EP4268126A1 - Verfahren und vorrichtung zur sensordatenverarbeitung - Google Patents
Verfahren und vorrichtung zur sensordatenverarbeitungInfo
- Publication number
- EP4268126A1 EP4268126A1 EP21847937.6A EP21847937A EP4268126A1 EP 4268126 A1 EP4268126 A1 EP 4268126A1 EP 21847937 A EP21847937 A EP 21847937A EP 4268126 A1 EP4268126 A1 EP 4268126A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- data
- scene
- vehicle
- objects
- database
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3833—Creation or updating of map data characterised by the source of data
- G01C21/3837—Data obtained from a single source
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L15/00—Indicators provided on the vehicle or train for signalling purposes
- B61L15/0058—On-board optimisation of vehicle or vehicle train operation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
- B61L23/041—Obstacle detection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L25/00—Recording or indicating positions or identities of vehicles or trains or setting of track apparatus
- B61L25/02—Indicating or recording positions or identities of vehicles or trains
- B61L25/025—Absolute localisation, e.g. providing geodetic coordinates
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Definitions
- the invention relates to a method and a device for sensor data processing in a vehicle and a vehicle.
- Sensor data processing is known, for example, in connection with driver assistance systems or even autonomously driving vehicles.
- the surroundings of an at least partially autonomously driving vehicle can be recorded, the corresponding sensor data can be analyzed and objects can thus be recognized.
- the vehicle can thus be controlled at least partially using the detected objects.
- the functionality of systems for autonomous or at least semi-autonomous control of vehicles can be increased if a map containing information about the route traveled by the vehicle is also accessed.
- Digitized maps which can be present in the form of databases, are used, for example, for route planning and/or monitoring the progress of the journey in navigation devices. It is also known to store additional information about the surroundings of the roads in these databases, for example about so-called "points of interest" such as gas stations, train stations, sights and/or the like, in addition to the information about the course of roads or paths.
- points of interest such as gas stations, train stations, sights and/or the like
- the corresponding databases contain a particularly large amount of such additional information.
- This additional information can in particular characterize so-called landmarks.
- the landmarks describe, for example, traffic signs, traffic lights, street lamps, buildings and/or other prominent objects in the vicinity of streets or paths with an extremely high spatial resolution. Due to their high level of detail, these maps can therefore even be used for so-called landmark-based navigation.
- the sensor data generated when capturing the vehicle environment is compared with the data from the corresponding database. The position of the vehicle can be determined extremely precisely by found matches. This can be used to keep an at least semi-autonomous vehicle “on track”.
- such a map can also be used to obtain information relevant to driving, such as the maximum permitted speed, priority regulations, road conditions and/or the like.
- information relevant to driving such as the maximum permitted speed, priority regulations, road conditions and/or the like.
- the vehicle can then navigate at least partially autonomously.
- a scene from the surroundings of the vehicle is detected by sensors and corresponding sensor data is generated.
- objects are recognized in the scene and corresponding object data, which characterize the recognized objects, are generated.
- the generated object data are compared with scene data stored in a database and quality-assured, which characterize objects in the scene. Depending on a result of the comparison, a reliability of the sensory Scene capture and / or data processing of the sensor data and / or the object recognition and / or the database assessed.
- a scene in the sense of the invention can be understood as a driving situation of the vehicle.
- a scene can represent a “snapshot” of the area surrounding the vehicle at a point in time.
- a scene is therefore expediently defined by objects from the area surrounding the vehicle and their arrangement relative to one another and/or to the vehicle at a point in time.
- Data processing of sensor data within the meaning of the invention can be understood as meaning an analysis, in particular algorithmic, of the sensor data.
- mathematical operations and/or pattern recognition can be carried out with the sensor data.
- Data processing of sensor data is preferably carried out by artificial intelligence, for example by a trained neural network and/or the like.
- Data processing of sensor data can in particular include processing of the data with the aid of at least one algorithm for digital image processing.
- Quality-assured scene data within the meaning of the invention can be understood in particular as data to which a particularly high degree of reliability is attributed.
- the information contained in such data can be trusted to a particular degree.
- Quality-assured scene data can, for example, meet a specified safety standard, in particular one of several safety levels such as a SIL (Safety Integrity Level).
- SIL Safety Integrity Level
- the scene data can, for example, characterize properties, also referred to below as features, of the objects.
- the quality assurance of the scene data expediently includes, among other things, that at least one combination of the properties or Features specific to each through the scene data characterized object is .
- it can be provided for quality-assured scene data that the unambiguous description of an object is secured by at least one feature, in particular a combination of features, with regard to specificity compared to other objects.
- One aspect of the invention is based on the approach of controlling the movement of a vehicle, in particular a rail vehicle such as a train or at least one railcar or a locomotive, for example along a specified route using a database.
- the database contains scene data which characterize objects preferably in different scenes along the route.
- objects in a scene from the area surrounding the vehicle are preferably identified on the basis of sensor data generated when the area surrounding the vehicle is detected by sensors.
- object data which are generated when the objects are recognized with the aid of, in particular, algorithmic data processing and which characterize the recognized objects are compared with at least part of the scene data.
- the reliability of the sensory scene detection and/or the data processing of the sensor data i.e. the recognition algorithm itself, and/or the object recognition or . -Identification to be assessed. Alternatively or additionally, it is also conceivable to assess the reliability of the database.
- the reliability of the sensors is preferably assessed, d. H . for example whether a sensor device is working correctly.
- the reliability of the method according to which the sensor data is processed is preferably assessed. For example, the reliability of a corresponding algorithm or be judged by an artificial intelligence.
- the reliability of the result of the data processing is preferably assessed, d. H . for example, whether the correct properties have been assigned to an object.
- the reliability of the scene data is preferably assessed, i. H . for example whether the scene data correctly reflects reality.
- a reliability measure is preferably assigned to the sensory scene detection and/or the data processing and/or the object recognition and/or the database. For example, depending on a result of the comparison of the scene data with the object data of the sensory scene detection and/or the data processing and/or the object recognition, a measure for the reliability of the scene data can be assigned. In other words, trust in the database can be transferred to the vehicle's sensors, the algorithms used for data processing in the vehicle and/or the "virtual" scene based on the sensory detection.
- a measure of reliability within the meaning of the invention can be understood in particular as a safety standard.
- a measure of reliability can, for example, correspond to one of several safety levels, such as an SIL (Safety Integrity Level).
- the measure of the reliability of the scene data is expediently dependent on quality assurance of the scene data, in particular defined by quality assurance.
- the measure of the reliability of the scene data that can be associated with quality assurance can be identified on the scene tion, data processing and/or object recognition.
- the object data essentially match the scene data, a robust object recognition or Obj ektidenti fikation be assumed.
- the object data do not match or do not match sufficiently with the scene data, it can be assumed that the object recognition is faulty or defective. Since this has a direct effect on the reliability, for example, of the control of an at least partially automated, in particular driverless, operated vehicle, the comparison thus also allows an assessment of the driving safety of such a vehicle.
- a measure of the reliability of the scene data in particular the scene data contained in it, can be associated with the object recognition, for example with the detection of the environment and/or the recognition of the objects in the scene .
- the safety of the correct scene detection, data processing and/or object recognition is provided by the Consistency of a multitude of specific characteristics of the objects recorded by sensors and recorded in the database is determined. If the specific features match at least to a degree that is preferably predetermined, it is possible to conclude that the overall system is functioning correctly.
- the correct detection of an object at a position stored in the database can also be used to determine the location of the vehicle, the calibration of sensors set up for detection, the function of the sensors and the sensor fusion, the flawless function of the hardware and software for information processing and communication .
- the information about the reliability of the individual components, in particular in the form of the result of the comparison, can be reported to a health management system of object recognition, for example, which reduces performance parameters when errors or limitations are detected.
- a database is therefore preferably used whose authorship is classified as reliable and/or which is correspondingly certified.
- the method is expediently based on a database that has been at least partially created or at least checked by a human operator.
- the database or the data contained therein conforms to a specified security standard, such as the DIN standard EN 61508.
- the object data By comparing the object data with the scene data, it is also possible, when automating vehicle functions, to determine an "uncertain", i.e. possibly non-certified Algorithm for object recognition or whose reliability has been tested under all operating conditions. -Use identification of obj ects. As long as at least part of the object data at least essentially matches the scene data, i.e. for example positions, structures and/or shapes of objects determined during sensory detection of the environment correspond to a description of the environment according to the scene data, the measure for the reliability of the scene data associated with the object recognition and the object data are used accordingly, for example, to control the vehicle.
- an "uncertain" i.e. possibly non-certified Algorithm for object recognition or whose reliability has been tested under all operating conditions.
- -Use identification of obj ects As long as at least part of the object data at least essentially matches the scene data, i.e. for example positions, structures and/or shapes of objects determined during sensory
- object data that have no correspondence in the database can then also be used to control the vehicle. It can be assumed that such "additional" object data characterize objects in the scene that are not recorded in the database.
- the trust that was built up when recognizing objects recorded in the database can be transferred at least partially to the recognition of these "additional", unknown obj ects. With such obj ects it can be for example non-stationary objects such as people on a platform, animals in the track bed and/or the like, the occurrence of which along the route cannot be foreseen.
- the database forms the map of a route along which the vehicle is traveling and the scene data includes map data from a portion of the map.
- a measure of the reliability is determined which is determined by the scope of the scene data.
- the degree of reliability preferably depends on the amount of information contained in the scene data.
- the scene data can have, for example, so-called feature vectors for each object from the scene, with the feature vectors preferably having specific features of the detected objects as entries.
- the length of the vectors, i. H. the number of features they describe then corresponds appropriately to the degree of reliability.
- a large amount of scene data allows the validation of objects from the scene detected using the sensor data with a high level of reliability.
- an object recognized on the basis of the sensor data can be identified in the database with a high degree of certainty by a combination of features, ie it can be associated with an object recorded in the database.
- the feature vectors corresponding to the scene data are expediently overdetermined. D. H . that already a subset of specific features contained in the feature vectors is sufficient to clearly recognize the object. As a result, the robustness when comparing with the object data or the feature vectors corresponding to the object data are increased.
- a degree of correspondence for the correspondence of the object data with the scene data is determined.
- the degree of agreement can also be interpreted as a degree of confidence which characterizes the reliability of the detection of the objects in the area surrounding the vehicle, in particular the strength of deviations between the object data and the scene data.
- the degree of agreement can be used to specify a specificity with which an object is recognized on the basis of the sensor data.
- the reliability of the object recognition can be assessed in a particularly simple manner on the basis of the degree of agreement.
- the information about the reliability of the object recognition can be further processed in a particularly efficient manner on the basis of the degree of agreement or used for the control of the vehicle.
- the degree of agreement can, for example, assume a high value if the object data not only characterizes objects that are also characterized by the scene data, but also if the characterization by the respective data essentially matches.
- the scene data can not only contain information about the position of an object, but also about other quality-assured features, the traceability and specificity of which can be proven to an expert.
- the scene data can, for example, also contain information about the shape, structure, extent, texture, color and/or the like of an object. The greater the proportion of this information that corresponds to the corresponding information from the object data is correct, the greater the ascertained degree of agreement can be.
- the determined degree of correspondence can assume a small value if the information and shape contained in the object data about a position of a detected object essentially corresponds to the corresponding information from the scene data, but the information about the extent and texture does not.
- a check is made as to whether the degree of correspondence reaches or exceeds a predetermined correspondence threshold value.
- the match threshold can be used as an indicator of whether a match is considered sufficient or reliably specified number of properties of a recognized object matches the information contained in the scene data. If this is the case, it can be assumed that the objects have been reliably identified. From this, conclusions can be drawn, for example, about the reliability of the position determination of the vehicle, the reliable and precise functioning of the sensors for detecting and determining the object positions and, if necessary, the correct calibration of several sensors with one another. If this is not the case, it can be assumed that the object was not recognized correctly.
- the agreement threshold value preferably depends on the security requirements or can be selected as a function of them. If the match threshold value is chosen to be large and the match level reaches or exceeds it, a high security level can in principle be associated with the object recognition. On the other hand, if the matching threshold value is selected to be smaller and the degree of matching is reached or exceeded, only a low security level can be associated with the object recognition.
- the control is carried out depending on a result of the test as to whether the degree of conformity meets the specified meets or exceeds a match threshold. If this is the case, error-free object recognition can be assumed and the object data determined in the process can be used as a basis for the control of the vehicle. On the other hand, if the degree of agreement falls below the agreement threshold value, an incorrect or incorrect object recognition can be assumed. In this case, the object data should not be used as a basis for controlling the vehicle. Rather, it may be necessary to transfer the vehicle to a safe state, at least if no redundant system for controlling the vehicle is available or if this is also faulty.
- the vehicle can be stopped, for example, because the object data are classified as no longer reliable.
- the sensor data together with at least part of the scene data for example the information as to which objects should actually have been recognized with which properties, can be stored in a training database for retraining the object recognition.
- the degree of conformity in particular that which is output, is logged.
- the degree of conformity in particular a time profile of the degree of conformity, can be stored. This allows verification of the reliability of the scene detection and/or data processing of the sensor data and/or the object recognition and/or the database.
- the logged degree of conformity can, for example, be presented to an authority or an expert in order to obtain approval for a control system for the vehicle, which is at least partially based on the object data.
- the degree of agreement can be demonstrated much more efficiently using the degree of agreement than using a conventional, direct analysis, for example of the algorithm on which the object recognition is based or whose source codes .
- a source code analysis usually requires considerable effort.
- the determination of the degree of conformity also has the advantage that it is a proof of reliability essentially in real time and thus even during regular operation of the vehicle or. of the corresponding control system.
- the degree of agreement can also serve as a basis for increasing or at least maintaining trust in the database and the scene data contained therein. If there is a high degree of agreement, it can not only be assumed that the object recognition works reliably, but also that the database is correct. If the degree of conformity is logged, the logged degree of conformity can be used to prove the reliability of the database when the database is used again later for monitoring the journey of the same vehicle or another vehicle. In particular, the logged degree of agreement can be interpreted as a certificate from the database.
- the generated object data or the scene data are compared, in particular additionally, with dynamic data provided by at least one object from the environment of the vehicle.
- a reliability of the sensory scene detection and/or the data processing of the sensor data and/or the object recognition and/or the database is assessed.
- a measure of the reliability of the dynamic data can be associated with the scene detection and/or the data processing and/or the object recognition and/or the database.
- the dynamic data can be transmitted wirelessly from the at least one object to the vehicle.
- a train approaching the vehicle staff working in the track bed for maintenance tion, a maintenance tool such as drag shoes and/or the like transmits dynamic data to the vehicle, with which the generated object data can then be compared.
- the dynamic data in particular in real time, to be transmitted to the database and included in the database.
- the reliability of the dynamic data can be assessed as a function of a result of the comparison of the generated object data or the scene data with the dynamic data provided.
- a reliability measure associated with the reliability of the scene recognition and/or the data processing of the sensor data and/or the object recognition and/or the database can be associated with the dynamic data.
- the measure of the reliability of the scene data which in one possible embodiment is associated with the scene recognition and/or the data processing of the sensor data and/or the object recognition on the basis of the comparison of the object data with the scene data. was also associated with the dynamics data . For example, if an object is attached to a correct -d. H . If the position validated by the scene data is recognized, the quality of the dynamic data can also be assured if they match the object data and/or the scene data.
- the vehicle and the object can thus form a so-called reliability community (community of dependability).
- Such quality assurance of the dynamic data can also be provided for the object itself and/or for other vehicles or other road users.
- the vehicles or Road users for example, use their sensors independently of other vehicles or have road users validated. This allows an increase in the reliability of the overall system, i. H . of the system Vehicles and obj ects that provide such dynamic data or. belong to the reliability community.
- errors for example in the sensors for capturing the scene or the object recognition, can be detected or corrected faster and more reliably. diagnose .
- a position of the vehicle on a route is determined and the scene from the surroundings of the vehicle is recorded at the determined position. Based on the determined position, the relevant scene data from the database can be identified particularly effi ciently and made available for comparison. Accordingly, the generated object data are compared with scene data stored in the database, which characterize objects in the vicinity of the determined position of the vehicle.
- the position of the vehicle is not only determined with the help of the database and/or information read from the database is used directly to control the vehicle. Rather, the position of the vehicle can be used as a basis for a comparison of the object data with the route data.
- the position can be determined using conventional or methods known from the prior art, such as using GPS signals.
- the scene data is expediently filtered on the basis of the determined position. Filtered scene data is preferably provided for comparison with the object data. This makes it possible to ensure that the object data are only compared with those scene data that characterize objects in the area surrounding the vehicle at the determined position. In other words, it can be ruled out that the object data are compared with scene data that characterize objects that are located in a different section of the route.
- the comparison identifies a detected object with an object recorded in the database, but the detected position of the object differs slightly from the position stored in the database, depending on the reliability of the information from the other sources, either (i) the determined current position of the vehicle can be corrected, (ii) if the deviation is only determined for a recognized object, the stored position information in the database is adjusted or (iii) a calibration or alignment of a sensor device, for example a camera, in relation to the vehicle to be adjusted. Which correction or adjustment (i), (ii) or (iii) is made is preferably determined on the basis of error models.
- hazardous objects in the area surrounding the vehicle are determined on the basis of a result of the comparison.
- a dangerous object is to be understood here in particular as an object that can (negatively) impair the travel of the vehicle.
- a dangerous object can therefore be particularly dangerous for the vehicle and/or endangered by the vehicle.
- a risk assessment is to be understood here in particular as an analysis and assessment of the scene with regard to a risk to the vehicle and/or an object.
- the endangered objects are expediently selected from objects that are characterized by the object data.
- objects are preferably selected which are recognized on the basis of the sensor data but are not characterized by scene data.
- a classification with regard to the risk to the vehicle and/or the objects is preferably limited to objects that are not recorded in the database. This allows the number of objects on which the risk assessment is based can be significantly reduced . In particular, it can be ensured in this way that when analyzing the scene, only objects are taken into account that could actually be associated with a hazard potential. Accordingly, a more ef fi cient risk assessment is possible.
- landmarks and thus stationary objects such as the roadway, signaling systems, buildings and/or the like are recorded in the database.
- Such objects are also referred to as previously known objects and generally do not pose a threat to the vehicle's travel. They therefore do not have to be taken into account for a risk assessment.
- Moving objects such as people on a platform or animals on the track bed, on the other hand, are usually not included in the database. The number of objects to be checked for a possible hazard is reduced significantly by precisely these mobile and a priori unknown objects being identified and selected when comparing the object data with the scene data.
- the risk objects on which the risk assessment is based can also be selected on the basis of the object data, in particular on the basis of a distance from the vehicle. As a result, the number of objects to be taken into account for the risk assessment can be further reduced.
- the risk assessment is preferably only based on objects that are located at a specified distance, in particular in a specified distance range, from the vehicle. For example, based on the comparison of the object data with the scene data, all moving objects in the vicinity of the vehicle can first be selected and this selection can then be reduced to those moving objects that are located at the specified distance from the vehicle. In this way, objects that are not recorded in the database but are too far away from the vehicle can be represent a hazard be excluded from the hazard assessment . This means that the risk assessment can be carried out even more efficiently.
- an excess list of all objects characterized by the object data that are not characterized by scene data is determined during the comparison.
- the comparison can be used to create a list of objects in the area surrounding the vehicle that are not recorded in the database.
- These objects can be, for example, moving objects such as people on a railway track, animals on the track bed and/or the like.
- the surplus list is then preferably output at least as part of the result.
- the surplus list allows an analysis of the driving situation at the determined position of the vehicle to be reduced to relevant objects. For example, the objects on which the risk assessment is based can be selected using the surplus list.
- a control system of the vehicle can be designed, for example, to only take into account the objects contained in the surplus list when controlling the vehicle. This is based on the idea that there is no need to react surprisingly to objects that are recorded in the database and are therefore already known. As a result, a particularly efficient control of the vehicle can be achieved.
- object data of a recognized object are determined on the basis of the scene data.
- further object data are preferably determined, in particular for objects not characterized by the scene data.
- the object data can also be supplemented on the basis of the scene data. This allows the reliability in the detection of obj ects based on the Sensor data, especially when generating the corresponding object data, are further increased.
- the position of objects recognized on the basis of the sensor data that are not recorded in the database can be determined more precisely on the basis of a position relative to a recognized object that is recorded in the database. If a person is detected in the vicinity of a signal system based on the sensor data and the signal system is recorded in the database, the distance of the vehicle to the person can be derived from the distance between the signal system and the vehicle characterized by the corresponding scene data.
- the object data of newly recognized objects that are not recorded in the database are preferably stored as provisional scene data in the database—at least if they are stationary. Alternatively or additionally, these objects can be entered in a candidate list. If these objects are found in the same position on several journeys, they can be included in a checklist and/or the provisional scene data can then be subjected to a quality control and, if necessary, permanently added to the database.
- the database at least meets the DIN standard EN 61508, in particular in the 2010 version.
- the database preferably has at least one safety requirement level (S IL for "Safety Integrity Level” for short) of 1.
- S IL Safety Integrity Level
- This safety requirement level then applies, for example, to the function of error disclosure for sensor systems for obstacle detection and to simplify scenes for obstacle detection systems and the position verification of Vehicles Due to the safety requirement level 1, it can be assumed that with constant use of the database and corresponding quality assurance, a maximum of 1 error will occur in around 11 years A particularly large amount of trust is placed in object data with the scene data. In particular, it can then be assumed that if at least part of the object data matches the scene data, the object recognition is error-free with an equally high probability.
- a check is made as to whether object properties match.
- at least one feature vector corresponding to the object data is expediently compared with a feature vector corresponding to the scene data. For example, it can be checked whether a position of the detected objects relative to the vehicle, a structure, in particular a topology, of the detected objects and/or a shape of the detected objects matches corresponding properties of objects recorded in the database. It is preferably checked whether and, if so, how large the deviations between the object properties are. In particular, based on the object properties or whose deviations are used to determine the degree of conformity.
- properties that can be checked are, for example, expansion, change in shape (in the case of vegetation, for example due to growth, change of season, pruning, harvesting and/or the like), color, temperature, relative temperature to the environment, reflectivity and/or the like.
- These properties can also be present in the database as part of the scene data in the form of a feature vector.
- the feature vector preferably has a minimum size, i . H . a minimum number of entries, so that a coincidental coincidence of the characteristics of objects recorded in the database with the properties characterized by the object data is so unlikely that this case can be ruled out with sufficient certainty.
- a point in time of the sensory detection of the surroundings of the vehicle is determined and the comparison of the object data with the scene data is used as a basis. This makes it possible to dynamic events or Include operations when comparing . Confidence in object recognition can thus be increased even further.
- the day-night change and/or change of season can be included in this way. In the dark, certain objects or at least parts of them may no longer be recognizable. It is conceivable that specific light sources, such as position lights, signal lights and/or the like, are used for detection.
- specific light sources such as position lights, signal lights and/or the like.
- the changes in vegetation caused by the change of season for example in the form of harvested fields or leafless trees, can also be taken into account.
- an object is located in the vicinity of the vehicle at the determined position only at a specified point in time or at least within a specified period of time.
- Such an object can be a train, for example, which is approaching the vehicle at the determined position according to the timetable. If the vehicle passes the same position at a different point in time, it will not meet the (scheduled) train (at this position).
- the scene data is expediently filtered on the basis of the time determined. In this way, scene data can be excluded from the comparison for which no correspondence can be found in the object data a priori due to the time determined.
- At least part of the scene data is converted into, in particular a renewed, detection of further objects from the scene on the basis of the sensor data included . If certain objects are not found on the basis of the sensor data, but which are characterized by scene data, it does not necessarily have to be assumed that there is a lack of reliability in the object recognition. If, for example, the degree of agreement for objects that are characterized by both the scene data and the object data assumes a high value, the position of objects in the sensor data that are characterized by the scene data but not by the object data precisely these objects are searched for in order to complete the scene and thus further simplify the interpretation of the driving situation. Such a renewed “search” for further objects in the sensor data can be useful, for example, if an object is at least partially covered by another, moving object.
- the device according to the invention for sensor data processing in a vehicle has a sensor device that is set up to detect a scene from the area surrounding the vehicle and to generate corresponding sensor data.
- the device has a data processing device which is set up to recognize objects in the scene on the basis of data processing of the sensor data and to generate corresponding object data which characterize the recognized objects.
- the data processing device is also set up to compare the generated object data with quality-assured scene data stored in a database and characterizing the objects in the scene, and depending on a result of the comparison, to determine the reliability of the scene detection and/or the Assess data processing of the sensor data and/or the object recognition and/or the database.
- scene recording, data processing, object j ect detection or . -Identification and/or the database can be efficiently checked and assessed for reliability.
- the data processing device can be designed in terms of hardware and/or software. For example, it can have one or more programs or program modules. Alternatively or additionally, it can be a, preferably with a memory and / or bus system data or. have a signal-connected, in particular digital, processing unit, such as a microprocessor unit (CPU). In particular, the CPU can be designed to process commands that are implemented as a program stored in a memory system.
- the data processing device can in particular be set up to carry out at least part of the method according to the invention.
- the device has a memory device in which the database is stored.
- the storage device can have one or more, in particular different, storage media.
- the storage device can in particular have optical, magnetic, solid-state and/or other non-volatile media.
- the vehicle according to the invention in particular a rail vehicle, has a device according to the invention.
- the movement of the vehicle can be monitored particularly reliably and efficiently with the aid of the device.
- scene detection, data processing and/or object recognition or identification are monitored and assessed for reliability.
- FIG. 1 shows an example of a driving situation from the perspective of a vehicle on a route
- FIG. 2 shows an example of a device for sensor data processing in a vehicle
- FIG. 3 shows an example of a method for sensor data processing in a vehicle on a route.
- the vehicle (20) is a rail vehicle (also: "Rail-bound vehicle”), such as a train, so that route 1 is specified by the course of rails la.
- rail vehicle also: "Rail-bound vehicle”
- the driving situation is preferably characterized by objects 3a, 3b, 3c, 3d in the surroundings 2 of the vehicle 20.
- the driving situation can be characterized by the arrangement of objects 3a, 3b, 3c, 3d relative to vehicle 20.
- the driving situation is therefore sometimes also referred to as a scene.
- FIG. 1 The objects shown in FIG. 1, purely by way of example, are an embankment 3a on the track bed, a signal system 3b for controlling rail traffic on route 1, a structure 3c—here a bridge over the track bed—and people 3d.
- vehicles in particular vehicles that drive autonomously or at least partially autonomously with the help of a corresponding control system, are preferably equipped with a sensor device 11 that is set up to detect the environment 2 and can have, for example, one or more camera sensors, radar sensors, lidar sensors and/or the like .
- Sensor data generated in the process can be evaluated, for example by means of algorithms for recognizing the objects 3a, 3b, 3c, 3d, and the driving situation or scene can be analyzed in this way.
- the objects 3a-3d can be divided into two groups: previously known objects 3a-3c and unknown objects 3d.
- Known objects 3a-3c can, for example, be stationary objects that occur each time vehicle 20 travels along predetermined route 1, in particular always at the same position.
- Unknown objects 3d can be dynamic objects that happen to be in the area 2 when driving on route 1 .
- the appearance of the previously known objects 3a-3c in the area 2 along route 1 can easily be predicted.
- a database in which, for example, all stationary objects 3a-3c are recorded.
- Such a database can contain scene data which characterizes the stationary objects 3a-3c.
- the scene data contain, for example, the information as to which route section on route 1 contains which of the previously known objects 3a-3c and in what arrangement relative to vehicle 20.
- dynamic 3d objects often cannot be recorded in the database or since their occurrence in area 2 along route 1 or . their location relative to vehicle 20 is unpredictable. Exceptions to this are possible, in particular with regard to dynamic objects that are related to a regularly occurring event and/or are set up to characterize them. provide rising dynamic data.
- a train that is running according to the timetable and that meets the vehicle 20 on route 1 in a predetermined route section could be recorded in the database.
- this train to transmit dynamic data, which contain information on the current position, the direction of movement and/or the type of train, for example, to the vehicle 20 via a radio link or another communication link. On the basis of this information, further data can then be read from the database, for example on specific characteristics of the train. Alternatively, this information can also be transmitted directly from the train to the vehicle 20 .
- Another example is a scheduled aircraft that is visible in the sky from vehicle 20 on certain days at a certain time from a predetermined route segment.
- the transmission of the dynamic data is preferably secured via a security protocol.
- the dynamic data itself can be quality-assured.
- the further route ie, for example, the course of the track bed 3a
- the route is preferably determined from the sensor data.
- the route can be characterized particularly well and is therefore proportionate in terms of sensors easy or can be reliably detected. If the route is validated by comparing it with the scene data, for example the position of objects 3b, 3c, 3d detected in the area 2 of the vehicle 20 can be determined relative to the route and thus particularly reliably. It can also be reliably assessed for objects 3c, 3d at greater distances as to whether they are on or next to the track, ie about the track bed 3a.
- the comparison of the object data with the scene data can provide information about the reliability of the scene detection, the data processing of the sensor data, the object recognition and/or even supply the database itself . If objects are recorded in the database that are not recognized during the processing of the sensor data, this can be an indication of faulty or at least inadequate object recognition. Accordingly, the control of vehicle 20 should no longer be based on the object data generated during object recognition, since these are to be regarded as unreliable. Rather, the vehicle 20 should be brought into a safe state, ie stopped, for example. If necessary, this can also be an indication of an outdated database. The database can then be updated accordingly, for example after the absence of the objects has been checked by other vehicles.
- FIG. 2 shows an example of a device 10 for sensor data processing in a vehicle, in particular in a rail vehicle.
- a device 10 for sensor data processing in a vehicle, in particular in a rail vehicle.
- the device 10 has a sensor device 11 , which is set up to capture a scene from the surroundings of the vehicle and to generate corresponding sensor data, as well as a data processing device 12 .
- the data processing device 12 is set up to process the sensor data so that obj ects recognized in the scene on the basis of the sensor data and corresponding object data which characterize the recognized objects are generated.
- the sensor device 11 expediently has one or more sensors, in particular of an optical type.
- the sensor device 11 can have a camera, for example, which is set up to generate sensor data in the form of an image of the surroundings when the surroundings of the vehicle are detected.
- the sensor device 11 can have one or more lidar sensors, radar sensors and/or imaging devices for the infrared and/or ultraviolet spectral range.
- the data processing device 12 preferably has an algorithm for object recognition or can apply such an algorithm to the sensor data.
- the detected objects can be classified and properties of the objects, such as their position relative to the vehicle, size, structure or Identify topology and/or the like.
- the object data expediently contain this information.
- the data processing device 12 has access to a database 13 in which scene data are stored.
- the scene data characterize previously known, for example stationary, objects in the scene.
- the database 13 can, but does not have to be part of the device 10 .
- the database 13 can, for example, also be held by a server with which the data processing device 12 installed in the vehicle can communicate.
- the device 10 also has a position determination device 14 which is set up to determine the (current) position of the vehicle on the route.
- the position determination device 14 can be embodied, for example, as a GPS receiver or the like, in order to use received signals to determine the position of the to secure the vehicle. Alternatively or additionally, odometry data of the vehicle can also be used.
- the data processing device 12 is preferably set up to link the position determined by the position determination device 14 with the object data generated when the objects were recognized.
- the object data can thus be clearly assigned to a position of the vehicle on the route.
- the object data can therefore also be referred to as position-specific or location-resolved object data.
- the data processing device 12 is set up to base the comparison of the object data with the scene data on the determined position of the vehicle on the route.
- the data processing device 12 is preferably set up to compare the object data with the scene data with regard to the determined position of the vehicle.
- the data processing device 12 can in particular be set up to compare the object data with the scene data that characterize objects in the vicinity of the determined position of the vehicle. For this purpose, an assignment of the scene data to possible positions of the vehicle along the route is expediently provided in the database 13 .
- the data processing device 12 can be set up, for example, to filter the scene data with regard to the determined position.
- the data processing device 12 is expediently set up to extract precisely those scene data from the database 13 which are assigned to the determined position.
- the data processing device 12 can be set up to access the scene data taken from the database 13 which are assigned to the determined position.
- the data processing device 12 is set up to use a result of the comparison to assess the reliability of the sensory scene detection and/or the data processing of the sensor data and/or the object recognition and/or the database.
- the data processing device 12 can be set up to associate a measure of the reliability of the scene data 13 with the sensory scene detection and/or the data processing of the sensor data and/or the object recognition.
- the device 10 expediently has an interface 15 with the aid of which the result of the comparison can be made available.
- the result can contain an excess list of all recognized objects that were recognized on the basis of the sensor data but are not recorded in the database 13 or at least are not assigned to the determined position.
- the result can contain filtered object data. The result then expediently contains only that part of the object data for which the data processing device 12 was unable to determine a match with the scene data.
- the data processing device 12 can use this surplus list or provide the filtered object data to a control system, for example, via the interface 15 .
- the control system can analyze the driving situation, in particular a risk assessment, using the surplus list or of the filtered object data. Based on the analysis, the vehicle can be controlled by the control system. However, it is also conceivable that the data processing device 12 is already set up to analyze the driving situation, possibly also to control the vehicle, on the basis of a result of the comparison.
- FIG. 3 shows an example of a method 100 for sensor data processing in a vehicle, in particular in a rail vehicle.
- a position of the vehicle on the route is determined in a method step S 1 .
- a position determination device can be provided which, for example, receives a GPS signal and/or the like and uses this to determine the (current) position of the vehicle.
- the determined position can in particular be or will be assigned to a route section.
- a scene from the surroundings of the vehicle is detected by sensors, for example with the aid of a sensor device.
- Corresponding sensor data are generated in the process.
- the position determined in method step S 1 is or is preferably assigned to the generated sensor data, for example by the position being determined at the same time as the generation of the sensor data.
- a further method step S3 objects in the scene are recognized on the basis of data processing of the sensor data, and corresponding object data, which characterize the recognized objects, are generated.
- the sensor data is, for example, image data that was generated by a camera of the sensor device
- the sensor data can be evaluated using an algorithm for object recognition.
- the resulting information on the class of the recognized object and its physical properties such as position relative to the vehicle, size, structure or Topology and/or the like is expediently provided at least as part of the object data, for example in the form of a feature vector.
- the object data are compared with scene data stored in a database, which characterize objects in the scene.
- scene data are expediently filtered in relation to the determined position of the vehicle.
- a degree of correspondence can be determined which indicates the degree of correspondence between the object data and the—possibly filtered—scene data.
- the degree of correspondence can, for example, assume a high value if at least part of the object data at least essentially corresponds to the scene data.
- the degree of correspondence can assume a high value in particular if all objects characterized by the scene data and known in the vicinity of the determined position of the vehicle were also recognized in method step S3.
- the degree of correspondence preferably assumes a high value if the properties of the recognized objects mapped by the object data match at least to a high degree with the properties of the previously known objects mapped by the scene data.
- the selected features are preferably selected in such a way that there is a high probability that they only occur in combination with one type or one instance of an object.
- the degree of agreement can indicate a specificity of the object recognition.
- an assessment of the reliability of the scene detection from method step S2, the data processing of the sensor data and/or the object recognition from method step S3 can subsequently be undertaken. For example, it can be checked whether the degree of agreement reaches or exceeds a predetermined agreement threshold value. Depending on a result of this check, in a further method step S5, the reliability of the sensory scene detection from method step S2, the data processing of the sensor data and/or the object recognition from method step S3 can be assessed. Alternatively or additionally, the reliability of the database can also be assessed.
- a measure of the reliability of the scene data can be associated with the scene detection in method step S2 and/or with the data processing and/or with the object identification in method step S3.
- the sensor data processing can be assigned a specific security standard without a detailed analysis of the sensor data processing having to be carried out for this purpose.
- the object data can be output to a control system, which uses them to control the vehicle.
- a part of the object data which is not characterized by scene data, i. H . unknown, such as non-stationary or . can be assigned to dynamic objects in the form of a surplus list as the result of the comparison from step S4.
- the driving situation can The basis of the surplus list can then be analyzed more ef fi ciently than on the basis of the original object data, which characterize all objects detected in the area surrounding the vehicle—that is, also previously known objects that are not relevant to the control of the vehicle.
- step S6 - due to the associated lack of trust in the object recognition from method step S3 - it can be checked whether a redundant system for controlling the vehicle, at least for object recognition, is operational or . works flawlessly. If so, control of the vehicle can be transferred to the redundant system. Otherwise the vehicle should be transferred to a safe condition.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Mechanical Engineering (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102021200822.4A DE102021200822A1 (de) | 2021-01-29 | 2021-01-29 | Verfahren und Vorrichtung zur Sensordatenverarbeitung |
| PCT/EP2021/085888 WO2022161694A1 (de) | 2021-01-29 | 2021-12-15 | Verfahren und vorrichtung zur sensordatenverarbeitung |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4268126A1 true EP4268126A1 (de) | 2023-11-01 |
Family
ID=80001345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP21847937.6A Pending EP4268126A1 (de) | 2021-01-29 | 2021-12-15 | Verfahren und vorrichtung zur sensordatenverarbeitung |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20240118104A1 (de) |
| EP (1) | EP4268126A1 (de) |
| DE (1) | DE102021200822A1 (de) |
| WO (1) | WO2022161694A1 (de) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4141838A1 (de) * | 2021-08-23 | 2023-03-01 | Zenseact AB | Validierung von umgebenden objekten, die von einem ads-ausgerüsteten fahrzeug wahrgenommen werden |
| US12266188B2 (en) * | 2022-05-09 | 2025-04-01 | GM Global Technology Operations LLC | Method and apparatus for leveraging infrastructure camera for vehicle positioning |
| DE102022134369A1 (de) * | 2022-12-21 | 2024-06-27 | Valeo Schalter Und Sensoren Gmbh | Selbsttätiges Manövrieren eines Fahrzeugs basierend auf Freigaben |
| US12415527B2 (en) | 2023-07-14 | 2025-09-16 | GM Global Technology Operations LLC | Range sensor based calibration of roadside cameras in ADAS applications |
| WO2025062184A2 (en) * | 2023-09-21 | 2025-03-27 | Hitachi Rail Gts Canada Inc. | Method for high-integrity localization of vehicle on tracks using on-board sensors and scene-based position algorithms |
| EP4671083A1 (de) * | 2024-06-28 | 2025-12-31 | Siemens Mobility GmbH | Verfahren zum orten eines spurgeführten fahrzeugs |
| DE102024208187A1 (de) * | 2024-08-28 | 2026-03-05 | Siemens Mobility GmbH | Verfahren und Einrichtungen zum Betreiben eines Schienenfahrzeugs |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8718861B1 (en) | 2012-04-11 | 2014-05-06 | Google Inc. | Determining when to drive autonomously |
| DE102013213106A1 (de) | 2013-09-18 | 2015-03-19 | Continental Teves Ag & Co. Ohg | Verfahren und System zur Bewertung einer Zuverlässigkeit eines sensorikbasierten Fahrzeugsystems |
| DE102014220687A1 (de) | 2014-10-13 | 2016-04-14 | Continental Automotive Gmbh | Kommunikationsvorrichtung für ein Fahrzeug und Verfahren zum Kommunizieren |
| GB2542115B (en) * | 2015-09-03 | 2017-11-15 | Rail Vision Europe Ltd | Rail track asset survey system |
| TR201702439A2 (tr) * | 2017-02-17 | 2018-09-21 | Ekin Teknoloji Sanayi Ve Ticaret Anonim Sirketi | Çevre takibi ve güvenliği için bir sistem. |
| EP3477616A1 (de) | 2017-10-27 | 2019-05-01 | Sigra Technologies GmbH | Verfahren zur steuerung eines fahrzeugs mithilfe eines maschinenlernsystems |
| DE102017223632A1 (de) * | 2017-12-21 | 2019-06-27 | Continental Automotive Gmbh | System zur Berechnung einer Fehlerwahrscheinlichkeit von Fahrzeugsensordaten |
| PL3722182T3 (pl) * | 2019-04-12 | 2025-08-04 | Hitachi Rail Gts Deutschland Gmbh | Sposób bezpiecznego i autonomicznego określania informacji o położeniu pociągu na torach |
| DE102019209357B3 (de) | 2019-06-27 | 2020-10-29 | Audi Ag | Verfahren zum Ermitteln zumindest eines aktuellen Vertrauenswerts eines Datensatzes eines Kraftfahrzeugs sowie ein Rechensystem hierzu |
| DE102020202163B4 (de) | 2020-02-20 | 2025-03-13 | Volkswagen Aktiengesellschaft | Verfahren und Vorrichtung zur Detektierung von Objekten und/oder Strukturen im Umfeld eines Fahrzeugs |
-
2021
- 2021-01-29 DE DE102021200822.4A patent/DE102021200822A1/de not_active Withdrawn
- 2021-12-15 WO PCT/EP2021/085888 patent/WO2022161694A1/de not_active Ceased
- 2021-12-15 EP EP21847937.6A patent/EP4268126A1/de active Pending
- 2021-12-15 US US18/263,560 patent/US20240118104A1/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| US20240118104A1 (en) | 2024-04-11 |
| DE102021200822A1 (de) | 2022-08-04 |
| WO2022161694A1 (de) | 2022-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4268126A1 (de) | Verfahren und vorrichtung zur sensordatenverarbeitung | |
| DE102016120505B4 (de) | Koordiniertes Testen in Fahrzeugpulks | |
| DE102014008578B4 (de) | Verfahren zur Ermittlung von Positionsdaten zur Nutzung beim Betrieb eines Fahrzeugsystems eines Kraftfahrzeugs und Positionsdatenermittlungs- und-verteilssystem | |
| DE102016219455B4 (de) | Verfahren und aktive Infrastruktur zur Überprüfung einer Umfelderfassung eines Kraftfahrzeugs | |
| EP3438901A1 (de) | Testfahrtszenario-datenbanksystem für realitätsnahe virtuelle testfahrtszenarien | |
| DE102011081614A1 (de) | Verfahren und Vorrichtung zur Analysierung eines von einem Fahrzeug zu befahrenden Streckenabschnitts | |
| WO2020002261A1 (de) | Lokalisierungssystem und verfahren zum betreiben desselben | |
| EP3945338B1 (de) | Vorrichtung zur umfelderkennung eines automatisiert betreibbaren fahrsystems | |
| DE102020118629B4 (de) | Computerimplementiertes Verfahren zum Bestimmen der Validität einer geschätzten Position eines Fahrzeugs | |
| DE102021123270B3 (de) | Verfahren und Steuerschaltung zum Überprüfen, ob ein aktuell aktiver Fahrmodus innerhalb seiner ODD betrieben wird, sowie System und Backend-Server | |
| WO2021190840A1 (de) | Verfahren zur bewertung von streckenabschnitten | |
| DE102016220581A1 (de) | Verfahren und vorrichtung zur bestimmung eines umfeldmodells | |
| DE102021200408A1 (de) | Sicherheitskritische bordseitige Überwachung der Umgebung eines Schienenfahrzeugs | |
| DE102016212774B4 (de) | Verfahren und Vorrichtung zur Erzeugung einer Umfeldkarte sowie zur Lokalisierung eines Fahrzeugs | |
| DE102010033372A1 (de) | Verfahren und System zum Ermitteln der Position eines Schienenfahrzeugs | |
| DE102020118628A1 (de) | Verfahren und Vorrichtung zum Bestimmen einer Position eines Fahrzeugs | |
| DE102022204298A1 (de) | Verfahren zum automatisierten Bewegen eines Kraftfahrzeugs | |
| EP4119417B1 (de) | Überwachungsverfahren und -system | |
| DE102021201512A1 (de) | Verfahren zur Modellierung der Umgebung eines automatisierten Fahrzeugs | |
| DE102021124736A1 (de) | Verfahren und Vorrichtung zur Ermittlung einer Positions-Hypothese | |
| DE102021207415A1 (de) | Verfahren zur Informationsbeschaffung und Assistenzsystem | |
| WO2022122250A1 (de) | Infrastrukturgestützte trajektorienermittlung für autonome fahrzeuge | |
| EP3625106B1 (de) | Sensoriell gesteuertes anpassen von fusionsgewichten an wetterbedingungen in einer odometrieeinheit eines schienenfahrzeugs | |
| EP4113392B1 (de) | Verfahren zum prüfen der zuverlässigkeit einer ki-basierten objekt-detektion | |
| DE102024207864A1 (de) | Landkarte eines Schienenstreckensystems mit Sensorparameterdaten |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20230725 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20250818 |
|
| RAP3 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: SIEMENS MOBILITY GMBH |