EP4029757A1 - Procédé de commande d'une situation de circulation - Google Patents

Procédé de commande d'une situation de circulation Download PDF

Info

Publication number
EP4029757A1
EP4029757A1 EP21202312.1A EP21202312A EP4029757A1 EP 4029757 A1 EP4029757 A1 EP 4029757A1 EP 21202312 A EP21202312 A EP 21202312A EP 4029757 A1 EP4029757 A1 EP 4029757A1
Authority
EP
European Patent Office
Prior art keywords
vehicle
image recording
property
traffic
data processing
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.)
Withdrawn
Application number
EP21202312.1A
Other languages
German (de)
English (en)
Inventor
Andrew Palmer
Emanuel Brämer
Markus Wilhelm
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens Mobility GmbH
Original Assignee
Siemens Mobility GmbH
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Siemens Mobility GmbH filed Critical Siemens Mobility GmbH
Publication of EP4029757A1 publication Critical patent/EP4029757A1/fr
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • 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
    • B61L15/0081—On-board diagnosis or maintenance
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
    • B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
    • B61L27/50—Trackside diagnosis or maintenance, e.g. software upgrades
    • B61L27/57—Trackside diagnosis or maintenance, e.g. software upgrades for vehicles or trains, e.g. trackside supervision of train conditions

Definitions

  • the invention relates to a method for controlling a traffic situation.
  • the invention also relates to a data processing unit and a system having a data processing unit for executing the method for determining a property of a vehicle.
  • the object of the invention is to provide an improved method for controlling a traffic situation.
  • the invention is also based on the object of providing a data processing unit and a system with a data processing unit for carrying out the method.
  • At least one property of another vehicle can be determined by object recognition based on surroundings sensor data of a vehicle and a traffic control function can be executed based on the determined property if the determined property of the other vehicle is a traffic-relevant property.
  • the roadworthiness of vehicles can thus be checked by the vehicles of the other road users based on the surroundings sensor data of the vehicles. If it is detected that a vehicle is unfit to drive in the form of a traffic-relevant property, various measures in the form of a traffic control function can be carried out in order to ensure that a vehicle is a risk to road safety or to inform the respective driver that his vehicle is a traffic hazard.
  • the vehicle and the additional vehicle are each designed as a rail vehicle, with the rail vehicle and the additional rail vehicle being arranged on one rail track or on two rail tracks arranged next to one another.
  • the rail vehicles can check the roadworthiness that can be seen from the outside of other rail vehicles that are approaching on other tracks or that are driving ahead on other tracks or on the same track. This can improve the safety of rail traffic.
  • the property includes damage and/or dirt and/or the presence of a foreign body and/or a lack of an identification number of the other vehicle.
  • the technical advantage can be achieved that damage, dirt or, for example, the presence of foreign objects on the vehicle can be determined.
  • other externally visible damage to vehicles can be determined. This allows a precise determination of the roadworthiness based on externally visible damage or deviations from the normal condition of the vehicle. This can further increase road safety for road users.
  • the traffic control function includes outputting a warning signal and/or a warning message to the vehicle and/or the additional vehicle and/or reducing a speed of the vehicle and/or the additional vehicle and/or ending a journey of the vehicle and/or the additional vehicle.
  • the technical advantage can be achieved that when determining a traffic-relevant property, efficient control of the traffic situation and avoidance of a traffic hazard can be achieved.
  • warning signals or warning messages can be output to the vehicles involved in the traffic situation, the speed of the vehicles can be reduced or the journeys of the vehicles can be terminated. If traffic-relevant characteristics are present, the vehicles concerned can be secured or the traffic hazard reduced.
  • a traffic-relevant property is a property of a vehicle that can reduce the traffic safety of the vehicle and, in connection therewith, cause a traffic hazard for the respective vehicle and other road users.
  • the comparison includes: adapting and/or aligning the image recording and the reference image recording by performing an alignment of feature points of the image recording of the reference image recording.
  • the technical advantage can be achieved that a precise comparison of the image recordings of the surroundings sensor data with the respective reference image recordings and, associated with this, a precise determination of the deviation and, associated with this, a precise identification of the properties of the checked vehicles can be provided.
  • these are adapted and aligned with one another based on alignments of feature points of the recorded images and the reference recorded images.
  • the comparison of the image recordings with the reference image recordings and the determination of the respective deviations between the recordings can be made more precise.
  • identifying the property includes: classifying the property as a hazardous property or as a non-hazardous property.
  • the technical advantage can be achieved that the respective traffic control functions are only executed in the case of traffic-relevant properties. If there are discrepancies between the image recordings and the reference image recordings, which are based on properties that are not relevant to traffic and which therefore do not pose a threat to traffic, the execution of the traffic control function can be dispensed with. As a result, precise control of the traffic situation can be brought about.
  • the comparison of the image recording with the reference image recording, the determination of the deviation, the identification of the property and the classification of the property are carried out by a trained artificial intelligence.
  • the trained artificial intelligence can be designed in particular by a trained artificial neural network.
  • the comparison of the image recording with the reference image recording, the determination of the deviation, the identification of the property and the classification of the property are carried out by trained personnel.
  • the technical advantage can be achieved that a precise determination can be made, particularly in the case of deviations that are difficult to detect or in the case of properties that are difficult to classify of the traffic-related properties can be provided.
  • assessment by trained personnel can be advantageous over automatic assessment.
  • a combination of execution by the trained artificial intelligence and by trained personnel can also be advantageous.
  • a pre-selection or pre-assessment can be carried out by the artificial intelligence and a final classification or final identification of the individual features can be carried out by the trained personnel.
  • the recognition of the further vehicle in a vehicle recognition is carried out by a trained artificial intelligence.
  • the technical advantage can be achieved that precise object recognition can be provided based on the image recordings of the surroundings sensor data.
  • the trained artificial intelligence can in particular be embodied as a trained artificial neural network, which is trained for object recognition.
  • the method is executed by a data processing unit of the vehicle and/or by an external data processing unit.
  • the method according to the invention can be carried out by a data processing unit within the vehicles and/or by an external data processing unit which is operated, for example, in a rail traffic control center.
  • the respective drivers of the vehicles, in particular the rail vehicles can carry out the process through the in the vehicles trained data processing units are immediately given the appropriate instruction for controlling the traffic situation.
  • the respective drivers of the vehicles can react immediately to the traffic hazard.
  • the execution of the method by the external data processing unit for example in the rail traffic control center, can thus be used to control a global traffic situation that includes a plurality of different vehicles.
  • the vehicles affected by the traffic situation can thus be notified centrally by the control center or controlled or driven to carry out the traffic control function.
  • the environment sensor unit includes an RGB camera, a stereo camera, a LiDAR system or a radar system.
  • the technical advantage can be achieved that a precise determination of the properties of the vehicles is made possible. In this way, in particular, precise control of the traffic situation can be achieved.
  • a computer program product which includes instructions which, when the program is executed by a computing unit, cause the latter to execute the method according to the invention for controlling a traffic situation according to one of the preceding embodiments.
  • a data processing unit is provided which is designed to carry out the method according to the invention for controlling a traffic situation according to one of the preceding embodiments.
  • a system with a data processing unit is provided, which is designed to control the method according to the invention Execute traffic situation according to one of the preceding embodiments.
  • FIG 1 shows a graphical representation of a method for controlling a traffic situation according to an embodiment.
  • the method for controlling a traffic situation is carried out by a system 200 with a data processing unit 202 .
  • the system 200 includes a vehicle 201 in which the data processing unit 202 is designed to execute the method for controlling the traffic situation.
  • a traffic situation with two rail vehicles 201, 203 is shown, which are each moved on rails 215 arranged next to one another.
  • vehicle 201 records surroundings sensor data from a surroundings sensor unit 205, via which further vehicle 203 can be detected.
  • an object recognition which in the embodiment shown by an artificial intelligence 217, for example correspondingly trained artificial neural network, is executed, the additional vehicle 203 is detected based on the surroundings sensor data from surroundings sensor 205 .
  • Images 207 of surroundings sensor unit 205 are recorded for object recognition.
  • the surroundings sensor unit can comprise, for example, an RGB camera, a stereo camera, a LiDAR system or a radar system.
  • reference images 209 of the respectively identified vehicle 203 are then determined.
  • the reference image recordings 209 can be stored in a corresponding database, for example.
  • method 100 for controlling a traffic situation is executed by data processing unit 202 inside vehicle 201 .
  • the corresponding reference image recordings 209 can be stored in a corresponding database of the data processing unit 202 .
  • the method for controlling a traffic situation can be carried out by an external data processing unit (in FIG 1 not shown), which is operated, for example, within a control center for rail traffic.
  • a corresponding system 200 comprises at least the control center and the data processing unit integrated therein.
  • the reference image recordings 209 can be stored in corresponding databases of the external data processing unit.
  • the reference image recordings 209 can be created individually for each rail vehicle that is within a traffic network that is controlled, for example, by the respective control center and can each represent a certain perspective of the respective rail vehicle.
  • the respective surroundings sensor unit 205 is in a front area or in a rear area of the vehicle 201 arranged.
  • the images 207 recorded by surroundings sensor unit 205 thus show the front area or rear area of the additional vehicle 203.
  • the reference image 209 selected for this purpose shows the identical perspective of the additional vehicle 203 in the embodiment shown and thus also represents the front or rear area of the additional vehicle 203 represent.
  • the surroundings sensor units 205 can be formed at any desired points of the vehicle 201, so that any perspectives of the respective further vehicles 203 can be shown in the images 207.
  • different reference image recordings 209 can be displayed in the corresponding databases for different perspectives of a vehicle.
  • the recorded images 207 and the stored reference images 209 of a vehicle 203 can be adapted or aligned to compare the recorded images 207 and the stored reference images 209 .
  • different feature points of the image recording 207 and the respective reference image recording 209 can be aligned with one another. This can be carried out, for example, by algorithms known from the prior art, such as SIFT, SURF, ORB, FAST and others.
  • the data processing unit 202 is able to select the respectively stored reference image recordings 209 corresponding to the recognized vehicle 203.
  • the data processing unit 202 After selection of the respective reference image recordings 209 suitable for the recognized vehicle 203 , the data processing unit 202 compares the image recordings created based on the surroundings sensor data of the surroundings sensor 205 207 with the respectively stored reference image recordings 209.
  • a discrepancy 211 is detected.
  • a comparison recording 213 can be created in the embodiment shown, in which the deviation 211 is highlighted in each case.
  • the deviation 211 is shown as damage located in the lower left corner of the front or rear area of the further vehicle 203 .
  • the damage to the other vehicle 203 is not shown in the reference images 209, which show the other vehicle 203 in a functional state.
  • the data processing unit 202 is thus able to detect the damage to the other vehicle 203.
  • the deviation 211 determined in each case is then identified as a corresponding property of the additional vehicle 203, in the embodiment shown as damage to the additional vehicle 203.
  • the identified property is then classified and the identified property is classified as traffic-relevant or non-traffic-relevant.
  • Traffic-relevant properties are properties that reduce the roadworthiness of the respective vehicle and can jeopardize a corresponding traffic safety of the traffic situation.
  • the property determined in each case is embodied as damage to the other vehicle 203, the property determined is classified as relevant to traffic.
  • the corresponding traffic control function can then be executed.
  • a warning message or a warning signal can be displayed for this purpose, for example the driver of the vehicle 201 or to the driver of the additional vehicle 203 or to the control center for controlling the rail traffic.
  • the method 100 according to the invention is executed by an external data processing unit, for example in the control center, the speed of the vehicle 201 or the other vehicle 203 and/or the journey of the vehicle 201 or the other vehicle can be stopped 203 by sending corresponding requests to the respective driver or by automatically controlling the vehicles 201, 203.
  • the execution of the respective traffic control function or the selection of the appropriate traffic control function can be based on the classification of the classified properties of the additional vehicle 203 . Depending on the hazard potential of the recognized vehicle characteristics, traffic control functions appropriate to the situation can be selected and executed.
  • the method according to the invention for controlling a traffic situation can be carried out by a suitably trained artificial intelligence 217, for example by a suitably trained artificial neural network.
  • images 207 of a plurality of surroundings sensor units 205 can be taken into account for determining the properties of the other vehicle 203 .
  • an identification number shown as xyz, of the other vehicle 203 can also be seen, for example. According to one specific embodiment, this identification number can be taken into account additionally or alternatively, for example to identify the additional vehicle 203 .
  • the two rail vehicles 201, 203 shown can be moved one after the other on the same track 215.
  • the vehicles 201, 203 can be embodied as autonomous motor vehicles, for example.
  • the vehicles 201, 203 shown can be autonomous rail vehicles that are operated without a driver, or at least partially autonomous vehicles that are at least partially controlled by a corresponding vehicle driver.
  • the data communication between vehicles 201, 203 and an external data processing unit can, in particular, be wireless.
  • the external data processing unit can be in the form of a cloud computer or a cloud server, for example.
  • the execution of the method and in particular the recognition of the property and the classification of the property as traffic-relevant or non-traffic-relevant can be carried out during the operation of the vehicles 201, 203 and immediately after recognizing the respective property.
  • the detection of the property or the classification of the property as traffic-relevant or non-traffic-relevant can be carried out at a later point in time than the object detection of the further vehicle 203 by the vehicle 201 .
  • FIG 2 shows a flowchart of the method 100 for controlling a traffic situation according to an embodiment.
  • a further vehicle 203 is initially recognized based on an image recording 207 of at least one surroundings sensor unit 205 of a vehicle 201 .
  • the recorded image 207 of the additional vehicle 203 is compared with a reference recorded image 209 of the additional vehicle 203 .
  • the image recording 207 and the reference image recording 209 can be adapted or aligned to one another in a method step 111 by carrying out an alignment of feature points of the image recording 207 and the reference image recording 209.
  • a method step 105 at least one discrepancy 211 between the image recording 207 of the additional vehicle 203 and the reference image recording 209 of the additional vehicle 203 is then determined.
  • the determined deviation 211 is identified as a property of the other vehicle 203.
  • the property can be classified as a traffic-relevant property or as a non-traffic-relevant property.
  • a traffic control function is then executed in the event that the determined property of the other vehicle 203 is a traffic-relevant property.
  • FIG. 3 shows a schematic representation of a computer program product 300.
  • FIG 3 shows a computer program product 300, comprising instructions which, when the program is executed by a computing unit, cause the latter to execute the method according to one of the above-mentioned embodiments.
  • the computer program product 300 is stored on a storage medium 301 in the embodiment shown.
  • the storage medium 301 can be any storage medium known from the prior art.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)
EP21202312.1A 2021-01-13 2021-10-13 Procédé de commande d'une situation de circulation Withdrawn EP4029757A1 (fr)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
DE102021200252.8A DE102021200252A1 (de) 2021-01-13 2021-01-13 Verfahren zum Steuern einer Verkehrssituation

Publications (1)

Publication Number Publication Date
EP4029757A1 true EP4029757A1 (fr) 2022-07-20

Family

ID=78134890

Family Applications (1)

Application Number Title Priority Date Filing Date
EP21202312.1A Withdrawn EP4029757A1 (fr) 2021-01-13 2021-10-13 Procédé de commande d'une situation de circulation

Country Status (2)

Country Link
EP (1) EP4029757A1 (fr)
DE (1) DE102021200252A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102006029844B3 (de) * 2006-06-27 2007-10-25 Deutsches Zentrum für Luft- und Raumfahrt e.V. Vorrichtung und Verfahren zur fahrzeugseitigen Überwachung eines schienengebundenen Fahrzeugsverbandes
WO2019092248A1 (fr) * 2017-11-10 2019-05-16 Db Fernverkehr Ag Procédé et système d'analyse de données brutes enregistrées avec un système d'inspection pour l'inspection optique d'un véhicule
EP3647153A1 (fr) * 2018-11-01 2020-05-06 Hitachi Rail Ltd. Système de support de couplage de train

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102014219691A1 (de) 2014-09-29 2016-01-21 Siemens Aktiengesellschaft Verfahren zur Überwachung einer Umgebung einer Schienenfahrbahn und Überwachungssystem

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102006029844B3 (de) * 2006-06-27 2007-10-25 Deutsches Zentrum für Luft- und Raumfahrt e.V. Vorrichtung und Verfahren zur fahrzeugseitigen Überwachung eines schienengebundenen Fahrzeugsverbandes
WO2019092248A1 (fr) * 2017-11-10 2019-05-16 Db Fernverkehr Ag Procédé et système d'analyse de données brutes enregistrées avec un système d'inspection pour l'inspection optique d'un véhicule
EP3647153A1 (fr) * 2018-11-01 2020-05-06 Hitachi Rail Ltd. Système de support de couplage de train

Also Published As

Publication number Publication date
DE102021200252A1 (de) 2022-07-14

Similar Documents

Publication Publication Date Title
DE102015206144B4 (de) Verfahren und Vorrichtung zum sicheren Abstellen eines Fahrzeuges
EP3271231B1 (fr) Procédé et dispositif pour surveiller une trajectoire de consigne à parcourir par un véhicule au sujet de l'absence de collision
EP2464992B1 (fr) Collision surpervision pour véhicule
DE112017006397B4 (de) System für ein Fahrzeug
DE102016115371A1 (de) Verfahren und vorrichtung zur meidung von rückwärtigem querverkehr
WO2020200792A1 (fr) Procédé pour contrôler un capteur de perception de l'environnement d'un véhicule et procédé pour faire fonctionner un véhicule
EP3373268A1 (fr) Procédé de fonctionnement d'un système d'aide à la conduite pour un véhicule sur une chaussée et système d'aide à la conduite
DE102018127059A1 (de) Verfahren zur Überprüfung mindestens eines Umfelderfassungssensors eines Fahrzeugs
AT523834B1 (de) Verfahren und System zum Testen eines Fahrerassistenzsystems
DE102020113611A1 (de) Verfahren und Sicherheitssystem zum Absichern einer automatisierten Fahrzeugfunktion und Kraftfahrzeug
DE102018203063A1 (de) Kollisionsrisiko-Vorhersageeinheit
DE102019105739A1 (de) Verfahren zum zumindest teilautomatisierten Führen eines Kraftfahrzeugs
DE102019205957A1 (de) Verfahren zum kontrollierten Befahren einer Gegenfahrbahn
EP3968213A1 (fr) Procédé de détermination d'un chemin ferroviaire dans une voie ferrée et dispositif de mise en uvre dudit procédé
EP1422111B1 (fr) Procédé et dispositif pour la prédiction de la dynamique de mouvement d'un véhicule et programme pour ordinateur correspondant
DE102019129904A1 (de) Automatische Fahrkompetenzanalyse
EP4029757A1 (fr) Procédé de commande d'une situation de circulation
EP2942253B1 (fr) Véhicule automobile
WO2022157025A1 (fr) Procédé à base d'images pour simplifier une prise de contrôle d'un véhicule automobile depuis l'extérieur du véhicule, système d'assistance et véhicule automobile
DE102017211044A1 (de) Fahrerassistenzsystem zur Kollisionswarnung durch Radwinkelbestimmung benachbarter Fahrzeuge
WO2021213715A1 (fr) Procédé d'approbation de passage
DE102020207990B4 (de) Verfahren zum Betreiben eines Fahrerassistenzsystems und Fahrerassistenzsystem
WO2023202751A1 (fr) Procédé destiné à surveiller si un véhicule a franchi une limite d'une zone dans laquelle le véhicule peut se déplacer, et système d'aide à la conduite
DE102022204086A1 (de) Verfahren zur Ermittlung einer dynamischen Fremdobjekt-Fahrkorridor-Assoziation
EP4086773A1 (fr) Procédé mis en uvre par ordinateur permettant de fournir automatiquement un avis de processus pour processus d'essai

Legal Events

Date Code Title Description
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: THE APPLICATION HAS BEEN PUBLISHED

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

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20230121