and infrastructure centric metrics that use the number of received CAMs, their accuracy, safety importance, and vehicle heading. We then implement the standard CAM signature and verification procedure in the ITS standard. Using simulation results and our proposed metrics, we show the impact of security signature and verification speed on the level of vehicle awareness and, hence, QoS in different road traffic conditions.