A method and device for determining vehicle driving strategy, and a vehicle
By obtaining and analyzing vehicle driving path and obstacle information, determining the driving strategy of autonomous driving vehicles, the safety problems caused by the inability to change the driving path of autonomous driving vehicles are solved and driving safety is improved.
Patent Information
- Application Number
- CN202210565492.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-05-23
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2042-05-23
AI Technical Summary
When an autonomous vehicle detects that it is approaching the vehicle during driving, it cannot change its driving path, resulting in a high risk factor for autonomous driving.
By obtaining the preset driving path and obstacle information of the target vehicle, determine the driving intention and path of the obstacle, and determine the driving strategy of the target vehicle based on this, including giving way, rushing or parallelism, selecting the best through scoring and sorting Strategy.
It improves the driving safety of autonomous vehicles when they encounter close to vehicles and reduces the risk factor.
Smart Images

Figure CN114852103B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicles, and in particular to a method and device for determining a vehicle driving strategy, and a vehicle. Background Art
[0002] In the related technologies, in recent years, autonomous driving is increasingly entering people's field of vision. At the same time, the safety issues brought by autonomous driving are also attracting more and more attention. Autonomous driving can automatically and safely operate the vehicle without active operation. When an autonomous driving vehicle detects a vehicle approaching during driving, it cannot change the path in time, threatening the life safety of people.
[0003] With respect to the above-mentioned problems existing in the related technologies, no effective solution has been proposed yet. Summary of the invention
[0004] The main purpose of the present invention is to provide a method and device for determining a vehicle driving strategy, and a vehicle, so as to solve the problem in the related art that when an autonomous driving vehicle detects an approaching vehicle during driving, it is unable to change the driving path, resulting in a high risk factor for autonomous driving.
[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present invention, a method for determining a vehicle driving strategy is provided. The invention comprises: obtaining a preset driving path corresponding to a target vehicle; obtaining obstacle information and map information of a target area, wherein the target area is the area where the target vehicle is located, and the obstacle information at least includes the size information of the obstacle, the dynamic and static state of the obstacle, the position information of the obstacle, and the speed information of the obstacle; determining the driving intention of the obstacle based on the obstacle information and the map information, and determining the first driving path corresponding to the obstacle based on the driving intention, wherein the driving intention is any one of the following: the obstacle stops running, the obstacle starts from being stationary, the obstacle drives along the current lane, the obstacle changes lanes, the obstacle drives along the current lane and turns, and the obstacle bypasses other obstacles on the current lane; determining the target driving strategy of the target vehicle based on the first driving path.
[0006] Furthermore, before determining the driving strategy of the target vehicle based on the driving intention of the obstacle and the first driving path, the method also includes: determining multiple sampling points corresponding to the preset driving path based on the preset driving path; determining the posture information of the target vehicle arriving at the target sampling point and the first arrival time of the target sampling point, the posture information at least including the driving speed of the target vehicle and the occupied space of the target vehicle arriving at the sampling point, the target sampling point being any sampling point between the multiple sampling points; determining the second arrival time corresponding to the obstacle arriving at the target sampling point; determining multiple driving strategies corresponding to the target vehicle at the sampling point based on the posture information of the target vehicle arriving at the target sampling point, the first arrival time, the second arrival time of the obstacle arriving at the target sampling point and the first driving path, wherein the driving strategy is any one of the following strategies: the target vehicle gives way to the obstacle, the target vehicle rushes over the obstacle, and the target vehicle and the obstacle are parallel; determining the target driving strategy based on the multiple driving strategies.
[0007] Furthermore, a target driving strategy is determined based on multiple driving strategies, including: scoring the multiple driving strategies and obtaining multiple scores corresponding to the multiple driving strategies; sorting the multiple scores and determining the driving strategy corresponding to the lowest score as the target driving strategy.
[0008] Furthermore, scoring is performed on multiple driving strategies, and multiple scores corresponding to the multiple driving strategies are obtained, including: determining multiple scoring dimensions corresponding to each driving strategy, and determining multiple initial scores corresponding to the multiple scoring dimensions, wherein the multiple scoring dimensions include at least the following dimensions: comfort corresponding to the driving strategy, safety corresponding to the driving strategy, and operational difficulty corresponding to the driving strategy; determining multiple weights corresponding to the multiple scoring dimensions corresponding to each driving strategy; and determining multiple scores corresponding to the multiple driving strategies based on the multiple weights and the multiple initial scores.
[0009] Furthermore, before determining multiple scoring dimensions corresponding to each driving strategy and determining multiple initial scores corresponding to the multiple scoring dimensions, the method includes: determining the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle at the sampling point based on any driving strategy and the first driving path corresponding to the obstacle; determining the initial score corresponding to each scoring dimension based on the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle.
[0010] Furthermore, when the scoring dimension is comfort, the initial score corresponding to each scoring dimension is determined based on the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: determining the maximum acceleration of the target vehicle when the target vehicle arrives at the target sampling point to execute the driving strategy, the maximum acceleration being any one of the following: lateral acceleration, longitudinal acceleration; determining the acceleration interval to which the maximum acceleration belongs, and determining the initial score corresponding to the comfort based on the acceleration interval, wherein there is a preset relationship between the acceleration interval and the initial score.
[0011] Further, the acceleration interval to which the maximum acceleration belongs is determined, and based on the acceleration interval, the initial score corresponding to the comfort is determined, including: when the maximum acceleration is in a first acceleration range, the initial score corresponding to the comfort is determined to be a first initial score; when the maximum acceleration is in a second acceleration range, the initial score of the comfort is determined to be a second initial score, and the minimum value of the second acceleration range is greater than the maximum value of the first acceleration range; when the maximum acceleration is in a third acceleration range, the initial score of the comfort is determined to be a third initial score, and the maximum value of the third acceleration range is greater than the maximum value of the second acceleration range.
[0012] Furthermore, when the scoring dimension is safety, the initial score corresponding to each scoring dimension is determined based on the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: obtaining the distance between the target vehicle and the obstacle at the target sampling point, wherein the distance is any one of the following: the lateral distance between the target vehicle and the obstacle, the longitudinal distance between the target vehicle and the obstacle; determining the distance interval to which the distance belongs, and determining the initial score corresponding to the distance based on the distance interval, wherein there is a preset relationship between the distance interval and the initial score.
[0013] Further, determine the distance interval to which the distance belongs, and determine the initial score corresponding to the distance based on the distance interval, including: when the distance belongs to the first distance interval, determine the initial score corresponding to the safety degree as the fourth initial score; when the distance belongs to the second distance interval, determine the initial score corresponding to the safety degree as the fifth initial score, and the minimum value of the second distance interval is greater than the maximum value of the first distance interval; when the distance belongs to the third distance interval, determine the initial score corresponding to the safety degree as the sixth initial score, and the minimum value of the third distance interval is greater than the maximum value of the second distance interval.
[0014] Furthermore, when the scoring dimension is operation difficulty, the initial score corresponding to each scoring dimension is determined based on the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: determining the target motion state reached by the target vehicle when the target vehicle performs the corresponding action at the target sampling point; determining the degree difference between the target motion state and the preset motion state, and determining the difference interval to which the degree difference belongs; determining the initial score corresponding to the operation difficulty based on the difference interval, wherein there is a preset relationship between the difference interval and the initial score.
[0015] Furthermore, determining an initial score corresponding to the operation difficulty based on the gap interval includes: when the degree gap belongs to the first gap interval, determining the initial score corresponding to the operation difficulty as the seventh initial score; when the degree gap belongs to the second gap interval, determining the initial score corresponding to the operation difficulty as the eighth initial score, wherein the minimum value of the second gap interval is greater than the maximum value of the first gap interval; when the degree gap belongs to the third gap interval, determining the initial score corresponding to the operation difficulty as the ninth initial score, wherein the minimum value of the third gap interval is greater than the maximum value of the second gap interval.
[0016] Furthermore, obtaining obstacle information includes: obtaining obstacle information through a vehicle-mounted sensor provided on the target vehicle.
[0017] Furthermore, the driving intention of the obstacle is determined based on the obstacle information and the map information. The method also includes: determining the road condition information within the target range where the obstacle is located based on the map information; and predicting the driving intention based on the road condition information.
[0018] Furthermore, determining a first arrival time of the target vehicle at the target sampling point includes: obtaining a current driving speed of the target vehicle; determining a current position of the target vehicle and a position of the target sampling point, and determining a first driving distance based on the current position of the target vehicle and the position of the target sampling point; determining a first arrival time based on the current driving speed of the target vehicle and the first driving distance.
[0019] Furthermore, determining a second arrival time corresponding to when the obstacle arrives at the target sampling point includes: obtaining a current travel speed of the obstacle; determining a current position of the obstacle and a position of the target sampling point, and determining a second travel distance based on the current position of the obstacle and the position of the target sampling point; determining a second arrival time based on the current travel speed of the obstacle and the second travel distance.
[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present invention, a device for determining a vehicle driving strategy is provided. The device comprises: a first acquisition unit, used to acquire a preset driving path corresponding to a target vehicle; a second acquisition unit, used to acquire obstacle information and map information of a target area, wherein the target area is the area where the target vehicle is located, and the obstacle information at least includes the size information of the obstacle, the dynamic and static state of the obstacle, the position information of the obstacle, and the speed information of the obstacle; a first determination unit, used to determine the driving intention of the obstacle based on the obstacle information and the map information, and determine the first driving path corresponding to the obstacle based on the driving intention, wherein the driving intention is any one of the following: the obstacle stops running, the obstacle starts from rest, the obstacle drives along the current lane, the obstacle changes lanes, the obstacle drives along the current lane and turns, and the obstacle bypasses other obstacles on the current lane; the second determination unit, used to determine the target driving strategy of the target vehicle based on the first driving path.
[0021] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a vehicle is provided, which includes an on-board sensor for obtaining obstacle information; a device for determining a vehicle driving strategy, which is used to execute any one of the above-mentioned methods for determining a vehicle driving strategy.
[0022] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is provided, the computer-readable storage medium comprising a stored program, wherein the program executes any one of the above-mentioned methods for determining a vehicle driving strategy.
[0023] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a processor is provided, and the processor is used to run a program, wherein the program executes any one of the above-mentioned methods for determining a vehicle driving strategy.
[0024] Through the present invention, the following steps are adopted: obtaining a preset driving path corresponding to a target vehicle; obtaining obstacle information and map information of a target area, wherein the target area is an area where the target vehicle is located, and the obstacle information at least includes size information of the obstacle, dynamic and static states of the obstacle, position information of the obstacle, and speed information of the obstacle; determining the driving intention of the obstacle based on the obstacle information and map information, and determining a first driving path corresponding to the obstacle based on the driving intention, wherein the driving intention is any one of the following: the obstacle stops running, the obstacle starts from rest, the obstacle travels along the current lane, the obstacle changes lanes, the obstacle turns along the current lane, and the obstacle bypasses other obstacles on the current lane; determining a target driving strategy for the target vehicle based on the first driving path, solving the problem in the related art that when an autonomous driving vehicle detects an approaching vehicle during driving, the driving path cannot be changed, resulting in a high risk factor for autonomous driving, thereby achieving the technical effect of improving the driving safety of the autonomous driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:
[0026] Figure 1 is a flow chart of a method for determining a vehicle driving strategy provided according to an embodiment of the present invention;
[0027] Figure 2 A schematic diagram of multiple scoring dimensions corresponding to a driving strategy corresponding to a target sampling point (any specific sampling point) is determined based on the target sampling point;
[0028] Figure 3 A schematic diagram of determining multiple scoring dimensions corresponding to a driving strategy corresponding to a target sampling point based on the target sampling point;
[0029] Figure 4 A schematic diagram of a specific embodiment provided for this application;
[0030] Figure 5 is a schematic diagram of a device for determining a vehicle driving strategy provided according to an embodiment of the present invention.
[0031] The following reference numerals are included:
[0032] d1: the longitudinal distance required for the obstacle to reach the target sampling point;
[0033] d2: safe distance between the obstacle and the autonomous vehicle;
[0034] d3: the longitudinal distance required for the target vehicle to reach the target sampling point;
[0035] d4: The lateral distance required for the obstacle to reach the target sampling point. DETAILED DESCRIPTION
[0036] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0037] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so as to describe the embodiments of the present invention described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0039] According to an embodiment of the present invention, a method for determining a vehicle driving strategy is provided.
[0040] Figure 1 FIG. 1 is a flow chart of a method for determining a vehicle driving strategy according to an embodiment of the present invention. Figure 1 As shown, the invention comprises the following steps:
[0041] Step S101, obtaining a preset driving path corresponding to a target vehicle.
[0042] Step S102, obtaining obstacle information and map information of a target area, wherein the target area is the area where the target vehicle is located, and the obstacle information at least includes size information of the obstacle, dynamic and static states of the obstacle, location information of the obstacle, and speed information of the obstacle.
[0043] Step S103, determining the driving intention of the obstacle based on the obstacle information and the map information, and determining the first driving path corresponding to the obstacle based on the driving intention, wherein the driving intention is any one of the following: the obstacle stops running, the obstacle starts from rest, the obstacle moves along the current lane, the obstacle changes lanes, the obstacle turns along the current lane, and the obstacle bypasses other obstacles in the current lane.
[0044] Step S104: determining a target driving strategy for the target vehicle according to the first driving path.
[0045] In an optional embodiment provided in the present application, the target vehicle is an autonomous driving vehicle, and the obstacle is a social vehicle that is very close to the autonomous driving vehicle.
[0046] This application predicts the driving intention of social vehicles by obtaining information about obstacles and map information of the driving area of the autonomous driving vehicle.
[0047] The driving paths of social vehicles are predicted by predicting their driving intentions. After the driving paths of social vehicles are determined, the driving strategies of autonomous driving vehicles are determined.
[0048] As mentioned above, the preset driving path of the autonomous driving vehicle is planned in advance.
[0049] In an optional example, before determining the driving strategy of the target vehicle based on the driving intention of the obstacle and the first driving path, the method also includes: determining multiple sampling points corresponding to the preset driving path based on the preset driving path; determining the posture information of the target vehicle arriving at the target sampling point and the first arrival time of the target sampling point, the posture information at least includes the driving speed of the target vehicle and the occupied space of the target vehicle arriving at the sampling point, and the target sampling point is any sampling point between the multiple sampling points; determining the second arrival time corresponding to the obstacle arriving at the target sampling point; determining multiple driving strategies corresponding to the target vehicle at the sampling point based on the posture information of the target vehicle arriving at the target sampling point, the first arrival time, the second arrival time of the obstacle arriving at the target sampling point and the first driving path, wherein the driving strategy is any one of the following strategies: the target vehicle gives way to the obstacle, the target vehicle rushes over the obstacle, and the target vehicle and the obstacle are parallel; determining the target driving strategy based on the multiple driving strategies.
[0050] In an optional example, a target driving strategy is determined based on multiple driving strategies, including: scoring the multiple driving strategies and obtaining multiple scores corresponding to the multiple driving strategies; sorting the multiple scores and determining the driving strategy corresponding to the lowest score as the target driving strategy.
[0051] In an optional instance, multiple driving strategies are scored and multiple scores corresponding to the multiple driving strategies are obtained, including: determining multiple scoring dimensions corresponding to each driving strategy, and determining multiple initial scores corresponding to the multiple scoring dimensions, wherein the multiple scoring dimensions include at least the following dimensions: comfort corresponding to the driving strategy, safety corresponding to the driving strategy, and operational difficulty corresponding to the driving strategy; determining multiple weights corresponding to the multiple scoring dimensions corresponding to each driving strategy; and determining multiple scores corresponding to the multiple driving strategies based on the multiple weights and the multiple initial scores.
[0052] As described above, multiple driving strategies are scored, and the score corresponding to each driving strategy is determined by determining the scores corresponding to multiple scoring dimensions corresponding to each driving strategy, and the driving strategy corresponding to the lowest score is determined as the final target driving strategy.
[0053] Furthermore, the scoring dimensions are divided into comfort, safety and operating difficulty. In other optional embodiments, the scoring dimensions also include vehicle fuel consumption corresponding to the driving strategy, etc.
[0054] In an optional example, before determining multiple scoring dimensions corresponding to each driving strategy and determining multiple initial scores corresponding to the multiple scoring dimensions, the method includes: determining the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle at the sampling point according to any driving strategy and the first driving path corresponding to the obstacle; determining the initial score corresponding to each scoring dimension according to the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, wherein, if Figure 2 As shown, Figure 2 In order to determine the multiple scoring dimensions corresponding to the driving strategy corresponding to the target sampling point (any specific sampling point) according to the target sampling point, Figure 2 In the specific embodiment shown, the target vehicle is an autonomous driving vehicle. When it is predicted that the autonomous driving vehicle will give way to an obstacle at the target sampling point, the longitudinal distance and lateral distance corresponding to the obstacle reaching the target sampling point can be predicted. At the same time, the longitudinal distance of the autonomous driving vehicle to the target sampling point can be predicted and calculated, and the safe distance between the autonomous driving vehicle and the obstacle, as well as the acceleration of the obstacle and the autonomous driving vehicle when they travel to the target sampling point respectively, the difficulty of operation and other parameters corresponding to a series of scoring dimensions are determined through the driving information of the autonomous driving vehicle and the driving information of the obstacle. Furthermore, through the series of parameters determined above, the score of the driving strategy corresponding to the target sampling point is determined to score the driving strategy.
[0055] Figure 3 Another specific embodiment provided for the above embodiment, Figure 3 A schematic diagram of multiple scoring dimensions corresponding to a driving strategy corresponding to a target sampling point is determined based on a target sampling point. The target vehicle is an autonomous driving vehicle. At the target sampling point, when it is predicted that the autonomous driving vehicle needs to rush over an obstacle at the target sampling point, the position information and motion state information of the autonomous driving vehicle and the obstacle reaching the target sampling point are calculated respectively through the predicted trajectory of the obstacle and the predicted trajectory of the autonomous driving vehicle. Then, the lateral distance and longitudinal distance corresponding to the target sampling point, as well as the lateral acceleration, longitudinal acceleration, and operation difficulty corresponding to a series of scoring dimensions are determined through the above information. The score of the driving strategy corresponding to the target sampling point is determined through the above parameters.
[0056] In the above, after predicting the driving path of social vehicles, multiple sampling points are determined on the driving path of the autonomous driving vehicle. The posture information of the autonomous driving vehicle reaching each sampling point is determined by the driving speed and driving time of the autonomous driving vehicle. The multiple driving strategies of the autonomous driving vehicle are determined by the posture information of the autonomous driving vehicle reaching the sampling point and the driving path of the social vehicles. If the lateral driving distance between the autonomous driving vehicle and the social vehicles is large when the autonomous driving vehicle reaches the sampling point, the driving strategy of the autonomous driving vehicle is determined to be parallel to the social vehicles. If the front and rear distance is large, the driving strategy of the autonomous driving vehicle is determined to continue driving at the existing speed. If the lateral distance between the autonomous driving vehicle and the social vehicles is small at the sampling point, the driving strategy of the autonomous driving vehicle is determined to be rushing or giving way. Therefore, at each sampling point, the autonomous driving vehicle will correspond to multiple driving strategies. Each driving strategy is scored and then the target driving strategy is determined to achieve the technical effect of finding the optimal driving method. The above corresponds to a specific embodiment, such as Figure 4 As shown, Figure 4 A schematic diagram of a specific embodiment provided for the present application, in which the driving condition of an autonomous driving vehicle on a four-lane road is determined through a preset driving path of the autonomous driving vehicle, and through the preset driving path, multiple sampling points corresponding to the preset driving path are selected, and the posture information of the autonomous driving vehicle reaching each sampling point, the time when the autonomous driving vehicle arrives at the sampling point, and the time when the obstacle reaches the sampling point are predicted, the above information corresponding to each sampling point is traversed, multiple strategies are solved, and the driving strategy corresponding to one of the sampling points with the lowest cost is determined as the target driving strategy of the autonomous driving vehicle.
[0057] In an optional example, when the scoring dimension is comfort, the initial score corresponding to each scoring dimension is determined based on the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: determining the maximum acceleration of the target vehicle when the target vehicle reaches the target sampling point to execute the driving strategy, the maximum acceleration is any one of the following: lateral acceleration, longitudinal acceleration; determining the acceleration interval to which the maximum acceleration belongs, and determining the initial score corresponding to the comfort according to the acceleration interval, wherein there is a preset relationship between the acceleration interval and the initial score. Determining the acceleration interval to which the maximum acceleration belongs, and determining the initial score corresponding to the comfort according to the acceleration interval, including: when the maximum acceleration is in the first acceleration range, determining the initial score corresponding to the comfort as the first initial score; when the maximum acceleration is in the second acceleration range, determining the initial score of the comfort as the second initial score, the minimum value of the second acceleration range is greater than the maximum value of the first acceleration range; when the maximum acceleration is in the third acceleration range, determining the initial score of the comfort as the third initial score, the minimum value of the third acceleration range is greater than the maximum value of the second acceleration range. In the embodiment provided in this application, the larger the acceleration range corresponding to the acceleration interval, the higher the initial score corresponding to the comfort scoring dimension.
[0058] In an optional example, when the scoring dimension is safety, the initial score corresponding to each scoring dimension is determined according to the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: obtaining the distance between the target vehicle and the obstacle at the target sampling point, wherein the distance is any one of the following: the lateral distance between the target vehicle and the obstacle, the longitudinal distance between the target vehicle and the obstacle; determining the distance interval to which the distance belongs, and determining the initial score corresponding to the distance according to the distance interval, wherein there is a preset relationship between the distance interval and the initial score. Determining the distance interval to which the distance belongs, and determining the initial score corresponding to the distance according to the distance interval, including: when the distance belongs to the first distance interval, determining the initial score corresponding to the safety degree as a fourth initial score; when the distance belongs to the second distance interval, determining the initial score corresponding to the safety degree as a fifth initial score, the minimum value of the second distance interval is greater than the maximum value of the first distance interval; when the distance belongs to the third distance interval, determining the initial score corresponding to the safety degree as a sixth initial score, the minimum value of the third distance interval is greater than the maximum value of the second distance interval.
[0059] Specifically, in the above embodiment provided by the present application, the initial score corresponding to the distance is determined by determining the preset relationship between the distance interval and the initial score, so as to score the driving strategy. At the same time, the distance here refers to the lateral distance and the longitudinal distance. In the above embodiment, at the target sampling point, the larger the distance interval to which the distance between the vehicle and the obstacle belongs, the lower the initial score corresponding to the safety scoring dimension.
[0060] In an optional example, when the scoring dimension is the difficulty of operation, the initial score corresponding to each scoring dimension is determined according to the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: determining the target motion state reached by the target vehicle when the target vehicle performs the corresponding action at the target sampling point; determining the degree difference between the target motion state and the preset motion state, and determining the difference interval to which the degree difference belongs; determining the initial score corresponding to the difficulty of operation according to the difference interval, wherein there is a preset relationship between the difference interval and the initial score. Determining the initial score corresponding to the difficulty of operation according to the difference interval includes: when the degree difference belongs to the first difference interval, determining the initial score corresponding to the difficulty of operation as the seventh initial score; when the degree difference belongs to the second difference interval, determining the initial score corresponding to the difficulty of operation as the eighth initial score, wherein the minimum value of the second difference interval is greater than the maximum value of the first difference interval; when the degree difference belongs to the third difference interval, determining the initial score corresponding to the difficulty of operation as the ninth initial score, wherein the minimum value of the third difference interval is greater than the maximum value of the second difference interval.
[0061] In the above-mentioned embodiments, the present application provides a preset motion state when the vehicle performs a corresponding action, that is, a standard motion state. For example, when the vehicle turns to an emergency direction, what are the motion parameters of the standard motion state that the vehicle should reach? When the vehicle actually performs the action, what are the actual motion parameters corresponding to the motion state (target motion state) actually achieved? The score corresponding to the difficulty of the action operation is determined by the standard motion state and the actual motion state. The score interval corresponding to the degree difference is also provided to determine the initial score corresponding to the difficulty of the operation. In this embodiment, when the gap between the target motion state achieved by the vehicle in performing the action is greater and the standard motion state is greater, the difficulty of performing the action is greater, that is, the initial score corresponding to the difficulty of performing the action is greater.
[0062] The above is an optional embodiment provided by the present application, in which the initial score corresponding to each dimension is determined by three intervals corresponding to each dimension, wherein each interval corresponds to an initial score.
[0063] In an optional example, obtaining obstacle information includes: obtaining obstacle information through a vehicle-mounted sensor provided on the target vehicle.
[0064] In an optional example, the driving intention of the obstacle is determined based on the obstacle information and the map information. The method also includes: determining the road condition information within the target range where the obstacle is located based on the map information; and predicting the driving intention based on the road condition information.
[0065] As mentioned above, predicting the driving intention of social vehicles through map information is mainly based on the road condition information displayed in the map to predict the driving intention of social vehicles.
[0066] In an optional example, determining a first arrival time of a target vehicle at a target sampling point includes: obtaining a current driving speed of the target vehicle; determining a current position of the target vehicle and a position of the target sampling point, and determining a first driving distance based on the current position of the target vehicle and the position of the target sampling point; and determining a first arrival time based on the current driving speed of the target vehicle and the first driving distance.
[0067] In an optional example, determining a second arrival time corresponding to when the obstacle arrives at the target sampling point includes: obtaining a current travel speed of the obstacle; determining a current position of the obstacle and a position of the target sampling point, and determining a second travel distance based on the current position of the obstacle and the position of the target sampling point; and determining a second arrival time based on the current travel speed of the obstacle and the second travel distance.
[0068] A method for determining a vehicle driving strategy provided by an embodiment of the present invention comprises the following steps: obtaining a preset driving path corresponding to a target vehicle; obtaining obstacle information and map information of a target area, wherein the target area is an area where the target vehicle is located, and the obstacle information at least includes size information of the obstacle, dynamic and static states of the obstacle, position information of the obstacle, and speed information of the obstacle; determining the driving intention of the obstacle based on the obstacle information and map information, and determining a first driving path corresponding to the obstacle based on the driving intention, wherein the driving intention is any one of the following: the obstacle stops running, the obstacle starts from being stationary, the obstacle drives along the current lane, the obstacle changes lanes, the obstacle turns along the current lane, and the obstacle bypasses other obstacles on the current lane; determining the target driving strategy of the target vehicle based on the first driving path, thereby solving the problem in the related art that when an autonomous driving vehicle detects an approaching vehicle during driving, the driving path cannot be changed, resulting in a high risk factor for autonomous driving, thereby achieving the technical effect of improving the driving safety of the autonomous driving vehicle.
[0069] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0070] The embodiment of the present invention further provides a device for determining a vehicle driving strategy. It should be noted that the device for determining a vehicle driving strategy in the embodiment of the present invention can be used to execute a method for determining a vehicle driving strategy provided in the embodiment of the present invention. The following introduces a device for determining a vehicle driving strategy provided in the embodiment of the present invention.
[0071] Figure 5 is a schematic diagram of a device for determining a vehicle driving strategy according to an embodiment of the present invention. Figure 5 As shown, the device includes: a first acquisition unit 501, used to acquire a preset driving path corresponding to the target vehicle; a second acquisition unit 502, used to acquire obstacle information and map information of a target area, wherein the target area is the area where the target vehicle is located, and the obstacle information at least includes size information of the obstacle, dynamic and static states of the obstacle, position information of the obstacle, and speed information of the obstacle; a first determination unit 503, used to determine the driving intention of the obstacle based on the obstacle information and map information, and determine the first driving path corresponding to the obstacle based on the driving intention, wherein the driving intention is any one of the following: the obstacle stops running, the obstacle starts from rest, the obstacle travels along the current lane, the obstacle changes lanes, the obstacle turns along the current lane, and the obstacle bypasses other obstacles on the current lane; a second determination unit 504, used to determine the target driving strategy of the target vehicle based on the first driving path.
[0072] In an optional example, the device further includes: a third determination unit, which is used to determine a plurality of sampling points corresponding to the preset driving path according to the preset driving path before determining the driving strategy of the target vehicle according to the driving intention of the obstacle and the first driving path; a fourth determination unit, which is used to determine the posture information of the target vehicle arriving at the target sampling point and the first arrival time of the target sampling point, wherein the posture information at least includes the driving speed of the target vehicle and the occupied space of the target vehicle arriving at the sampling point, and the target sampling point is any one of the multiple sampling points; a fifth determination unit, which is used to determine the second arrival time corresponding to the obstacle arriving at the target sampling point; a sixth determination unit, which is used to determine a plurality of driving strategies corresponding to the target vehicle at the sampling point according to the posture information of the target vehicle arriving at the target sampling point, the first arrival time, the second arrival time of the obstacle arriving at the target sampling point and the first driving path, wherein the driving strategy is any one of the following strategies: the target vehicle gives way to the obstacle, the target vehicle rushes over the obstacle, and the target vehicle and the obstacle are parallel; a seventh determination unit, which is used to determine the target driving strategy according to the plurality of driving strategies.
[0073] In an optional instance, the seventh determination unit includes: a first acquisition subunit, used to score multiple driving strategies and obtain multiple scores corresponding to the multiple driving strategies; a first determination subunit, used to sort the multiple scores and determine the driving strategy corresponding to the lowest score as the target driving strategy.
[0074] In an optional instance, the first acquisition subunit includes: a first determination module, used to determine multiple scoring dimensions corresponding to each driving strategy, and determine multiple initial scores corresponding to the multiple scoring dimensions, wherein the multiple scoring dimensions include at least the following dimensions: comfort corresponding to the driving strategy, safety corresponding to the driving strategy, and operating difficulty corresponding to the driving strategy; a second determination module, used to determine multiple weights corresponding to the multiple scoring dimensions corresponding to each driving strategy; and a third determination module, used to determine multiple scores corresponding to multiple driving strategies based on multiple weights and multiple initial scores.
[0075] In an optional instance, the device includes: an eighth determination unit, which is used to determine the driving information of the target vehicle at the sampling point, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle based on any driving strategy and the first driving path corresponding to the obstacle before determining multiple scoring dimensions corresponding to each driving strategy and determining multiple initial scores corresponding to the multiple scoring dimensions; a ninth determination unit, which is used to determine the initial score corresponding to each scoring dimension based on the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle.
[0076] In an optional instance, the ninth determination unit includes: a second determination subunit, used to determine the maximum acceleration of the target vehicle when the target vehicle arrives at the target sampling point to execute the driving strategy, the maximum acceleration being any one of the following: lateral acceleration, longitudinal acceleration; a third determination subunit, used to determine the acceleration interval to which the maximum acceleration belongs, and determine an initial score corresponding to the comfort level based on the acceleration interval, wherein there is a preset relationship between the acceleration interval and the initial score.
[0077] In an optional instance, the third determination subunit includes: a fourth determination module, which is used to determine that the initial score corresponding to the comfort is a first initial score when the maximum acceleration is in a first acceleration range; a fifth determination module, which is used to determine that the initial score of the comfort is a second initial score when the maximum acceleration is in a second acceleration range, and the minimum value of the second acceleration range is greater than the maximum value of the first acceleration range; and a sixth determination module, which is used to determine that the initial score of the comfort is a third initial score when the maximum acceleration is in a third acceleration range, and the minimum value of the third acceleration range is greater than the maximum value of the second acceleration range.
[0078] In an optional instance, the ninth determination unit includes: a second acquisition subunit, used to obtain the distance between the target vehicle and the obstacle at the target sampling point, wherein the distance is any one of the following: a lateral distance between the target vehicle and the obstacle, a longitudinal distance between the target vehicle and the obstacle; a fourth determination subunit, used to determine the distance interval to which the distance belongs, and determine an initial score corresponding to the distance based on the distance interval, wherein there is a preset relationship between the distance interval and the initial score.
[0079] In an optional instance, the fourth determination subunit includes: a seventh determination module, which is used to determine that the initial score corresponding to the safety level is a fourth initial score when the distance belongs to the first distance interval; an eighth determination module, which is used to determine that the initial score corresponding to the safety level is a fifth initial score when the distance belongs to the second distance interval, and the minimum value of the second distance interval is greater than the maximum value of the first distance interval; and a ninth determination module, which is used to determine that the initial score corresponding to the safety level is a sixth initial score when the distance belongs to the third distance interval, and the minimum value of the third distance interval is greater than the maximum value of the second distance interval.
[0080] In an optional instance, the ninth determination unit includes: a fifth determination subunit, used to determine the target motion state reached by the target vehicle when the target vehicle performs a corresponding action at a target sampling point; a sixth determination subunit, used to determine the degree difference between the target motion state and the preset motion state, and determine the difference interval to which the degree difference belongs; a seventh determination subunit, used to determine an initial score corresponding to the operation difficulty based on the difference interval, wherein there is a preset relationship between the difference interval and the initial score.
[0081] In an optional instance, the seventh determination subunit includes: a tenth determination module, which is used to determine that the initial score corresponding to the operation difficulty is a seventh initial score when the degree gap belongs to the first gap interval; an eleventh determination module, which is used to determine that the initial score corresponding to the operation difficulty is an eighth initial score when the degree gap belongs to the second gap interval, wherein the minimum value of the second gap interval is greater than the maximum value of the first gap interval; and a twelfth determination module, which is used to determine that the initial score corresponding to the operation difficulty is a ninth initial score when the degree gap belongs to the third gap interval, wherein the minimum value of the third gap interval is greater than the maximum value of the second gap interval.
[0082] In an optional example, the second acquisition unit 502 includes: a third acquisition subunit, configured to acquire obstacle information through a vehicle-mounted sensor provided on the target vehicle.
[0083] In an optional example, the device also includes: a tenth determination unit, used to determine the driving intention of the obstacle based on the obstacle information and map information, and to determine the road condition information within the target range where the obstacle is located based on the map information; a prediction unit, used to predict the driving intention based on the road condition information.
[0084] In an optional example, the fourth determination unit includes: a fourth acquisition subunit, used to acquire the current driving speed of the target vehicle; an eighth determination subunit, used to determine the current position of the target vehicle and the position of the target sampling point, and determine the first driving distance based on the current position of the target vehicle and the position of the target sampling point; a ninth determination subunit, used to determine the first arrival time based on the current driving speed of the target vehicle and the first driving distance.
[0085] In an optional example, the fifth determination unit includes: a fifth acquisition subunit, used to acquire the current driving speed of the obstacle; a tenth determination subunit, used to determine the current position of the obstacle and the position of the target sampling point, and determine the second driving distance based on the current position of the obstacle and the position of the target sampling point; an eleventh determination subunit, used to determine the second arrival time based on the current driving speed of the obstacle and the second driving distance.
[0086] An embodiment of the present invention provides a device for determining a vehicle driving strategy, which uses a first acquisition unit 501 to acquire a preset driving path corresponding to a target vehicle; a second acquisition unit 502 to acquire obstacle information and map information of a target area, wherein the target area is the area where the target vehicle is located, and the obstacle information at least includes size information of the obstacle, the dynamic and static state of the obstacle, the position information of the obstacle, and the speed information of the obstacle; a first determination unit 503 is used to determine the driving intention of the obstacle based on the obstacle information and the map information, and determine the first driving path corresponding to the obstacle based on the driving intention, wherein the driving intention is any one of the following: the obstacle stops running, the obstacle starts from rest, the obstacle drives along the current lane, the obstacle changes lanes, the obstacle drives along the current lane, and the obstacle bypasses other obstacles on the current lane; the second determination unit 504 is used to determine the target driving strategy of the target vehicle based on the first driving path, which solves the problem in the related art that when the autonomous driving vehicle detects an approaching vehicle during driving, the driving path cannot be changed, resulting in a high risk factor of autonomous driving, thereby achieving the technical effect of improving the driving safety of the autonomous driving vehicle.
[0087] A device for determining a vehicle driving strategy includes a processor and a memory. The first acquisition unit 501 and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.
[0088] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to solve the problem in the related technology that when the autonomous driving vehicle detects an approaching vehicle during driving, it cannot change the driving path, resulting in a high risk factor for autonomous driving.
[0089] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0090] An embodiment of the present invention provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, a method for determining a vehicle driving strategy is implemented.
[0091] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes a method for determining a vehicle driving strategy when running.
[0092] An embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining a preset driving path corresponding to a target vehicle; obtaining obstacle information and map information of a target area, wherein the target area is an area where the target vehicle is located, and the obstacle information at least includes size information of the obstacle, dynamic and static states of the obstacle, position information of the obstacle, and speed information of the obstacle; determining a driving intention of the obstacle based on the obstacle information and map information, and determining a first driving path corresponding to the obstacle based on the driving intention, wherein the driving intention is any one of the following: the obstacle stops running, the obstacle starts from being stationary, the obstacle travels along the current lane, the obstacle changes lanes, the obstacle turns along the current lane, and the obstacle bypasses other obstacles in the current lane; and determining a target driving strategy for the target vehicle based on the first driving path.
[0093] Furthermore, before determining the driving strategy of the target vehicle based on the driving intention of the obstacle and the first driving path, the method also includes: determining multiple sampling points corresponding to the preset driving path based on the preset driving path; determining the posture information of the target vehicle arriving at the target sampling point and the first arrival time of the target sampling point, the posture information at least including the driving speed of the target vehicle and the occupied space of the target vehicle arriving at the sampling point, the target sampling point being any sampling point between the multiple sampling points; determining the second arrival time corresponding to the obstacle arriving at the target sampling point; determining multiple driving strategies corresponding to the target vehicle at the sampling point based on the posture information of the target vehicle arriving at the target sampling point, the first arrival time, the second arrival time of the obstacle arriving at the target sampling point and the first driving path, wherein the driving strategy is any one of the following strategies: the target vehicle gives way to the obstacle, the target vehicle rushes over the obstacle, and the target vehicle and the obstacle are parallel; determining the target driving strategy based on the multiple driving strategies.
[0094] Furthermore, a target driving strategy is determined based on multiple driving strategies, including: scoring the multiple driving strategies and obtaining multiple scores corresponding to the multiple driving strategies; sorting the multiple scores and determining the driving strategy corresponding to the lowest score as the target driving strategy.
[0095] Furthermore, scoring is performed on multiple driving strategies, and multiple scores corresponding to the multiple driving strategies are obtained, including: determining multiple scoring dimensions corresponding to each driving strategy, and determining multiple initial scores corresponding to the multiple scoring dimensions, wherein the multiple scoring dimensions include at least the following dimensions: comfort corresponding to the driving strategy, safety corresponding to the driving strategy, and operational difficulty corresponding to the driving strategy; determining multiple weights corresponding to the multiple scoring dimensions corresponding to each driving strategy; and determining multiple scores corresponding to the multiple driving strategies based on the multiple weights and the multiple initial scores.
[0096] Furthermore, before determining multiple scoring dimensions corresponding to each driving strategy and determining multiple initial scores corresponding to the multiple scoring dimensions, the method includes: determining the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle at the sampling point based on any driving strategy and the first driving path corresponding to the obstacle; determining the initial score corresponding to each scoring dimension based on the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle.
[0097] Furthermore, when the scoring dimension is comfort, the initial score corresponding to each scoring dimension is determined based on the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: determining the maximum acceleration of the target vehicle when the target vehicle arrives at the target sampling point to execute the driving strategy, the maximum acceleration being any one of the following: lateral acceleration, longitudinal acceleration; determining the acceleration interval to which the maximum acceleration belongs, and determining the initial score corresponding to the comfort based on the acceleration interval, wherein there is a preset relationship between the acceleration interval and the initial score.
[0098] Furthermore, the acceleration interval to which the maximum acceleration belongs is determined, and based on the acceleration interval, an initial score corresponding to the comfort is determined, including: when the maximum acceleration is in a first acceleration range, the initial score corresponding to the comfort is determined to be a first initial score; when the maximum acceleration is in a second acceleration range, the initial score of the comfort is determined to be a second initial score, and the minimum value of the second acceleration range is greater than the maximum value of the first acceleration range; when the maximum acceleration is in a third acceleration range, the initial score of the comfort is determined to be a third initial score, and the minimum value of the third acceleration range is greater than the maximum value of the second acceleration range.
[0099] Furthermore, when the scoring dimension is safety, the initial score corresponding to each scoring dimension is determined based on the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: obtaining the distance between the target vehicle and the obstacle at the target sampling point, wherein the distance is any one of the following: the lateral distance between the target vehicle and the obstacle, the longitudinal distance between the target vehicle and the obstacle; determining the distance interval to which the distance belongs, and determining the initial score corresponding to the distance based on the distance interval, wherein there is a preset relationship between the distance interval and the initial score.
[0100] Further, determine the distance interval to which the distance belongs, and determine the initial score corresponding to the distance based on the distance interval, including: when the distance belongs to the first distance interval, determine the initial score corresponding to the safety degree as the fourth initial score; when the distance belongs to the second distance interval, determine the initial score corresponding to the safety degree as the fifth initial score, and the minimum value of the second distance interval is greater than the maximum value of the first distance interval; when the distance belongs to the third distance interval, determine the initial score corresponding to the safety degree as the sixth initial score, and the minimum value of the third distance interval is greater than the maximum value of the second distance interval.
[0101] Furthermore, when the scoring dimension is operation difficulty, the initial score corresponding to each scoring dimension is determined based on the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: determining the target motion state reached by the target vehicle when the target vehicle performs the corresponding action at the target sampling point; determining the degree difference between the target motion state and the preset motion state, and determining the difference interval to which the degree difference belongs; determining the initial score corresponding to the operation difficulty based on the difference interval, wherein there is a preset relationship between the difference interval and the initial score.
[0102] Furthermore, determining an initial score corresponding to the operation difficulty based on the gap interval includes: when the degree gap belongs to the first gap interval, determining the initial score corresponding to the operation difficulty as the seventh initial score; when the degree gap belongs to the second gap interval, determining the initial score corresponding to the operation difficulty as the eighth initial score, wherein the minimum value of the second gap interval is greater than the maximum value of the first gap interval; when the degree gap belongs to the third gap interval, determining the initial score corresponding to the operation difficulty as the ninth initial score, wherein the minimum value of the third gap interval is greater than the maximum value of the second gap interval.
[0103] Furthermore, obtaining obstacle information includes: obtaining obstacle information through a vehicle-mounted sensor provided on the target vehicle.
[0104] Furthermore, the driving intention of the obstacle is determined based on the obstacle information and the map information. The method also includes: determining the road condition information within the target range where the obstacle is located based on the map information; and predicting the driving intention based on the road condition information.
[0105] Furthermore, determining a first arrival time of the target vehicle at the target sampling point includes: obtaining a current driving speed of the target vehicle; determining a current position of the target vehicle and a position of the target sampling point, and determining a first driving distance based on the current position of the target vehicle and the position of the target sampling point; determining a first arrival time based on the current driving speed of the target vehicle and the first driving distance.
[0106] Furthermore, determining a second arrival time corresponding to when the obstacle arrives at the target sampling point includes: obtaining a current travel speed of the obstacle; determining a current position of the obstacle and a position of the target sampling point, and determining a second travel distance based on the current position of the obstacle and the position of the target sampling point; determining a second arrival time based on the current travel speed of the obstacle and the second travel distance.
[0107] The devices in this article can be servers, PCs, PADs, mobile phones, etc.
[0108] The present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: obtaining a preset driving path corresponding to a target vehicle; obtaining obstacle information and map information of a target area, wherein the target area is an area where the target vehicle is located, and the obstacle information at least includes size information of the obstacle, dynamic and static states of the obstacle, position information of the obstacle, and speed information of the obstacle; determining the driving intention of the obstacle based on the obstacle information and map information, and determining a first driving path corresponding to the obstacle based on the driving intention, wherein the driving intention is any one of the following: the obstacle stops running, the obstacle starts from being stationary, the obstacle travels along the current lane, the obstacle changes lanes, the obstacle turns along the current lane, and the obstacle bypasses other obstacles on the current lane; and determining a target driving strategy for the target vehicle based on the first driving path.
[0109] Furthermore, before determining the driving strategy of the target vehicle based on the driving intention of the obstacle and the first driving path, the method also includes: determining multiple sampling points corresponding to the preset driving path based on the preset driving path; determining the posture information of the target vehicle arriving at the target sampling point and the first arrival time of the target sampling point, the posture information at least including the driving speed of the target vehicle and the occupied space of the target vehicle arriving at the sampling point, the target sampling point being any sampling point between the multiple sampling points; determining the second arrival time corresponding to the obstacle arriving at the target sampling point; determining multiple driving strategies corresponding to the target vehicle at the sampling point based on the posture information of the target vehicle arriving at the target sampling point, the first arrival time, the second arrival time of the obstacle arriving at the target sampling point and the first driving path, wherein the driving strategy is any one of the following strategies: the target vehicle gives way to the obstacle, the target vehicle rushes over the obstacle, and the target vehicle and the obstacle are parallel; determining the target driving strategy based on the multiple driving strategies.
[0110] Furthermore, a target driving strategy is determined based on multiple driving strategies, including: scoring the multiple driving strategies and obtaining multiple scores corresponding to the multiple driving strategies; sorting the multiple scores and determining the driving strategy corresponding to the lowest score as the target driving strategy.
[0111] Furthermore, scoring is performed on multiple driving strategies, and multiple scores corresponding to the multiple driving strategies are obtained, including: determining multiple scoring dimensions corresponding to each driving strategy, and determining multiple initial scores corresponding to the multiple scoring dimensions, wherein the multiple scoring dimensions include at least the following dimensions: comfort corresponding to the driving strategy, safety corresponding to the driving strategy, and operational difficulty corresponding to the driving strategy; determining multiple weights corresponding to the multiple scoring dimensions corresponding to each driving strategy; and determining multiple scores corresponding to the multiple driving strategies based on the multiple weights and the multiple initial scores.
[0112] Furthermore, before determining multiple scoring dimensions corresponding to each driving strategy and determining multiple initial scores corresponding to the multiple scoring dimensions, the method includes: determining the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle at the sampling point based on any driving strategy and the first driving path corresponding to the obstacle; determining the initial score corresponding to each scoring dimension based on the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle.
[0113] Furthermore, when the scoring dimension is comfort, the initial score corresponding to each scoring dimension is determined based on the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: determining the maximum acceleration of the target vehicle when the target vehicle arrives at the target sampling point to execute the driving strategy, the maximum acceleration being any one of the following: lateral acceleration, longitudinal acceleration; determining the acceleration interval to which the maximum acceleration belongs, and determining the initial score corresponding to the comfort based on the acceleration interval, wherein there is a preset relationship between the acceleration interval and the initial score.
[0114] Furthermore, the acceleration interval to which the maximum acceleration belongs is determined, and based on the acceleration interval, an initial score corresponding to the comfort is determined, including: when the maximum acceleration is in a first acceleration range, the initial score corresponding to the comfort is determined to be a first initial score; when the maximum acceleration is in a second acceleration range, the initial score of the comfort is determined to be a second initial score, and the minimum value of the second acceleration range is greater than the maximum value of the first acceleration range; when the maximum acceleration is in a third acceleration range, the initial score of the comfort is determined to be a third initial score, and the minimum value of the third acceleration range is greater than the maximum value of the second acceleration range.
[0115] Furthermore, when the scoring dimension is safety, the initial score corresponding to each scoring dimension is determined based on the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: obtaining the distance between the target vehicle and the obstacle at the target sampling point, wherein the distance is any one of the following: the lateral distance between the target vehicle and the obstacle, the longitudinal distance between the target vehicle and the obstacle; determining the distance interval to which the distance belongs, and determining the initial score corresponding to the distance based on the distance interval, wherein there is a preset relationship between the distance interval and the initial score.
[0116] Further, determine the distance interval to which the distance belongs, and determine the initial score corresponding to the distance based on the distance interval, including: when the distance belongs to the first distance interval, determine the initial score corresponding to the safety degree as the fourth initial score; when the distance belongs to the second distance interval, determine the initial score corresponding to the safety degree as the fifth initial score, and the minimum value of the second distance interval is greater than the maximum value of the first distance interval; when the distance belongs to the third distance interval, determine the initial score corresponding to the safety degree as the sixth initial score, and the minimum value of the third distance interval is greater than the maximum value of the second distance interval.
[0117] Furthermore, when the scoring dimension is operation difficulty, the initial score corresponding to each scoring dimension is determined based on the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, including: determining the target motion state reached by the target vehicle when the target vehicle performs the corresponding action at the target sampling point; determining the degree difference between the target motion state and the preset motion state, and determining the difference interval to which the degree difference belongs; determining the initial score corresponding to the operation difficulty based on the difference interval, wherein there is a preset relationship between the difference interval and the initial score.
[0118] Furthermore, determining an initial score corresponding to the operation difficulty based on the gap interval includes: when the degree gap belongs to the first gap interval, determining the initial score corresponding to the operation difficulty as the seventh initial score; when the degree gap belongs to the second gap interval, determining the initial score corresponding to the operation difficulty as the eighth initial score, wherein the minimum value of the second gap interval is greater than the maximum value of the first gap interval; when the degree gap belongs to the third gap interval, determining the initial score corresponding to the operation difficulty as the ninth initial score, wherein the minimum value of the third gap interval is greater than the maximum value of the second gap interval.
[0119] Furthermore, obtaining obstacle information includes: obtaining obstacle information through a vehicle-mounted sensor provided on the target vehicle.
[0120] Furthermore, the driving intention of the obstacle is determined based on the obstacle information and the map information. The method also includes: determining the road condition information within the target range where the obstacle is located based on the map information; and predicting the driving intention based on the road condition information.
[0121] Furthermore, determining a first arrival time of the target vehicle at the target sampling point includes: obtaining a current driving speed of the target vehicle; determining a current position of the target vehicle and a position of the target sampling point, and determining a first driving distance based on the current position of the target vehicle and the position of the target sampling point; determining a first arrival time based on the current driving speed of the target vehicle and the first driving distance.
[0122] Furthermore, determining a second arrival time corresponding to when the obstacle arrives at the target sampling point includes: obtaining a current travel speed of the obstacle; determining a current position of the obstacle and a position of the target sampling point, and determining a second travel distance based on the current position of the obstacle and the position of the target sampling point; determining a second arrival time based on the current travel speed of the obstacle and the second travel distance.
[0123] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0124] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0125] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0127] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0128] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0129] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0130] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0131] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0132] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims
1. A method for determining a vehicle driving strategy, It is characterized in that include: Obtaining a preset driving path corresponding to the target vehicle; Obtaining obstacle information and map information of a target area, wherein the target area is an area where the target vehicle is located, and the obstacle information at least includes size information of the obstacle, dynamic and static state information of the obstacle, location information of the obstacle, and speed information of the obstacle; Determine the driving intention of the obstacle according to the obstacle information and the map information, and determine the first driving path corresponding to the obstacle according to the driving intention, wherein the driving intention is any one of the following: the obstacle stops running, the obstacle starts from rest, the obstacle moves along the current lane, the obstacle changes lanes, the obstacle turns along the current lane, and the obstacle bypasses other obstacles on the current lane; Determining a target driving strategy for the target vehicle based on the first driving path; Wherein, before determining the driving strategy of the target vehicle according to the driving intention of the obstacle and the first driving path, the method further includes: determining a plurality of sampling points corresponding to the preset driving path according to the preset driving path; determining the posture information of the target vehicle arriving at the target sampling point and the first arrival time of the target sampling point, wherein the posture information at least includes the driving speed of the target vehicle and the occupied space of the target vehicle arriving at the sampling point, and the target sampling point is any one of the plurality of sampling points; determining the second arrival time corresponding to the obstacle arriving at the target sampling point; determining a plurality of driving strategies corresponding to the target vehicle at the sampling point according to the posture information of the target vehicle arriving at the target sampling point, the first arrival time, the second arrival time of the obstacle arriving at the target sampling point and the first driving path, wherein the driving strategy is any one of the following strategies: the target vehicle gives way to the obstacle, the target vehicle rushes over the obstacle, and the target vehicle and the obstacle run parallel; determining the target driving strategy according to the plurality of driving strategies; Determining the target driving strategy according to the plurality of driving strategies includes: scoring the plurality of driving strategies and obtaining a plurality of scores corresponding to the plurality of driving strategies; sorting the plurality of scores and determining the driving strategy corresponding to the lowest score as the target driving strategy; Scoring the multiple driving strategies and obtaining the multiple scores corresponding to the multiple driving strategies includes: determining the multiple scoring dimensions corresponding to each of the driving strategies, and determining the multiple initial scores corresponding to the multiple scoring dimensions, wherein the multiple scoring dimensions include at least the following dimensions: the comfort level corresponding to the driving strategy, the safety level corresponding to the driving strategy, and the operating difficulty corresponding to the driving strategy; determining the multiple weights corresponding to the multiple scoring dimensions corresponding to each of the driving strategies; and determining the multiple scores corresponding to the multiple driving strategies based on the multiple weights and the multiple initial scores.
2. The method according to claim 1, It is characterized in that Before determining a plurality of scoring dimensions corresponding to each of the driving strategies and determining a plurality of initial scores corresponding to the plurality of scoring dimensions, the method includes: According to any one of the driving strategies and the first driving path corresponding to the obstacle, determining the driving information of the target vehicle at the sampling point, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle; The initial score corresponding to each scoring dimension is determined based on the driving information of the target vehicle, the driving information of the obstacle, the difficulty of the action corresponding to the driving strategy, and the distance between the target vehicle and the obstacle.
3. The method according to claim 2, It is characterized in that In the case where the scoring dimension is the comfort level, determining the initial score corresponding to each scoring dimension according to the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle includes: Determine the maximum acceleration of the target vehicle when the target vehicle reaches the target sampling point and executes the driving strategy, the maximum acceleration being any one of the following: lateral acceleration and longitudinal acceleration; An acceleration interval to which the maximum acceleration belongs is determined, and an initial score corresponding to the comfort level is determined based on the acceleration interval, wherein a preset relationship exists between the acceleration interval and the initial score.
4. The method according to claim 3, It is characterized in that Determining the acceleration interval to which the maximum acceleration belongs, and determining an initial score corresponding to the comfort level according to the acceleration interval, including: When the maximum acceleration is within a first acceleration range, determining the initial score corresponding to the comfort level as a first initial score; In a case where the maximum acceleration is within a second acceleration range, determining the initial score of the comfort level to be a second initial score, a minimum value of the second acceleration range being greater than a maximum value of the first acceleration range; In a case where the maximum acceleration is within a third acceleration range, the initial score of the comfort level is determined to be a third initial score, and a minimum value of the third acceleration range is greater than a maximum value of the second acceleration range.
5. The method according to claim 2, It is characterized in that In the case where the scoring dimension is the safety degree, determining the initial score corresponding to each scoring dimension according to the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, includes: Acquire the distance between the target vehicle and the obstacle at the target sampling point, wherein the distance is any one of the following: a lateral distance between the target vehicle and the obstacle, or a longitudinal distance between the target vehicle and the obstacle; Determine the distance interval to which the distance belongs, and determine an initial score corresponding to the distance according to the distance interval, wherein there is a preset relationship between the distance interval and the initial score.
6. The method according to claim 5, It is characterized in that Determining the distance interval to which the distance belongs, and determining an initial score corresponding to the distance according to the distance interval, including: When the distance belongs to the first distance interval, determining that the initial score corresponding to the safety level is a fourth initial score; In a case where the distance belongs to a second distance interval, determining that the initial score corresponding to the safety level is a fifth initial score, and a minimum value of the second distance interval is greater than a maximum value of the first distance interval; In the case that the distance belongs to the third distance interval, the initial score corresponding to the safety level is determined to be a sixth initial score, and the minimum value of the third distance interval is greater than the maximum value of the second distance interval.
7. The method according to claim 2, It is characterized in that In the case where the scoring dimension is the operation difficulty, determining the initial score corresponding to each scoring dimension according to the driving information of the target vehicle, the driving information of the obstacle, the action difficulty corresponding to the driving strategy, and the distance between the target vehicle and the obstacle, includes: Determining a target motion state reached by the target vehicle when the target vehicle performs a corresponding action at the target sampling point; Determining a degree difference between the target motion state and a preset motion state, and determining a difference interval to which the degree difference belongs; An initial score corresponding to the operation difficulty is determined according to the difference interval, wherein a preset relationship exists between the difference interval and the initial score.
8. The method according to claim 7, It is characterized in that Determining an initial score corresponding to the operation difficulty according to the gap interval includes: When the degree difference belongs to the first difference interval, determining the initial score corresponding to the operation difficulty as the seventh initial score; In the case where the degree difference belongs to the second difference interval, determining that the initial score corresponding to the operation difficulty is an eighth initial score, wherein the minimum value of the second difference interval is greater than the maximum value of the first difference interval; When the degree difference belongs to a third difference interval, the initial score corresponding to the operation difficulty is determined to be a ninth initial score, wherein the minimum value of the third difference interval is greater than the maximum value of the second difference interval.
9. The method according to claim 1, It is characterized in that Obtain obstacle information, including: The obstacle information is obtained through a vehicle-mounted sensor provided on the target vehicle.
10. The method according to claim 1, It is characterized in that Determining the driving intention of the obstacle based on the obstacle information and the map information, the method further includes: Determine the road condition information within the target range where the obstacle is located based on the map information; The driving intention is predicted based on the road condition information.
11. The method according to claim 1, It is characterized in that Determining the first arrival time of the target vehicle at the target sampling point includes: Obtaining the current speed of the target vehicle; Determine the current position of the target vehicle and the position of the target sampling point, and determine a first driving distance based on the current position of the target vehicle and the position of the target sampling point; The first arrival time is determined according to the current driving speed of the target vehicle and the first driving distance.
12. The method according to claim 1, It is characterized in that Determining a second arrival time corresponding to the obstacle arriving at the target sampling point includes: Obtaining the current speed of the obstacle; Determine the current position of the obstacle and the position of the target sampling point, and determine a second driving distance according to the current position of the obstacle and the position of the target sampling point; The second arrival time is determined according to the current travel speed of the obstacle and the second travel distance.
13. A device for determining a vehicle driving strategy, It is characterized in that include: A first acquisition unit, used to acquire a preset driving path corresponding to the target vehicle; A second acquisition unit, configured to acquire obstacle information and map information of a target area, wherein the target area is an area where the target vehicle is located, and the obstacle information at least includes size information of the obstacle, dynamic and static state information of the obstacle, position information of the obstacle, and speed information of the obstacle; a first determining unit, configured to determine a driving intention of the obstacle according to the obstacle information and the map information, and determine a first driving path corresponding to the obstacle according to the driving intention, wherein the driving intention is any one of the following: the obstacle stops running, the obstacle starts from rest, the obstacle moves along the current lane, the obstacle changes lanes, the obstacle turns along the current lane, and the obstacle bypasses other obstacles on the current lane; A second determining unit, configured to determine a target driving strategy for the target vehicle according to the first driving path; Wherein, the device further includes a third determining unit, a fourth determining unit, a fifth determining unit, a sixth determining unit, and a seventh determining unit; the third determining unit is used to determine a plurality of sampling points corresponding to the preset driving path according to the preset driving path before determining the driving strategy of the target vehicle according to the driving intention of the obstacle and the first driving path; the fourth determining unit is used to determine the posture information of the target vehicle arriving at the target sampling point and the first arrival time of the target sampling point, the posture information at least includes the driving speed of the target vehicle, the occupied space of the target vehicle reaching the sampling point, and the target sampling point is any one of the plurality of sampling points sampling points; the fifth determining unit is used to determine the second arrival time corresponding to the arrival of the obstacle at the target sampling point; the sixth determining unit is used to determine a plurality of driving strategies corresponding to the target vehicle at the sampling point according to the posture information of the target vehicle reaching the target sampling point, the first arrival time, the second arrival time of the obstacle arriving at the target sampling point, and the first driving path, wherein the driving strategy is any one of the following strategies: the target vehicle gives way to the obstacle, the target vehicle rushes over the obstacle, and the target vehicle and the obstacle are parallel; the seventh determining unit is used to determine the target driving strategy according to the plurality of driving strategies; The seventh determination unit includes a first acquisition subunit and a first determination subunit; the first acquisition subunit is used to score the multiple driving strategies and obtain multiple scores corresponding to the multiple driving strategies; the first determination subunit is used to sort the multiple scores and determine the driving strategy corresponding to the lowest score as the target driving strategy; The first acquisition subunit includes a first determination module, a second determination module and a third determination module; the first determination module is used to determine multiple scoring dimensions corresponding to each of the driving strategies, and determine multiple initial scores corresponding to the multiple scoring dimensions, wherein the multiple scoring dimensions include at least the following dimensions: comfort corresponding to the driving strategy, safety corresponding to the driving strategy, and operation difficulty corresponding to the driving strategy; the second determination module is used to determine multiple weights corresponding to the multiple scoring dimensions corresponding to each of the driving strategies; the third determination module is used to determine multiple scores corresponding to the multiple driving strategies based on the multiple weights and the multiple initial scores.
14. A vehicle, It is characterized in that include: A vehicle-mounted sensor, used to obtain the obstacle information; A device for determining a vehicle driving strategy, used to execute a method for determining a vehicle driving strategy as described in any one of claims 1 to 12 above.
15. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute a method for determining a vehicle driving strategy as described in any one of claims 1 to 12.
16. A processor, It is characterized in that The processor is used to run a program, wherein the program, when running, executes a method for determining a vehicle driving strategy as described in any one of claims 1 to 12.
