CN112445878A - Method, device and vehicle for prediction, storage medium and electronic equipment - Google Patents
Method, device and vehicle for prediction, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN112445878A CN112445878A CN201910804825.1A CN201910804825A CN112445878A CN 112445878 A CN112445878 A CN 112445878A CN 201910804825 A CN201910804825 A CN 201910804825A CN 112445878 A CN112445878 A CN 112445878A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- autologous
- pattern
- driving data
- grid
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000009826 distribution Methods 0.000 claims abstract description 34
- 230000006399 behavior Effects 0.000 claims description 44
- 230000009471 action Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 description 8
- 230000001133 acceleration Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
Images
Classifications
-
- G06Q50/40—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/12—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time in graphical form
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/20—Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
- G08G1/205—Indicating the location of the monitored vehicles as destination, e.g. accidents, stolen, rental
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
- B60R25/30—Detection related to theft or to other events relevant to anti-theft systems
- B60R25/33—Detection related to theft or to other events relevant to anti-theft systems of global position, e.g. by providing GPS coordinates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Traffic Control Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Algebra (AREA)
- Evolutionary Computation (AREA)
- Burglar Alarm Systems (AREA)
- Remote Sensing (AREA)
Abstract
The invention relates to a method for predicting a location of a stop and/or a driving behavior of an autologous vehicle, wherein individual and collective driving data of different vehicles are detected and processed in such a way that a probability distribution pattern for the stop of the autologous vehicle or the driving behavior of the autologous vehicle is determined. The invention also relates to a corresponding device for predicting a stopping point and/or driving behavior of an autologous vehicle, a vehicle comprising the device, a computer-readable storage medium and an electronic device.
Description
Technical Field
The invention relates to a method for predicting a stopping point and/or driving behavior of an autologous vehicle. The invention also relates to a corresponding device for predicting a location of a stop and/or driving behavior of an autologous vehicle, a vehicle comprising the device, a computer-readable storage medium and an electronic device
Background
The stopping location of the vehicle can be determined via different mechanisms for tracking the vehicle. There are, for example, so-called trackers which track the position of the vehicle, for example by means of GPS or other satellite-assisted methods, but also via a wireless mobile communication network.
Tracking vehicles can be for different reasons. Thus enabling, for example, monitoring of fleet vehicles. Tracking the vehicle can be particularly helpful if the vehicle is stolen. There are methods for identifying theft, as shown for example in DE112012004781T5 or EP2229668B1, and methods for tracking, for example by means of a wireless mobile communication network, as disclosed in US 5895436A.
However, methods for tracking vehicles known to date use only data recorded by in-vehicle sensor devices or data provided by means of vehicle-to-vehicle communication. However, all possibilities for tracking vehicles and in particular for identifying vehicle theft have not been exploited. Up to now, a method capable of predicting a place of stay and/or driving behavior of an own vehicle has not been known.
Disclosure of Invention
It is therefore an object of the present invention to provide a corresponding method which allows for predicting a stopping location and/or driving behavior of an autologous vehicle. This object is achieved according to the invention by the features of the independent claims. Advantageous embodiments are the subject matter of the dependent claims.
A method for predicting a stopping location and/or driving behavior of an autologous vehicle is proposed, wherein individual and collective driving data of different vehicles are detected and processed in such a way that a probability distribution pattern for the stopping of the autologous vehicle and/or the driving behavior of the autologous vehicle is determined.
By determining with which probability a vehicle stays in a certain area or moves in a certain area, a conclusion can be drawn as to whether the vehicle is stolen or not.
Current and future vehicles have a plurality of sensor devices and communication mechanisms that allow the vehicle to be located and its direction of travel and driving behavior to be determined. The communication means are usually connected to an external data processing device, for example a data center, for data exchange. The data center collects and processes data to, for example, pre-notice traffic jams, provide routes for navigation systems, and the like. However, the data can also be used to perform the proposed method and provide the results when needed. That is, the proposed method, which is described in detail below, is executed by means of a computer program which performs a corresponding processing based on data obtained from a plurality of vehicles in order to determine a probability distribution pattern.
It is also proposed that the probability distribution pattern is formed as a grid network with mutually adjacent grids, wherein each grid is assigned a probability value with which the autologous vehicle stops in the grid. The value can also be dependent on other factors, for example on the time of day or day of the week. Alternatively or additionally, at least one grid adjacent to the grid on which the autologous vehicle is stopping is assigned a probability value with which the autologous vehicle moves into the grid or into the region comprised by the grid. With the large amount of data which forms the basis for the evaluation and thus for the grid network, it can also be determined if the destination of travel is unknown: whether the vehicle is behaving in a conventional manner.
Thus, by using a grid network made up of many adjacent grids, it is possible to determine more accurately: whether the monitored vehicle is still in a region common to its driving behavior, i.e. is standing or moving there. If the vehicle is far away from the area, i.e. driven into a grid with a low probability, this can indicate that the vehicle is stolen, for example.
It is further proposed that the probability distribution pattern is determined on the basis of collective driving behavior, with at least one or a combination of the following parameters: location, day of week, time of day, current environmental information. The driving behaviour of a vehicle, i.e. its place of stay and direction of movement, can vary from country to country, city to city, even city to city, village to village. It is therefore expedient when creating a pattern to also take into account the location at which the vehicle is located or in which the vehicle is located or is moving. The day of the week and time of day, and combinations thereof, also indicate where the vehicle should currently be. Environmental information, such as construction sites or traffic jams, can also have an effect on the pattern, since they are, for example, bypassed and the vehicle is therefore moved into areas which do not normally correspond to its normal driving behavior.
Furthermore, it is proposed that driver-specific driving data for the self-vehicle are additionally detected for the pattern or a region thereof and are assigned to the pattern as conventional self-driving data. By using additional data relating to the driving behavior of the driver of the own vehicle, it can be better predicted: whether the monitored vehicle or the own vehicle shows regular driving behavior. On the one hand, the probability distribution obtained by the collective driving behavior when monitoring a specific vehicle to be monitored by paying attention to driver-specific driving data can be individually adapted to the own vehicle. On the other hand, driver-specific driving data can be compared with collective driving data, and regular or irregular driving behavior can be identified therefrom.
It is also proposed that the driving data are detected periodically and the probability distribution pattern is updated periodically. Thus, the pattern can be changed together with the behavior of the vehicle and the driver, thereby always displaying a very accurate and current probability distribution for the stop of the own vehicle and/or the driving behavior of the own vehicle.
Furthermore, a method using deep learning and artificial intelligence techniques is proposed for generating the probability distribution pattern. By using a method that is capable of both processing large amounts of data and learning from the data, realistic and current probability distribution patterns can be provided.
It is also proposed that current autopilot data of a preset autologous vehicle are detected and compared with a probability distribution pattern, and that a theft is assumed and a preset action is carried out if the driving data show that the autologous vehicle is staying in an area of the pattern with a probability above or below a preset threshold value. Alternatively, if the driving data shows that the own vehicle moves toward an area of the pattern having a probability higher or lower than a preset threshold, it can be assumed that it is stolen and a preset action is performed.
By the following possibilities: comparing the current driving data of the own vehicle with a pattern generated from a very large amount of driving data, which in turn can give a probability distribution of where the own vehicle should stay or in which direction it should move, provides a new possibility for theft monitoring.
Advantageously, the threshold is determined based on at least one or a combination of the following parameters: day of the week, time of day, vehicle make, vehicle model, driver-specific driving behavior, current road segment information such as construction site or traffic congestion, available road segment data, for example from a navigation device. To avoid false alarms or undesired actions, the threshold value can be determined based on a number of different parameters. The parameter can be a typical collective behavior, but can also be a typical individual behavior of the autologous driver, which can include driving at a particular time of day and driving behavior like a characterized acceleration or vehicle setting. The impact of the vehicle make or model can also be incorporated into the theft probability. Also, parameters caused by, for example, the environment are focused. Here, a detour due to traffic congestion or a construction site can lead to a lower probability of driving into the grid, but does not constitute a theft due to the detour. By providing a combination and concatenation of the available data and forming a theft probability therefrom, the accuracy of identifying the theft can be improved.
It is furthermore proposed that, if conventional driving data are additionally detected, the conventional driving data are compared with current autopilot driving data, and theft is detected if a deviation between the conventional driving data and the current driving data exceeds or falls below a preset threshold value. Each driver has an individual driving behavior which can be characterized, for example, by the type of acceleration, the type of activation after a stop, the type of overtaking, the type of adherence or exceeding of a speed limit, setting vehicle parameters such as seat, mirror, radio, type of volume, type of transmitter, for example, and the like. Since a specific, predefinable deviation of the current driving data from the expected conventional driving data, at least: the intended driver is not in the vehicle. Thus enabling the identification of theft.
It is furthermore proposed that the preset action is one or a combination of the following cases: and (3) sending the message: "the autologous vehicle may be stolen" to authorized personnel, such as the owner, driver, security service provider or also the police or persons thereof; marking the vehicle as stolen, for example by means of a digital mark or token; intervening with vehicle control, such as triggering an alarm or notification or disabling vehicle movement. Here, the intended user can be asked in advance: the system determines whether it is reasonable to have "theft". If the intended user denies the identification of the theft, for example by acting on his smartphone, no action is taken. If he confirms this, he can take appropriate action depending on the equipment of the vehicle, the current settings of the vehicle, the place where the vehicle is located or the direction of movement of the vehicle, in order to protect the vehicle as quickly as possible.
In a further aspect, the invention proposes a device for predicting a stopping location and/or a driving behavior of an autologous vehicle, wherein the device is designed to detect and process individual and collective driving data of different vehicles in such a way that a pattern of probability distributions is determined for the stopping of the autologous vehicle and/or the driving behavior of the autologous vehicle.
In addition, the invention proposes a vehicle comprising an apparatus for predicting a stopping place and/or driving behavior of an autologous vehicle as described above.
Furthermore, the invention proposes a computer-readable storage medium comprising executable instructions, wherein the instructions, when executed, cause a computer to perform the method for predicting a stopping location and/or driving behavior of an autologous vehicle as described above.
Furthermore, the invention proposes an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the computer program is executed by the processor to perform the method for predicting a stopping location and/or driving behavior of an autologous vehicle as described above.
Further features and advantages of the invention emerge from the following description of an embodiment of the invention with the aid of the drawing which shows details according to the invention and from the claims. The individual features can be implemented individually or in any combination in the variants of the invention.
Drawings
Preferred embodiments of the invention are explained in detail below with the aid of the drawing.
Fig. 1 shows a schematic view of a grid network according to a first embodiment of the present invention.
Fig. 2 shows a schematic diagram of a grid network according to another embodiment of the present invention.
Detailed Description
In the following description of the figures, identical elements or functions are provided with the same reference numerals.
In principle, driving data are to be understood as meaning all data which represent the location of the vehicle, but also the direction of movement or the driving behavior of the vehicle.
The basic design scheme of the invention is as follows: based on the large amount of data periodically provided by the vehicle, probability distribution patterns 1-6 for the stay of the own vehicle as shown in fig. 1 and/or the driving behavior of the own vehicle as shown in fig. 2 are generated, i.e., predicted.
In an advantageous embodiment, the pattern can be provided as a grid network. It is advantageous here to select polygons which are arranged next to one another as a mesh shape, since there is a defined boundary surface with the next adjacent mesh. The more area provided, the more accurate the grading in the normal driving direction. In an advantageous embodiment, the grid is formed as a pentagon, hexagon or octagon.
The pattern can be generated based on collective driving data, but also based on individual driving data and combinations thereof. The collective driving data is driving data determined based on a large amount of data of the vehicle. Thus, for example, the regular direction of travel of the vehicle at a particular time of day can be determined. In fig. 2, this is shown as follows: the grid adjacent to the grid 0 in which the self-vehicle is located in the normal driving direction is provided with corresponding probability values or indices 1, 2, 4, 5, which represent the probability of the self-vehicle entering a certain grid according to the probability distribution obtained from the collective data, wherein the grid with indices 1 and 2 is identified as the next grid that is likely to enter, and the grids with indices 4 and 5 are identified as the next grid that is less likely to enter up to extremely unlikely to enter. Based on this recognition, in the case where the own vehicle moves from its grid 0 into a grid with an index of 4 or 5, it can be recognized that, for example, a suspicious behavior that the vehicle is stolen can be inferred.
Furthermore, the usual stopping points of the vehicle can be determined by evaluating the collective driving data and the unlikely to impossible stopping points, which is illustrated in fig. 1 by the indices 1 to 6, wherein index 1 represents a very likely or usual stopping point and index 6 represents a very unlikely stopping point. The evaluation divisions mentioned here are only visible by way of example. Another evaluation division can also be used.
A region without an index is a region for which there is no data or sufficient data to give an explanation about the probability of stay. However, by applying mathematical methods or models accordingly, the region between two meshes with estimated probability can be identified as a probability, for example, by means of extrapolation, for example, as an average value in adjacent meshes.
By using methods applying deep learning or machine learning, so-called artificial intelligence, grid networks and meshes with associated probability distributions can be generated on the basis of large amounts of data and can be updated and improved permanently.
One application of the method is: potential theft is identified. In this case, the current autopilot data of the pre-set autologous vehicle are detected and compared with a pattern of probability distributions 1-6 determined from the collective driving data and (possibly) driver-specific driving data. If the driving data shows that the own vehicle stays in the area of the pattern having a probability higher than the preset threshold or the own vehicle moves toward the area of the pattern having a probability higher than the preset threshold, theft is deemed and the preset action is performed.
The threshold value can be a value that does not exceed a preset value for the index or probability distribution 1-6 of the grid, wherein in this embodiment the highest index gives a high probability of an unconventional stopping location or unconventional direction of travel. Thus, exceeding the threshold is an increase in the probability of theft or irregular driving. Mention is made explicitly here of: the evaluation and determination of the threshold values is related to the respective embodiment and the criteria preset by the person skilled in the art, so that the designation or index etc. chosen here is merely to illustrate how the evaluation can be performed.
In the case where the own vehicle does not behave as it would according to the determined pattern and probability distribution, theft can be presumed and an action performed. Such an action can be performed immediately or only after the system reinsurance, for example at the owner or driver of the own vehicle, who can transmit a confirmation to the system, for example via his smartphone, about whether he agrees with his identification of the theft. Thus, false alarms or false actions can be avoided.
Likewise, it can be determined based on typical behavior of the driver of the autologous vehicle, known for example by in-vehicle sensor means: whether the driver is the intended driver. If this is not the case, theft can be inferred. To avoid false alarms, multiple parameters can be incorporated into the evaluation in a combined manner, so that some type of theft monitor is formed. Theft can be identified if the plurality of parameters are significantly different from the expected parameters. Here, weighting of the parameters can be performed. Such parameters can be both the current stopping location, the direction of travel, but also travel time, acceleration and deceleration behavior, use of interior and exterior lights, seat configuration, air conditioning behavior. The parameters can be determined individually for each driver and compared with currently detected parameters or settings.
Actions that can be performed at the time of a potential theft can be: sending a message that the autologous vehicle is likely stolen to authorized personnel such as the owner or driver; the vehicle is electronically marked as stolen, for example by means of a corresponding marking; or else it is possible to intervene in the vehicle control, for example by outputting an alarm or a notification or intervening in the actuator system, for example in deceleration.
In principle, as already mentioned, further parameters for determining the probability distribution pattern can be incorporated into the evaluation of the data. Thus, for example, an increased probability of theft for a vehicle of a particular brand or model or in a particular area, such as an urban area, can be incorporated into the determination. Time of day or day of week can also be incorporated into the evaluation.
Claims (23)
1. A method for predicting a stopping location and/or driving behavior of an autologous vehicle, wherein individual and collective driving data of different vehicles are detected and processed in such a way that a pattern of probability distributions (1-6) is determined for the stopping of the autologous vehicle and/or the driving behavior of the autologous vehicle.
2. The method according to claim 1, wherein the pattern of probability distributions (1-6) is formed as a grid network with meshes adjacent to each other,
-each grid is assigned a probability value with which the autologous vehicle stops in the grid, and/or
-at least one grid adjacent to the grid on which said autologous vehicle is staying is assigned a probability value with which said autologous vehicle moves into the grid.
3. The method of one of the preceding claims, wherein the pattern of probability distributions (1-6) is determined based on collective driving behavior, the pattern of probability distributions having at least one or a combination of the following parameters: location, day of week, time of day, current environmental information.
4. Method according to one of the preceding claims, wherein driver-specific driving data for the autologous vehicle are additionally detected for the pattern or a region thereof and assigned to the pattern as conventional autologous driving data.
5. Method according to one of the preceding claims, wherein the driving data are detected periodically and the pattern of the probability distributions (1-6) is updated periodically.
6. The method according to one of the preceding claims, wherein the pattern of probability distributions (1-6) is generated by means of deep learning and artificial intelligence techniques.
7. Method according to one of the preceding claims, wherein current autopilot data of a preset autologous vehicle are detected and compared with the pattern of the probability distribution (1-6) and if the driving data are
-displaying said autologous vehicle stopping in a region of said pattern having a probability above or below a preset threshold, or
-the autologous vehicles moving towards the direction of the regions of the pattern having a probability above or below a preset threshold,
the theft is identified and a preset action is performed.
8. The method of claim 7, wherein the threshold is determined based on at least one or a combination of the following parameters: day of the week, time of day, vehicle make, vehicle model, driver specific driving behavior, current road segment information, available road segment data.
9. Method according to claim 7 or 8, wherein if regular driving data is additionally detected, said driving data is compared with current autologous driving data, and theft is deemed if the deviation between regular driving data and current driving data exceeds or falls below a preset threshold.
10. The method of claim 7, 8 or 9, wherein the preset action is one or a combination of:
-sending a message: sending the 'possible stolen self vehicle' to an authorized person; marking the vehicle as stolen; the control of the vehicle is intervened,
wherein the intended user can be asked in advance: and determining whether the theft is reasonable.
11. An apparatus for predicting a stopping location and/or driving behavior of an autologous vehicle, wherein the apparatus is configured for detecting and processing individual and collective driving data of different vehicles such that a pattern of probability distributions (1-6) is determined for the stopping of the autologous vehicle and/or the driving behavior of the autologous vehicle.
12. The device according to claim 11, wherein the pattern of probability distributions (1-6) is formed as a grid network with meshes adjacent to each other,
-each grid is assigned a probability value with which the autologous vehicle stops in the grid, and/or
-at least one grid adjacent to the grid on which said autologous vehicle is staying is assigned a probability value with which said autologous vehicle moves into the grid.
13. The apparatus according to one of claims 11 to 12, wherein the pattern of probability distributions (1-6) is determined based on collective driving behavior, the pattern of probability distributions having at least one or a combination of the following parameters: location, day of week, time of day, current environmental information.
14. The device according to one of claims 11 to 13, wherein the device is further configured for additionally detecting driver-specific driving data for the autologous vehicle for the pattern or a region thereof and assigning it as conventional autologous driving data to the pattern.
15. The device according to one of claims 11 to 14, wherein the device is further configured for periodically detecting the driving data and periodically updating the pattern of probability distributions (1-6).
16. The apparatus according to one of claims 11 to 15, wherein the pattern of probability distributions (1-6) is generated by means of deep learning and artificial intelligence techniques.
17. The device according to one of claims 11 to 16, wherein the device is further configured for detecting and comparing current autopilot data of a preset autologous vehicle with the pattern of probability distributions (1-6) and if the driving data
-displaying said autologous vehicle stopping in a region of said pattern having a probability above or below a preset threshold, or
-the autologous vehicles moving towards the direction of the regions of the pattern having a probability above or below a preset threshold,
the theft is identified and a preset action is performed.
18. The apparatus of claim 17, wherein the threshold is determined based on at least one or a combination of the following parameters: day of the week, time of day, vehicle make, vehicle model, driver specific driving behavior, current road segment information, available road segment data.
19. The apparatus according to claim 17 or 18, wherein if regular driving data is additionally detected, said driving data is compared with current autologous driving data, and if the deviation between regular driving data and current driving data exceeds or falls below a preset threshold, theft is declared.
20. The apparatus of claim 17, 18 or 19, wherein the preset action is one or a combination of:
-sending a message: sending the 'possible stolen self vehicle' to an authorized person; marking the vehicle as stolen; the control of the vehicle is intervened,
wherein the intended user can be asked in advance: and determining whether the theft is reasonable.
21. Vehicle comprising an arrangement for predicting a stopping location and/or driving behavior of an autologous vehicle according to one of claims 11 to 20.
22. Computer-readable storage medium comprising executable instructions, wherein the instructions, when executed, cause a computer to perform a method for predicting a stopping location and/or driving behavior of an autologous vehicle according to one of claims 1 to 10.
23. Electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the computer program is executed by the processor to perform the method for predicting a stopping location and/or driving behavior of an autologous vehicle according to one of claims 1 to 10.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910804825.1A CN112445878A (en) | 2019-08-29 | 2019-08-29 | Method, device and vehicle for prediction, storage medium and electronic equipment |
DE102020122638.1A DE102020122638A1 (en) | 2019-08-29 | 2020-08-31 | Method for predicting a location and / or driving behavior of an ego vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910804825.1A CN112445878A (en) | 2019-08-29 | 2019-08-29 | Method, device and vehicle for prediction, storage medium and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112445878A true CN112445878A (en) | 2021-03-05 |
Family
ID=74565017
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910804825.1A Pending CN112445878A (en) | 2019-08-29 | 2019-08-29 | Method, device and vehicle for prediction, storage medium and electronic equipment |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112445878A (en) |
DE (1) | DE102020122638A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AT524868B1 (en) * | 2021-05-25 | 2022-10-15 | Avl List Gmbh | METHOD OF PREDICTIVE ESTIMATING A HISTORY |
-
2019
- 2019-08-29 CN CN201910804825.1A patent/CN112445878A/en active Pending
-
2020
- 2020-08-31 DE DE102020122638.1A patent/DE102020122638A1/en active Pending
Also Published As
Publication number | Publication date |
---|---|
DE102020122638A1 (en) | 2021-03-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10997849B1 (en) | Methods of facilitating emergency assistance | |
US11380193B2 (en) | Method and system for vehicular-related communications | |
US11294370B2 (en) | Determining driver engagement with autonomous vehicle | |
CN104103188B (en) | Inputted based on vehicle community provides the apparatus and method of customized information to vehicle user | |
KR102226419B1 (en) | Electronic device for vehicle, and method for operating thereof | |
WO2018220971A1 (en) | Communication control device, communication control method, and computer program | |
CN101655380B (en) | Method for determining a property of a driver-vehicle-environment state | |
CN109933062A (en) | The alarm system of automatic driving vehicle | |
US11170639B2 (en) | Transportation threat detection system | |
CN104730949A (en) | Affective user interface in an autonomous vehicle | |
CN104859662A (en) | Fault handling in an autonomous vehicle | |
Saiprasert et al. | Driver behaviour profiling using smartphone sensory data in a V2I environment | |
CN101648550A (en) | Method for allowing or suppressing a request for presenting information to a user | |
CN112445878A (en) | Method, device and vehicle for prediction, storage medium and electronic equipment | |
CN110223535A (en) | Crash protection based on connection equipment | |
KR20220089138A (en) | Road Dangerous Object Recognition Apparatus and Method | |
CN116834655A (en) | Dangerous early warning method and device and vehicle | |
JP7233299B2 (en) | Driving behavior control method and driving behavior control device | |
WO2018022069A1 (en) | Determining driver engagement with autonomous vehicle | |
CN108025747B (en) | Enhanced lane passing | |
JP7293077B2 (en) | Traffic control system and information provision method | |
US20230392948A1 (en) | Vehicle communication and navigation systems for road safety | |
JP2021189597A (en) | Accident prediction device and accident prediction method | |
JP2024006480A (en) | Terminal and information processing device | |
CN115759316A (en) | User driving behavior monitoring method, device, medium and equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |