Search

Achieving sufficient safety measures is among the major challenges in developing automated vehicles that can operate safely in an urban environment. Data fusion between an in-vehicle camera and a LiDAR sensor can be used for detection and tracking of other road users in an automated vehicle. In addition, simulated environments together with high-level deterministic, supervised and reinforcement learning-based autonomous control could provide traffic safety benefits in the future. These AI-based technologies have been studied in the AI4DI project to enable the Mobility as a Service (MaaS) operators fleet management of automated vehicles. The development and testing of these methods are presented in this chapter with the first promising results. The Camera - LiDAR fusion algorithm provided very good results with the accuracy evaluation using the KITTI dataset.The real-time applicability of the fusion algorithm was also successfully verified.

Systems and methods described herein are provided for determining a platoon configuration for a group of vehicles, determining a set of routes connecting two locations, determining for each route segment the platoon configurations supported and the availability of roadside units on the route segment, and selecting a route from the set of routes connecting the two locations. A route may be selected based on the availability of a roadside unit (RSU) to request an extended time period for a green light to enable a length of the platoon to traverse through an intersection prior to the time period ending. Systems and methods described herein may enable a reconfiguration of a platoon to meet a platoon size restriction for a segment of the selected route.Patent family as of 23.3.2022 DE602017026073 D1 20201112 DE201760026073T 20171206 EP3552071 A1 20191016 EP20170822847 20171206 EP3552071 B1 20201021 EP20170822847 20171206 US2020064140 AA 20200227 US20170461311 20171206 WO18106774 A1 20180614 WO2017US64851 20171206Link to current family on right

This work shows and analyzes the LiDAR performance in real-world heavy winter conditions captured in Northern Europe. We review how low temperatures, salted roads and turbulent snow in front of a passenger car influence LiDAR systems developed for automated driving functions. Two test cars were driven in the north of Finland and Sweden for 1.5 weeks to gather a large amount of point cloud data in different urban and rural scenarios. We show that the benchmarked LiDAR sensors have surprising performance differences in winter. Some of the sensors got mechanically frozen whereas others went out of the measurement range and were completely blind. Especially the latest multi-layer sensors showed significant problems. We propose countermeasures such as heating and protecting in order to improve the performance and suggest how the software can take the performance degradation into account.

EU-China 5G collaboration trials will be conducted addressing two specific scenarios: (1) enhanced Mobile Broadband (eMBB) on the 3.5GHz band; and (2) Internet of Vehicles (IoV) based on LTE-V2X using the 5.9 GHz band for Vehicle-to-Vehicle (V2V) and the 3.5 GHz band for Vehicle-to-Network (V2N). This paper discussed scenario 2, and presents the use cases based on next generation communication technologies in the domain of Cooperative Intelligent Transport Systems (C-ITS) for cooperative and automated road transport. In addition, it describes for each use case the developed physical architecture. Finally, it provides an overview of the joint V2X trials to be conducted in the EU and China, in the context of the 5G-DRIVE project.

For vehicles and road users, accurate and real-time weather, road condition and traffic situation information are key elements when improving road safety. This chapter discussed novel use cases and system architecture, utilizing the enhanced capacity and properties of next -generation 5G mobile technology in the automotive and transport domains. The use cases aimed to improve road safety through new road weather and safety services, real-time V2V video and lidar data streaming, as well as the enhancement of automated driving in diverse conditions. The overall solution encompassed sophisticated services and procedures, designed into the vehicle entity as well as in the distributed cloud, including MEC. The use cases were implemented into real pilot constructions and this chapter provided an overview of the experiences and results. The real service pilots gave valuable insights into the benefits that 5G and supporting technologies like MEC will bring to vehicular services. However, for some of the non -critical or less bandwidth consuming services, current 4G/LTE networks and ITS -G5 technology (if supported) could provide sufficient performance to already facilitate the development and deployment of network -assisted vehicular services now in the pre -5G era

This paper presents the first results of the publicly funded ECSEL project DENSE (Adverse weather environmental sensing system). DENSE seeks to eliminate one of the most pressing problems of automated driving: the inability of current systems to sense their surroundings under all weather conditions. The task in DENSE is to develop a sensor suite for automatic driving, by means of which the vehicle environment can be reliably detected 24/7 under these bad weather conditions. In this paper, the state of the art of environmental sensor technology is first examined and evaluated in the CEREMA weather chamber. Then, the architecture of the DENSE Sensor Suite is presented and the development results of the most important system components are described. The results show that the realization of a 24/7 all-weather sensor suite is absolutely feasible with these components .

The development of 5G is taking steps forward to solve the communication challenges of the future. One of the main application areas to benefit from 5G is intelligent traffic and vehicular communication. This paper discusses the recent advances in the development and piloting of novel road weather and safety services. The services considered in the paper exploit extensive vehicular observation data, of which transmission is enabled by a 5G communications architecture. The purpose of the services is to provide enhancements to road users, road maintenance operations as well as to 3 rd parties. Furthermore, low latency 5G networks will enable future automated driving functionality, considered in the paper as well. The paper presents use cases and a generic system architecture for the envisioned service concepts. In addition, selected results obtained from testing the services in real vehicular and 5G test network environments are presented.

The H2020 project 5G-DRIVE (5G HarmoniseD Research and TrIals for serVice Evolution between EU and China) cooperates with the Chinese twin project to trial and validate key functions of 5G networks operating at 3.5 GHz bands for enhanced Mobile Broadband (eMBB) and 3.5 GHz and 5.9 GHz bands for V2X scenarios. 5G-DRIVE will instil significant impact on the validation of standards and trigger the roll-out of real 5G networks and V2X innovative solutions driving new business opportunities and creating thereby new jobs and brand new business models. This paper presents the overall approach of 5G-DRIVE, the advances beyond the current state of the art for key 5G enabling technologies, as well as the considered use cases.

Automated driving technology offers new business opportunities for a wide range of organisations. Testing facilities, both test tracks and areas as well as test vehicles are required for testing new vehicle hardware and software components and novel mobility concepts. VTT has converted passenger cars for supporting the development of automated driving functions in an open and modular way, enabling collaboration partners to test new prototypes and concepts quickly. The paper gives several examples of the use cases developed by the vehicles.

The ECSEL joint undertaking RobustSENSE1 focuses on technologies and solutions for automated driving in adverse weather conditions. One of the main technology challenges is to improve laser scanner performance in fog where the existing 905 nm lidar reliability degrades below tolerances. This report briefly summarizes the results of experimental fog absorbance measurements, which were conducted in VTT icing wind tunnel located in VTT's premises. The content of the presentation will focus on spectral absorbance measurements in artificial fog in near infrared band.

Professional truck drivers are an essential part of transportation in keeping the global economy alive and commercial products moving. In order to increase productivity and improve safety, an increasing amount of automation is implemented in modern trucks. Transition to automated heavy good vehicles is intended to make trucks accident-free and, on the other hand, more comfortable to drive. This motivates the automotive industry to bring more embedded ICT into their vehicles in the future. An avenue towards autonomous vehicles requires robust environmental perception and driver monitoring technologies to be introduced. This is the main motivation behind the DESERVE project. This is the study of sensor technology trials in order to minimize blind spots around the truck and, on the other hand, keep the river's vigilance at a sufficiently high level. The outcomes are two innovative truck demonstrations: one R & D study for bringing equipment to production in the future and one implementation to the driver training vehicle. The earlier experiments include both driver monitoring technology which works at a 60% - 80% accuracy level and environment perception (stereo and thermal cameras) whose performance rates are 70% - 100%. The results are not sufficient for autonomous vehicles, but are a step forward, since they are in-line even if moved from the lab to real automotive implementations.

Systems and methods are provided for enhancing pedestrian safety, particularly in or near sensor-equipped smart spaces. A pedestrian indicates to a security service of a smart space that he wishes to walk from a starting location to a destination. The service identifies a plurality of pedestrian routes to the destination. The service also receives, from a nearby connected vehicles, information indicating what areas are coved by sensors of those vehicles. For each route, the system calculates a security metric based at least in part on the proportion of the route covered by the vehicle sensors. The system informs the pedestrian of the different routes and their associated security metrics. In some embodiments, the system may direct an autonomous vehicle to reposition itself to improve sensor coverage along a selected route.

The paper focuses on the innovative strength that the DESERVE platform has brought on the Advanced Driver Assistance Systems (ADAS) market in terms of major safety and economic affordability. DESERVE is a project aimed at designing and implementing a low-cost, integrated platform for ADAS: the creation of innovative software and hardware modules to be integrated in ADAS applications will pave the way to a standardization of the single components in order to achieve a full integration of diversified models despite their complexity. The achievement of such objective will end up in an increase of the reliability level of the system and in a cost reduction for ADAS functions and for development costs as well. In this paper the results of the application of the modularisation philosophy to the DESERVE platform architecture and to the human machine interface (HMI) concepts will be presented.

This paper suggest a new schema for improving accuracy of estimation of traffic CO 2 emissions. The emission estimation is implemented as a part of novel traffic surveillance system which is movable and uses data fusion of several sensors and databases. The system is able to determine the emissions in real-time based on the traffic flow observed and this provides advantages over the current methods. The emissions are often approximated by using estimates of average traffic flow and emission rates but this produces very unreliable results. Another way is to use gas sensors but they are expensive and provide only point measurement data. In this paper, we show the feasibility of the novel schema.

Road friction measurement is an important issue for active safety systems on vehicles; hence knowledge of this key parameter can significantly improve the interventions on vehicle dynamics. This study compares two different on-board sensors for the classification of road conditions with polarised infrared light. Several tests are performed on a dedicated track, with focus on detection of dry or wet surfaces, and the presence of ice or snow. The work shows the capability of both sensors to provide a correct classification. In particular, results indicate how the monitored area, the presence of active illumination and the mounting position influence measurements and response times. It is concluded that both systems classify different road conditions in all cases. Performance of the Road eye system varied from 80 to 90 % whereas the camera based IcOR achieved 70-80 % accuracy level. Since these are being prototype sensors more development is needed before implemented into advanced safety applications

This article proposes an advanced roadside monitoring sub-system for future cooperative intersection infrastructure. The sub-system consists of the camera for road condition monitoring, traffic light controller, Laserscanners, local dynamic maps database and V2I communication module. These components are interfaced to the high level fusion platform which is intended extract information and enable risk assessment if the situation is turning safety critical. The system is part of the European INTERSAFE-2 project which focuses on introducing cooperative traffic safety in intersection environment. Approximately every third of traffic incidences are intersection related. The project is expected emerge technology to influence beneficiary in 80% of the intersection related accidents with injuries and fatalities.

This paper presents experimental results regarding road condition monitoring by machine vision techniques. The system will be further developed by VTT in the European INTERSAFE-2 project, focused on applications at road intersections. Knowing the presence of adverse conditions such as icy or wet roads, important effects can be obtained for intersection safety by means of more effective driver assistance functions. A very good reliability up to 93% has been found for the detection of icy roads, while lower values around 60% have been measured in the case of wet surfaces, due to a higher sensitivity to environmental conditions, especially outdoor light. Future steps will include an advanced classification algorithm and the implementation of active lighting. Integration of the vision equipment into a cooperative system for intersection safety is being investigated.

This paper presents a method and evaluation results to monitor and detect road conditions (ice, water, snow and dry asphalt). The developed device bases on light polarization changes when reflected from road surface. The recognition capability has been improved with texture analysis which estimates contrast content of an image. Test drives were performed with a vehicle equipped also with a commercial solution from Vaisala which was used as the reference sensor. The results show that the proposed solution does not currently adapt to different conditions perfectly well. Therefore, further development targets have been identified to include not only more adjustable classifier but externally lighting to stabilizing ambient illumination.

This article focuses on monitoring a driver's cognitive impairment due to talking to passengers or on a mobile phone, daydreaming, or just thinking about other than driving-related matters. This paper describes an investigation of cognitive distraction, firstly, giving an overall idea of its effects on the driver and, secondly, discussing the practical implementation of an algorithm for detection of cognitive distraction using a support vector machine (SVM) classifier. The evaluation data have been gathered by recruiting 12 professional drivers to drive for approximately 45 min in various environments and inducing cognitive tasks, i.e. arithmetic calculations. According to the prior knowledge and the experimental analysis, gaze, head and lane-keeping variances over a 15 s time window were selected indicative features. The SVM classifier's performance was optimized through exhaustive parameter tuning. The executed tests show that the cognitive workload can be detected with approximately 65-80 per cent confidence despite the fact that the test material represented medium-difficulty cognitive tasks (i.e. the induced workload was not very high). Thus, it could be assumed that a more challenging cognitive task would yield better detection results.

This chapter presents the improvements to a camera calibration method, including a compact calibration object, and possibility to perform the calibration with only one captured image. Currently available calibration methods are described shortly, and a new type of calibration object which is suitable for use in, e.g. small parts assembly cells, is presented along with a method of searching the calibration points. The purpose of the camera calibration is to define the accurate camera model, which also takes into account the distortions in the image. The advantage of the new calibration method is that it is fully automatic, while previously several manual steps were needed, and several pictures of test images had to be taken. The tests of the method show that significant improvement of the accuracy was achieved for cameras that use short focal length lenses. In several tests the method was found to give reliable results when the novel calibration object was used. A few successful tests were also performed for determining the position and orientation of the camera with the same method.

The ECSEL joint undertaking RobustSENSE focuses on technologies and solutions for automated driving in adverse weather conditions. One of the main technology challenges is to improve laser scanner performance in fog where the existing 905 nm LIDAR reliability degrades below tolerances. This report briefly summarizes the results of experimental fog absorbance measurements, which were conducted in test laboratories located in VTT's premises. The content of the presentation will focus on spectral absorbance at low visibility artificial fog in near infrared band.