US20200172135A1

US20200172135A1 - Sensor-controlled adjustment of odometric measurement parameters to weather conditions

Info

Publication number: US20200172135A1
Application number: US16/637,835
Authority: US
Inventors: Steven Alexander Calder; Hamed KETABDAR; Navid Nourani-Vatani; Andrew Palmer
Original assignee: Siemens Mobility GmbH
Current assignee: Siemens Mobility GmbH
Priority date: 2017-08-10
Filing date: 2018-07-19
Publication date: 2020-06-04
Also published as: WO2019029969A1; EP3625106A1; CN111032476A; CN111032476B; ES2946763T3; EP3625106B1

Abstract

A method for adjusting measurement parameters of an odometry unit of a rail vehicle includes acquiring sensor data from the interior and/or the surroundings of the rail vehicle with the aid of at least one sensor unit that includes an internal image-recording unit. Weather data are determined on the basis of the acquired sensor data. Lastly, fusion weightings for the fusion of odometric data that have been determined on the basis of odometric sensor data from different types of odometric sensors are defined depending on the determined weather data. An adjustment device and a rail vehicle are additionally provided.

Description

Sensor-controlled adjustment of odometric measurement parameters to weather conditions
The invention relates to a method for adjusting measurement parameters of an odometry unit of a rail vehicle. In addition, the invention relates to an adjustment facility. Moreover, the invention relates to a rail vehicle.
Speed measurements are indispensable for autonomous driving and vehicle assistance systems. Speed data can be used for many different purposes. Examples of this are the monitoring of adherence to statutory requirements, the planning of journeys, the introduction of braking processes and position determinations. A determination of the speed is typically achieved by the fusion of measurement results of different sensors. Sensors used for the speed determination can produce faulty data. This can be the case for instance on account of poor weather conditions, such as, for instance, rain, snow etc. Snow, fog and rain can negatively impact the performance of Doppler radar sensors. Rain can result in smooth carriageways or rail surfaces, which also contributes to the wheels slipping and overrunning, as a result of which the measuring accuracy of sensors, which measure the number of revolutions of the wheels, is negatively affected. There is therefore the problem of errors occurring when odometric data is measured by means of individual sensors, and the overall result of the odometric measurement is therefore falsified.
DE 10 2006 035 597 A1 describes a method for determining the travel distance and the speed of a vehicle, in particular for safety-critical automatic train protection systems. In this context sensor data from various sensors is fused.
DE 10 2009 006 113 A1 describes a device for depicting the environment of a vehicle, wherein the existence of objects is determined on the basis of fused sensor data.
US 2017/0307247 A1 describes the detection of weather conditions with the aid of on-board sensors of a motor vehicle.
In U.S. Pat. No. 9,676,393 B2 weather conditions are captured, which can negatively impact the function of a warning system of a rail vehicle.
There is therefore the object of adjusting a method for odometric measurement and a corresponding measuring facility so that these provide more precise results than has hitherto been the case, in spite of adverse weather conditions.
This object is achieved by a method for adjusting measurement parameters of an odometry unit of a vehicle as claimed in claim 1, an adjustment facility as claimed in claim 12 and a rail vehicle as claimed in claim 13.
In the method according to the invention for adjusting measurement parameters of an odometry unit of a rail vehicle, sensor data from the interior and/or the surroundings of the rail vehicle is captured with the aid of at least one sensor unit, which comprises an internal image-recording unit. The captured sensor data is used to determine weather data. The weather data is preferably determined in an automated manner, so that no additional personnel are required and the evaluation can take place in real time. Fusion weightings for the fusion of odometric data are defined as a function of the determined weather data. The odometric data itself, for instance speed data or position data, is determined on the basis of odometric sensor data from different types of odometric sensors by weighted combination or fusion, for instance by weighted addition in the odometry unit. Current weather data can advantageously be taken into account with the aid of defining the weights for the fusion of the odometric data to ensure that odometric sensors negatively impacted by the current weather situation or the odometric data thereof is weighted less heavily. This measure improves the accuracy of the odometric data and the robustness of the determination of this data. The definition of the fusion weightings is preferably carried out likewise automatically in order to enable a real time adjustment of the measurement parameters, i.e. of the fusion weightings.
Internal image-recording units may already be present in rail vehicles as monitoring cameras, for instance, in order to improve the personal safety of the passengers. Advantageously no additional cameras have to be installed in order to determine the weather situation, but the monitoring cameras which are already present can additionally take over the task of monitoring the weather situation. For this purpose, the monitoring cameras can occasionally be aligned in the direction of the windows of the rail vehicle, so that the external environment can be captured and weather data can be determined.
The inventive adjustment facility for a rail vehicle has a data input interface for receiving sensor data from a sensor unit, which comprises an internal image-recording unit, from the interior and/or the surroundings of the rail vehicle. Part of the adjustment facility is also a weather determination unit for determining weather data based on the captured sensor data. The inventive adjustment facility also comprises a defining unit for defining fusion weightings for the fusion of odometric data, which was determined on the basis of odometric sensor data from different types of odometric sensors, as a function of the determined weather data.
The inventive rail vehicle comprises at least one sensor unit, which comprises an internal image-recording unit, and the inventive adjustment facility. The inventive rail vehicle shares the advantages of the inventive adjustment facility.
Some components of the inventive adjustment facility can largely be embodied in the form of software components. This relates in particular to parts of the weather determination unit and the defining unit. Essentially these components can however also be realized to some extent, particularly if it involves particularly rapid calculations, in the form of software-assisted hardware, for instance FPGAs or suchlike. Similarly the required interfaces, for instance when it only involves a takeover of data from other software components, can be embodied as software interfaces. They can also be configured as interfaces constructed from hardware, which are controlled by suitable software.
A realization largely through software has the advantage that computer systems already available until now in a rail vehicle can easily be upgraded with a software update after a possible extension by means of additional hardware elements in order to operate in the manner according to the invention. In this respect, the object is also achieved by means of a corresponding computer program product with a computer program which is loadable directly into a storage apparatus of such a computer system, having program portions in order to carry out all the steps of the method according to the invention when the computer program is executed in the computer system.
Such a computer program product can comprise, where relevant, in addition to the computer program, further constituents, such as, for example, documentation and/or additional components including hardware components, for example, hardware keys (dongles, etc.) in order to use the software.
For transport to the storage apparatus of the computer system and/or for storage at the computer system, a computer-readable medium, for example, a memory stick, a hard disk or another transportable or permanently installed data carrier can be used on which the program portions of the computer program which can be read in and executed by a computer unit are stored. For this purpose, the computer unit can have, for example, one or more cooperating microprocessors or the like.
The dependent claims and the description below each contain particularly advantageous embodiments and developments of the invention. In particular the claims of one claim category can also be developed similarly to the dependent claims of another claim category and the description passages belonging thereto. In addition, in the context of the invention, the different features of different exemplary embodiments and claims can also be combined to form new exemplary embodiments.
In one embodiment of the inventive method for adjusting measurement parameters of an odometry unit of a rail vehicle, the at least one sensor unit comprises at least one of the following sensor types:

- an external image-recording unit,
- a temperature sensor,
- a humidity sensor,
- a LIDAR sensor for obstacle detection.

An external image-recording unit as a sensor unit enables weather phenomena to be captured visually and then identified. Conclusions with regard to the reliability of individual odometric sensors can in turn be drawn from the weather situation. Temperature sensors can likewise provide important criteria relating to the reliability of odometric sensors. For instance, frost can indicate the occurrence of snow, which in turn hampers a speed measurement with the aid of a Doppler radar. Humidity sensors may already be present for instance for the automated operation of windscreen wipers in rail vehicles and can now be used in accordance with the invention additionally to obtain weather data in order to assess the reliability of odometric sensors. LIDAR sensors can be used to identify the occurrence of fog, for instance. Fog in turn hampers the use of a speed measurement with the aid of a Doppler radar.
In one variant of the inventive method for adjusting measurement parameters of an odometry unit of a rail vehicle, a monitoring camera is used as an internal image-recording unit. As already mentioned, it is advantageously possible to revert to already existing installations, wherein an automated evaluation of the image data additionally takes place.
In one embodiment of the inventive method for adjusting measurement parameters of an odometry unit of a rail vehicle, the monitoring camera is set up to monitor the weather so that image data can be captured from the external surroundings of the rail vehicle. Advantageously, information relating to the external surroundings of the rail vehicle, which provides information as to the current weather situation, can be captured with the monitoring camera.
In one variant of the inventive method for adjusting measurement parameters of an odometry unit of a rail vehicle, the monitoring camera is set up to monitor the weather so that image data can be captured from an internal area of the rail vehicle. In this variant, the inward alignment of the monitoring cameras can be retained and indirect information about the weather situation are on the basis of the clothing and equipment of the passengers. The monitoring of the interior and the external surroundings can also be combined with one another in order to obtain more reliable weather data.
In one embodiment of the inventive method for adjusting measurement parameters of an odometry unit of a rail vehicle, a current weather situation is determined on the basis of the image data captured by the monitoring camera. Advantageously the image data can additionally be used to monitor and also to determine the weather situation so that no additional hardware is required for capturing weather information.
In a preferred embodiment of the inventive method for adjusting measurement parameters of an odometry unit of a rail vehicle, in order to determine the current weather situation, an image evaluation method is applied to the captured image data which is based on the machine vision.
With the image evaluation method, a comparison of the image data can preferably be carried out with different image patterns which are assigned in each case to a different weather situation.
The different weather situations can comprise the following weather situations, for instance:

- snow fall,
- fog,
- rain.

As already mentioned, the cited weather situations have an influence on the reliability of the odometric sensors. For instance, snow can negatively impact the reliability of a Doppler radar. Rain can result in the wheels of the rail vehicle slipping and thus in reduced reliability of the rotary frequency sensors.
Current operating data of an air-conditioning system of the rail vehicle can be used to determine the weather situation. The operating data can be used to conclude a current temperature, which in turn provides details about the current weather situation.
In one embodiment of the inventive method for adjusting measurement parameters of an odometry unit of a rail vehicle, fusion weightings of sensors, which are classified as fault-prone on account of the weather data, are reduced as a function of the determined weather data. The accuracy of the determined odometric data is advantageously improved in this way.

The invention is explained again in more detail below with reference to the appended drawings on the basis of exemplary embodiments, which show:

FIG. 1 a flow diagram which illustrates a method for adjusting measurement parameters of an odometry unit of a rail vehicle according to a first exemplary embodiment of the invention,

FIG. 2 a block diagram which illustrates an adjustment facility according to an exemplary embodiment of the invention,

FIG. 3 a block diagram which illustrates a rail vehicle according to an exemplary embodiment of the invention.

FIG. 1 illustrates a method for adjusting measurement parameters of an odometry unit of a rail vehicle. In step 1.I, sensor data, in this exemplary embodiment image data BD, is captured from the surroundings of the rail vehicle, which is captured by a monitoring camera, temperature data TD is captured by a temperature sensor, which measures an external temperature, humidity sensor data FSD is captured by a humidity sensor and Lidar sensor data LSD is captured by a Lidar Sensor. In step 1.II, weather data WD is determined on the basis of the captured sensor data BD, TD, FSD, LSD. For instance, it is possible to determine with the aid of the humidity sensor data whether it is currently raining and how heavily it is raining. Finally, in step 1.III, fusion weightings FG for the fusion of odometric data, for instance a measured speed or covered distance, are determined on the basis of the determined weather data WD. The odometric data itself is determined after adjustment with the aid of a rotary frequency sensor and a Doppler radar, for instance, and is then combined weighted, with the aid of the cited fusion weighting FG, in order to determine a vehicle speed or a covered distance.
FIG. 2 describes an adjustment facility 20 for a rail vehicle 40 (see FIG. 3). The adjustment facility 20 comprises a data input interface 21, which is designed to receive sensor data SD from the interior and/or the surroundings of the rail vehicle 40. The sensor data SD is transmitted to a weather determination unit 22, which is used to determine weather data WD on the basis of the captured sensor data SD. Part of the adjustment facility 20 is also a defining unit 23, which is designed to define fusion weightings FG for the fusion of odometric data v, P(t), which was determined on the basis of sensor data FD, DRD of different types of sensors 15, 16 (see FIG. 3), as a function of the determined weather data WD. The determined weightings FG are output by way of an output interface 24 and transmitted to an evaluation unit 30 (see FIG. 3).
FIG. 3 shows a block diagram which illustrates a rail vehicle 40. The rail vehicle 40 comprises a plurality of different sensor units 10, 11, 12, 13, with which sensor data BD, TD, FSD, LSD is captured as the basis of the determination of weather data WD. The sensor units 10, 11, 12, 13 comprise a monitoring camera 10, which receives image data BD from the surroundings of the rail vehicle 40, a temperature sensor 11 for determining external temperature data TD, a humidity sensor unit 12 for determining humidity sensor data FSD, which conveys information about the air humidity, and a Lidar sensor unit 13, which, with the aid of Lidar, can determine information about the occurrence of precipitation, for instance rain or snow, and fog. Furthermore, the rail vehicle 40 has another two odometric sensors 15, 16. A first odometric sensor 15 is embodied as a rotary frequency meter and a second odometric sensor is embodied as a Doppler radar sensor. Frequency data FD or Doppler radar data DRD is transmitted from the two odometric sensors to an evaluation unit 30, also odometry unit, which obtains data relating to fusion weightings FG to be applied in addition to the adjustment facility 20. The evaluation unit 30 determines, on the basis of the odometric frequency data FD, first odometric data records v_F, P_F(t) relating to the speed and the position of the rail vehicle 40 and on the basis of the Doppler radar data DRD second odometric data records V_D, P_D(t), which likewise specify the speed and the position of the rail vehicle 40. The determined odometric data records v_F, P_F(t), v_D, P_D(t) are combined weighted with the aid of the determined weightings FG to form fused odometric data v, P(t). The fused odometric data v, P(t) is transmitted to a control unit 31, which carries out automatic control processes on the basis thereof, and sends the data v P(t) to a display unit (not shown), on which they are shown graphically to the operating personnel.
Finally, it should again be noted that the methods and devices described above are merely preferred exemplary embodiments of the invention and that the invention can be modified by a person skilled in the art without departing from the field of the invention, insofar as it is specified by the claims. For the sake of completeness, it should be noted that the use of the indefinite articles “a” or “an” does not preclude the relevant features from also being present plurally. Similarly, the expression “unit” does not preclude this consisting of a plurality of components which can possibly also be spatially distributed.

Claims

1-15. (canceled)

16. A method for adjusting measurement parameters of an odometry unit of a rail vehicle, the method comprising the following steps:

using at least one sensor unit including an internal image-recording unit to capture sensor data from at least one of an interior or surroundings of the rail vehicle;

determining weather data based on the captured sensor data; and

determining fusion weightings for a fusion of odometric data having been determined on a basis of sensor data of different types of odometric sensors, as a function of the determined weather data.

17. The method according to claim 16, which further comprises selecting the at least one sensor unit as at least one of:

an external image-recording unit,

a temperature sensor,

a humidity sensor,

a LIDAR sensor for obstacle detection.

18. The method according to claim 17, which further comprises selecting a monitoring camera as the internal image-recording unit.

19. The method according to claim 18, which further comprises using the monitoring camera to observe the weather so that image data can be captured from external surroundings of the rail vehicle.

20. The method according to claim 18, which further comprises using the monitoring camera to observe the weather so that image data can be captured from the internal area of the rail vehicle.

21. The method according to claim 19, which further comprises determining a current weather situation based on the image data captured by the monitoring camera.

22. The method according to claim 21, which further comprises applying an image evaluation method based on machine vision to the captured image data to determine the current weather situation.

23. The method according to claim 22, which further comprises carrying out the image evaluation method by comparing the image data with different image patterns each being assigned to a different weather situation.

24. The method according to claim 23, which further comprises selecting different weather situations as:

snow fall,

fog,

rain.

25. The method according to claim 16, which further comprises using current operating data of an air-conditioning system of the rail vehicle to determine a weather situation.

26. The method according to claim 16, which further comprises reducing fusion weightings of sensors classified as fault-prone due to weather data, as a function of the determined weather data.

27. An adjustment facility for a rail vehicle, the adjustment facility comprising:

a data input interface for receiving captured sensor data from a sensor unit including an internal image-recording unit recording images of at least one of an interior or surroundings of the rail vehicle;

a weather determination unit for determining weather data based on the captured sensor data; and

a defining unit for defining fusion weightings for a fusion of odometric data having been determined on a basis of odometric sensor data from different types of odometric sensors as a function of the determined weather data.

28. A rail vehicle, comprising:

at least one sensor unit having an internal image-recording unit; and

an adjustment facility according to claim 27.

29. A non-transitory computer program product having a computer program which is directly loadable into a storage unit of a computer unit of a rail vehicle, having program portions that when executed on a processor, perform all of the steps of claim 16.

30. A non-transitory computer-readable medium on which program portions that are executable by a computer unit are stored, in order to carry out all of the steps of claim 16 when the program portions are executed by the computer unit.