Obstacle detection in rail traffic

Abstract

The invention relates to a method for a rail vehicle (T) for improving the decision-making process in the context of obstacle detection. An object detection process is carried out by a rail vehicle-internal system (SYS TRAIN) using first information relating to the surroundings of the rail vehicle (T), and a first hazard evaluation with respect to the safety relevance of a detected object (K) is carried out on the basis of the object detection process. A request is transmitted to a rail vehicle-external system for a second hazard evaluation using second information relating to the surroundings of the rail vehicle (T), whereupon a decision is made regarding the course of action to be carried out in response to the object (K) while taking into consideration the first and / or the second hazard evaluation. The invention additionally relates to a corresponding device or system for processing data, to a rail vehicle (T), to a computer program, to a computer-readable data carrier, and to a transmission signal.

Description

[0001] Description

[0002] Obstacle detection in rail transport

[0003] The invention relates to a method for obstacle detection for a rail vehicle.

[0004] In rail vehicles, obstacle detection during travel plays a major role in the safe operation of the vehicle. Obstacles can be, for example, fallen trees or living creatures on the tracks. Various technologies are used to detect the presence of obstacles on or near the tracks and, in response to a detected obstacle, to take appropriate action to prevent dangerous situations or collisions. For example, there is track monitoring, for which sensors are installed on the rails to monitor the condition of the track. Trains can also be equipped with signal detection systems that detect and interpret signals on the tracks. By monitoring the signals in this way, a train can determine whether it has a clear path or whether a signal is red, which may indicate an obstacle.

[0005] Due to the high safety relevance of reliable obstacle detection, we are continuing to seek improvements in this regard. In particular, we are attempting to eliminate the possibility of obstacles being overlooked due to human error, particularly due to driver inattention.

[0006] The invention is based on the object of demonstrating an improved method for obstacle detection for a rail vehicle. This object is achieved by a method having the features of claim 1. Furthermore, the invention relates to a corresponding device or a system for data processing, a rail vehicle, a corresponding computer program, a corresponding computer-readable, preferably non-volatile, storage medium, and a corresponding transmission signal. Advantageous embodiments and further developments are the subject of subclaims.

[0007] The method according to the invention serves to improve decision-making within the framework of obstacle detection for a rail vehicle. An internal rail vehicle system first carries out object detection using first information relating to the surroundings of the rail vehicle. Then, based on the object detection, a first risk assessment is carried out with regard to the safety relevance of a detected object. Subsequently, the internal rail vehicle system sends a request to a system external to the rail vehicle for a second risk assessment using second information relating to the surroundings of the rail vehicle. Finally, the internal rail vehicle system makes a decision on a course of action to be carried out in response to the object, taking into account the first and / or the second risk assessment.

[0008] The first hazard assessment is performed within the rail vehicle based on initial information about the rail vehicle's surroundings. This hazard assessment relates to a detected object located in the rail vehicle's surroundings; this object can be located on or near the tracks. The hazard assessment indicates whether and, if so, to what extent the object poses a hazard, so that an appropriate response to the hazard can be decided upon.

[0009] The significance and usability of the first risk assessment depends in particular on how good the initial information is. If this information describes the rail vehicle’s surroundings well, it may be sufficient to base a decision on how to react to a detected object on the first risk assessment alone. However, to obtain a better risk assessment, it is advisable to generate this using further information about the rail vehicle’s surroundings. For this purpose, the system on the rail vehicle sends a request to a system external to the rail vehicle. The external system therefore represents an escalation level and can provide additions and / or corrections to the results of the system on the rail vehicle. The external system provides a second risk assessment in accordance with the request.The on-board system can then base its decision regarding the response to the object on the first hazard assessment, the second hazard assessment, or both hazard assessments. Both the question of whether to involve the off-board system and the question of which hazard assessment to base the decision regarding the response to the object on are decisions made by the on-board system.

[0010] Preferably, the first include the environment of the

[0011] Information concerning the rail vehicle includes measured values ​​recorded by sensors on the rail vehicle. Cameras, lidar, and radar sensors are particularly suitable for this purpose. These can be specifically intended for use in the invention or alternatively used for other purposes.

[0012] Object detection can be performed using an AI system. Such a system is trained with training data corresponding to the initial information to detect objects and, if necessary, classify them.

[0013] The result of object recognition can be: a classification of the object, and / or a size of the object, and / or a position of the object, and / or an indication of the reliability of the object recognition, ie the confidence.

[0014] Preferably, all of this information is used as the basis for the initial risk assessment. Depending on the object detection algorithm used, additional information about a detected object may be output.

[0015] The risk assessments - both the first and the second risk assessment - indicate the extent of the risk to the rail vehicle and / or to people inside the rail vehicle and / or to the object and / or to another object, preferably one located in the immediate vicinity of the rail vehicle. This can be given as a binary indication, i.e. is a hazard present or not. Alternatively, a scale for indicating the level of hazard is possible, e.g. from 1 to 10. It is advantageous if, before the request is sent to the system external to the rail vehicle, a decision is made as to whether to send the request based on the first risk assessment and current information concerning the rail vehicle, in particular the position and / or route of the rail vehicle.Once the first risk assessment is available, a decision-making process is carried out within the rail vehicle. The result of this process is whether the external system should be included. Taking current information concerning the rail vehicle into account makes it possible, for example, to identify a particular urgency due to a particular position of the vehicle, which argues against including the external system. Furthermore, the current information concerning the rail vehicle can also be used to estimate the likelihood of success of a risk assessment by the external system, for example if it is known that the external system can use certain sensors whose coverage area includes the position of the detected object.

[0016] The second risk assessment by the system external to the rail vehicle can take into account the object detection of the system internal to the rail vehicle. In this way, the object detection already carried out by the system internal to the rail vehicle can be combined with the second information in order to be able to carry out improved object detection in the system external to the rail vehicle. This then results in a correspondingly improved risk assessment. In addition to the object detection of the system internal to the rail vehicle, the second risk assessment can also take into account further information from the system internal to the rail vehicle. The decision on the course of action to be carried out can be made based on only the second risk assessment, provided that this is made available within a specified time. For this purpose, the system internal to the rail vehicle can, for example,Use a timer, after which the first risk assessment is used after the request has been sent to the external system, if the second risk assessment was not provided by the external system. Conversely, if the second risk assessment is received before the timer expires, this second risk assessment can be used for the decision.

[0017] The procedure to be implemented in response to the object preferably includes braking the rail vehicle. This can avoid a collision with the object. Other measures, such as darkening the windows or activating a microphone, can be used alternatively or additionally.

[0018] The method according to the invention and / or one or more functions, features and / or steps of the method according to the invention and / or one of its embodiments can be computer-aided. It can be carried out or implemented, for example, by means of one or more computers, processors, application-specific integrated circuits (AS TG), digital signal processors (DSP) and / or so-called “field programmable gate arrays” (FPGA). It can also be carried out at least partially in a cloud and / or in an edge computing environment. One or more interacting computer programs are used for the computer-aided process. If multiple programs are used, they can be stored together on and executed by one computer, or on different computers at different locations.Since this is functionally equivalent, the terms "the computer program" and "the computer" are used in the singular.

[0019] The invention is explained in more detail below using an exemplary embodiment. In the following:

[0020] Figure 1 : a rail vehicle with an obstacle detection system,

[0021] Figure 2 : Processes and components of the obstacle detection system, as well as processes and components of an external system,

[0022] Figure 3 : a flow chart,

[0023] Figure 4 : an obstacle detection system for a rail vehicle.

[0024] As the level of automation in rail transport increases, solutions are being sought to automate some of the train driver's tasks, or even make them unnecessary. The focus here is particularly on the detection of obstacles on the track. The size and type of obstacle, as well as its position in relation to the track on which it is traveling, are crucial for the risk assessment. In particular, living beings are endangered by the train on the one hand, and they can also pose a danger to the train. In response to the detection of a dangerous situation, braking is usually initiated and / or a warning signal is issued via a loudspeaker.

[0025] Figure 1 shows a rail vehicle T with a SYS TRAIN system for obstacle detection. At present, obstacles are usually detected by the train driver who looks out of the window F of the train. An obstacle is understood to be an object that is on or near the tracks G and represents a danger to the safe operation of the rail vehicle T or that could be endangered by the movement of the rail vehicle T. As an example, Figure 1 shows a child K running near the tracks G, which represents such an obstacle.

[0026] Obstacle detection is carried out automatically by the SYS TRAIN system, as described below. For this purpose, the rail vehicle T is equipped with sensors SENS, which can be cameras, radar sensors or lidar sensors, for example. Unlike in Figure 1, these do not have to be located in the front centre of the locomotive. The processes and components of the SYS TRAIN system for obstacle detection are shown in Figure 2. The SYS TRAIN system is not only responsible for detecting obstacles, but also for classifying and assessing them, for deciding how to deal with a detected hazardous situation and for taking measures to avert damage. The initial input data is the measured values ​​SENS MEAS from the SENS sensors. These are made available to a KI system, which detects and classifies obstacles.Known methods can be used here, which were developed for the automotive sector, for example. Based on the input SENS MEAS from the sensors, the AI-based obstacle detection analyzes the surroundings of the rail vehicle T and creates an object model in which the objects detected in the track area and in the immediate vicinity are listed. This object model contains the position of the objects relative to the train and track area, their size and also the respective classification of the objects by category, e.g. person, animal, object. In addition, information on the confidence or reliability of the respective classification and also regarding the other parameters of the object such as size and position can be provided.

[0027] The ASSESS component performs a risk assessment based on the created object model. This serves to determine whether a safety-relevant situation exists. A situation is particularly safety-relevant if it involves a danger to a person or other living being, both in the track area and in the rail vehicle. Also safety-relevant are situations that could lead to damage and / or derailment of the rail vehicle, whereby the latter can also involve a danger or injury to passengers and personnel on the rail vehicle.

[0028] System context information KON can be included in the risk assessment. This is provided by the train control system ZS. This is the control system of the rail vehicle, which on the one hand serves to provide the system context information KON, but on the other hand also implements actuator-based decisions of the action strategy via an interface to the DECIDE component explained later, such as activating a warning tone and / or initiating braking. The system context information KON includes data such as the date, time of day, route information, as well as rail vehicle-specific parameters such as weight and also the current speed and position of the rail vehicle.From the route information in combination with the current position of the rail vehicle, it is possible to determine whether the rail vehicle is near a tunnel, a level crossing, a station, or similar hazardous locations. From rail vehicle-specific parameters such as the vehicle weight and the current speed, it is possible to determine the braking distance with which the vehicle could be brought to a standstill. Other parameters can be taken into account here, such as the gradient of the route, the time required to build up braking force, and the braking capacity.

[0029] The goal of the risk assessment is therefore to decide whether or not a safety-relevant situation exists. However, this can lead to false-positive assessments (i.e., the assessment of a non-hazardous situation as hazardous), as well as false-negative assessments (i.e., the assessment of a hazardous situation as not hazardous). This is because, on the one hand, the AI-based obstacle detection may have already detected the object only with low confidence. On the other hand, the assessment of the train's surroundings may not be appropriate due to the limited information.Making a decision about the existence or non-existence of a safety-relevant situation based solely on the sensors on the train and the AI-based automatic evaluation system is not sensible if, in a specific situation, no reliable decision is possible based solely on the information available in the rail vehicle. In this case, both false-positive and false-negative decisions are undesirable. In the former case, the decision that a safety-relevant situation exists even though this is not actually the case, and in the latter case, the decision that no safety-relevant situation exists even though this is the case in reality.

[0030] To ensure adequate safety, it would be possible to detect obstacles, for example, using multiple artificial intelligence systems, and to assume that a hazardous situation exists if there is a discrepancy. While this leads to a high level of safety, it can severely limit the availability of the rail vehicle due to insufficient precision or an excessively high fault-positive rate, for example, by initiating braking operations too frequently.

[0031] The aim is therefore to include information from other sensors not located on the rail vehicle in the decision-making process, e.g. from cameras on tracks or stations, or from sensors on other rail vehicles. The goal is to use this additional external information to increase the reliability of decision-making regarding the existence of a hazardous situation. The STRATEGY component is used to decide on an escalation strategy. This is intended to take into account the above-mentioned options for incorporating external information in order to improve decision-making quality and thus operational availability. The escalation strategy specifies whether and how external information should be used.The decision regarding the escalation strategy to be pursued is made based on the risk assessment performed in the ASSESS component, which also includes the existing estimate of the confidence of the object classification results. Furthermore, the system context information (KON) can also be included.

[0032] Escalation strategies include, for example:

[0033] • Delay in the decision on the risk assessment while external information is being requested .

[0034] • Immediate decision on the risk assessment, but still request external information to support the decision, and after receiving the external information, re-examine and, if necessary, revise the decision. In this regard, this escalation strategy should specifically specify the weight to be given to the two risk assessments, particularly when a decision from a land-based system contradicts local information from the rolling stock.

[0035] • Setting a timer within which external information must be available, otherwise the risk assessment is decided solely on the basis of the local information from the rail vehicle.

[0036] • Involvement of train crew to obtain specific information about the situation or instructions. • No request for external information, but decision on the risk assessment based solely on the local information from the rail vehicle.

[0037] The main decision regarding the escalation strategy is whether or not to involve an external system. If involved, questions regarding timing and prioritization follow.

[0038] Figure 2 shows the internal processes and components of the SYS TRAIN system as well as the processes and components of an external SYS REMOTE system. The external SYS REMOTE system can be located, for example, in a signal box, a control center, or an operations center. A decentralized location of the external SYS REMOTE system is also possible, for example, in a cloud-based environment.

[0039] The HANDLING component receives requests from the STRATEGY component of the rail vehicle and orchestrates the further processing sequence in the external system. Communication between the rail vehicle's internal system SYS TRAIN and the external system SYS REMOTE takes place wirelessly. The request from the STRATEGY component forwards the risk assessment made in the ASSESS component and requests an external risk assessment. The HANDLING component analyses this request and checks which external information could support the risk assessment. A corresponding query for external information is forwarded to the information supplementation module INFO MODULE. The information supplementation module INFO MODULE determines whether the corresponding information relevant for the risk assessment is available. This is obtained from external sensors EXT SENS 1, EXT SENS 2, ..., EXT SENS n, e.g.Cameras on platforms, tunnels and bridges, or sensors on the tracks, e.g. for wayside train monitoring, are used to extract the information. In addition to or instead of measurements, information about known obstacles on the track, such as fallen trees, or weather data can be used as external information. The latter can indicate that obstacles on the tracks are to be expected, for example due to severe weather. Finally, information from other rail vehicles can also be used, e.g. if they have detected and reported obstacles or damage to the vehicle or tracks. The external information is made available to the EXT ASSESS component for external evaluation of the risk assessment.

[0040] For the external risk assessment, the risk assessment carried out internally in the ASSESS component is merged with the external information. In the EXT ASSESS component, a comprehensive risk assessment can thus be carried out based on external and internal information, which is then made available to the requesting system SYS TRAIN. In the requesting system SYS TRAIN, this external risk assessment is received by the DECIDE component. This is a decision maker which decides on an action strategy and implements it. Implementation takes place via an instruction to the train control system ZS, which then controls the corresponding actuators or triggers processes.

[0041] Fundamental to the decision on the

[0042] Actions is the escalation strategy issued by the STRATEGY component, which is binding for the DECIDE component. If, according to this escalation strategy, for example, no further waiting for input from the external system is necessary after a timer has expired, then an action strategy based on the internal risk assessment of the ASSESS component must be developed. If, on the other hand, for example, the external risk assessment is fundamentally decisive according to the escalation strategy, then an action strategy based on the external risk assessment of the EXT ASSESS component must be developed. If, for example, according to the escalation strategy, a query to the external system is not advisable due to time constraints because the obstacle identified on the basis of the internal information is located a short distance in front of the rail vehicle, then an action strategy based on the internal risk assessment of the ASSESS component must be developed.It is also possible that, together with the external risk assessment, the external system SYS REMOTE issues an instruction that this assessment must be adopted; in this case, the escalation strategy would be corrected as a result of this instruction.

[0043] The decision-maker DECIDE thus decides on the course of action based on the selected escalation strategy, based on the information received from the external system and / or the internal risk assessment, whereby the system context information GON can also be taken into account. The latter could, for example, indicate that the rail vehicle is in a tunnel, so that braking to a standstill would currently be unfavorable.

[0044] A two-level risk assessment is therefore introduced: this is divided into the level of the internal system of the rail vehicle and the land-based escalation level, which represents the external system. The escalation strategy determines the roles of the two levels. The decision-making authority as to when and to what extent the land-based system should be involved lies with the internal system of the rail vehicle. With a single-level approach, however, the information available at the other level could not be used effectively, which is disadvantageous. Using both levels, however, offers several advantages:

[0045] • Greater availability of the rail vehicle in unclear hazard situations through escalation to the external system due to an improved hazard assessment of the situation by the external system.

[0046] • By selecting one of the available escalation strategies it is ensured that the most suitable approach is selected and pursued under various relevant aspects such as the expected response time of the external system or the prospects of success of the query of the external system in the current context.

[0047] • The option of escalation to the external system allows an internal automated function for object detection and risk assessment to be parameterized to a sufficiently high security level, consciously accepting an increased proportion of false-positive alarms.

[0048] These false-positive cases can be corrected by the external system.

[0049] • Time monitoring using a timer ensures that a timely, safe response can be made even if the external system is unavailable. Figure 3 summarizes the process described, with only the most important steps being shown. Firstly, an internal risk assessment GFB INT is drawn up in the internal system SYS TRAIN based on the local information from the rail vehicle. Based on this and on system context information that describes the current status of the rail vehicle, particularly with regard to its position and braking capability, a decision is made as to the escalation strategy ESK to be used. If this requires the external system SYS REMOTE to be included, the internal system SYS TRAIN queries the external system SYS REMOTE to draw up a risk assessment GFB EXT.Taking this external risk assessment (GFB EXT) into account, the internal system (SYS TRAIN) can then decide on the ACTION action to be taken and initiate it. If the escalation strategy (ESK) does not include the external system (SYS REMOTE), the decision on the ACTION action to be taken is based solely on the internal risk assessment (GFB INT).

[0050] Figure 4 shows how the internal system SYS TRAIN can be structured. While the components explained in more detail below are shown simply in the figure, it is also possible for them to be present in multiple versions, e.g. as a distributed system. In this way, the functionality of the system SYS TRAIN can be divided between several, possibly hierarchically linked, systems. This or these systems can be located in the rail vehicle. The system SYS TRAIN comprises a computing unit or a processor PRO. This is connected to a memory MEM in which a computer program PROGRAM is stored. The memory MEM is preferably a non-volatile computer-readable data storage medium. The storage can be carried out in any way that is suitable for ensuring readability by a computing unit, such as magnetic storage, e.g. using a floppy disk, optical storage, e.g.B . mittels CD, magneto-optische Speicherung, ROM (Read Only Memory) Speicherung, RAM (Random Access Memory) Speicherung, EPROM (Erasable Programmable Read-Only Memory) , EEPROM (Electrically Erasable Programmable Read-Only Memory) , Flash-Memory .

[0051] By executing the instructions of the PROGRAM program in the PRO processor, the steps of the procedure explained above are carried out. In particular, objects are detected and classified, a risk assessment is carried out, a decision is made about the escalation strategy, and a decision is made about the action strategy based on a risk assessment. For this purpose, the PRO processor is connected to an IN / OUT input and output unit, via which information can be exchanged between the SYS TRAIN system and other components and / or a user. This interface can be designed in a suitable manner, preferably via radio, and communication can take place using suitable standards. A request for an external risk assessment can be sent and a requested external risk assessment can be received via the IN / OUT input and output unit.

[0052] The invention has been described above using an exemplary embodiment. It is understood that numerous changes and modifications are possible without departing from the scope of the invention.

Claims

Patent claims 1. Method for a rail vehicle (T) for improving decision-making within the framework of obstacle detection, in which an object detection is carried out by a rail vehicle internal system (SYS TRAIN) using first information (SENS MEAS) relating to the surroundings of the rail vehicle (T), a first risk assessment with regard to a safety relevance of a detected object (K) is carried out on the basis of the object detection, a request is sent to a rail vehicle external system (SYS REMOTE) after a second risk assessment using second information relating to the surroundings of the rail vehicle (T), a decision is made about a course of action to be carried out in response to the object (K) taking into account the first and / or the second risk assessment.

2. Method according to claim 1, wherein the first information (SENS MEAS) relating to the surroundings of the rail vehicle (T) comprises measured values ​​acquired by sensors (SENS) of the rail vehicle (T).

3. Method according to claim 1 or 2, wherein the object recognition is carried out using a Kl system.

4. Method according to one of claims 1 to 3, in which the result of the object recognition is: a classification of the object (K), and / or a size of the object (K), and / or a position of the object (K), and / or an indication of the reliability of the object recognition.

5. Method according to one of claims 1 to 4, wherein the risk assessments indicate a level of risk for the rail vehicle (T) and / or for persons within the rail vehicle (T) and / or for the object (K) and / or for another object.

6. Method according to one of claims 1 to 5, in which, before the request to the system external to the rail vehicle (SYS REMOTE), a decision is made on sending the request based on the first risk assessment and current information concerning the rail vehicle (T), in particular the position and / or the route of the rail vehicle (T).

7. Method according to one of claims 1 to 6, in which the second risk assessment is carried out by the rail vehicle external system (SYS REMOTE) taking into account the object detection of the rail vehicle internal system (SYS TRAIN).

8. A method according to any one of claims 1 to 7, wherein the decision on the course of action to be taken is made based on only the second risk assessment, provided that this is made available within a predetermined time.

9. Method according to one of claims 1 to 8, wherein the procedure to be carried out in response to the object (K) comprises braking the rail vehicle (T), and / or darkening windows and / or operating a microphone.

10. Device or system for data processing (SYS TRAIN) comprising means for carrying out the method according to one of claims 1 to 9.

11. Rail vehicle (T) with a device according to claim 10, with Sensors (SENS) for detecting the first information (SENS MEAS) concerning the surroundings of the rail vehicle (T), and Actuators for implementing the action to be taken in response to the object (K) according to the decision.

12. Computer program (PROGRAM) comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of the method according to one of claims 1 to 9.

13. Computer-readable storage medium (MEM) with a computer program (PROGRAM) according to claim 12.

14. Transmission signal transmitting the computer program (PROGRAM) according to claim 12.

Images