Path selection method and device, equipment, medium and vehicle
Through multiple evaluations of path static assessment, screening assessment and dynamic assessment, intelligent driving vehicles can determine the optimal path on complex urban roads, solving the problem of wrong path selection on complex roads and improving safety and user experience.
Patent Information
- Application Number
- CN202311737918.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-18
- Publication Date
- 2025-06-20
AI Technical Summary
When facing complex urban roads, intelligently driven vehicles may have anti-human and wrong path selection, affecting the user experience and posing safety risks.
By obtaining the candidate path set, using the static information of the road itself for path static evaluation, obtaining the first penalty score of each path; filtering and evaluating the paths arranged according to the scores to obtain a preset number of candidate paths; finally, dynamic evaluation of the paths in the road is used for path dynamic evaluation, and the optimal target path is determined.
With all factors fully considered, the optimal target path is determined to improve vehicle driving safety, improve user experience, and reduce user takeover.
Smart Images
Figure CN120176699A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of intelligent driving technology, and in particular, to a path selection method, apparatus, device, medium, and vehicle. Background Art
[0002] At present, automotive companies and Internet giants at home and abroad are actively developing assisted driving technologies. Currently, they can meet the requirement of automatic driving for intelligent vehicles on simple roads in highway and urban expressway scenarios.
[0003] In related technologies, urban general roads have complex road elements, such as complex intersections and diverse traffic participants. When intelligent driving vehicles face complex roads, there may be many situations of anti-human and incorrect path selection, which not only affects the user experience but also poses potential safety hazards. At this time, users need to take over the vehicle. Therefore, in the process of autonomous driving, how to select a suitable autonomous driving path and reduce the occurrence of user takeover situations has become an urgent problem to be solved. Summary of the Invention
[0004] To solve the above technical problems, the present disclosure provides a path selection method, apparatus, device, medium, and vehicle.
[0005] In a first aspect, the present disclosure provides a path selection method, including:
[0006] Obtaining a candidate path set, where the candidate path set includes multiple candidate paths;
[0007] Performing path static evaluation on the candidate path set by using the static information of the road itself to obtain a first penalty score corresponding to each candidate path in the candidate path set;
[0008] Performing path screening evaluation on multiple candidate paths arranged according to the first penalty score to obtain a preset number of candidate paths;
[0009] Performing path dynamic evaluation on the preset number of candidate paths by using the dynamic information of the objects in the road to obtain an optimal target path.
[0010] In a second aspect, the present disclosure provides a path selection apparatus, including:
[0011] A path acquisition module, configured to obtain a candidate path set, where the candidate path set includes multiple candidate paths;
[0012] A first evaluation module, configured to perform path static evaluation on the candidate path set by using the static information of the road itself to obtain a first penalty score corresponding to each candidate path in the candidate path set;
[0013] A second evaluation module, configured to perform path screening and evaluation on multiple candidate paths arranged according to the first penalty score, and obtain a preset number of candidate paths;
[0014] A third evaluation module, configured to perform path dynamic evaluation on a preset number of candidate paths by using the dynamic information of the objects in the road, and obtain an optimal target path.
[0015] In a third aspect, the present disclosure provides a path selection device, including:
[0016] A processor;
[0017] A memory, configured to store executable instructions;
[0018] Wherein, the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the path selection method of the first aspect.
[0019] In a fourth aspect, the present disclosure provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor is caused to implement the path selection method of the first aspect.
[0020] In a fifth aspect, the present disclosure provides a vehicle, including the path selection device as described above.
[0021] The technical solutions provided by the embodiments of the present disclosure have the following advantages compared with the prior art:
[0022] The path selection method, device, equipment, medium and vehicle of the embodiments of the present disclosure can obtain a candidate path set, the candidate path set includes multiple candidate paths, then perform path static evaluation on the candidate path set by using the static information of the road itself, obtain the first penalty score corresponding to each candidate path in the candidate path set, then perform path screening and evaluation on the multiple candidate paths arranged according to the first penalty score, obtain a preset number of candidate paths, and finally perform path dynamic evaluation on the preset number of candidate paths by using the dynamic information of the objects in the road, obtain an optimal target path. Thus, through multiple evaluations of path static evaluation, path screening evaluation and path dynamic evaluation, the optimal target path is determined among multiple candidate paths, so as to determine the target path considering various factors, improve the driving safety of the vehicle and enhance the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages and aspects of the embodiments of the present disclosure will become more obvious. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and the original elements and elements are not necessarily drawn to scale.
[0024] Figure 1Flow diagram of a path selection method provided by an embodiment of the present disclosure;
[0025] Figure 2 Flow diagram of another path selection method provided by an embodiment of the present disclosure;
[0026] Figure 3 Structural diagram of a path selection device provided by an embodiment of the present disclosure;
[0027] Figure 4 Structural diagram of a path selection device provided by an embodiment of the present disclosure. Detailed implementation manners
[0028] Embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not used to limit the protection scope of the present disclosure.
[0029] It should be understood that the steps recited in the method embodiments of the present disclosure can be executed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.
[0030] As used herein, the term "including" and its variants are open-ended, that is, "including but not limited to". The term "based on" is "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.
[0031] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence relationship of the functions executed by these devices, modules or units.
[0032] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".
[0033] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.
[0034] To solve the above problems, embodiments of the present disclosure provide a path selection method, apparatus, device, medium, and vehicle. First, the path selection method provided by the embodiments of the present disclosure will be described in detail below in conjunction with Figures 1 to 2 This is a detailed description of the path selection method provided by the embodiments of the present disclosure.
[0035] Figure 1 The flowchart of a path selection method provided by an embodiment of the present disclosure is shown.
[0036] In the embodiments of the present disclosure, the path selection method can be executed by an electronic device. Specifically, the electronic device may include, but is not limited to, mobile terminals such as computer devices, mobile phones, vehicle-mounted devices, vehicle controllers, tablet computers, wearable devices, etc.
[0037] As Figure 1 shown, the path selection method may include the following steps.
[0038] S110. Obtain a candidate path set, where the candidate path set includes multiple candidate paths.
[0039] In the embodiments of the present disclosure, the electronic device may obtain a candidate path set.
[0040] Optionally, the candidate path set may include multiple candidate paths.
[0041] Optionally, the candidate path may be a candidate path that may be traveled.
[0042] Specifically, when the vehicle determines the driving destination, the electronic device may obtain a candidate path set for the destination, and the candidate path set may include multiple candidate paths.
[0043] S120. Use the static information of the road itself to perform a static evaluation of the candidate path set, and obtain a first penalty score corresponding to each candidate path in the candidate path set.
[0044] In the embodiments of the present disclosure, the electronic device may use the static information of the road itself to perform a static evaluation of the candidate path set, and obtain a first penalty score corresponding to each candidate path in the candidate path set.
[0045] Optionally, the path static evaluation may be an evaluation in combination with the static information of the road itself.
[0046] Optionally, the static information of the road itself may include driving information, lane information, etc., which is not limited herein.
[0047] Optionally, using the static information of the road itself to perform a static evaluation of the candidate path set may include a global static evaluation and a local static evaluation.
[0048] Optionally, the global static evaluation can be performed by combining global static factors.
[0049] Optionally, the local static evaluation can be performed by combining local static factors.
[0050] Optionally, the first penalty score can be a score used to characterize the penalty degree of a candidate path. For example, the larger the first penalty score, the greater the penalty degree of the candidate path, that is, the less compliant the candidate path is; the smaller the first penalty score, the smaller the penalty degree of the candidate path, that is, the more compliant the candidate path is.
[0051] Specifically, after obtaining the candidate path set, the electronic device can perform path static evaluation on the candidate path set by using the static information of the road itself, that is, perform global static evaluation and local static evaluation. After quantifying and normalizing the global static evaluation and local static evaluation, for example, using a mathematical method to determine the corresponding quantitative result evaluation scores A and B for the global static evaluation and local static evaluation, and then calculating the corresponding penalty scores for evaluation scores A and B through a normalization calculation formula, that is, the first penalty score corresponding to each candidate path included in the candidate path set can be obtained.
[0052] For example, the normalization calculation can include Z-score normalization (Standardization), decimal scaling normalization (Decima1 scaling normalization), etc., which are not limited here.
[0053] Among them, the Z-score normalization calculation formula can be:
[0054] x_normalized = (x - x_mean) / x_std
[0055] x_normalized is the penalty score, x_mean is the average value, such as the average value of evaluation scores A and B, and x_std is the standard deviation, such as the standard deviation of evaluation scores A and B.
[0056] Among them, the decimal scaling normalization calculation can be to divide the data by an appropriate base number for normalization. The base number is generally selected as the maximum absolute value in the data, so that the data falls within the range of [-1, 1] or [-0.1, 0.1]. For example, if evaluation score A is the maximum absolute value, divide evaluation scores A and B by the absolute value of evaluation score A respectively to make the data fall within the range of [-1, 1] or [-0.1, 0.1].
[0057] S130. Perform path screening evaluation on multiple candidate paths arranged according to the first penalty score to obtain a preset number of candidate paths.
[0058] In an embodiment of the present disclosure, the electronic device may perform path screening and evaluation on multiple candidate paths arranged according to the first penalty score to obtain a preset number of candidate paths.
[0059] Optionally, the path screening and evaluation may be an evaluation for screening error paths, duplicate paths, etc.
[0060] Optionally, the preset number may be a pre-set number. For example, the preset number may be 3, 4, etc., and there is no limitation here.
[0061] Specifically, after the electronic device obtains the first penalty scores corresponding to multiple candidate paths, it may arrange the multiple candidate paths according to the first penalty score, such as arranging them from low to high according to the first penalty score, and then perform path screening and evaluation on the multiple candidate paths to obtain a preset number of candidate paths, such as obtaining 3 candidate paths.
[0062] S140. Use the dynamic information of the objects in the road to perform path dynamic evaluation on a preset number of candidate paths to obtain the optimal target path.
[0063] In an embodiment of the present disclosure, the electronic device may use the dynamic information of the objects in the road to perform path dynamic evaluation on a preset number of candidate paths to obtain the optimal target path.
[0064] Optionally, the dynamic information of the objects in the road may include traffic flow information, obstacle information, etc., and there is no limitation here.
[0065] Optionally, the path dynamic evaluation may be an evaluation in combination with path dynamic factors.
[0066] Optionally, the target path may be the optimal path among multiple candidate paths.
[0067] Specifically, the electronic device may use the dynamic information of the objects in the road to perform path dynamic evaluation on a preset number of candidate paths, such as performing path dynamic evaluation on 3 candidate paths, so as to obtain the optimal target path.
[0068] Thus, in the embodiments of the present disclosure, a candidate path set can be obtained. The candidate path set includes multiple candidate paths. Then, the static information of the road itself is used to perform path static evaluation on the candidate path set to obtain the first penalty score corresponding to each candidate path in the candidate path set. Then, path screening evaluation is performed on the multiple candidate paths arranged according to the first penalty score to obtain a preset number of candidate paths. Finally, the dynamic information of the objects in the road is used to perform path dynamic evaluation on the preset number of candidate paths to obtain the optimal target path. Thus, through multiple evaluations of path static evaluation, path screening evaluation, and path dynamic evaluation, the optimal target path is determined among multiple candidate paths, so that the target path is determined considering various factors, improving the driving safety of the vehicle and enhancing the user experience.
[0069] Optionally, S110 may specifically include: determining the vehicle driving route according to the navigation map; determining multiple candidate paths according to the vehicle driving route and lane information to obtain a candidate path set.
[0070] In the embodiments of the present disclosure, the electronic device may determine the vehicle driving route according to the navigation map.
[0071] Optionally, the navigation map may be a map for displaying navigation information. For example, the corresponding navigation map displayed by the navigation software.
[0072] Optionally, the vehicle driving route may be a pre-planned route for the vehicle to drive to the destination.
[0073] Specifically, the electronic device may determine the vehicle driving route according to the navigation map. For example, a navigation software may be installed in the vehicle terminal, and the user may input the destination address. The navigation software may plan the corresponding vehicle driving route according to the destination address and display the navigation map including the vehicle driving route.
[0074] Further, the electronic device may determine multiple candidate paths according to the vehicle driving route and lane information to obtain a candidate path set.
[0075] Optionally, the lane information may be the information corresponding to a certain lane. For example, the lane information may be lane connection information, lane number information, etc.
[0076] Specifically, the electronic device may determine multiple candidate paths according to the vehicle driving route and lane information to obtain a candidate path set. For example, according to the vehicle driving route, one of the roads passed through can be determined, and this road includes two lanes. The electronic device may determine these two lanes as two candidate paths, thereby obtaining a candidate path set composed of multiple candidate paths.
[0077] Optionally, the global static evaluation may include an assessable driving distance evaluation, a navigation lane deviation evaluation, a lane change frequency evaluation, and / or a left / right turn cross-lane evaluation.
[0078] Optionally, the assessable driving distance evaluation refers to the distance evaluation of selecting a lane that can drive farther in the same road during navigation.
[0079] Optionally, the navigation lane deviation evaluation refers to the number of lane changes required for the vehicle to enter the navigation lane (such as a right-turn lane) from the candidate lane (such as a straight-ahead lane), and an evaluation with a smaller number of lane changes is expected.
[0080] Optionally, the lane change frequency evaluation refers to the situation where two lanes merge into one lane, and there may be interference between the vehicle traveling along one of the lanes before merging and the vehicles on the other lane at the merging point. An evaluation to reduce such interference is expected.
[0081] Optionally, the left / right turn cross-lane evaluation refers to entering the corresponding lane in the lane order when turning left or right at an intersection. For example, if the vehicle enters the intersection from the second left-turn lane from the left, it is generally recommended that the vehicle also leaves the intersection from the second lane from the left.
[0082] Optionally, the local static evaluation may include a lane curvature evaluation, a path smoothness evaluation, and / or a static occupancy obstacle evaluation.
[0083] Optionally, the lane curvature evaluation refers to avoiding driving along some sharp curves as much as possible to improve the riding comfort.
[0084] Optionally, the path smoothness evaluation refers to, when selecting a bifurcated lane, preferably taking a bifurcation that naturally extends from the previous lane rather than an extended lane.
[0085] Optionally, the static occupancy obstacle evaluation refers to checking for static objects within the lane that affect traffic flow and avoiding such obstacles in the path selection section.
[0086] In the embodiments of the present disclosure, the electronic device may quantify and normalize each of the above evaluation items to obtain a first penalty score corresponding to each candidate path.
[0087] For example, the assessable distance evaluation, navigation lane departure evaluation, lane change times evaluation and / or left / right turn cross-lane evaluation, as well as lane curvature evaluation, path smoothness evaluation and / or static occupancy obstacle evaluation can be quantified, that is, the corresponding quantitative results are determined by mathematical methods respectively. For each evaluation item, a corresponding evaluation threshold is preset, and the evaluation score corresponding to each evaluation item is determined according to the evaluation threshold. For example, for the assessable distance evaluation, a distance threshold is preset. If the assessable distance is greater than the distance threshold, the evaluation score A1 is 0.2, otherwise the evaluation score A1 is 0.8. Another example is for the lane change times evaluation, a number threshold is preset. If the lane change times is greater than the number threshold, the evaluation score A2 is 0.3, otherwise the evaluation score A1 is 0.7, and so on, so as to obtain the evaluation scores corresponding to each evaluation item respectively: evaluation score A1, evaluation score A2, evaluation score A3 and evaluation score A4, as well as evaluation score B1, evaluation score B2 and evaluation score B3. Then, the corresponding penalty scores are calculated through the normalization calculation formula.
[0088] In some examples, the average value x_mean and the standard deviation x_std of the evaluation scores A1, A2, A3, A4, B1, B2 and B3 are calculated, and the corresponding first penalty score is calculated through the Z-score normalization calculation formula x_normalized = (x - x_mean) / x_std.
[0089] In other examples, it is determined that the evaluation score A1 is the maximum absolute value. The evaluation scores A1, A2, A3 and A4, as well as the evaluation scores B1, B2 and B3 are divided by the absolute value of the evaluation score A1 respectively, so that the data falls within the range of [-1, 1] or [-0.1, 0.1], and the corresponding first penalty score is calculated through the decimal scaling normalization.
[0090] Thus, in the embodiments of the present disclosure, the path static evaluation can be first used to initially screen multiple candidate paths, so as to obtain more suitable candidate paths.
[0091] Optionally, S130 may specifically include: according to the road navigation information, screening out the candidate paths with navigation errors among the multiple candidate paths arranged according to the first penalty score to obtain effective candidate paths; and performing screening processing on the repeated candidate paths among the effective candidate paths to obtain a preset number of non-repeated candidate paths.
[0092] In the embodiments of the present disclosure, the electronic device can screen out the candidate paths with navigation errors among the multiple candidate paths arranged according to the first penalty score according to the road navigation information to obtain effective candidate paths.
[0093] Optionally, the road navigation information may be information for vehicle driving to perform road route navigation.
[0094] Specifically, the electronic device can screen out the candidate paths with navigation errors among multiple candidate paths arranged according to the first penalty score. For example, during the vehicle driving process, the road navigation information can display the information of the next road for the vehicle to drive on. The electronic device can screen the multiple candidate paths arranged according to the first penalty score, and remove the candidate paths that are different from the information of the next road displayed by the road navigation information. For example, if the road navigation information shows that the vehicle needs to turn right at the next intersection, and there is a candidate path that is a left-turn lane, that is, the candidate path is an incorrect candidate path, and the electronic device can remove the incorrect candidate path to obtain valid candidate paths.
[0095] Furthermore, the electronic device can screen and process the duplicate candidate paths among the valid candidate paths to obtain a preset number of non-duplicate candidate paths.
[0096] Specifically, the electronic device can screen and process the duplicate candidate paths among the valid candidate paths. For example, if there are two duplicate candidate paths, the electronic device can remove the candidate path with a higher first penalty score and retain the candidate path with a lower first penalty score. Finally, 3 non-duplicate candidate paths with lower first penalty scores are obtained.
[0097] Thus, in the embodiments of the present disclosure, re-screening can be continued through path screening and evaluation, so as to obtain more suitable candidate paths.
[0098] Optionally, the path dynamic evaluation can include dynamic traffic flow evaluation, roadside object evaluation, lane occupancy obstacle evaluation, and / or straight intersection smoothness evaluation.
[0099] Optionally, the dynamic traffic flow evaluation refers to evaluating the traffic flow that may interfere with the candidate path to reduce the risk of dangerous confluence with fast traffic flow or congested traffic flow.
[0100] Optionally, the roadside object evaluation refers to fully considering the situation where vulnerable road users (VRUs) (such as non-motor vehicles and pedestrians) on the roadside enter the motor vehicle lane, reducing the driving time in the outermost lane, and avoiding dangerous collisions between the vehicle and the pedestrians and non-motor vehicles on the roadside.
[0101] Optionally, the lane occupancy obstacle evaluation refers to evaluating the impact of the construction area on the lane and avoiding the construction area.
[0102] Optionally, the straight intersection smoothness evaluation refers to when going straight through the intersection, as much as possible, selecting a lane that has no interference with other traffic flows geometrically and avoiding cutting into the adjacent lane obliquely.
[0103] Optionally, S140 may specifically include: performing path dynamic evaluation on a preset number of candidate paths to obtain a second penalty score corresponding to each candidate path; and determining the candidate path with the lowest second penalty score as the optimal target path.
[0104] In an embodiment of the present disclosure, the electronic device may perform path dynamic evaluation on a preset number of candidate paths to obtain a second penalty score corresponding to each candidate path.
[0105] Optionally, the second penalty score may be a score used to characterize the penalty degree of the candidate path. For example, the larger the second penalty score, the greater the penalty degree of the candidate path, that is, the less compliant the candidate path is; the smaller the second penalty score, the smaller the penalty degree of the candidate path, that is, the more compliant the candidate path is.
[0106] Specifically, the electronic device may perform path dynamic evaluation on a preset number of candidate paths, that is, perform dynamic traffic flow evaluation, roadside object evaluation, occupying obstacle evaluation, and / or straight intersection smoothness evaluation on the candidate paths. After quantifying and normalizing the above evaluation items, a second penalty score corresponding to each candidate path is obtained, such as obtaining second penalty scores corresponding to 3 candidate paths respectively.
[0107] For example, quantifying the dynamic traffic flow evaluation, roadside object evaluation, occupying obstacle evaluation, and / or straight intersection smoothness evaluation, that is, respectively using mathematical methods to determine the corresponding quantification results. For each evaluation item, a corresponding evaluation threshold is preset, and the evaluation score corresponding to each evaluation item is determined according to the evaluation threshold. For example, for the dynamic traffic flow evaluation, a flow threshold is preset. If the dynamic traffic volume is greater than the flow threshold, the obtained evaluation score C1 is 0.2, otherwise the obtained evaluation score C1 is 0.8; for another example, for the occupying obstacle evaluation, a quantity threshold is preset. If the number of occupying obstacles is greater than the quantity threshold, the obtained evaluation score A2 is 0.3, otherwise the obtained evaluation score A1 is 0.7, etc., so as to obtain the evaluation scores corresponding to each evaluation item: evaluation score C1, evaluation score C2, evaluation score C3, and evaluation score C4, and then calculate the corresponding penalty score through the normalization calculation formula.
[0108] Similarly, by calculating the average value x_mean and standard deviation x_std of the evaluation scores C1, C2, C3, and C4, and using the Z-score normalization calculation formula x_normalized = (x - x_mean) / x_std, the corresponding second penalty score is calculated.
[0109] Similarly, determine that the evaluation score C1 has the largest absolute value, and divide the evaluation scores C1, C2, C3, and C4 by the absolute value of the evaluation score C1 respectively, so that the data falls within the range of [-1, 1] or [-0.1, 0.1], and calculate the corresponding second penalty score through decimal scaling normalization.
[0110] Further, the electronic device determines that the candidate path with the lowest second penalty score is the optimal target path.
[0111] Specifically, after the electronic device obtains the second penalty score corresponding to each candidate path, for example, obtains the second penalty scores corresponding to 3 candidate paths respectively, it can use the candidate path with the lowest second penalty score among the 3 candidate paths as the optimal target path.
[0112] Figure 2 The flowchart of another path selection method provided by the embodiments of the present disclosure is shown.
[0113] As Figure 3 shown, the electronic device can obtain a set of candidate paths, and then perform path static evaluation on the set of candidate paths, such as performing global static evaluation: drivable distance evaluation, navigation lane deviation evaluation, lane change times evaluation, and / or left and right turn cross-lane evaluation, and performing local static evaluation: lane curvature evaluation, path smoothness evaluation, and / or static occupancy obstacle evaluation, to obtain a set of initially evaluated paths, where the set of initially evaluated paths includes multiple candidate paths arranged in ascending order of the first penalty score, and then perform path screening evaluation on the set of initially evaluated paths to obtain a set of re-evaluated paths, and the set of re-evaluated paths may include a preset number of candidate paths, and finally perform path dynamic evaluation on the set of re-evaluated paths to obtain the optimal target path.
[0114] Figure 3 The structural schematic diagram of a path selection device provided by the embodiments of the present disclosure is shown.
[0115] In some embodiments of the present disclosure, Figure 3 the path selection device shown can be set in an electronic device. Specifically, the electronic device may include but is not limited to mobile terminals such as computer devices, mobile phones, vehicle-mounted devices, vehicle controllers, tablet computers, wearable devices, etc.
[0116] As Figure 3 shown, the path selection device 300 may include a path acquisition module 310, a first evaluation module 320, a second evaluation module 330, and a third evaluation module 340.
[0117] The path acquisition module 310 may be used to acquire a set of candidate paths, and the set of candidate paths includes multiple candidate paths.
[0118] The first evaluation module 320 can be used to perform path static evaluation on the candidate path set by using the static information of the road itself, and obtain the first penalty score corresponding to each candidate path in the candidate path set.
[0119] The second evaluation module 330 can be used to perform path screening evaluation on multiple candidate paths arranged according to the first penalty score, and obtain a preset number of candidate paths.
[0120] The third evaluation module 340 can be used to perform path dynamic evaluation on a preset number of candidate paths by using the dynamic information of the objects in the road, and obtain the optimal target path.
[0121] Thus, in the embodiments of the present disclosure, a candidate path set can be obtained. The candidate path set includes multiple candidate paths. Then, path static evaluation is performed on the candidate path set by using the static information of the road itself to obtain the first penalty score corresponding to each candidate path in the candidate path set. Then, path screening evaluation is performed on multiple candidate paths arranged according to the first penalty score to obtain a preset number of candidate paths. Finally, path dynamic evaluation is performed on a preset number of candidate paths by using the dynamic information of the objects in the road to obtain the optimal target path. Thus, through multiple evaluations of path static evaluation, path screening evaluation, and path dynamic evaluation, the optimal target path is determined among multiple candidate paths, so that the target path is determined considering various factors, improving the driving safety of the vehicle and enhancing the user experience.
[0122] In some embodiments of the present disclosure, the path acquisition module 310 may specifically include a first determination unit and a second determination unit.
[0123] The first determination unit can be used to determine the vehicle driving route according to the navigation map.
[0124] The second determination unit can be used to determine multiple candidate paths according to the vehicle driving route and lane information, and obtain a candidate path set.
[0125] In some embodiments of the present disclosure, performing path static evaluation on the candidate path set by using the static information of the road itself may include global static evaluation and local static evaluation.
[0126] In some embodiments of the present disclosure, the global static evaluation may include drivable distance evaluation, navigation lane deviation evaluation, lane change times evaluation, and / or left and right turn cross-lane evaluation; the local static evaluation may include lane curvature evaluation, path smoothness evaluation, and / or static occupancy obstacle evaluation.
[0127] In some embodiments of the present disclosure, the second evaluation module 330 may specifically include a first processing unit and a second processing unit.
[0128] The first processing unit can be used to screen out the candidate paths with navigation errors from multiple candidate paths arranged according to the first penalty score based on road navigation information, so as to obtain valid candidate paths.
[0129] The second processing unit can be used to screen and process the duplicate candidate paths among the valid candidate paths to obtain a preset number of non-duplicate candidate paths.
[0130] In some embodiments of the present disclosure, the path dynamic evaluation may include dynamic traffic flow evaluation, roadside object evaluation, occupied road obstacle evaluation, and / or straight intersection smoothness evaluation.
[0131] In some embodiments of the present disclosure, the third evaluation module 340 may specifically include a third processing unit and a third determination unit.
[0132] The third processing unit can be used to perform path dynamic evaluation on a preset number of candidate paths by using the dynamic information of the objects in the road, so as to obtain a second penalty score corresponding to each candidate path.
[0133] The third determination unit can be used to determine the candidate path with the lowest second penalty score as the optimal target path.
[0134] It should be noted that Figure 3 the path selection device 300 shown can execute Figures 1 to 2 each step in the method embodiments shown, and achieve Figures 1 to 2 each process and effect in the method embodiments shown, which will not be elaborated here.
[0135] Figure 4 Fig. shows a schematic structural diagram of a path selection device provided by an embodiment of the present disclosure.
[0136] In some embodiments of the present disclosure, Figure 4 the path selection device shown may be an electronic device for which a user wants to perform path selection. Specifically, the electronic device may include, but is not limited to, mobile terminals such as mobile phones, in-vehicle devices, vehicle controllers, tablet computers, wearable devices, and smart home devices.
[0137] As Figure 4 shown, the path selection device may include a processor 401 and a memory 402 storing computer program instructions.
[0138] Specifically, the above-mentioned processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.
[0139] The memory 402 may include a mass memory for information or instructions. By way of example and not limitation, the memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 402 may include removable or non-removable (or fixed) media. Where appropriate, the memory 402 may be internal or external to the integrated gateway device. In a particular embodiment, the memory 402 is a non-volatile solid-state memory. In a particular embodiment, the memory 402 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these.
[0140] The processor 401 reads and executes the computer program instructions stored in the memory 402 to perform the steps of the path selection method provided by the embodiments of the present disclosure.
[0141] In one example, the path selection device may further include a transceiver 403 and a bus 404. Among them, as Figure 4 shown, the processor 401, the memory 402, and the transceiver 403 are connected through the bus 404 and complete communication with each other.
[0142] The bus 404 includes hardware, software, or both. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side BUS (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable bus or a combination of two or more of these. Where appropriate, the bus 404 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.
[0143] Embodiments of the present disclosure also provide a computer-readable storage medium that may store a computer program, which, when executed by a processor, causes the processor to implement the path selection method provided by the embodiments of the present disclosure.
[0144] The above storage medium may include, for example, a memory 402 storing computer program instructions, and the above instructions may be executed by a processor 401 of the path selection device to complete the path selection method provided by the embodiments of the present disclosure. Optionally, the storage medium may be a non-transitory computer-readable storage medium. For example, the non-transitory computer-readable storage medium may be a ROM, a Random Access Memory (RAM), a Compact Disc ROM (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.
[0145] Embodiments of the present disclosure also provide a vehicle, which includes the path selection device as described above. It can be understood that the vehicle may also include: a processor, a memory, and a computer program. The computer program is stored in the memory and configured to be executed by the processor to implement the path selection method provided by the embodiments of the present disclosure. The processor and the memory have been described in the part of the embodiments shown in Figure 4 and will not be elaborated here.
[0146] It should be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article, or device that comprises a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or device.
[0147] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.
Claims
1. A path selection method, characterized in that, Including: Obtain a set of candidate paths, where the set of candidate paths includes multiple candidate paths; Perform path static evaluation on the set of candidate paths using the static information of the road itself, and obtain the first penalty score corresponding to each candidate path in the set of candidate paths; Perform path screening evaluation on multiple candidate paths arranged according to the first penalty score, and obtain a preset number of candidate paths; Perform path dynamic evaluation on the preset number of candidate paths using the dynamic information of objects in the road, and obtain the optimal target path.
2. The method according to claim 1, characterized in that, The performing path static evaluation on the set of candidate paths using the static information of the road itself includes global static evaluation and local static evaluation.
3. The method according to claim 2, characterized in that, The global static evaluation includes drivable distance evaluation, navigation lane deviation evaluation, lane change times evaluation, and / or left and right turn cross-lane evaluation; the local static evaluation includes lane curvature evaluation, path smoothness evaluation, and / or static occupancy obstacle evaluation.
4. The method according to claim 1, characterized in that, The performing path screening evaluation on multiple candidate paths arranged according to the first penalty score to obtain a preset number of candidate paths includes: According to the road navigation information, filter out the candidate paths with navigation errors in multiple candidate paths arranged according to the first penalty score, and obtain valid candidate paths; Perform screening processing on the duplicate candidate paths in the valid candidate paths to obtain the preset number of non-duplicate candidate paths.
5. The method according to claim 1, characterized in that, The path dynamic evaluation includes dynamic traffic flow evaluation, roadside object evaluation, occupancy obstacle evaluation, and / or straight intersection smoothness evaluation.
6. The method according to claim 1, characterized in that, The performing path dynamic evaluation on the preset number of candidate paths using the dynamic information of objects in the road to obtain the optimal target path includes: Perform path dynamic evaluation on the preset number of candidate paths using the dynamic information of objects in the road, and obtain the second penalty score corresponding to each candidate path; Determine the candidate path with the lowest second penalty score as the optimal target path.
7. A path selection device, characterized in that, Including: A path acquisition module, configured to obtain a set of candidate paths, where the set of candidate paths includes multiple candidate paths; A first evaluation module, configured to perform path static evaluation on the set of candidate paths using the static information of the road itself, and obtain the first penalty score corresponding to each candidate path in the set of candidate paths; A second evaluation module, configured to perform path screening evaluation on multiple candidate paths arranged according to the first penalty score, and obtain a preset number of candidate paths; A third evaluation module, configured to perform path dynamic evaluation on the preset number of candidate paths using the dynamic information of objects in the road, and obtain the optimal target path.
8. A path selection device, characterized in that, Including: A processor; A memory, configured to store executable instructions; Wherein, the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the path selection method according to any one of claims 1-6 above.
9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and when the computer program is executed by the processor, the processor is enabled to implement the path selection method according to any one of claims 1-6 above.
10. A vehicle, characterized in that, Comprising the path selection device according to claim 7 or the path selection apparatus according to claim 8 or the computer-readable storage medium according to claim 9.