Search

Recently, multi-sensor localization strategies are gaining attention in the railway scenario. In fact, the current trend is to reduce or remove the physical equipment deployed along the track for positioning purposes and to exploit on-board sensors to realize the same functionalities. Although GNSS is one of the major resources to perform this task, its performances dramatically decrease in presence of sources of local hazards like multipath, shadowing and blockage. For this reason, multi-sensor positioning methods are under study. Among them, those based on the detection of landmarks constituted by georeferenced trackside infrastructure elements like rail signs, and the estimation of the relative position of the train with respect to them are rather promising. Thus, in this paper we focus on the construction of the section of a Rail Digital Map related to these infrastructure elements on the basis of the fusion of the outputs of a stereo video camera and a LIDAR. In particular, the algorithms for object detection, single epoch landmark position estimation and landmark tracking are discussed. Results of the performance assessment based on Monte Carlo simulations are also reported.

One of the major challenges in the design of high accuracy, high integrity localization procedures for rail applications based on Global Navigation Satellite Systems is represented by the local hazards that cannot be mitigated by resorting to augmentation networks. By fact, combining smoothed code pseudoranges with (differential) carrier phase and/or with Inertial Measurement Unit's outputs is ineffective against multipath low frequency components. These issues can be mitigated by processing images, depth maps and/or pointclouds provided by imaging sensors placed on board. The absolute position of the train can be determined by combining its relative position with respect to georeferenced rail infrastructure elements (e.g., panels, signals, signal gantries) provided by the visual localization processing unit with the landmark absolute position. In addition, the visual input can be exploited for determining on which track the train is located and can be used as complementary odometry source. Moreover, the information provided by the visual localization processing unit can be used to monitor integrity and compute the protection levels. In this contribution we present a localization system that integrates a Global Navigation Satellite System receiver, Inertial Measurement Units, and video sensors (such as monocular and stereo video camera, Time of Flight camera and LIDAR), and has the potential to overcome some of the operational and economical limitations of the current train localization system employed in the European Railway Traffic Management System.

Current high accuracy positioning systems for transport applications require high safety and high accuracy. Considering that some of the most relevant errors leading to a loss of integrity are multipath and interferences this paper introduces the use of a set of digital maps for mitigating the presence of such hazards. Moreover, relevant statistical modelling of multipath and interference errors is provided. More in details, three maps are introduced: the satellite visibility map, the multipath map and the interference map. The satellite visibility map, through a piecewise constant function, allows the receiver determining, for each azimuth, the minimum elevation of a satellite to consider it suitable for PVT. Moreover, a quantized version of such parameters allows designing an optimized version of the data to be transmitted. Concerning the interference map, it is constituted by a list of the prevailing radio frequency interferences and their spectral characteristics. As for the multipath map, a statistical model where the variance of the multipath error is considered as a random variable with a discrete distribution is considered. More in details, the multipath variance is modelled as the product of a geometrical factor, depending on the satellite elevation, and the C/N0, and a stochastically modeled inflating factor. These assumptions result in a distribution of the multipath error which follows a Gaussian Mixture. Therefore, a Mean Square receiver position solution, and the application of Solution Separation for satellite fault determination and PL calculation under the Gaussian Mixture distribution hypothesis, is derived. A Monte Carlo simulation is carried out for determining the estimation error, with respect to a Weighted Least Square solution and a classical Gaussian distribution of the multipath error with inflating factor equal to 1. Thanks to the better matching of the measurement error distribution, larger errors are attenuated and accounted for by the protection level. A consistent reduction in misleading information is demonstrated through a Stanford Plot analysis.

Before deployment and commissioning of new positioning products/applications, manufacturers need to perform long and often expensive field trials in targeted operational environments in order to assess and certify future behaviour. The community trust on GNSS (Global Navigation Satellite System) is so high that more and more safety critical applications based on satellite navigation are under development. With the increase of criticality level of GNSS applications, a relevant means to predict the performances and reliability of future applications is needed. Thus in this paper we introduce a new architecture based on Machine Learning that combines classical observables for local hazard detection, with the outcome of advanced RAIM in order to determine whether a given point of a railway is suitable for a safe and reliable use of GNSS for train positioning.

This paper investigates a novel communication system architecture for traffic management and data control in railway scenarios. The proposed solution should be integrated in the existing European Railway Traffic Management System/European Train Control System, the most advanced and successful standard even outside the European countries. Our system integrates public land mobile networks that usually offer best-effort packet services, with a quality-of-service (QoS) guaranteed satellite network. It represents a cost-effective substitution for 4G and 5G networks, aiming to replace current well-known GSM-R standard. The coexistence of heterogeneous networks is guaranteed by the multi-path transmission control protocol (TCP) protocol that addresses specific “add and drop” subflow policies and priority handling logics, in order to realize efficient seamless handovers. Providing priority to TCP subflows corresponds to select QoS-guaranteed, and the best effort networks able to fulfill railway requirements. The logic of adding and dropping subflows exploits both a real-time check of the current status of the serving network and “a priori” network performance information. Experimental results have been carried out in both city and harsh environments, where the main performance metrics ( i.e. , average delay, jitter, and bit rate) have been assessed.

The ERTMS-ETCS train control system relies on the GSM-R dedicated radio network for train to ground communications and on terrestrial dedicated network(s) for communications between the control center and the wayside equipments. However GSM-R technology will become obsolete in the next years, has limited capacity to accommodate growing traffic needs and is suffering from interference caused by the LTE. With the introduction of IP technology in the evolution path of the ERTMS-ETCS a number of possible alternatives are being analyzed and, among them we have studied an hybrid telecom system based on public networks (cellular + satellite). Although public cellular services are provided as best-effort, satellite can act as intelligent backup to complement the cellular networks and, all together, provide QoS in line with the ERTMS-ETCS requirements. This paper outlines the results of a specific test campaign to assess the performance of the cellular networks and satellite communications in a 300 km railways line for a cumulative 18,000 travelled Km in 21 days. These results, have been processed to estimate the achievable performance in the rail environment and to pave the way for realizing the multi-bearer solution. An economical assessment of the multi-bearer solution is presented making reference to the local and regional lines for which the deployment of a dedicated network is difficult to justify.

WCRR 2022, World Congress on Railway Research, Birmingham, ROYAUME-UNI, 06-/06/2022 - 10/06/2022; Novel signalling systems are expected to use Digital Maps to implement Automatic Train Operation (ATO) functions or to augment technologies such as European Global Navigation Satellite Systems (EGNSS), inertial sensors or optical sensors for localization purposes. However, the construction of a Digital Map requires with current technologies expensive railway surveying campaigns. Additionally, the cost for their maintenance and update is a major challenge that prevents its adoption. With regard to the evolution of Control-Command and Signalling (CCS) systems, a new verification infrastructure is also needed to characterize new on-board solutions in terms of train position, speed and acceleration errors, as well as to assess their expected performance. Our research, on one side, aims to develop a methodology and related toolset for executing railway surveying, building and maintaining Digital Maps based on the post-processing of data recorded by trains in commercial service, equipped with Commercial Off The Shelf (COTS) sensors like GNSS receivers, cameras, Inertial Measurement Units (IMUs), and LIDARs. On the other side, a similar approach and development can be used to provide « high precision and high accuracy ground truth reference data » as true values for carrying out error and performance analysis. This Ground Truth methodology does not require installation of trackside equipment or modifications to existing trackside signalling systems and a-priori knowledge of track databases. This paper summarizes the main user needs of (1) the use of Digital Maps for signalling subsystems purposes, (2) the availability of innovative Ground Truth sources for performance assessments. These user needs are essential for the future design of such methodologies and toolsets.