Method, computer-readable medium, system, and vehicle for requesting a predicted route from a backet-end

By determining a set of decision points in the vehicle and dynamically requesting predicted routes, the problem of delay and unnecessary requests when the vehicle requests predicted routes is solved, faster and more accurate route prediction is achieved, and communication channel load is reduced.

CN119032255APending Publication Date: 2024-11-26BAYERISCHE MOTOREN WERKE AG
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380033657.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-05-16
Filing Date
2023-03-01
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

In the prior art, delays may occur when a vehicle requests a predicted driving route from a backend server, and unnecessary requests and data transmissions increase the load on the communication channel.

Method used

By determining a set of decision points in the vehicle and dynamically requesting and receiving predicted driving routes based on these decision points, reducing unnecessary requests and data transmissions, achieving faster and more flexible route prediction. The method includes receiving a predicted route and a set of decision points, filtering the decision points according to probability, transmitting only decision points with importance above the threshold, and requesting updated routes and a set of decision points after passing the decision point.

Benefits of technology

It effectively reduces the number of requests and data volumes to the backend server, improves the speed and accuracy of route prediction, avoids unnecessary communication channels, and ensures that the vehicle can quickly receive the current predicted route and navigate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119032255A_ABST
    Figure CN119032255A_ABST
Patent Text Reader

Abstract

The invention relates to a method for requesting a predicted route by a vehicle from a back-end server, the method comprising: receiving, by the vehicle from the back-end server, a predicted route and a set of decision points for the predicted route; determining that a vehicle passes through one decision point in the decision point set; transmitting a request from the vehicle to a back-end server to provide another predicted route and another set of decision points after the vehicle travels through the decision points; and receiving, by the vehicle from the back-end server, the other predicted route and the other set of decision points.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a method for requesting a predicted route from a back-end server by a vehicle. The present invention also relates to a computer-readable medium for requesting a predicted route from a back-end server by a vehicle, a system for requesting a predicted route from a back-end server by a vehicle, and a vehicle comprising the system for requesting a predicted route from a back-end server by a vehicle. Background Art

[0002] Current vehicles can request a predicted route from a backend server and provide the predicted route to the vehicle user. Delays may occur when providing the predicted route to the vehicle user. Summary of the invention

[0003] Therefore, the object of the present invention is to provide a predicted driving route to a vehicle more efficiently. In particular, the object of the present invention is to request a predicted driving route from a backend server more quickly and / or more flexibly.

[0004] This object is achieved by the features of the independent claim. Advantageous embodiments and developments of the invention are disclosed in the dependent claims.

[0005] According to a first aspect, the present invention is characterized by a method for requesting a predicted route from a backend server by a vehicle. The method may be a computer-implemented method and / or a controller-implemented method. The vehicle may be a land vehicle. For example, the vehicle may be a motor vehicle or a motorcycle. The backend server may be a vehicle-external server coupled to the vehicle via one or more communication channels. The predicted route may be a navigation route of the vehicle, which is expected to be traveled by a vehicle user. Preferably, the predicted route is the vehicle navigation route that the vehicle user is most likely to travel. The method includes receiving, by the vehicle from the backend server, a predicted route and a set of decision points for the predicted route. In addition, the method may receive a probability of the predicted route. Additionally or alternatively, the method may receive multiple predicted routes and / or a set of decision points about the multiple predicted routes. If the method receives multiple predicted routes, the method may additionally receive a probability of each predicted route. In addition, the method may additionally or alternatively transmit one or more predicted routes from the backend server to a mobile terminal device. The mobile terminal device may provide the one or more predicted routes to the vehicle user. The predicted route can be provided to the user of the mobile terminal device and / or the vehicle user according to the predicted probability of the route. If the predicted probability of the route exceeds a predetermined probability threshold, the method can provide the predicted route to the user.

[0006] The method includes determining, by the vehicle, to pass through a decision point in the set of decision points. In addition, the method includes transmitting, from the vehicle to a backend server, a request for providing another predicted route and another set of decision points after the vehicle passes through the decision point. Finally, the method may include receiving, by the vehicle, the another predicted route and the another set of decision points from the backend server.

[0007] Advantageously, the method can dynamically request one or more predicted vehicle routes from the backend server based on the passing of the decision point. Thus, the vehicle can automatically receive the current predicted route. Thus, the vehicle can effectively control the request of the predicted route from the backend server. Unnecessary requests to the backend server can be effectively avoided. In addition, the amount of data required for the communication channel to request the predicted route can be effectively reduced. For example, the received predicted route can be provided to the navigation system. The navigation system can therefore automatically perform destination navigation to the navigation destination using the received predicted route via the provided route.

[0008] According to an advantageous embodiment of the invention, the decision point may be a path point at which the driving route of the vehicle diverges. The request for the predicted route can thereby be effectively controlled.

[0009] According to another advantageous embodiment of the present invention, the set of decision points may be determined by the backend server according to one or more historical trajectories of the vehicle user, thereby effectively determining the set of decision points.

[0010] According to another advantageous embodiment of the invention, an importance may be associated with each decision point and / or the set of decision points may include one or more decision points whose importance exceeds a predetermined minimum importance threshold. The importance may be an importance value or an importance parameter. Thereby, the set of decision points may be efficiently determined. In particular, the number of decision points of the set of decision points may be efficiently determined. Addition of unimportant decision points to the set of decision points may be effectively prevented. Furthermore, unnecessary transmission of unimportant decision points from the backend server to the vehicle may be avoided.

[0011] According to another advantageous embodiment of the invention, the method may further comprise: providing the predicted route as a navigation route suggestion to the vehicle user, and / or providing the other predicted route as another navigation route suggestion to the vehicle user, and / or activating the vehicle's navigation using the predicted route and / or the other predicted route in response to an operational input from the vehicle user accepting the navigation route suggestion and / or the other navigation route suggestion. The predicted route received by the vehicle can thereby be efficiently processed. An inactivated navigation system of the vehicle can be automatically activated by route guidance using the predicted route, and / or a suggestion to activate route guidance by the user can be provided to the vehicle user.

[0012] According to another advantageous embodiment of the invention, it can be determined that a decision point has been passed if the vehicle first enters a first predetermined circle around the decision point and then exits a second predetermined circle around the decision point, wherein preferably the radius of the first circle is smaller than the radius of the second circle, and wherein preferably the vehicle receives the radius of the first circle and the radius of the second circle for each decision point from the backend server along with the set of decision points. Passing by the decision point can be determined effectively by the vehicle. Inaccuracies in the determination of the vehicle position can be effectively avoided by using circles. Passing by the decision point can be determined more reliably and / or more accurately.

[0013] According to another advantageous embodiment of the invention, the method may comprise: transmitting a time-controlled request from the vehicle to the backend server for providing another predicted route and another set of decision points if the last request exceeds a predetermined time period. And / or the method may comprise: blocking a time-controlled request from the vehicle to the backend server for providing another predicted route and another set of decision points if the distance of the vehicle to the next decision point of the predicted route is below a predetermined distance threshold and / or the time period to reach the next decision point is below a predetermined time threshold. Thereby, requests for decision points and / or one or more predicted routes may be effectively controlled.

[0014] According to another aspect, the invention features a computer-readable medium for requesting a predicted route by a vehicle from a backend server, wherein the computer-readable medium includes instructions that, when executed by a computer or controller, perform the method described above.

[0015] According to another aspect, the invention features a system for requesting a predicted route by a vehicle from a backend server, the system being configured to perform the above method.

[0016] According to another aspect, the invention features a vehicle including the above-described system for requesting, by the vehicle, a predicted route from a backend server.

[0017] Further features of the invention are apparent from the claims, the drawings and the description of the drawings. All features and feature combinations mentioned above in the description and below in the description of the drawings and / or shown individually in the drawings can be used not only in the respectively given combination but also in other combinations or individually. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The preferred embodiment of the present invention is described below with the aid of the accompanying drawings. Further details, preferred embodiments and extensions of the present invention are obtained from this. The accompanying drawings are as follows:

[0019] Figure 1 An exemplary method for requesting a predicted route from a backend server by a vehicle is shown;

[0020] Figure 2 An exemplary scenario for determining a drive-through decision point is shown;

[0021] Figure 3 showing a first scenario with a predicted route and decision points; and

[0022] Figure 4 A second scenario is shown with a predicted route and decision points. DETAILED DESCRIPTION

[0023] Figure 1 An exemplary method 100 for requesting a predicted route from a backend server by a vehicle is shown in detail. Specifically, if the vehicle user is not using the vehicle's navigation system, the method 100 can request the predicted route from the backend server. After each trip using the vehicle, the vehicle can transmit the vehicle trajectory that has been traveled to the backend server. The vehicle trajectory that has been traveled can include a list of vehicle locations determined by means of a satellite-based navigation system. In addition, the vehicle can transmit a timestamp of the start of the trip, a timestamp of the end of the trip, and / or a timestamp of each vehicle location to the backend server. The backend server can use the time information and / or a database of historical vehicle route information to determine decision points and / or predict the vehicle route.

[0024] The method 100 may transmit a request, in particular a request message, from the vehicle to the backend server for providing the predicted route and decision point set. For example, the request may be transmitted at the beginning of the journey and / or during the journey of the vehicle. The request may include the current vehicle position and / or the vehicle trajectory. For example, the vehicle trajectory may include the trajectory that has been traveled since the beginning of the journey and / or a predetermined number of positions of the vehicle trajectory that has been traveled, such as the last 1, 2, 3, 4, ..., n positions.

[0025] The method 100 may receive 102 one or more predicted routes, the probability of each predicted route and / or a set of decision points for the one or more predicted routes from a backend server by the vehicle. Preferably, the vehicle receives one predicted route, i.e., the most likely route for the vehicle. If the method 100 receives multiple predicted routes, the multiple predicted routes include the most likely route and one or more alternative routes to the most likely route. In addition, the backend server may transmit the one or more predicted routes to a mobile terminal device of one or more users of the vehicle. The mobile terminal device may receive the one or more predicted routes and provide them to one or more users of the vehicle. Thus, the method may automatically inform the one or more users of the vehicle of the one or more predicted routes.

[0026] The set of decision points may be determined by the backend server using historical traveled routes. For example, the backend server may determine the location of a path point from the historical traveled routes of the user and / or vehicle, at which the historical traveled route diverges. A path point - at which the historical traveled route diverges - may be a decision point in the set of decision points. Furthermore, the backend server may calculate an importance, in particular an importance value, for each decision point. The backend server may filter the decision points using importance. For example, the backend server may only add decision points with a predetermined minimum importance to the set of decision points. Additionally or alternatively, a maximum number of decision points for the set of decision points may be predetermined. If the maximum number of decision points for the set of decision points is predetermined, decision points with the greatest importance may be determined up to the maximum number and added to the set of decision points.

[0027] Preferably, the importance of a decision point indicates the probability of the most likely route change when passing the decision point. The following formula is used here:

[0028]

[0029] Among them, p(out_path i ) is through the path out_path under the condition that the decision point EP has been reached i The conditional probability of leaving the decision point EP; and

[0030] If the path out_path is passed i The most likely route change after passing the decision point is important_update(out_path i ) is 1, otherwise 0. Preferably, the minimum probability of the most likely route is taken into account, from which the navigation system of the vehicle is automatically started, for example. In this case, if out_path iThe minimum probability is reached only after passing the decision point or passing through out_path i There is also an important change if the minimum probability is no longer reached after passing the decision point.

[0031] Furthermore, the importance of the decision point defined above can be multiplied by the probability of reaching the decision point from the current vehicle position.

[0032] Alternatively, the importance of a decision point indicates what information gain can be expected in terms of the predicted route by utilizing that decision point.

[0033] For example, the importance of a decision point can be calculated using the expected value of information gain as follows:

[0034]

[0035] in,

[0036] X is a decision point;

[0037] IG is information gain;

[0038] D X is the set of possible driving decisions X; driving d is defined by the incoming and outgoing segments at a fork (such as an intersection or a roundabout);

[0039] P(d): The probability of passing the decision point X from the current vehicle position;

[0040] R: route probability at the current vehicle position;

[0041] R|d: route probability after passing d decision points X;

[0042] H: Entropy.

[0043] Here the sum of the probabilities of all driving through the decision point Corresponds to the probability of passing decision point X in any way starting from the current vehicle position.

[0044] The backend server may additionally transmit the location for each decision point in the set of decision points to the vehicle. The vehicle may receive the location of each decision point along with the set of decision points.

[0045] Instead of calculating the importance of the decision points and filtering the decision points based on this, the following simple method can be used instead. Only those predicted routes whose probability exceeds a minimum probability of, for example, 0.1 are considered when calculating the decision points. Alternatively, only the most likely predicted routes are considered when calculating the decision points up to a maximum number of routes. Both methods ensure that only the most important decision points are considered.

[0046] Additionally, method 100 may determine 104 that the vehicle has passed a decision point from the set of decision points. Figure 2 An exemplary scenario 200 for determining the passing decision point EP is shown in detail. Figure 2 (not shown in the figure) if the vehicle first enters circle K1 and then exits circle K2 along the driving route of the vehicle, the decision point EP can be considered to be passed in the method 100. Circle K1 and circle K2 are preferably circles centered on the decision point EP. In addition, the radius of circle K1 is smaller than the radius of circle K2. The radius of circle K1 can be 90m, for example, and the radius of circle K2 can be 100m, for example. The radii of circles K1 and K2 can be predetermined separately for each decision point. Alternatively, the radii of circles K1 and K2 for all decision points can be the same. The two circles K1 and K2 can describe a hysteresis function, which prevents entering a circle in the case of inaccurate GNSS signals and being erroneously identified as leaving the circle within a short time interval by the inaccurate GNSS signals. Transmitting a separate radius for each decision point can have the following advantages: multiple decision points can be merged into one decision point, whose circles K1 and K2 have larger radii. For example, the number of decision points may be reduced by increasing the radius of the circles K1 and K2 of a decision point to merge adjacent decision points into one decision point.

[0047] In addition, the method 100 may transmit 106 from the vehicle to the backend server a request for providing another predicted route and another set of decision points after the decision point is driven past by the vehicle. The method 100 may transmit from the vehicle to the backend server a request for providing another predicted route and another set of decision points after each other decision point in the set of decision points is driven past by the vehicle. The method 100 may stop transmitting from the vehicle to the backend server a request for providing another predicted route and another set of decision points if a predetermined maximum number of requests issued to the backend server is exceeded since the start of the drive with the vehicle and / or a predetermined maximum time has elapsed since the start of the drive with the vehicle.

[0048] If the decision point set includes multiple decision points along one or more predicted routes of the vehicle, the vehicle may transmit a request from the vehicle to the backend server for providing another predicted route and another set of decision points after each time the vehicle passes a decision point. This may result in frequent, unnecessary requests from the vehicle to the backend server, such as requests within a few seconds. In order to reduce the number of times the vehicle sends requests to the backend server, the backend server can reduce the number of decision points in the decision point set by increasing the importance threshold and the backend server only adds decision points whose importance is higher than the increased importance threshold to the decision point set. Additionally or alternatively, the vehicle may filter decision points from the decision point set based on their importance. For example, the vehicle can only transmit a request to the backend server if the importance of the decision point passed by has a predetermined minimum importance.

[0049] Furthermore, the number of decision points can be reduced by considering only the decision points with the largest distance from the current vehicle position. Alternatively, the decision points with the smallest distance from the current vehicle position can be determined up to a maximum number.

[0050] Furthermore, the number of requests after a decision point can be reduced by defining a predetermined minimum duration (e.g., 1, 2, 3, ... minutes) between transmitting two requests from the vehicle to the backend server. Transmitting a request from the vehicle to the backend server is delayed until the predetermined minimum duration has elapsed since the vehicle issued the previous request to the backend server.

[0051] Furthermore, if the vehicle deviates from the predicted route at a location where no decision point in the set of decision points exists, the method 100 may transmit a request from the vehicle to the backend server to provide another predicted route and another set of decision points.

[0052] Furthermore, the method 100 may transmit one or more requests for providing another predicted route and another set of decision points from the vehicle to the backend server in a time-controlled manner. For example, the vehicle may transmit requests to the backend server in a time-controlled manner at periodic intervals, for example every 10 minutes. The time-controlled request by the vehicle to provide another predicted route and another set of decision points has the advantage that even in the case of a small number of decision points in the decision point set, requests can be regularly transmitted to the backend server and the current predicted route and the current set of decision points can thereby be transmitted from the backend server to the vehicle. The vehicle can therefore always receive the current predicted route and the current set of decision points from the backend server. The current predicted route can be provided to the vehicle user, the navigation system of the vehicle and / or the mobile terminal device of the vehicle user. The current set of decision points can be used to effectively control the timing for further requests based on the decision points of the current set of decision points.

[0053] In addition, the method 100 may prevent one or more time-controlled requests before the decision point is passed by the vehicle. If the vehicle is closer to the decision point than a predetermined distance, such as 1000 m, the method 100 may prevent the transmission of a time-controlled request from the vehicle to the backend server. Additionally or alternatively, if the estimated time until the decision point is reached is less than a predetermined threshold, such as less than 3 minutes, the method 100 may prevent the transmission of a time-controlled request from the vehicle to the backend server. To calculate the estimated time, for example, the length of a straight line or route from the vehicle's current location to the decision point may be used to estimate how long it is expected to take until the decision point is reached.

[0054] By preventing one or more time-controlled requests, time-controlled requests from the vehicle to the backend server may be prevented for a longer period of time (e.g., 10, 20, 30, ..., 50 minutes), even if the vehicle does not pass through a decision point. This may occur, for example, when there are multiple decision points near the vehicle route (i.e., within a predetermined distance from one or more decision points) that prevent one or more time-controlled requests from the vehicle to the backend server. The vehicle may transmit a time-controlled request from the vehicle to the backend server if a predetermined maximum time, e.g., 10 minutes, has elapsed since the last request from the vehicle to the backend server. This may prevent the vehicle from not transmitting a request from the vehicle to the backend server for providing another predicted route and another set of decision points for a longer period of time.

[0055] The method 100 may include receiving 108 the other predicted route and the other set of decision points from the backend server by the vehicle. The vehicle may provide the predicted route and / or the other predicted route as a navigation route suggestion to the vehicle user. If the user accepts the navigation route suggestion, the navigation system of the vehicle may be activated using the navigation route suggestion.

[0056] In addition, method 100 can provide one or more predicted routes and / or information about one or more predicted routes, especially route-related information, to the vehicle user. Therefore, even when the navigation system of the vehicle is not used, the user can be informed of route-related information. For example, route-related information such as estimated driving duration, estimated arrival time, route length and / or information about road closures, traffic reports and / or traffic jam reports along the one or more predicted routes can be provided to the vehicle user. Therefore, even if the navigation system is deactivated, the vehicle can provide route-related information to the vehicle user. The navigation system of the vehicle can use the predicted route to calculate one or more routes that replace the predicted route. Therefore, an alternative route that reaches the driving destination faster than using the predicted route can be quickly provided to the user. For example, the vehicle can inform the vehicle user of the delay on the predicted route with a fast alternative route or a possible fast alternative route. The user can start the destination navigation of the navigation system on the predicted route or on an alternative route to the predicted route by operating input.

[0057] The backend server can predict the route using known methods and determine the probability of the predicted route. If the probability of the predicted route is equal to or exceeds a predetermined minimum probability, the predicted route can be provided to the vehicle user. If the probability of the predicted route is less than the predetermined minimum probability, it is not provided to the vehicle user. This can increase the user's acceptance of starting the destination navigation of the navigation system using the predicted route. For example, the probability can be compared with the predetermined minimum probability at the beginning of the journey and / or in each new predicted route. This can ensure that changes in the predicted route probability are taken into account and the predicted route is provided to the vehicle user in a timely manner.

[0058] Figure 3 A first scenario 300 is shown with a predicted route and decision points at the beginning of a journey. Figure 4A second scenario 400 with predicted routes and decision points during driving is shown. Each scenario 300 and 400 includes three navigation destinations D1, D2 and D3, four predicted routes R1, R2, R3 and R4, and three decision points EP1, EP2 and EP3. The vehicle starts driving at decision point EP1. At the start of driving, the probability P(R1) of route R1 is equal to 0.5, the probability P(R2) of route R2 is equal to 0.3, the probability P(R3) of route R3 is equal to 0.1 and the probability P(R4) of route R4 is equal to 0.1. The vehicle 402 drives from EP1 to EP2. The probability P(R1) of route R1 is now 0, the probability P(R2) of route R2 is equal to 0.6, the probability P(R3) of route R3 is equal to 0.2, and the probability P(R4) of route R4 is equal to 0.2. If the predetermined minimum probability of the predicted route is, for example, 0.6, the predicted route is not displayed to the user in scenario 300 , whereas the predicted route R2 is provided to the user in scenario 400 .

[0059] Advantageously, the method can more effectively determine the time of further requests for providing one or more further predicted routes using the set of decision points. Thus, the predicted route can be provided to the vehicle more quickly. Furthermore, the number of requests can be effectively controlled using the number of decision points in the set of decision points. Using the decision points in the set of decision points, the method can more effectively control the vehicle's requests for predicted routes to the backend server. As a result, the forecast of the route to the driving destination can be effectively improved. The vehicle can provide the user with a more accurate route forecast. The vehicle user can obtain information about the forecasted or predicted route without the route guidance of the navigation system being activated by the user.

[0060] Reference numerals list

[0061] 100 Methods

[0062] 102 Receiving the predicted route

[0063] 104 Confirm passing the decision point

[0064] 106 Send Request

[0065] 108 Receive another predicted route

[0066] 200 scenes

[0067] EP Decision Point

[0068] K1 Circle

[0069] K2 Circle

[0070] 300 scenes

[0071] 400 scenes

[0072] 402 Vehicle

Claims

1. A method for requesting a predicted route from a backend server by a vehicle, the method include: Receiving, by the vehicle, a predicted route and a set of decision points for the predicted route from a backend server; The vehicle determines to pass through a decision point in the decision point set; After the decision point is driven by the vehicle, transmitting from the vehicle to the backend server a request for providing another predicted route and another set of decision points; The another predicted route and the another set of decision points are received by the vehicle from the backend server.

2. The method according to claim 1, in, Decision points are waypoints at which the vehicle's traveled path diverges.

3. The method according to any one of the preceding claims, in, The decision point set is determined by the backend server according to one or more historical trajectories of the vehicle user.

4. The method according to any one of the preceding claims, in, An importance is associated with each decision point; and / or the set of decision points includes one or more decision points whose importance exceeds a predetermined minimum importance threshold.

5. The method according to any one of the preceding claims, in, The method further comprises: providing the predicted route as a navigation route suggestion to a vehicle user; and / or providing the other predicted route to the vehicle user as another navigation route suggestion; and / or In response to an operation input by a vehicle user for accepting the navigation route suggestion and / or the other navigation route suggestion, navigation of the vehicle is activated while using the predicted route and / or the other predicted route.

6. The method according to any one of the preceding claims, in, If the vehicle first enters a first predetermined circle around the decision point and then exits a second predetermined circle around the decision point, the decision point is determined to be passed; Preferably, the radius of the first circle is smaller than the radius of the second circle; and The vehicle preferably receives the radius of the first circle and the radius of the second circle for each decision point from the backend server along with the set of decision points.

7. A method according to any one of the preceding claims, wherein include: transmitting from the vehicle to the backend server a time-controlled request for providing another predicted route and another set of decision points if the last request is older than a predetermined period of time; and / or If the distance between the vehicle and the next decision point of the predicted route is below a predetermined distance threshold and / or the time period to reach the next decision point is below a predetermined time threshold, a time-controlled request from the vehicle to the backend server for providing another predicted route and another set of decision points is blocked.

8. A computer readable medium for requesting, by the vehicle, the predicted route from a backend server, in, The computer readable medium comprises instructions which, when executed by a computer or a controller, perform the method according to any one of claims 1 to 7.

9. A system for requesting a predicted route from a backend server by a vehicle, in, The system is designed to carry out the method according to any one of claims 1 to 7 .

10. A vehicle comprising the system for requesting a predicted route from a backend server by the vehicle according to claim 9.