EP3625519A1

EP3625519A1 - The monitoring of sensor data and odometry data for a rail vehicle on the basis of map data

Info

Publication number: EP3625519A1
Application number: EP18746591.9A
Authority: EP
Inventors: Steven Alexander Calder; Hamed Ketabdar; Navid Nourani-Vatani; Andrew Palmer
Original assignee: Siemens Mobility GmbH
Current assignee: Siemens Mobility GmbH
Priority date: 2017-07-27
Filing date: 2018-07-09
Publication date: 2020-03-25
Also published as: WO2019020349A1

Abstract

A method for monitoring sensor data (SD) and/or odometry data for a rail vehicle (30) is described. In the method, sensor data (SD) and/or odometry data are detected. In addition, map data (KD) regarding a current driving route are determined. The map data (KD) are used as a limiting secondary condition in the monitoring and/or evaluation of the sensor data (SD) and/or odometry data. A monitoring device (20) is also described. In addition, a rail vehicle (30) is described.

Description

description

Monitoring sensor data and odometry data of a rail vehicle based on map data

The invention relates to a method for monitoring sensor data and / or odometry data of a rail vehicle. Moreover, the invention relates to a monitoring device. Furthermore, the invention relates to a rail vehicle.

Rail vehicles need exact sensor data and

Odometric data in order to operate safely. Rail vehicles rely on a variety of on-board sensors, such as encoders, dual radar, GPS and balise detectors, to determine their position and speed. Cameras, lidar and radar are used to detect signals, signs, barriers or walls ^¬ re relevant elements of the environment. However, these sensors can produce unreliable or anomalous information, and the common object detection methods can often produce false-positive messages.

In conventional Odometrieeinrichtungen are filter, play as examples Kalman filter, used to merge readings of less than ^¬ retired union sensors. To prevent abnormal sensor values, methods are used that perform statistical tests. However, not all the information about the environment and the system verwen- det, but only the determined position and speed values VELOCITY ^¬.

In methods for detecting signals and obstacles, false-positive results are often generated. To suppress such errors, preliminary information about the respective objects or information boards is often used. Example ^¬ as the color of a kind of billboard is known, so that different colored, but similar signs shaped ignore can be rationed. But she may experience errors even with Berücksichti ^¬ account the preliminary information anyway.

DE 10 2006 007 788 A1 describes a method in which object recognition is performed by a track-bound vehicle. Here, based on a system model a sub ^¬ distinction is made between landmarks and obstacles.

In DE 10 2013 219 805 Al a position determination for a rail vehicle with the aid of reflected Radarsigna ^¬ len is described. Positions of reflectors are stored in a digital map. If a reflected radar signal is received, a position of the rail vehicle can be determined on the basis of the digital map.

DE 10 2013 224 672 A1 describes a method for vehicle position detection. In this case, a track-side access point, the position of which is known, sensed detected by means of a transmitting / receiving device.

There is therefore the task of developing improved detection methods and evaluation methods with which the aforementioned problems can at least be alleviated. This object is achieved by a method for monitoring

Sensor data and Odometriedaten a rail vehicle according to claim 1, a monitoring device according to claim 9 and a rail vehicle according to claim 10 solved.

In the method according to the invention for monitoring sensor data and / or odometry data of a rail vehicle, sensor data and / or odometry data are acquired. The sensor data may include, for example, image data acquired by optical sensors. They may also include sensor data collected by other types of electromagnetic waves. For example, odometry data may include information about a distance traveled or a current speed or have an average speed. Wei ^¬ terhin map data are determined to a current route. For example, the map data may be based on general geographic information about a rail line and its surroundings. The map data is used as a limiting secondary condition in the monitoring and / or evaluation of the sensor data and / or odometry data. A restrictive secondary condition is to be understood as an information which restricts the range of values of the sensor data and / or odometry data to a subarea of this value range. The combination of the map information with the sensor data or odometry data advantageously improves the accuracy of information determined on the basis of this data, such as position data, speed data or data about a traveled trajectory. In general, the reliability and robustness of sensor systems and odometric systems can be improved with the method according to the invention, since extreme deviations from measured values to the correct values, which are also referred to as "outliers", can be determined and discarded.

In this way, false-positive measured values can also be detected and associated false alarms are usually avoided. Moreover, a disassembly can be limited, thus increasing the speed of a detection method for Whether ^¬ jekterkennung the detection range or search area by the based on the limiting constraint restricting a range of values.

The monitoring device according to the invention for a rail vehicle comprises a data receiving unit for detecting sensor data and / or odometry data. Part of the monitoring device according to the invention is also a detection unit which is set up to determine map data to a ak ^¬ tual route. The monitoring device according to the invention also comprises an evaluation unit for using the map data as a restrictive secondary condition in the monitoring and / or evaluation of the sensor data and / or odometry data. The monitoring Device shares the advantages of the method according to the invention for monitoring sensor data and / or odometry data of a rail vehicle. The rail vehicle according to the invention has the erfindungsge ^¬ Permitted monitoring device. The time ^¬ estimating device according to the invention shares the advantages of the monitoring device according to the invention. Some components of the monitoring device according to the invention can be designed predominantly in the form of software components. This applies in particular to parts of the determination unit and the evaluation unit. In principle, however, these components can also be partly realized, in particular in the case of particularly fast calculations, in the form of software-supported hardware, for example FPGAs or the like. Similarly, the required interfaces, for example, if it is only about a transfer of data from other software components, be designed as a software interface parts. However, they can also be configured as hardware-based interfaces, which are controlled by suitable software.

A largely software-based implementation has the advantage that already existing in a rail vehicle computer systems can be retrofitted in a simple way by a software update to work on the inventive way. Insofar as the object is also achieved by a corresponding computer program product with a computer program, which is directly in a storage device ei ^¬ nes such a computer system can be loaded, ^¬ lead with Programmabschnit ^¬ th order for For all steps of the inventive method when the computer program in the computer system is performed.

Such a computer program ^product , in addition to the computer ^¬ program optionally additional components, such as a documentation and / or additional components, also Hardware components, such as hardware keys (dongles, etc.) for using the software include.

For transport to the storage device of the computer system and / or for storage on the computer system, a computer-readable medium, for example a memory stick, a hard disk or another portable or permanently installed data carrier can be used, on which the computer program readable and executable by a computer unit are stored. The computer unit may be for example a purpose or more cooperating micropro ^¬ processors or the like.

The dependent claims and the following description each contain particularly advantageous embodiments and further developments of the invention. The claims of claim category may further be formed analogously to the dependent claims ^¬ from a different category of claim and the description parts in particular. In addition, in the context of the invention, the various features of different embodiments and claims can also be combined to form new embodiments.

In one embodiment of the method according to the invention for monitoring sensor data and / or odometry data of a

Rail vehicle, in the event that he odometry ^¬ averages or be detected, the current course of the rails, or the direction of the current rail curve as a ^¬ restrictive constraint for the determination of

Used odometry data. For example, it is thus advantageously possible to determine a permitted value range for an orientation or direction of movement of the rail vehicle. If measured values are outside this range, they can be detected as faulty and discarded.

In a preferred embodiment of the method according to the invention for monitoring sensor data and / or odometry data of a rail vehicle, a Kalman filter is used in the Processing of the sensor data and / or Odometriedaten used so that the sensor data and / or Odometriedaten meet the restrictive constraint. That is, the Kalman filter is set so that detected state data such as the direction of travel or a distance traveled does not violate the determined restrictions.

In one variant of the inventive method for monitoring sensor data and / or odometry a rail nenfahrzeugs be based on the rail curve Sensorda ^¬ th and / or odometry, which indicate incorrect direction of travel discarded. That is, soft data, which relate to the direction of movement or a lateral acceleration, from a specified range of the rail track range, so these data are detected as defective and discarded.

In one embodiment of the inventive method for monitoring sensor data and / or odometry data of a rail vehicle that the current shift ^¬ nenverlauf being determined on the basis of the map data as is the case, an acceleration transverse to the direction of travel is determined to be defective and the corresponding sensor data is discarded , Advantageously, incorrect lateral acceleration values, which would lead, for example, to a faulty reduction of the driving speed, can be detected and thus unnecessary delays in the travel of the rail vehicle can be avoided. In a variant of the method according to the invention for monitoring sensor data and / or odometry data of a rail vehicle, the sensor data for object recognition are evaluated and the detected objects are compared with the map data in such a way that objects drawn in the map at a current position or in a current location area recognized object to be compared. Advantageously, result data of an object recognition with the information about an object that is drawn in a map ^

is to be matched. In this case,, for the case that in the map data at the current position or in the current location area no object is located, the detected Whether ^¬ ject to be discarded.

Furthermore, a position of a drawn object in the map data can be used to restrict an image area or scanning area to be selected for object detection to an area around the position of the marked object. Advantageously, the search time for an object to be detected can be reduced within the scope of object recognition.

The invention will be explained in more detail below with reference to the beige ^¬ added figures using ^exemplary embodiments. Show it:

1 shows a flowchart which illustrates a method for monitoring sensor data and / or odometry data of a rail vehicle according to an embodiment of the invention,

FIG 2 is a block diagram veran ^¬ illustrating a monitoring device according to an embodiment of the invention,

3 shows a block diagram illustrating a rail vehicle with egg ^¬ ner monitoring device according to an embodiment of the invention.

In FIG 1 a flow chart 100 is shown which illustrates veran ^¬ a ^¬ Ver drive for monitoring of sensor data SD of a rail vehicle according to an embodiment of the invention. In step 1.1, sensor data SD is first received by one or more sensor units. In step l.II, position data PD is additionally received via a receiving unit for receiving satellite navigation signals. The position data PD provide information about the current position or a current location area of the rail vehicle. Furthermore, in step l.III, based on the position data PD, map data KD is determined, which Information about the course of the rail as well as possibly existing objects ^¬ present in the area of the determined position data PD. In step 1.IV, the map data KD is then compared with the sensor data SD. If, for example, the sensor data SD provides information about an orientation of the rail vehicle, then this can be compared with the direction of the rail guide in the map data KD. In the event that the two data sets SD, KD match, which is marked "j" in FIG. 1, then the process proceeds to step IV and the sensor data SD is released for further processing was determined in step 1. IV that the two data sets differ, which is marked in Figure 1 with "n", it is moved to the step l.VI, in which a fault avoidance is issued and rejected the sensor data SD become .

In FIG 2, a block diagram is shown, which according to one embodiment of the ER- illustrates a surveil ^¬ monitoring device 20 invention. The monitoring device 20 includes fully, a sensor data receiving interface 21, with the Sen ^¬ sordaten SD of one or more sensor units are received. The sensor data SD are transmitted to an evaluation unit 23. General map data AKD and Positionsinformatio ^¬ NEN PD be a second input interface 24 is received and weiterge to a determination unit 22 derives ^¬ which determines based on this data AKD, PD site-specific map data KD, so the map data associated with a current position. The map data KD are then also transmitted to the evaluation unit 23. The evaluation unit 23 subsequently performs an adjustment between the map data KD and the sensor data SD and outputs result data ED, which provide information about the quality of the sensor data SD. In the event that the sensor data SD are in order, the sensor data SD is output via an output interface 25. If the sensor data SD is classified as faulty, an error message ED is issued. ben, which notifies that the tested sensor data SD are faulty.

In Figure 3, a rail vehicle 30 is schematically illustrated according to an embodiment of the invention. The

Rail vehicle 30 includes a sensor unit 31, for example ^¬ an encoder unit, with the basis of the rotational ^¬ frequency of the wheels of the rail vehicle 30 whose speed and the distance traveled is determined. The sensor data SD are transmitted to a monitoring unit 20. The monitoring unit 20 checks the sensor data SD to in connection with Figures 1 and 2 illustrate ^¬ light manner. For this purpose, the monitoring unit 20 also receives position data PD via an input interface 32. The sensor data SD and possibly also an error message ED are output to a central control device 33, to which, for example, display units for the operating personnel as well as automated control units, such as automated braking units connected are.

It is finally pointed out once again that this han ^¬ punched in the above-described methods and devices by only preferred embodiments of the invention and that the invention can be varied by the skilled person without departing from the scope of the invention in so far as determined by the claims is. It is the Fully ^¬ ness sake also noted that the use of the indefinite article "a" and does not exclude "a" that the features in question can also be present more than once. Similarly, the term "unit" does not exclude that it consists of several components, which may also be spatially distributed.

Claims

claims

A method of monitoring sensor data (SD) and / or odometry data of a rail vehicle (30), comprising the steps of:

Acquisition of sensor data (SD) and / or odometry data,

Determining map data (KD) for a current route,

- Using the map data (KD) as a restrictive constraint in the monitoring and / or evaluation of the sensor data (SD) and / or odometry data, wherein the range of values of the sensor data and / or odometry data is limited to a portion of this range and from the ^¬ sem value range deviating sensor data (SD) and / or

Odometry data are discarded.

2. The method according to claim 1, wherein in the event that

Odometry data is recorded, the current track is used as a limiting constraint for the determination of odometry data.

3. The method of claim 1 or 2, wherein a Kalman filter in the processing of the sensor data (SD) and / or

Odometer data is used so that the sensor data (SD) and / or Odometriedaten meet the restrictive constraint.

4. The method of claim 2 or 3, wherein on the basis of the rail track sensor data (SD) and / or odometry data indicating a wrong direction, are discarded.

5. The method according to any one of claims 2 to 4, wherein in the event that the current rail track based on the map ^¬ data (KD) is determined to be straight, an acceleration across the direction of travel is determined to be faulty and the corresponding sensor data (SD) be discarded.

6. The method according to any one of the preceding claims, wherein

- The sensor data (SD) are evaluated for object recognition and

- The detected objects with the map data (KD) are compared to the effect that in the map at a current position or in a current location area drawn objects are compared with the detected object.

7. The method of claim 6, wherein for the case that in the map data (KD) at the current position or in the current location area no object is drawn, the detected object is discarded.

8. The method of claim 6 or 7, wherein a position of a drawn object in the map data (KD) is used to restrict to be selected for Obj ektdetektion image area or scanning area to an area around the position of the drawn object.

9. Monitoring device (20) for a rail vehicle, comprising:

a data reception unit (21) for acquiring sensor data (SD) and / or odometry data,

a determination unit (22) for determining map data (KD) for a current route,

- An evaluation unit (23) for using the map data (KD) as a limiting constraint in the monitoring and / or evaluation of the sensor data (SD) and / or

Odometry data, the range of sensor data and / or odometry data is limited to a portion of this range of values and from this value range from ^¬ softening sensor data (SD) and / or odometry data are discarded.

10. Rail vehicle (30), comprising a Überwachungssein ^¬ direction (20) according to claim 9.

11. A computer program product with a computer program, wel ^¬ ches directly in a storage unit of a rail vehicle (30) is loadable, is with program sections to perform all the steps of a method according to one of claims 1 to 8 auszufüh ^¬ reindeer, when the computer program being in the rail vehicle ,

12. A computer-readable medium on which are stored by a computer unit executable program sections to perform all the steps of the method according to any one of claims 1 to when the program sections are executed by the computer unit.