Traffic intersection passage methods, devices and electronic equipment, storage media
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHIDAO NETWORK TECH (BEIJING) CO LTD
- Filing Date
- 2022-06-01
- Publication Date
- 2026-05-26
AI Technical Summary
Existing autonomous driving technologies, when dealing with vehicle conflict passage at traffic intersections, either have good algorithm prediction results but require high computing power, or they do not require high computing power but have poor prediction results, making it difficult to achieve high-precision safe passage in practical applications.
By acquiring vehicle trajectory planning information and combining it with local high-precision map data, a virtual lane set for the vehicle and the target vehicle is constructed, conflict passage areas are identified, and passage strategies are determined based on arrival time, thereby reducing computing power requirements while improving accuracy.
With lower computing power requirements, it improves the accuracy and safety of traffic flow at intersections, ensuring the safe passage of vehicles at intersections.
Smart Images
Figure CN115042788B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of autonomous driving technology, and in particular to a method, apparatus, electronic device, and storage medium for traffic crossing at a traffic intersection. Background Technology
[0002] Advanced Driver Assistance Systems (ADAS) utilize various onboard sensors and decision-making and control algorithms to enable vehicles to perform actions such as lane changing, merging, overtaking, and following other vehicles. Especially in traffic intersection scenarios, effectively handling conflicting traffic from different directions is a major technical challenge that tests the autonomous driving capabilities of driverless cars.
[0003] Currently, there are two main approaches to solving this problem: neural network methods based on open environments and trajectory prediction methods based on historical data. However, due to the complexity and nonlinear characteristics of actual vehicles and road conditions, these approaches have two drawbacks in practical applications: 1) the algorithms have good prediction results but require high computing power; 2) the computing power requirements are not high but the algorithm prediction results are poor. Summary of the Invention
[0004] This application provides a traffic intersection passage method, device, electronic device, and storage medium to improve accuracy while reducing computing power requirements.
[0005] The embodiments of this application adopt the following technical solutions:
[0006] In a first aspect, embodiments of this application provide a method for traffic passage at a traffic intersection, wherein the method includes:
[0007] Obtain the trajectory planning information of the vehicle, and determine the target vehicle corresponding to the vehicle at the current traffic intersection based on the trajectory planning information of the vehicle;
[0008] Based on the vehicle's trajectory planning information and local high-precision map data, obtain the set of lane connection lines corresponding to the target vehicle;
[0009] The virtual lane corresponding to the vehicle is constructed based on the trajectory planning information of the vehicle, and the virtual lane set corresponding to the target vehicle is constructed based on the set of lane connection lines.
[0010] Based on the set of virtual lanes corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle, the conflict zone of the vehicle at the current traffic intersection is determined;
[0011] The arrival times of the autonomous vehicle and the target vehicle at the conflict zone are determined, and the autonomous vehicle's passage strategy at the current traffic intersection is determined based on the arrival times of the autonomous vehicle and the target vehicle at the conflict zone.
[0012] Optionally, obtaining the set of lane connection lines corresponding to the target vehicle based on the vehicle's trajectory planning information and local high-precision map data includes:
[0013] Based on the local high-precision map data, obtain the set of lanes where the target vehicle is located;
[0014] The associated lane of the target vehicle is determined based on the set of lanes in which the target vehicle is located;
[0015] Based on the lane set where the target vehicle is located and the associated lanes of the target vehicle, lane selection is performed using the vehicle's trajectory planning information;
[0016] Based on the filtering results, a set of lane connection lines corresponding to the target vehicle is generated.
[0017] Optionally, the step of constructing a virtual lane corresponding to the vehicle based on the vehicle's trajectory planning information, and constructing a virtual lane set corresponding to the target vehicle based on the lane connection line set, includes:
[0018] Obtain vehicle width information and lateral safety buffer information, and construct a virtual lane corresponding to the vehicle based on the vehicle width information, the lateral safety buffer information and the vehicle's trajectory planning information;
[0019] Each lane connector is extracted from the set of lane connectors, and a virtual lane is constructed based on the lane width corresponding to each lane connector, thus obtaining the set of virtual lanes corresponding to the target vehicle.
[0020] Optionally, determining the conflict zone of the vehicle at the current traffic intersection based on the virtual lane corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle includes:
[0021] Determine the overlapping area between the virtual lane corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle;
[0022] The overlapping area is taken as the conflict passage area of the vehicle at the current traffic intersection.
[0023] Optionally, determining the time when the vehicle and the target vehicle arrive at the conflict passage area includes:
[0024] Obtain the set of lanes where the target vehicle is located, and construct a Frenet coordinate system based on the set of lanes and the set of virtual lanes;
[0025] The observation information of the target vehicle is mapped onto the Frenet coordinate system;
[0026] Based on the observation information of the target vehicle in the Frenet coordinate system, the time when the target vehicle arrives at the conflict passage area is determined.
[0027] Optionally, determining the time when the vehicle and the target vehicle arrive at the conflict passage area includes:
[0028] Obtain the set of accelerations of the vehicle, wherein the set of accelerations includes multiple accelerations of the vehicle;
[0029] When the vehicle is traveling at multiple accelerations, determine the set of times when the vehicle arrives at the conflict passage area.
[0030] Optionally, obtaining the set of accelerations of the vehicle includes:
[0031] Based on the parameter information of the preset acceleration constraint, the acceleration constraint of the vehicle is constructed. The parameter information of the preset acceleration constraint includes at least one of the following: the speed limit value of the current traffic intersection, the size information of the vehicle, the speed limit of the vehicle, and the acceleration limit.
[0032] Based on the vehicle's acceleration constraints, acceleration is sampled at preset sampling intervals to obtain multiple acceleration sample values;
[0033] The vehicle's acceleration set is generated based on multiple acceleration sample values.
[0034] Optionally, determining the vehicle's passage strategy at the current traffic intersection based on the arrival times of the vehicle and the target vehicle at the conflict zone includes:
[0035] Based on the time set of the vehicle arriving at the conflict zone and the time of the target vehicle arriving at the conflict zone, determine the collision probability set between the vehicle and the target vehicle;
[0036] Determine the minimum collision probability in the set of collision probabilities;
[0037] Determine the target time corresponding to the minimum collision probability from the set of times when the vehicle arrives at the conflict passage area;
[0038] A target acceleration corresponding to the target time is determined from the set of accelerations, so as to control the vehicle to pass through the current traffic intersection according to the target acceleration.
[0039] Secondly, embodiments of this application also provide a traffic intersection passage device, wherein the device includes:
[0040] The first determining unit is used to acquire the trajectory planning information of the vehicle and determine the target vehicle corresponding to the vehicle at the current traffic intersection based on the trajectory planning information of the vehicle.
[0041] The acquisition unit is used to acquire the set of lane connection lines corresponding to the target vehicle based on the trajectory planning information of the vehicle and local high-precision map data;
[0042] The construction unit is used to construct a virtual lane corresponding to the vehicle based on the vehicle's trajectory planning information, and to construct a set of virtual lanes corresponding to the target vehicle based on the set of lane connection lines.
[0043] The second determining unit is used to determine the conflict passage area of the vehicle at the current traffic intersection based on the virtual lane corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle.
[0044] The third determining unit is used to determine the time when the autonomous vehicle and the target vehicle arrive at the conflict passage area, and to determine the autonomous vehicle's passage strategy at the current traffic intersection based on the time when the autonomous vehicle and the target vehicle arrive at the conflict passage area.
[0045] Thirdly, embodiments of this application also provide an electronic device, including:
[0046] Processor; and
[0047] A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform any of the methods described above.
[0048] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform any of the methods described above.
[0049] The above-mentioned at least one technical solution adopted in the embodiments of this application can achieve the following beneficial effects: The traffic intersection passage method of the embodiments of this application first obtains the trajectory planning information of the vehicle and determines the target vehicle corresponding to the vehicle at the current traffic intersection based on the trajectory planning information of the vehicle; then, based on the trajectory planning information of the vehicle and local high-precision map data, obtains the set of lane connection lines corresponding to the target vehicle; then, based on the trajectory planning information of the vehicle, constructs the virtual lane corresponding to the vehicle, and constructs the set of virtual lanes corresponding to the target vehicle based on the set of lane connection lines; then, based on the virtual lanes corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle, determines the conflict passage area corresponding to the vehicle at the current traffic intersection; finally, determines the time when the vehicle and the target vehicle arrive at the conflict passage area, and determines the passage strategy of the vehicle at the current traffic intersection based on the time when the vehicle and the target vehicle arrive at the conflict passage area. The traffic intersection passage method of the embodiments of this application determines the passage strategy that the vehicle should adopt at the traffic intersection based on the target vehicle information that may have conflict behavior at the traffic intersection and the lane structure information provided by the high-precision map, etc., which has higher accuracy with low computing power requirements and ensures the safety of vehicle passage at traffic intersections. Attached Figure Description
[0050] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0051] Figure 1 This is a flowchart illustrating a traffic intersection passage method according to an embodiment of this application;
[0052] Figure 2 This is a schematic diagram of the lane structure of a traffic intersection according to an embodiment of this application;
[0053] Figure 3 This is a schematic diagram of the structure of a traffic intersection passage device according to an embodiment of this application;
[0054] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation
[0055] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0056] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.
[0057] This application provides a method for traffic passage at an intersection, such as... Figure 1 The diagram shows a flowchart of a traffic intersection passage method according to an embodiment of this application. The method includes at least the following steps S110 to S150:
[0058] Step S110: Obtain the trajectory planning information of the vehicle, and determine the target vehicle corresponding to the vehicle at the current traffic intersection based on the trajectory planning information of the vehicle.
[0059] In determining the travel strategy of a vehicle at a traffic intersection, this embodiment of the application needs to first obtain the trajectory planning information of the vehicle, which represents the reference driving trajectory of the vehicle from the current moment to a future period of time.
[0060] Furthermore, based on the vehicle's current location information, the traffic intersection that the vehicle is about to pass through can be determined. Then, by combining the vehicle's trajectory when passing through the traffic intersection, target vehicles that may have traffic conflicts with the vehicle can be identified.
[0061] To facilitate understanding of the embodiments of this application, a rule for determining the target vehicle is further described herein, which may be, for example:
[0062] 1) If a vehicle turns left, the vehicles involved in the traffic conflict are either vehicles traveling straight or turning right in the opposite lane.
[0063] 2) If the vehicle is going straight, the vehicle that is causing the conflict is the vehicle turning left in the opposite lane.
[0064] 3) If a vehicle turns right, the vehicles involved in the traffic conflict are either vehicles traveling straight in the opposite direction or vehicles turning left in the opposite lane.
[0065] Of course, the specific rules for determining the target vehicle that is in conflict with the vehicle depend on information such as the actual road structure and lane structure. Therefore, the above rules are merely illustrative descriptions, and those skilled in the art can flexibly adjust them according to actual needs. No specific limitations are made here.
[0066] Furthermore, determining the current lanes of other vehicles is fundamental to identifying potential conflicts with the vehicle. This can be achieved using the vehicle's onboard sensors' observations of target vehicles and high-precision map data. This allows for a preliminary identification of which vehicles at the current intersection are likely to conflict with the vehicle. Moreover, since multiple target vehicles may exist in a single lane, only those closest to the intersection require the vehicle's attention; therefore, obviously irrelevant target vehicles can be filtered out beforehand.
[0067] Step S120: Based on the trajectory planning information of the vehicle and the local high-precision map data, obtain the set of lane connection lines corresponding to the target vehicle.
[0068] After identifying the target vehicle, this embodiment of the application also needs to obtain the corresponding local high-precision map data based on the current traffic intersection through which the vehicle is to pass. The local high-precision map data can provide lane structure information within a certain area, such as lane lines and lane connecting lines. Figure 2 As shown, a schematic diagram of a lane structure at a traffic intersection is provided in an embodiment of this application.
[0069] Lane lines can be understood as the boundary lines on both sides of a lane, while lane connector lines can be understood as lines connecting any two lanes. There are no actual lane lines in traffic intersection areas, but corresponding lane connector lines exist in high-precision map data. Therefore, this application embodiment can determine the lane connector lines corresponding to the lane where the target vehicle is located based on local high-precision map data, and determine the set of lane connector lines corresponding to the target vehicle based on the intersection of these lane connector lines with the vehicle's trajectory at the current traffic intersection.
[0070] For example, if the target vehicle a1 is currently located in lane 01, based on local high-precision map data, it can be determined that there is a lane connection line 012 between lane 01 and lane 02, and a lane connection line 013 between lane 01 and lane 03. The vehicle's driving trajectory intersects with lane connection line 012, but does not intersect with lane connection line 013. Therefore, lane connection line 012 can be stored in the lane connection line set.
[0071] Step S130: Construct a virtual lane corresponding to the vehicle based on the vehicle's trajectory planning information, and construct a virtual lane set corresponding to the target vehicle based on the lane connection line set.
[0072] As mentioned earlier, there are no actual lane lines or lanes in the traffic intersection area. Therefore, in order to accurately determine the possibility of a conflict between the vehicle and the target vehicle, a virtual lane corresponding to the vehicle in the traffic intersection area can be established based on the vehicle's trajectory planning information. At the same time, multiple virtual lanes can be established based on each lane connection line in the lane connection line set, which serves as the set of virtual lanes corresponding to the target vehicle.
[0073] Step S140: Based on the set of virtual lanes corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle, determine the conflict zone of the vehicle at the current traffic intersection.
[0074] The virtual lane corresponding to the vehicle represents the possible driving area of the vehicle at the current traffic intersection, while the set of virtual lanes corresponding to the target vehicle represents the possible driving area of the target vehicle at the current traffic intersection. Therefore, the conflict passage area of the vehicle at the current traffic intersection can be determined based on the intersection area between the two.
[0075] Step S150: Determine the arrival times of the autonomous vehicle and the target vehicle at the conflict zone, and determine the autonomous vehicle's passage strategy at the current traffic intersection based on the arrival times of the autonomous vehicle and the target vehicle at the conflict zone.
[0076] A conflict zone can be considered an area where both the vehicle and the target vehicle may pass through or potentially collide, meaning there is spatial overlap. However, this does not mean that the vehicle and the target vehicle will necessarily pass through the conflict zone at the same time. Therefore, this embodiment of the application needs to further determine the arrival times of the vehicle and the target vehicle in the conflict zone. Based on these arrival times, the likelihood of a conflict or collision between the vehicle and the target vehicle can be determined, thereby adjusting the vehicle's driving decisions to avoid temporal overlap within the conflict zone and ensuring the driving safety of both vehicles.
[0077] The traffic intersection passage method of this application determines the passage strategy that the vehicle should adopt at the traffic intersection based on the target vehicle information that may have conflicting behaviors at the traffic intersection and the lane structure information provided by the high-precision map. It has higher accuracy with low computing power requirements and ensures the safety of vehicle passage at traffic intersections.
[0078] In one embodiment of this application, obtaining the set of lane connections corresponding to the target vehicle based on the vehicle's trajectory planning information and local high-precision map data includes: obtaining the set of lanes where the target vehicle is located based on the local high-precision map data; determining the associated lanes of the target vehicle based on the set of lanes where the target vehicle is located; performing lane filtering using the vehicle's trajectory planning information based on the set of lanes where the target vehicle is located and the associated lanes of the target vehicle; and generating the set of lane connections corresponding to the target vehicle based on the filtering results.
[0079] In this embodiment of the application, when obtaining the set of lane connection lines corresponding to the target vehicle, the lane set LaneA of the lane where the target vehicle is located can be extracted from the high-precision map data. For example, the lane set LaneA may include lane information such as lane 01 where the target vehicle a is located and lane 02 where the target vehicle b is located. Then, based on the lane set LaneA of the lane where the target vehicle is located, the associated lanes of each target vehicle are determined. This can be determined based on the lane connection lines in the local high-precision map data. For example, there is a lane connection line between lane 01 and lane 03 where the target vehicle a is located, and there is a lane connection line between lane 02 and lane 04. Then lane 03 and lane 04 can be regarded as the associated lanes of the target vehicle, representing all possible next lanes that the target vehicle can enter from its current lane.
[0080] Then, based on the lane set LaneA where the target vehicle is located and the associated lanes, the vehicle's trajectory planning information is used to filter lane connection lines, thereby filtering out lane connection lines that do not obviously intersect with the vehicle's planned trajectory. Then, a lane connection line set LinesB can be generated based on the finally filtered lane connection lines.
[0081] In one embodiment of this application, the step of constructing a virtual lane corresponding to the vehicle based on the vehicle's trajectory planning information, and constructing a virtual lane set corresponding to the target vehicle based on the lane connection line set, includes: obtaining vehicle width information and lateral safety buffer information, and constructing a virtual lane corresponding to the vehicle based on the vehicle width information, the lateral safety buffer information, and the vehicle's trajectory planning information; extracting each lane connection line from the lane connection line set, and constructing a virtual lane based on the lane width corresponding to each lane connection line, thereby obtaining the virtual lane set corresponding to the target vehicle.
[0082] In constructing the virtual lane ego-Lane for a vehicle, this application embodiment can consider the vehicle's width ego-width and the size of the lateral safety buffer safe-buffer. The lateral buffer can be seen as the safe distance between the vehicle and the sides of the lane when the vehicle is driving on the lane. In this way, a virtual lane that conforms to the actual scenario can be established to represent the lane in which the vehicle is driving in the traffic intersection area.
[0083] In this embodiment of the application, when constructing the virtual lane set LaneB corresponding to the target vehicle, lane connecting lines can be extracted sequentially from the lane connecting line set LinesB, and then the virtual lane corresponding to each lane connecting line can be constructed in combination with the lane width. For example, the lane connecting line can be used as the center line of the virtual lane to be generated, and half the lane width can be extended outward on the left and right sides respectively, thereby generating the virtual lane set LaneB corresponding to the lane connecting line set LinesB.
[0084] In one embodiment of this application, determining the conflict zone of the vehicle at the current traffic intersection based on the virtual lane corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle includes: determining the overlapping area of the virtual lane corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle; and using the overlapping area as the conflict zone of the vehicle at the current traffic intersection.
[0085] In determining the conflict passage area, this application embodiment can determine the overlapping area based on each virtual lane in the virtual lane set LaneB corresponding to the vehicle and the target vehicle. This overlapping area indicates that the vehicle and the target vehicle may intersect on their driving trajectories, and therefore can be used as the conflict passage area ConflictZ in this application embodiment.
[0086] Since the set of virtual lanes LaneB corresponding to the virtual target vehicle includes multiple virtual lanes, these multiple virtual lanes may overlap with the virtual lane corresponding to the vehicle. Each overlapping area can be treated as a separate conflict passage area for subsequent processing.
[0087] In one embodiment of this application, determining the arrival time of the vehicle and the target vehicle at the conflict passage area includes: obtaining the lane set where the target vehicle is located, and constructing a Frenet coordinate system based on the lane set and the virtual lane set; mapping the observation information of the target vehicle to the Frenet coordinate system; and determining the arrival time of the target vehicle at the conflict passage area based on the observation information of the target vehicle in the Frenet coordinate system.
[0088] As mentioned earlier, a conflict zone indicates that the vehicle and the target vehicle have spatial overlap, but it does not mean that the vehicle and the target vehicle will definitely meet in the conflict zone. This is because the arrival times of the vehicle and the target vehicle in the conflict zone must also be considered. The probability of a conflict between the vehicle and the target vehicle is higher when their arrival times are the same or very close.
[0089] Based on this, the embodiments of this application can first determine the time when the target vehicle arrives at the conflict passage area. Specifically, first, the set of lanes LaneA and the set of virtual lanes LaneB where the target vehicle is located, as determined in the aforementioned embodiments, are obtained. Then, the lanes in LaneA and LaneB are extracted in sequence, and a Frenet coordinate system is constructed based on the connection relationship between the lanes. The Frenet coordinate system is a lane coordinate system that describes the position of the vehicle relative to the road. The vertical axis represents the distance along the road, and the horizontal axis represents the lateral vertical displacement relative to the vertical line. When the vehicle moves forward in the Frenet coordinate system, its trajectory in the lane is a straight line, which greatly simplifies the difficulty of trajectory planning.
[0090] After establishing the Frenet coordinate system, the observation information of the target vehicle sensed by the vehicle can be mapped to the Frenet coordinate system through coordinate transformation. Then, based on the observation information of the target vehicle in the Frenet coordinate system, the time for the target vehicle to reach the conflict crossing area can be calculated, specifically the time to reach the boundary position of the conflict crossing area. This observation information can include, for example, the target vehicle's current position, velocity Vxobj, and acceleration Axobj. Based on this observation information, the time for the target vehicle to reach the conflict crossing area can be calculated using the displacement calculation formula.
[0091] It should be noted that when there are multiple target vehicles, the time object-Ti for each target vehicle to reach its corresponding conflict passage area can be calculated separately.
[0092] In one embodiment of this application, determining the time when the vehicle and the target vehicle arrive at the conflict passage area includes: obtaining a set of accelerations of the vehicle, the set of accelerations including multiple accelerations of the vehicle; and determining the time set when the vehicle arrives at the conflict passage area when the vehicle is traveling with multiple accelerations respectively.
[0093] Based on the aforementioned embodiments, in addition to calculating the time it takes for the target vehicle to reach the conflict passage area, it is also necessary to calculate the time it takes for the self-vehicle to reach the conflict passage area. Since the self-vehicle needs to avoid meeting the target vehicle in the conflict passage area as much as possible, the self-vehicle needs to determine an optimal driving state as much as possible. Before that, multiple different driving states of the self-vehicle can be designed and the effect of each driving state can be evaluated.
[0094] Since the current speed of the vehicle is fixed, the time it takes for the vehicle to reach the conflict passage area is mainly determined by the vehicle's acceleration. Therefore, in this embodiment, an acceleration set Ax of the vehicle can be constructed in advance according to a certain strategy. The acceleration set Ax includes multiple accelerations that the vehicle can achieve or is allowed to achieve. Then, the time it takes for the vehicle to reach the conflict passage area when it travels at each acceleration based on the current speed is calculated to obtain a time set ego-Ti.
[0095] In one embodiment of this application, obtaining the acceleration set of the vehicle includes: constructing acceleration constraints for the vehicle based on parameter information of preset acceleration constraints, wherein the parameter information of the preset acceleration constraints includes at least one of the speed limit value of the current traffic intersection, the size information of the vehicle, the speed limit of the vehicle, and the acceleration limit; performing acceleration sampling according to a preset sampling interval based on the acceleration constraints of the vehicle to obtain multiple acceleration sampling values; and generating the acceleration set of the vehicle based on the multiple acceleration sampling values.
[0096] The embodiments of this application can generate a set of vehicle accelerations based on preset acceleration constraints. The preset acceleration constraints can be used to characterize a range of accelerations that the vehicle can achieve or is allowed to achieve. For example, the preset acceleration constraint rule-Ax can be constructed based on multiple parameters such as the speed limit value of the traffic intersection, the length and width of the vehicle, and the speed and acceleration limits of the vehicle.
[0097] Under this preset acceleration constraint, acceleration sampling can be performed at certain sampling intervals. For example, if the preset acceleration constraint determines an acceleration range of [-2, 2], then sampling can be performed within the range of [-2, 2] with a step size of 1, resulting in an acceleration set {-2, -1, 0, 1, 2} composed of multiple acceleration sample values. Of course, in addition to equal-interval sampling, non-equal-interval sampling is also possible. The specific sampling method can be flexibly set by those skilled in the art according to actual needs, and is not specifically limited here.
[0098] In one embodiment of this application, determining the travel strategy of the vehicle at the current traffic intersection based on the arrival times of the vehicle and the target vehicle at the conflict crossing area includes: determining a collision probability set between the vehicle and the target vehicle based on the time set of arrival times of the vehicle at the conflict crossing area and the time of arrival of the target vehicle at the conflict crossing area; determining the minimum collision probability in the collision probability set; determining the target time corresponding to the minimum collision probability in the time set of arrival times of the vehicle at the conflict crossing area; and determining the target acceleration corresponding to the target time in the acceleration set, so as to control the vehicle to travel at the current traffic intersection according to the target acceleration.
[0099] After obtaining the time set ego-Ti for the voluntary vehicle's arrival in the conflict zone and the time object-Ti for the target vehicle's arrival in the conflict zone, the collision probability between the voluntary and target vehicles in the conflict zone can be calculated based on each time in ego-Ti and the time of the target vehicle's arrival in the conflict zone, resulting in a collision probability set P. After obtaining the collision probability set P, the target time corresponding to the minimum collision probability can be determined from P, and the target acceleration corresponding to that target time can then be used as the vehicle's decision-making behavior.
[0100] Since there may be multiple target vehicles and multiple conflict zones, the collision probability set can be calculated separately for each target vehicle in each conflict zone during the actual calculation. For example, it can be represented in the form shown in Table 1 below:
[0101] Table 1
[0102]
[0103] When there are multiple collision probability sets, the one with the smallest overall collision probability can be selected. Alternatively, the relative positional relationship between the vehicle and each target vehicle and the conflict passage area can be comprehensively considered to select the optimal collision probability.
[0104] In addition, when calculating the collision probability set, in addition to considering the time it takes for the vehicle and the target vehicle to arrive at the conflict passage area, we can also consider the distance between the vehicle and each target vehicle and whether there is spatiotemporal overlap between the vehicle and each target vehicle. The farther the distance, the lower the collision probability. The lower the degree of spatiotemporal overlap, the lower the collision probability.
[0105] This application also provides a traffic intersection passage device 300, such as... Figure 3As shown, a schematic diagram of a traffic intersection passage device according to an embodiment of this application is provided. The device 300 includes: a first determining unit 310, an acquiring unit 320, a constructing unit 330, a second determining unit 340, and a third determining unit 350, wherein:
[0106] The first determining unit 310 is used to acquire the trajectory planning information of the vehicle and determine the target vehicle corresponding to the vehicle at the current traffic intersection based on the trajectory planning information of the vehicle.
[0107] The acquisition unit 320 is used to acquire the set of lane connection lines corresponding to the target vehicle based on the trajectory planning information of the vehicle and local high-precision map data.
[0108] The construction unit 330 is used to construct a virtual lane corresponding to the vehicle based on the trajectory planning information of the vehicle, and to construct a set of virtual lanes corresponding to the target vehicle based on the set of lane connection lines.
[0109] The second determining unit 340 is used to determine the conflict passage area of the vehicle at the current traffic intersection based on the virtual lane corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle.
[0110] The third determining unit 350 is used to determine the time when the autonomous vehicle and the target vehicle arrive at the conflict passage area, and to determine the autonomous vehicle's passage strategy at the current traffic intersection based on the time when the autonomous vehicle and the target vehicle arrive at the conflict passage area.
[0111] In one embodiment of this application, the acquisition unit 320 is specifically used to: acquire the lane set where the target vehicle is located based on the local high-precision map data; determine the associated lanes of the target vehicle based on the lane set where the target vehicle is located; perform lane filtering using the vehicle's trajectory planning information based on the lane set where the target vehicle is located and the associated lanes of the target vehicle; and generate a set of lane connection lines corresponding to the target vehicle based on the filtering results.
[0112] In one embodiment of this application, the construction unit 330 is specifically used to: obtain vehicle width information and lateral safety buffer information, and construct a virtual lane corresponding to the vehicle based on the vehicle width information, the lateral safety buffer information and the vehicle's trajectory planning information; extract each lane connection line from the lane connection line set, and construct a virtual lane based on the lane width corresponding to each lane connection line, thereby obtaining a set of virtual lanes corresponding to the target vehicle.
[0113] In one embodiment of this application, the second determining unit 340 is specifically used to: determine the overlapping area of the virtual lane corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle; and use the overlapping area as the conflict passage area of the vehicle at the current traffic intersection.
[0114] In one embodiment of this application, the third determining unit 350 is specifically used to: obtain the set of lanes where the target vehicle is located, and construct a Frenet coordinate system based on the set of lanes and the set of virtual lanes; map the observation information of the target vehicle to the Frenet coordinate system; and determine the time when the target vehicle arrives at the conflict passage area based on the observation information of the target vehicle in the Frenet coordinate system.
[0115] In one embodiment of this application, the third determining unit 350 is specifically used to: obtain the acceleration set of the vehicle, the acceleration set including multiple accelerations of the vehicle; and determine the time set of the vehicle arriving at the conflict passage area when the vehicle is traveling with multiple accelerations respectively.
[0116] In one embodiment of this application, the third determining unit 350 is specifically used to: construct the acceleration constraint of the vehicle according to the parameter information of the preset acceleration constraint, wherein the parameter information of the preset acceleration constraint includes at least one of the speed limit value of the current traffic intersection, the size information of the vehicle, the speed limit of the vehicle, and the acceleration limit; perform acceleration sampling according to the preset sampling interval based on the acceleration constraint of the vehicle to obtain multiple acceleration sampling values; and generate the acceleration set of the vehicle according to the multiple acceleration sampling values.
[0117] In one embodiment of this application, the third determining unit 350 is specifically configured to: determine a collision probability set between the vehicle and the target vehicle based on the time set of times the vehicle arrives at the conflict crossing area and the time of the target vehicle arriving at the conflict crossing area; determine the minimum collision probability in the collision probability set; determine the target time corresponding to the minimum collision probability in the time set of times the vehicle arrives at the conflict crossing area; and determine the target acceleration corresponding to the target time in the acceleration set, so as to control the vehicle to pass through the current traffic intersection according to the target acceleration.
[0118] It is understood that the above-mentioned traffic intersection passage device can realize each step of the traffic intersection passage method provided in the foregoing embodiments. The relevant explanations of the traffic intersection passage method are applicable to the traffic intersection passage device, and will not be repeated here.
[0119] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.
[0120] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.
[0121] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.
[0122] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, logically forming a traffic intersection control system. The processor executes the program stored in memory and specifically performs the following operations:
[0123] Obtain the trajectory planning information of the vehicle, and determine the target vehicle corresponding to the vehicle at the current traffic intersection based on the trajectory planning information of the vehicle;
[0124] Based on the vehicle's trajectory planning information and local high-precision map data, obtain the set of lane connection lines corresponding to the target vehicle;
[0125] The virtual lane corresponding to the vehicle is constructed based on the trajectory planning information of the vehicle, and the virtual lane set corresponding to the target vehicle is constructed based on the set of lane connection lines.
[0126] Based on the set of virtual lanes corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle, the conflict zone of the vehicle at the current traffic intersection is determined;
[0127] The arrival times of the autonomous vehicle and the target vehicle at the conflict zone are determined, and the autonomous vehicle's passage strategy at the current traffic intersection is determined based on the arrival times of the autonomous vehicle and the target vehicle at the conflict zone.
[0128] The above is as stated in this application. Figure 1 The method executed by the traffic intersection passage device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.
[0129] The electronic device can also perform Figure 1 The method for implementing traffic control devices at intersections, and the realization of traffic control devices at intersections in... Figure 1 The functions of the embodiments shown are not described in detail here.
[0130] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the traffic intersection passage device in the illustrated embodiment is specifically used to perform the following:
[0131] Obtain the trajectory planning information of the vehicle, and determine the target vehicle corresponding to the vehicle at the current traffic intersection based on the trajectory planning information of the vehicle;
[0132] Based on the vehicle's trajectory planning information and local high-precision map data, obtain the set of lane connection lines corresponding to the target vehicle;
[0133] The virtual lane corresponding to the vehicle is constructed based on the trajectory planning information of the vehicle, and the virtual lane set corresponding to the target vehicle is constructed based on the set of lane connection lines.
[0134] Based on the set of virtual lanes corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle, the conflict zone of the vehicle at the current traffic intersection is determined;
[0135] The arrival times of the autonomous vehicle and the target vehicle at the conflict zone are determined, and the autonomous vehicle's passage strategy at the current traffic intersection is determined based on the arrival times of the autonomous vehicle and the target vehicle at the conflict zone.
[0136] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.
[0137] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0138] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0139] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0140] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0141] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0142] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0143] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0144] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied 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.
[0145] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for navigating traffic at an intersection, wherein, The method includes: Obtain the trajectory planning information of the vehicle, and determine the target vehicle corresponding to the vehicle at the current traffic intersection based on the trajectory planning information of the vehicle; Based on the vehicle's trajectory planning information and local high-precision map data, obtain the set of lane connection lines corresponding to the target vehicle; The virtual lane corresponding to the vehicle is constructed based on the trajectory planning information of the vehicle, and the virtual lane set corresponding to the target vehicle is constructed based on the set of lane connection lines. Based on the set of virtual lanes corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle, the conflict zone of the vehicle at the current traffic intersection is determined; Determine the time when the autonomous vehicle and the target vehicle arrive at the conflict passage area, and determine the autonomous vehicle's passage strategy at the current traffic intersection based on the time when the autonomous vehicle and the target vehicle arrive at the conflict passage area; The step of obtaining the set of lane connection lines corresponding to the target vehicle based on the vehicle's trajectory planning information and local high-precision map data includes: Based on the local high-precision map data, determine the lane connection line corresponding to the lane where the target vehicle is located; Based on the trajectory planning information of the vehicle and the lane connection line corresponding to the lane where the target vehicle is located, determine the intersection between the lane connection line corresponding to the lane where the target vehicle is located and the driving trajectory of the vehicle at the current traffic intersection. Determine the set of lane connection lines corresponding to the target vehicle based on the intersection situation; The determination of the time when the vehicle and the target vehicle arrive at the conflict passage area includes: Obtain the set of accelerations of the vehicle, wherein the set of accelerations includes multiple accelerations of the vehicle; When the vehicle is traveling at multiple accelerations, determine the set of times when the vehicle arrives at the conflict passage area.
2. The method as described in claim 1, wherein, The step of obtaining the set of lane connection lines corresponding to the target vehicle based on the vehicle's trajectory planning information and local high-precision map data includes: Based on the local high-precision map data, obtain the set of lanes where the target vehicle is located; The associated lane of the target vehicle is determined based on the set of lanes in which the target vehicle is located; Based on the lane set where the target vehicle is located and the associated lanes of the target vehicle, lane selection is performed using the vehicle's trajectory planning information; Based on the filtering results, a set of lane connection lines corresponding to the target vehicle is generated.
3. The method as described in claim 1, wherein, The steps of constructing a virtual lane corresponding to the vehicle based on the vehicle's trajectory planning information, and constructing a virtual lane set corresponding to the target vehicle based on the lane connection line set, include: Obtain vehicle width information and lateral safety buffer information, and construct a virtual lane corresponding to the vehicle based on the vehicle width information, the lateral safety buffer information and the vehicle's trajectory planning information; Each lane connector is extracted from the set of lane connectors, and a virtual lane is constructed based on the lane width corresponding to each lane connector, thus obtaining the set of virtual lanes corresponding to the target vehicle.
4. The method as described in claim 1, wherein, The step of determining the conflict zone of the vehicle at the current traffic intersection based on the virtual lane corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle includes: Determine the overlapping area between the virtual lane corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle; The overlapping area is taken as the conflict passage area of the vehicle at the current traffic intersection.
5. The method as described in claim 1, wherein, The determination of the time when the vehicle and the target vehicle arrive at the conflict passage area includes: Obtain the set of lanes where the target vehicle is located, and construct a Frenet coordinate system based on the set of lanes and the set of virtual lanes; The observation information of the target vehicle is mapped onto the Frenet coordinate system; Based on the observation information of the target vehicle in the Frenet coordinate system, the time when the target vehicle arrives at the conflict passage area is determined.
6. The method of claim 1, wherein, The process of obtaining the set of accelerations of the vehicle includes: Based on the parameter information of the preset acceleration constraint, the acceleration constraint of the vehicle is constructed. The parameter information of the preset acceleration constraint includes at least one of the following: the speed limit value of the current traffic intersection, the size information of the vehicle, the speed limit of the vehicle, and the acceleration limit. Based on the vehicle's acceleration constraints, acceleration is sampled at preset sampling intervals to obtain multiple acceleration sample values; The vehicle's acceleration set is generated based on multiple acceleration sample values.
7. The method of claim 1, wherein, The step of determining the vehicle's passage strategy at the current traffic intersection based on the arrival times of the vehicle and the target vehicle at the conflict passage area includes: Based on the time set of the vehicle arriving at the conflict zone and the time of the target vehicle arriving at the conflict zone, determine the collision probability set between the vehicle and the target vehicle; Determine the minimum collision probability in the set of collision probabilities; Determine the target time corresponding to the minimum collision probability from the set of times when the vehicle arrives at the conflict passage area; A target acceleration corresponding to the target time is determined from the set of accelerations, so as to control the vehicle to pass through the current traffic intersection according to the target acceleration.
8. A traffic intersection control device, wherein, The device includes: The first determining unit is used to acquire the trajectory planning information of the vehicle and determine the target vehicle corresponding to the vehicle at the current traffic intersection based on the trajectory planning information of the vehicle. The acquisition unit is used to acquire the set of lane connection lines corresponding to the target vehicle based on the trajectory planning information of the vehicle and local high-precision map data; The construction unit is used to construct a virtual lane corresponding to the vehicle based on the vehicle's trajectory planning information, and to construct a set of virtual lanes corresponding to the target vehicle based on the set of lane connection lines. The second determining unit is used to determine the conflict passage area of the vehicle at the current traffic intersection based on the virtual lane corresponding to the vehicle and the set of virtual lanes corresponding to the target vehicle. The third determining unit is used to determine the time when the autonomous vehicle and the target vehicle arrive at the conflict passage area, and to determine the autonomous vehicle's passage strategy at the current traffic intersection based on the time when the autonomous vehicle and the target vehicle arrive at the conflict passage area. The acquisition unit is specifically used for: Based on the local high-precision map data, determine the lane connection line corresponding to the lane where the target vehicle is located; Based on the trajectory planning information of the vehicle and the lane connection line corresponding to the lane where the target vehicle is located, determine the intersection between the lane connection line corresponding to the lane where the target vehicle is located and the driving trajectory of the vehicle at the current traffic intersection. Determine the set of lane connection lines corresponding to the target vehicle based on the intersection situation; The third determining unit is specifically used for: Obtain the set of accelerations of the vehicle, wherein the set of accelerations includes multiple accelerations of the vehicle; When the vehicle is traveling at multiple accelerations, determine the set of times when the vehicle arrives at the conflict passage area.
9. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 7.
10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method of any one of claims 1 to 7.