Get best of the week

The development of unmanned technology in railway transport

The development of unmanned technologies on the railway began a long time ago, already in 1957, when the first experimental set of auto-driving for suburban trains was created. To understand the difference between the levels of automation for railway transport, the gradation defined in the IEC-62290-1 standard is introduced. In contrast to road transport, the railway has 4 degrees of automation, shown in Figure 1.

image
Figure 1. Degrees of automation in accordance with IEC-62290

Almost all trains operating on the Russian Railways network are equipped with a safety device corresponding to automation level 1. Trains with an automation level of 2 have been successfully operated on the Russian railway network for more than 20 years, several thousand locomotives. This level is implemented due to the traction control and braking algorithms of energy-optimal train guidance along a given route, taking into account the schedule and indications of automatic locomotive signaling systems received via an inductive channel from rail circuits. The use of level 2 reduces the fatigue of the driver and gives a gain in energy consumption and accuracy of execution of the movement schedule.

Level 3 implies the possible absence of a driver in the cab, which requires the introduction of a vision system.

Level 4 implies the complete absence of the driver on board, which requires a significant change in the design of the locomotive (electric train). For example, on-board circuit breakers are installed, which will be impossible to charge again when they operate without the presence of a person on board.

Currently, projects to achieve levels 3 and 4 are implemented by leading companies in the world, such as Siemens, Alstom, Thales, SNCF, SBB and others.

Siemens presented its project in the field of unmanned trams in September 2018 at the Innotrans exhibition. This tram has been operating in Potsdam with a GoA3 automation level since 2018.

Figure 2 Siemens Tram
In 2019, Siemens increased the length of the unmanned route by more than 2 times.
Russian Railways was one of the first companies in the world to develop unmanned railway vehicles. So, in 2015, a project to automate the movement of 3 shunting locomotives was launched at Lugskaya station, where NIIAS JSC acted as an integrator of the project and a developer of basic technologies.

The creation of an unmanned locomotive is a complex complex process, impossible without cooperation with other companies. Therefore, at the Luga station, together with JSC NIIAS, such companies as participate:

  • VNIKTI JSC regarding the development of an onboard control system;
  • Siemens - in terms of automation of the sorting slide (MSR-32 system) and automation of the carriage thrust operation;
  • Radioavionika JSC in terms of microprocessor centralization systems controlling arrows, traffic lights;
  • PKB CT - creation of a simulator;
  • Russian Railways as a project coordinator.

At the first stage, the task was to achieve level 2 of traffic automation, when the driver, under standard conditions for organizing shunting operations, does not use locomotive controls.

In the operation of conventional shunting locomotives, traffic control is carried out by transmitting voice commands from the dispatcher to the driver with setting the appropriate routes (by switching arrows, turning on traffic signals).

When moving to automation level 2, all voice communication was replaced by a system of commands transmitted over a digitally protected radio channel. Technically, the management of shunting locomotives at the Luga station was built on the basis of:

  • unified digital station model;
  • protocol for controlling the movement of shunting locomotives (for sending commands and monitoring execution);
  • interacting with the electrical centralization system to obtain information about the given routes, the position of the arrows and signals;
  • positioning systems for shunting locomotives;
  • reliable digital radio communications.

By 2017, 3 TEM-7A shunting locomotives 95% of the time worked at the Luzhskaya station in fully automatic mode, performing the following operations:

  • Automatic movement on a given route;
  • Automatic access to cars;
  • Automatic coupling with wagons;
  • Thrust of cars on a sorting slide.

In 2017, a project was launched to create a vision system for shunting locomotives and to introduce remote control in case of emergency.

In November 2017, the specialists of NIIAS JSC installed the first prototype of the technical vision system for shunting locomotives, consisting of radars, lidar and cameras (Figure 3).

Figure 3 The first versions of vision systems

During tests at the station of the Luga vision system in 2017 - 2018, the following conclusions were made:

  • , . 60-70 , , 1°. SNCF ( ).
  • . , , . , 2017 , .
  • Cameras are an indispensable element of the system of technical vision and are necessary for the tasks of detection, classification of objects, as well as remote control. To work at night and in difficult weather conditions, it is necessary to have infrared cameras or cameras with an extended wavelength range that can work in the near infrared range.

The main task of technical vision is to detect obstacles and other objects in the direction of travel, and since the movement is carried out along a rut, it is necessary to detect it.

Figure 4. Example of multiclass segmentation (track, wagons) and determination of the path axis using a binary mask

Figure 4 shows an example of track detection. In order to unambiguously determine the route of movement along the arrows, a priori information is used on the position of the arrow, the indications of traffic lights, transmitted via a digital radio channel from the electrical centralization system. Currently, there is a tendency on the world's railways to abandon traffic lights and switch to digital radio control systems. This is especially true for high-speed traffic, since at speeds of more than 200 km / h it becomes difficult to notice and recognize the indication of traffic lights. In Russia there are two sections operated without the use of traffic lights - this is the Moscow Central Ring and the Alpika-Service - Adler line.

In winter, situations may arise when the track is completely under the snow cover and recognition of the track becomes almost impossible, as shown in Figure 5.

Figure 5 Example of a track covered with snow.

In this case, it becomes unclear whether the detected objects interfere with the locomotive's movement, that is, they are on the way or not. In this case, at the Luzhskaya station, a high-precision digital model of the station and a high-precision on-board navigation system are used.

Moreover, the digital model of the station was created on the basis of geodetic measurements of base points. Then, based on the processing of many driveways of locomotives with a high-precision positioning system, a map was built along all the routes.

Figure 6 Digital model of the track development of the Luga station

One of the most important parameters for the on-board positioning system is the error in calculating the orientation (azimuth) of the locomotive. The orientation of the locomotive is necessary for the correct orientation of the sensors and objects they detected. With an orientation angle error of 1 °, the coordinate error of the object relative to the axis of the path at a distance of 100 meters will be 1.7 meters.

Figure 7 The effect of orientation error on the transverse coordinate error

Therefore, the maximum permissible error in measuring the orientation of the locomotive in the angle should not exceed 0.1 °. The on-board positioning system itself consists of two dual-frequency navigation receivers in RTK mode, the antennas of which are spaced the entire length of the locomotive to create a long base, strapdown inertial navigation system and connect to wheel sensors (odometers). The standard deviation of the determination of the coordinates of the shunting locomotive is not more than 5 cm.

Additionally, studies were conducted at the Luzhskaya station on the use of SLAM technologies (lidar and visual) to obtain additional location data.
As a result, the determination of the railway track for shunting locomotives at the Luzhskaya station is carried out by combining the results of track recognition and digital track model data based on positioning.

Obstacle detection is also carried out in several ways based on:

  • lidar data;
  • stereo vision data;
  • the work of neural networks.

One of the main data sources is lidars that provide a cloud of points from laser scanning. Algorithms in use primarily use classic data clustering algorithms. As part of the research, the effectiveness of the use of neural networks for the task of clustering lidar points, as well as for the joint processing of lidar data and data from cameras, is checked. Figure 8 shows an example of lidar data (a point cloud with different reflexivity) with the display of a man dummy against the background of a car at the Luga station.

Figure 8. Example of data from the lidar at the Luzhskaya station

. Figure 9 shows an example of the separation of a cluster from a wagon of complex shape according to two different lidars.

Figure 9. An example of interpretation of lidar data in the form of a cluster from a hopper car

It is worth noting separately that recently the cost of lidars has fallen by almost an order of magnitude, and their technical characteristics have grown. There is no doubt that this trend will continue. The detection range of objects by lidars used at the Luzhskaya station is about 150 meters.

A stereo camera using a different physical principle is also used to detect obstacles.

Figure 10. Disparity map from a stereo pair and detected clusters

Figure 10 shows an example of a stereo camera data with the detection of poles, trip boxes and a wagon.

In order to obtain sufficient accuracy of the point cloud at a sufficient distance for braking, it is necessary to use high-resolution cameras. An increase in image size increases the computational cost of obtaining a disparity card. Due to the necessary conditions for the resources used and the reaction time of the system, it is necessary to constantly develop and test algorithms and approaches for extracting useful data from video cameras.

Part of the tests and verification of algorithms is carried out using a railway simulator, which is developed by PKB CT jointly with NIIAS JSC. For example, Figure 11 shows the use of a simulator to test the operation of stereo camera algorithms.

Figure 11. A, B - left and right frames from the simulator; B is a top view of the reconstruction of data from a stereo camera; G - reconstruction of stereo camera images from a simulator.

The main task of neural networks is the detection of people, cars and their classification.
To work in severe weather conditions, the specialists of NIIAS JSC also tested using infrared cameras.

Figure 12. Data from an IR camera

Data from all sensors are compiled on the basis of association algorithms, where the probability of the existence of obstacles (objects) is estimated.

Moreover, not all objects on the way are obstacles; when performing shunting operations, the locomotive must automatically couple with the cars.

Figure 13. Example of visualization of the approach to the car with the detection of obstacles by different sensors.

When operating unmanned shunting locomotives, it is extremely important to quickly understand what is happening with the equipment in which it is in state. Situations are also possible when an animal, such as a dog, appears in front of the locomotive. On-board algorithms will automatically stop the locomotive, but what to do next if the dog does not go astray?

To monitor the situation on board and make decisions in case of emergency, a stationary remote control and control unit is designed to work with all unmanned locomotives at the station. At the Luzhskaya station, he was posted at the EC post.

Figure 14 Remote control and control

At the Luga station, the remote control, shown in Figure 14, controls the operation of three shunting locomotives. If necessary, using this remote control, you can control one of the connected locomotives by transmitting information in real time (delay not more than 300 ms, taking into account the transmission of data over the air).

Functional Security Issues


The most important issue in the implementation of unmanned locomotives is the issue of functional safety, defined by the IEC 61508 standards “Functional safety of electrical, electronic, programmable electronic safety-related systems” (EN50126, EN50128, EN50129), GOST 33435-2015 “Control, monitoring and safety devices for railway rolling stock ".

In accordance with the requirements for on-board safety devices, a safety integrity level of 4 (SIL4) must be ensured.

To comply with the SIL-4 level, all existing locomotive safety devices are built according to majority logic, where calculations are performed in parallel in two channels (or more) with a comparison of the results for a decision.

The computing unit for processing data from sensors on unmanned shunting locomotives is also built on a two-channel scheme with a comparison of the final result.

The use of vision sensors, work in various weather conditions and in different environments requires a new approach to the issue of proving the safety of unmanned vehicles.

In 2019, ISO / PAS 21448, Road Vehicles. Security of preset functions ”(SOTIF). One of the main principles of this standard is the scenario approach, which considers the behavior of the system in various circumstances. The total number of scenarios is infinity. The main objective of the development is to minimize areas 2 and 3, representing known unsafe scenarios and unknown unsafe scenarios.

Figure 15 Transformation of scenarios as a result of development

As part of the application of this approach, the specialists of NIIAS JSC analyzed all the situations (scenarios) that have arisen since the start of operation in 2017. Some situations that are difficult to encounter during actual operation are worked out using the PCB CT simulator.

Regulatory issues


In order to really completely switch to fully automatic control without the presence of a driver in the cab of a locomotive, it is also necessary to solve regulatory issues.

At present, Russian Railways has approved a schedule for the regulatory support of the implementation of measures for the introduction of railway rolling stock control systems in automatic mode. One of the most important issues is updating the Regulation on the procedure for official investigation and recording of accidents that have caused harm to the life or health of citizens who are not related to production in railway transport. In accordance with this plan in 2021 a package of documents regulating the operation of unmanned railway vehicles should be developed and approved.

Afterword


Currently, there are no analogues in the world of unmanned shunting locomotives that are operated at the Luzhskaya station. In 2018-2019, specialists from France (SNCF company), Germany, Holland (Prorail company), Belgium (Lineas company) got acquainted with the developed control system and are interested in implementing such systems. One of the main tasks of NIIAS JSC is to expand the functionality and replicate the created management system both on Russian railways and for foreign companies.

At the moment, Russian Railways is also conducting a project to develop unmanned electric trains Lastochka. Figure 16 shows a demonstration of the prototype of the automatic control system for the ES2G Lastochka electric train in August 2019 as part of. International Railway Salon of Space 1520 "PRO // Dvizhenie.Expo".

Figure 16. Demonstration of the operation of an unmanned electric train at the MCC

Creating an unmanned electric train is a much more difficult task due to the high speeds, significant braking distance, and ensuring safe boarding / disembarking of passengers at stopping points. At the moment, tests are actively being conducted at the MCC. The story about this project is planned to be published in the near future.

More articles:


All Articles