A method and device for determining a target path based on a path weight model

Abstract

An embodiment of the present invention provides a method and device for determining a target path based on a path weight model, the method comprising: obtaining a target scene element of a current driving scene of a moving vehicle; calculating the path weight according to the target scene element through a preset path weight model corresponding to different driving directions, and generating path weights corresponding to different driving directions; determining the target path from the paths of different driving directions according to the path weights corresponding to different driving directions, being able to flexibly formulate the vehicle's automatic driving control strategy according to real-time traffic conditions, and improving the safety of the vehicle's automatic driving; being able to more accurately determine the vehicle's driving strategy and improve the accuracy of decision-making.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method and device for determining a target path based on a path weight model. Background Art

[0002] Autonomous driving technology has made rapid progress in recent years, but safety has become a key issue facing autonomous driving technology. Safety is an important factor hindering the commercialization of autonomous vehicles and has also been a research hotspot in recent years. The autonomous driving decision-making planning module, as the "brain" of autonomous vehicles, has a significant impact on the safety of autonomous vehicles, especially in complex urban scenarios such as intersections. How to make autonomous and safe decisions has been widely studied in recent years.

[0003] In related technologies, the decision-making and planning module of autonomous driving vehicles mainly relies on static maps and preset path information to generate optimal driving behaviors, thereby safely completing driving tasks. However, this method cannot flexibly formulate the vehicle's autonomous driving control strategy according to real-time traffic conditions, resulting in low safety of vehicle autonomous driving. Summary of the invention

[0004] One object of the present invention is to provide a target path determination method based on a path weight model, which can flexibly formulate a vehicle's automatic driving control strategy according to real-time traffic conditions to improve the safety of vehicle automatic driving; it can more accurately determine the vehicle's driving strategy and improve the accuracy of decision-making. Another object of the present invention is to provide a target path determination device based on a path weight model. Another object of the present invention is to provide a computer-readable medium. Another object of the present invention is to provide a computer device.

[0005] In order to achieve the above objectives, the present invention discloses, on one hand, a target path determination method based on a path weight model, comprising:

[0006] Obtaining a target scene element of a current driving scene of a moving vehicle;

[0007] By using the preset path weight model corresponding to different driving directions, the path weight is calculated according to the target scene elements to generate the path weight corresponding to different driving directions;

[0008] According to the path weights corresponding to different driving directions, the target path is determined from the paths in different driving directions.

[0009] Preferably, before obtaining the target scene element of the current driving scene of the driving vehicle, the method further includes:

[0010] Get the current navigation path of the moving vehicle;

[0011] Generate a driving distance between the vehicle and the current intersection according to the current navigation path;

[0012] Determine whether the driving distance is less than a preset distance threshold;

[0013] If yes, continue to execute the step of obtaining the target scene element of the current driving scene of the driving vehicle;

[0014] If not, continue to execute the step of obtaining the current navigation path of the moving vehicle until the driving distance is less than the distance threshold.

[0015] Preferably, obtaining the target scene element of the current driving scene of the driving vehicle includes:

[0016] According to the current crossroad in the current navigation path, the confluence point and confluence point of each intersection are used as vertices, and the connection line between the confluence point and the confluence point is used as a directed connection edge to construct a path directed graph of the crossroad;

[0017] By using the recognition device, scene elements are recognized according to the path directed graph of the crossroads to generate target scene elements.

[0018] Preferably, the path weight models corresponding to different driving directions include a right-turn driving path weight model, a straight-through driving path signal light model, a left-turn driving path weight model, and a left-turn U-turn driving path weight model; the target scene elements include pedestrians at the confluence point, vehicles at the confluence point, pedestrians at the confluence point, vehicles at the confluence point, and the current signal light status;

[0019] Through the preset path weight model corresponding to different driving directions, the path weight is calculated according to the target scene elements to generate the path weight corresponding to different driving directions, including:

[0020] The right-turn path weight model is used to generate the right-turn path weight according to the preset signal light weight coefficient, vehicle driving parameters, pedestrians at the outgoing point, vehicles at the outgoing point, pedestrians at the incoming point, vehicles at the incoming point and the current signal light status;

[0021] The straight path weight is generated through the straight driving path signal light model according to the signal light weight coefficient, vehicle driving parameters and current signal light status;

[0022] The left-turn path weight model is used to generate the left-turn path weight according to the signal light weight coefficient, vehicle driving parameters, pedestrians at the confluence point, and the current signal light status;

[0023] The left-turn U-turn path weight model is used to generate the left-turn U-turn path weight according to the traffic light weight coefficient, vehicle driving parameters, vehicles at the merging point, vehicles at the merging point and the current traffic light status.

[0024] Preferably, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light;

[0025] The right-turn path weight model is used to generate the right-turn path weight according to the preset traffic light weight coefficient, vehicle driving parameters, pedestrians at the outgoing point, vehicles at the outgoing point, pedestrians at the incoming point, vehicles at the incoming point, and the current traffic light status, including:

[0026] By using the preset right-turn path parameters, the pedestrian influencing factor for right-turn pedestrians is generated by calculating according to the dynamic information of pedestrians on the crosswalk where the merging point on the right-turn path is located and pedestrians on the crosswalk where the merging point on the right-turn path is located;

[0027] Generate the signal light impact factor based on the signal light weight coefficient and the signal light start and end time according to the merging time;

[0028] Calculate according to the driving information of the vehicles on the motor vehicle lane where the exit point on the right-turn path is located, and generate the right-turn vehicle impact factor;

[0029] The right-turn path weight is generated based on the right-turn pedestrian influence factor, signal light influence factor and vehicle influence factor.

[0030] Preferably, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light;

[0031] Through the straight driving path signal light model, according to the signal light weight coefficient, vehicle driving parameters and current signal light status, the straight path weight is generated, including:

[0032] The straight path weight is generated based on the traffic light weight coefficient and the traffic light start and end times according to the merging time.

[0033] Preferably, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light;

[0034] The left-turn path weight model is used to generate the left-turn path weight according to the traffic light weight coefficient, vehicle driving parameters, pedestrians at the confluence point, and the current traffic light status, including:

[0035] Generate the signal light impact factor based on the signal light weight coefficient and the signal light start and end time according to the merging time;

[0036] By using the preset left-turn path parameters, the left-turn pedestrian impact factor is generated by calculating according to the dynamic information of pedestrians on the crosswalk where the confluence point on the left-turn path is located and the dynamic information of pedestrians on the non-motorized vehicle lane where the confluence point on the left-turn path is located;

[0037] Generate the left-turn path weight based on the traffic light influence factor and the left-turn pedestrian influence factor.

[0038] Preferably, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light;

[0039] The left-turn U-turn path weight model is used to generate the left-turn U-turn path weight according to the traffic light weight coefficient, vehicle driving parameters, outgoing point vehicle, incoming point vehicle and current traffic light status, including:

[0040] The first left-turn U-turn vehicle impact factor is generated by calculating the preset left-turn U-turn path parameters, the start and end times of the signal lights, and the merging time according to the driving information of the vehicles on the motor vehicle lane at the merging point on the left-turn U-turn path;

[0041] Generate a second left-turn vehicle impact factor based on the preset left-turn path parameters, signal light start and end times, and merging time;

[0042] The third left-turn U-turn vehicle impact factor is generated by calculating the preset left-turn U-turn path parameters and the merging time according to the driving information of the vehicle on the motor vehicle lane where the merging point on the left-turn U-turn path is located;

[0043] A left-turn U-turn path weight is generated according to the first left-turn U-turn vehicle influence factor, the second left-turn U-turn vehicle influence factor and the third left-turn U-turn vehicle influence factor.

[0044] The present invention also discloses a target path determination device based on a path weight model, comprising:

[0045] A target scene element acquisition unit, used to acquire a target scene element of a current driving scene of a driving vehicle;

[0046] A path weight generating unit, used to calculate the path weight according to the target scene elements by using the preset path weight models corresponding to different driving directions, and generate the path weights corresponding to different driving directions;

[0047] The target path determination unit is used to determine the target path from the paths of different driving directions according to the path weights corresponding to the different driving directions.

[0048] Preferably, the device further comprises:

[0049] A current navigation path acquisition unit, used to acquire the current navigation path of the moving vehicle;

[0050] A driving distance generating unit, used for generating a driving distance between a driving vehicle and a current crossroad according to a current navigation path;

[0051] The judgment unit is used to judge whether the driving distance is less than a preset distance threshold; if so, trigger the target scene element acquisition unit to continue to execute the step of acquiring the target scene element of the current driving scene of the driving vehicle; if not, trigger the current navigation path acquisition unit to continue to execute the step of acquiring the current navigation path of the driving vehicle until the driving distance is less than the distance threshold.

[0052] Preferably, the target scene element acquisition unit is specifically used to construct a path directed graph of the crossroad according to the current crossroad in the current navigation path, with the confluence point and the confluence point of each intersection as vertices, and the connection line between the confluence point and the confluence point as a directed connection edge; through the recognition device, scene elements are recognized according to the path directed graph of the crossroad to generate target scene elements.

[0053] Preferably, the path weight models corresponding to different driving directions include a right-turn driving path weight model, a straight-through driving path signal light model, a left-turn driving path weight model, and a left-turn U-turn driving path weight model; the target scene elements include pedestrians at the confluence point, vehicles at the confluence point, pedestrians at the confluence point, vehicles at the confluence point, and the current signal light status;

[0054] The path weight generating unit is specifically used to generate the right turn path weight through the right turn driving path weight model according to the preset signal light weight coefficient, vehicle driving parameters, pedestrians at the confluence point, vehicles at the confluence point, pedestrians at the confluence point, vehicles at the confluence point and the current signal light status; generate the straight path weight through the straight driving path signal light model according to the signal light weight coefficient, vehicle driving parameters and the current signal light status; generate the left turn path weight through the left turn driving path weight model according to the signal light weight coefficient, vehicle driving parameters, pedestrians at the confluence point and the current signal light status; generate the left turn U-turn path weight through the left turn U-turn driving path weight model according to the signal light weight coefficient, vehicle driving parameters, vehicles at the confluence point, vehicles at the confluence point and the current signal light status.

[0055] Preferably, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light;

[0056] The path weight generation unit is specifically used to generate a right-turn pedestrian influence factor by calculating based on the dynamic information of pedestrians on the crosswalk at the merging point on the right-turn path and the pedestrians on the crosswalk at the exit point on the right-turn path through preset right-turn path parameters; generate a signal light influence factor based on the merging time through the signal light weight coefficient and the start and end times of the signal light; generate a right-turn vehicle influence factor by calculating based on the driving information of the vehicle on the motor vehicle lane at the exit point on the right-turn path; generate a right-turn path weight based on the right-turn pedestrian influence factor, the signal light influence factor and the vehicle influence factor.

[0057] Preferably, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light;

[0058] The path weight generating unit is specifically used to generate the straight path weight according to the merging time through the signal light weight coefficient and the signal light start and end time.

[0059] Preferably, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light;

[0060] The path weight generating unit is specifically used to generate a signal light influence factor according to the merging time through the signal light weight coefficient and the start and end time of the signal light; to generate a left-turn pedestrian influence factor through calculation based on the dynamic information of pedestrians on the crosswalk where the merging point on the left-turn path is located and the dynamic information of pedestrians on the non-motorized vehicle lane where the merging point on the left-turn path is located through the preset left-turn path parameters; and to generate a left-turn path weight based on the signal light influence factor and the left-turn pedestrian influence factor.

[0061] Preferably, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light;

[0062] The path weight generating unit is specifically used to generate a first left-turn U-turn vehicle impact factor by calculating according to the preset left-turn U-turn path parameters, the start and end times of the traffic lights and the merging time, based on the driving information of the vehicles on the motor vehicle lane where the confluence point on the left-turn U-turn path is located; generate a second left-turn vehicle impact factor by calculating according to the preset left-turn U-turn path parameters, the start and end times of the traffic lights and the merging time; generate a third left-turn vehicle impact factor by calculating according to the preset left-turn U-turn path parameters and the merging time, based on the driving information of the vehicles on the motor vehicle lane where the confluence point on the left-turn U-turn path is located; generate a left-turn U-turn path weight according to the first left-turn vehicle impact factor, the second left-turn vehicle impact factor and the third left-turn vehicle impact factor.

[0063] The present invention also discloses a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the method described above is implemented.

[0064] The present invention also discloses a computer device, including a memory and a processor, wherein the memory is used to store information including program instructions, the processor is used to control the execution of program instructions, and the processor implements the above method when executing the program.

[0065] The present invention also discloses a computer program product, including a computer program / instruction, and the method described above is implemented when the computer program / instruction is executed by a processor.

[0066] The present invention obtains target scene elements of the current driving scene of a moving vehicle; calculates path weights according to target scene elements through preset path weight models corresponding to different driving directions, and generates path weights corresponding to different driving directions; determines target paths from paths in different driving directions according to path weights corresponding to different driving directions, and can flexibly formulate vehicle automatic driving control strategies according to real-time traffic conditions, thereby improving the safety of vehicle automatic driving; and can more accurately determine the vehicle's driving strategy, thereby improving the accuracy of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0068] Figure 1 A flow chart of a method for determining a target path based on a path weight model provided by an embodiment of the present invention;

[0069] Figure 2 A flowchart of another method for determining a target path based on a path weight model provided by an embodiment of the present invention;

[0070] Figure 3 A schematic diagram of a crossroad provided by an embodiment of the present invention;

[0071] Figure 4 A directed graph of paths for constructing a crossroad provided by an embodiment of the present invention;

[0072] Figure 5 A schematic diagram of the structure of a target path determination device based on a path weight model provided by an embodiment of the present invention;

[0073] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0075] It should be noted that the target path determination method and device based on the path weight model disclosed in the present application can be used in the field of artificial intelligence technology, and can also be used in any field outside the field of artificial intelligence technology. The application field of the target path determination method and device based on the path weight model disclosed in the present application is not limited.

[0076] The following takes the target path determination device based on the path weight model as an example of the execution subject to illustrate the implementation process of the target path determination method based on the path weight model provided by the embodiment of the present invention. It can be understood that the execution subject of the target path determination method based on the path weight model provided by the embodiment of the present invention includes but is not limited to the target path determination device based on the path weight model.

[0077] Figure 1 A flow chart of a target path determination method based on a path weight model provided by an embodiment of the present invention is as follows: Figure 1 As shown, the method includes:

[0078] Step 101: Acquire a target scene element of a current driving scene of a driving vehicle.

[0079] Step 102: Calculate the path weight according to the target scene elements through the preset path weight model corresponding to different driving directions to generate the path weight corresponding to different driving directions.

[0080] In the embodiment of the present invention, the path weight models corresponding to different driving directions include a right turn driving path weight model, a straight driving path signal light model, a left turn driving path weight model and a left turn U-turn driving path weight model.

[0081] Step 103: Determine a target path from the paths of different driving directions according to the path weights corresponding to the different driving directions.

[0082] In the technical solution provided by the embodiment of the present invention, the target scene element of the current driving scene of the moving vehicle is obtained; the path weight model corresponding to different preset driving directions is used to calculate the path weight according to the target scene element, and the path weights corresponding to different driving directions are generated; according to the path weights corresponding to different driving directions, the target path is determined from the paths of different driving directions, and the vehicle's automatic driving control strategy can be flexibly formulated according to the real-time traffic conditions to improve the safety of the vehicle's automatic driving; the vehicle's driving strategy can be determined more accurately to improve the accuracy of decision-making.

[0083] Figure 2 A flowchart of another method for determining a target path based on a path weight model provided by an embodiment of the present invention is shown in FIG. Figure 2 As shown, the method includes:

[0084] Step 201: Obtain the current navigation path of the moving vehicle.

[0085] In the embodiment of the present invention, each step is performed by a target path determination device based on a path weight model.

[0086] In an embodiment of the present invention, the current navigation path is the path currently traveled by the moving vehicle. The current navigation path of the vehicle can be obtained through the vehicle's navigation system or map service, so as to timely understand the navigation route or driving direction currently planned to be followed by the vehicle, laying the foundation for the subsequent formulation of the automatic driving control strategy.

[0087] Step 202: Generate a driving distance between the vehicle and the current intersection based on the current navigation path.

[0088] In an embodiment of the present invention, the current crossroad is the crossroad closest to the traveling vehicle on the current navigation path, and the driving distance between the traveling vehicle and the current crossroad is calculated based on the position coordinates of the current crossroad and the position coordinates of the traveling vehicle.

[0089] Step 203 , determine whether the driving distance is less than a preset distance threshold, if so, execute step 204 ; if not, execute step 201 .

[0090] In the embodiment of the present invention, the distance threshold may be a distance preset by a user, or a distance obtained through a limited number of experiments, or a distance obtained through a limited number of computer simulations, which is not limited in the embodiment of the present invention.

[0091] In the embodiment of the present invention, if the driving distance is less than the distance threshold, it indicates that the driving vehicle is close to the current intersection, and a path decision can be made based on the current traffic conditions, and step 204 is continued; if the driving distance is greater than or equal to the distance threshold, it indicates that the driving vehicle is far away from the current intersection, and there is no need to make a path decision based on the current traffic conditions, and step 201 is continued until the driving distance is less than the distance threshold.

[0092] In an embodiment of the present invention, when a moving vehicle approaches a current intersection, special attention needs to be paid, because intersections are usually high-incidence areas for accidents and traffic conflicts. The preset distance serves as a safety threshold. When the driving distance of the moving vehicle from the intersection is less than the preset distance, the automatic driving system can trigger a specific response.

[0093] Step 204: Acquire a target scene element of the current driving scene of the driving vehicle.

[0094] In the embodiment of the present invention, step 204 specifically includes:

[0095] Step 2041: According to the current crossroad in the current navigation path, a directed graph of the path of the crossroad is constructed by taking the confluence point and the confluence point of each intersection as vertices and the connection line between the confluence point and the confluence point as a directed connection edge.

[0096] In the embodiment of the present invention, the current crossroad includes four intersections. According to the driving paths in different directions, the point of entering the crossroad is the confluence point, and the point of exiting the crossroad is the confluence point; each intersection includes an confluence point and an confluence point. Figure 3 A schematic diagram of a crossroad provided by an embodiment of the present invention, such as Figure 3 As shown, the crossroad includes four confluence points, namely, I1, I3, I5, and I7, and four confluence points, namely, I2, I4, I6, and I8, and each path corresponds to a set of confluence points and confluence points. Figure 3 It mainly describes the relationship between the driving path of the vehicle entering and exiting the intersection and related scene elements, so as to facilitate the subsequent decision-making planning of the autonomous driving vehicle.

[0097] Specifically, based on the graph theory method, the confluence points and confluence points of each intersection are used as vertices, and the lines between the confluence points and the confluence points are used as directed connecting edges to construct a path directed graph of the cross intersection. Figure 3 Taking the cross intersection shown in the figure as an example, a directed graph of the paths of the cross intersection is constructed. Figure 4 A directed graph of paths for constructing a crossroads is provided in an embodiment of the present invention, such as Figure 4 As shown, the confluence points I1, I3, I5, I7 and the confluence points I2, I4, I6, I8 are taken as vertices, and the lines between a group of confluence points and confluence points corresponding to each path are taken as directed connecting edges, namely: I1I2, I1I4, I1I6, I1I8, I7I2, I7I4, I7I6, I7I8, I3I2, I3I4, I3I6, I3I8, I5I2, I5I4, I5I6, I5I8, to construct a directed path graph of the cross intersection.

[0098] Furthermore, according to the graph theory method, this intersection scene can be modeled as: G={V,E}; where V is the vertex set and E is the connecting edge set.

[0099] Furthermore, the vertex set V can be expressed as: V={I1,I2,I3,I4I5,I6,I7,I8}; the edge set E can be expressed as:

[0100]

[0101] The adjacency matrix can be expressed as:

[0102]

[0103] Step 2042: Using the recognition device, scene element recognition is performed based on the path directed graph of the crossroad to generate target scene elements.

[0104] In the embodiment of the present invention, the recognition device includes but is not limited to radar, sensor, perception device and other devices with a function. Specifically, the recognition device recognizes the scene elements of the intersection according to the path directed graph of the intersection to generate the target scene elements.

[0105] In the embodiment of the present invention, scene elements refer to various environmental factors and conditions related to the current navigation path. Scene elements include but are not limited to the state of traffic lights, the position and speed of vehicles, the position and speed of pedestrians, road signs, etc. These elements will affect the driving strategy of the autonomous driving vehicle.

[0106] It is understandable that in the decision-making stage of an autonomous vehicle, there are multiple paths that the vehicle can choose from when entering an intersection to exiting an intersection, but the constraints for choosing each path are different, which determines the weight of each path. The weight of each path is affected by multiple scene elements such as the state of traffic lights, pedestrians, vehicles, crosswalks, lane lines, etc.

[0107] Furthermore, different driving paths correspond to different path weight models, and the weight of the path can be evaluated according to the scene elements corresponding to the path, thereby reflecting the suitability of following the current navigation path or adopting other driving strategies. Figure 3 In the cross intersection shown in the figure, the present invention takes the current driving vehicle SV merging into the intersection from the merging point I1 as an example. After the vehicle SV enters the intersection from the merging point I1, the merging points that can exit the intersection include I2, I4, I6 and I8. Therefore, the driving paths that the vehicle SV can choose include I1I2, I1I4, I1I6, and I1I8. The weight of each path is different, representing the different driving difficulty (or driving risk) of the path. According to different navigation paths of the vehicle, a corresponding weight model can be selected to evaluate the driving difficulty (or driving risk) of the path, that is: if the current navigation path of the current driving vehicle SV is a right turn driving path (i.e., path I1I2), then the target path weight model is the right turn driving path weight model; if the current navigation path of the vehicle SV is a straight driving path (i.e., path I1I4), then the target path weight model is the straight driving path weight model; if the current navigation path of the vehicle SV is a left turn driving path (i.e., path I1I6), then the target path weight model is the left turn driving path weight model; if the current navigation path of the vehicle SV is a left turn U-turn driving path (i.e., path I1I8), then the target path weight model is the left turn U-turn driving path weight model.

[0108] Step 205, generate a right turn path weight through a right turn driving path weight model according to preset traffic light weight coefficients, vehicle driving parameters, pedestrians at the outgoing point, vehicles at the outgoing point, pedestrians at the incoming point, vehicles at the incoming point and current traffic light status.

[0109] In the embodiment of the present invention, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light. Figure 3 As shown, when the current navigation path of the vehicle SV is the right-turn driving path I1I2, the scene elements that cause path interference include: pedestrians at the crosswalks at the I1 intersection and the I2 intersection, the vehicle V1 going straight at the I7 intersection, and the current traffic light status. Considering the right of way and traffic yield rules, the vehicle V2 turning left at the I5 intersection and the vehicle V3 turning around at the I3 intersection will not affect the vehicle SV's driving along the path I1I2.

[0110] In the embodiment of the present invention, step 205 specifically includes:

[0111] Step 2051: Generate a right-turn pedestrian impact factor by calculating based on preset right-turn path parameters and the dynamic information of pedestrians on the crosswalk at the merging point on the right-turn path and the pedestrians on the crosswalk at the merging point on the right-turn path.

[0112] In the embodiment of the present invention, the right turn path parameters include but are not limited to the pedestrian influence weight and the total width of the road. The right turn pedestrian influence factor includes the influence function of pedestrians at the crosswalk on the right turn path on the right turn path.

[0113] like Figure 3 As shown, in the embodiment of the present invention, the pedestrians on the crosswalk where the merging point on the right-turn path is located are P1 and P5, and the pedestrians on the crosswalk where the merging point on the right-turn path is located are P2 and P3.

[0114] Analyze the impact of pedestrians at the crosswalks at intersections I1 and I2 on the vehicle SV traveling along path I1I2:

[0115] The scene elements that are mainly affected by the vehicle SV on the driving path I1I2 include: pedestrians P1 and P5 on the crosswalk at the I1 intersection, and pedestrians P2 and P3 on the crosswalk at the I2 intersection. For pedestrians P1 and P2, both start from the edge of the right lane and walk toward the opposite road. If pedestrians P1 and P2 do not reach the center line of the road, the vehicle SV needs to stop and wait for the pedestrians to pass; if pedestrians P1 and P2 reach or exceed the center line of the road, the vehicle SV can continue to move forward. At this time, the influence function of pedestrians P1 and P2 on the driving path I1I2 can be expressed as:

[0116]

[0117] Among them, P pi (d i ) is the influence function of the ith pedestrian on the driving path I1I2; i is the pedestrian number; d i is the distance that the i-th pedestrian walks starting from the edge of the right lane; k i is the influence weight of the ith pedestrian; w represents the total width of the road.

[0118] Assume that the i-th pedestrian P i The walking speed is v i , then:

[0119] d i =v i ×t

[0120] Among them, d i is the distance that the ith pedestrian walks starting from the edge of the right lane, and t is the preset travel time from the current moment to the intersection; v i is the i-th pedestrian P i Walking speed.

[0121] For pedestrians P3 and P5, they walk towards pedestrians P2 and P1 respectively, and their starting point is at the edge of the left lane. When the walking distance of pedestrians P3 and P5 reaches or exceeds the center line of the road surface, they begin to affect the driving path I1I2 of vehicle SV. When they do not reach the center line of the road surface, they will not affect the driving path I1I2. Therefore, the influence function of pedestrians P3 and P5 on the driving path I1I2 can be expressed as follows:

[0122]

[0123] Among them, P pj (t) is the influence function of the jth pedestrian on the driving path I1I2; t is the preset driving time from the current moment to the intersection; j is the pedestrian number, k j is the influence weight of the preset j-th pedestrian, v j is the walking speed of the jth pedestrian; w represents the total width of the road.

[0124] like Figure 3 As shown, the right-turn pedestrian influence factor includes the influence function of the i-th pedestrian on the driving path I1I2 and the influence function of the j-th pedestrian on the driving path I1I2.

[0125] Step 2052: Generate a signal light influence factor according to the merging time by using the signal light weight coefficient and the start and end times of the signal light.

[0126] In an embodiment of the present invention, the traffic light weight coefficient includes but is not limited to the weight coefficient during the red light period, the weight coefficient during the yellow light period and the weight coefficient during the green light period; the traffic light start and end times include but are not limited to the red light start time, the red light end time, the yellow light start time, the yellow light end time, the green light start time and the green light end time.

[0127] like Figure 3 As shown, in the embodiment of the present invention, according to the traffic rules of turning right to go straight, when the vehicle SV turns right, it needs to give way to the straight-going vehicle V1, but the driving condition of the straight-going vehicle V1 is affected by the state of the signal light in front of the vehicle V1, and the signal light state can be divided into a green light pass stage, a yellow light deceleration and stop driving stage, and a red light no-go stage. In the green light pass stage, the vehicle V1 can drive straight normally, and the vehicle SV needs to give way to the straight-going vehicle V1; in the yellow light deceleration and stop driving stage, the vehicle SV needs to give way to other straight-going vehicles in the intersection; in the red light no-go driving stage, the vehicle SV drives along the path I1I2, and there is no need to consider the influence of other straight-going vehicles at other intersections.

[0128] Among them, the traffic light model can be expressed as:

[0129]

[0130] Among them, S(t) is the traffic light influence factor; k r is the weight coefficient during the red light period, T r0 is the start time of the red light, T r1 is the time when the red light ends, k y is the weight coefficient during the yellow light period, T y0 is the starting time of the yellow light, T y1 The yellow light ends at k g is the weight coefficient during the green light period, T g0 is the green light start time, T g1 is the green light end time, and T is the merging time.

[0131] Step 2053: Calculate according to the driving information of the vehicles on the motor vehicle lane where the exit point on the right-turn path is located to generate a right-turn vehicle impact factor.

[0132] In the embodiment of the present invention, the driving information includes but is not limited to the vehicle position, the vehicle influence coefficient and the vehicle driving speed. It is worth noting that the driving information here is the driving information of the vehicle on the motor vehicle lane where the confluence point on the right turn path is located. The right turn vehicle influence factor refers to the degree of influence of other vehicles in the cross intersection on the current right turn path.

[0133] like Figure 3As shown, the straight vehicle V1 is a vehicle on the motor vehicle lane where the exit point on the right-turn path is located. The impact of the straight vehicle V1 on the vehicle SV traveling along the path I1I2 is analyzed:

[0134] The negative correlation effect of the straight vehicle V1 and the distance d from V1 to the confluence point I2 V1 Inversely proportional, that is, the distance d V1 The larger the value is, the smaller the influence of the straight-moving vehicle V1 on the driving path I1I2 of the vehicle SV is. Then the influence function of the straight-moving vehicle V1 is as follows:

[0135]

[0136] Among them, μ c is the influence coefficient of the straight-moving vehicle V1; C1(d V1 ) is the right-turn vehicle impact factor of the straight-moving vehicle V1; d V1 is the distance from the straight-moving vehicle V1 to the confluence point I2.

[0137] Step 2054: Generate a right-turn path weight according to the right-turn pedestrian influence factor, the traffic light influence factor, and the vehicle influence factor.

[0138] In the embodiment of the present invention, it is assumed that the speed of the straight-moving vehicle V1 is v c , considering the influence of the traffic light status on the straight vehicle V1, the influence function of the straight vehicle V1 on the vehicle SV driving path I1I2 is:

[0139]

[0140] Among them, V s (t) is the right-turn path weight; S(t) is the traffic light influence factor; k r is the weight coefficient during the red light period, T r0 is the start time of the red light, T r1 is the time when the red light ends, k y is the weight coefficient during the yellow light period, T y0 is the starting time of the yellow light, T y1 The yellow light ends at k g is the weight coefficient during the green light period, T g0 is the green light start time, T g1 is the green light end time, T is the merging time; μ c is the influence coefficient of the straight-moving vehicle V1; C1(d V1 ) is the right-turn vehicle impact factor of the straight-moving vehicle V1; d V1 v is the distance from the straight-moving vehicle V1 to the confluence point I2; c is the speed of the straight-moving vehicle V1.

[0141] In summary, the right-turn driving path weight model is:

[0142]

[0143] Among them, I m I n (t) is path I m I n The right turn path weight, P pi (t) is the impact of pedestrians at the exit and entry points on the current navigation path when the pedestrians walk from the edge of the right lane to the opposite road, P pj (t) is the impact of pedestrians at the exit and entry points on the current navigation path when the pedestrian walks from the edge of the left lane to the opposite road, V sn (t) is the impact of conflicting vehicles at the outgoing point and the incoming point on the current navigation path.

[0144] Step 206: Generate a straight path weight through the straight driving path signal light model according to the signal light weight coefficient, the vehicle driving parameters and the current signal light status.

[0145] In the embodiment of the present invention, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light.

[0146] Specifically, the straight path weight is generated according to the merging time by using the traffic light weight coefficient and the traffic light start and end times.

[0147] In the embodiment of the present invention, the straight driving path signal light model is:

[0148]

[0149]

[0150] Among them, I m I n (t) is path I m I n The straight path weight; S(t) is the traffic light influence factor; k r is the weight coefficient during the red light period, T r0 is the start time of the red light, T r1 is the time when the red light ends, k y is the weight coefficient during the yellow light period, T y0 is the starting time of the yellow light, T y1 The yellow light ends at k g is the weight coefficient during the green light period, T g0 is the green light start time, T g1 is the green light end time, and T is the merging time.

[0151] like Figure 3 As shown in the figure, when the current navigation path of the vehicle SV is straight driving I1I4, it is mainly affected by the state of the traffic light in front of the vehicle SV. Considering the factors of traffic rules and road rights, other traffic scenes will not affect the path I1I4. Therefore, the weight model of the straight path I1I4 is:

[0152] I1I4(t)=S4(t)

[0153] Wherein, S4(t) is the traffic light model of the confluence point I4.

[0154] Step 207: Generate a left turn path weight through a left turn driving path weight model according to a traffic light weight coefficient, vehicle driving parameters, pedestrians at the exit point, and the current traffic light status.

[0155] In the embodiment of the present invention, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light.

[0156] In the embodiment of the present invention, step 207 specifically includes:

[0157] Step 2071: Generate a signal light influence factor according to the merging time by using the signal light weight coefficient and the start and end times of the signal light.

[0158] In an embodiment of the present invention, the traffic light weight coefficient includes but is not limited to the weight coefficient during the red light period, the weight coefficient during the yellow light period and the weight coefficient during the green light period; the traffic light start and end times include but are not limited to the red light start time, the red light end time, the yellow light start time, the yellow light end time, the green light start time and the green light end time.

[0159] The traffic light model can be expressed as:

[0160]

[0161] Among them, S(t) is the traffic light influence factor; k r is the weight coefficient during the red light period, T r0 is the start time of the red light, T r1 is the time when the red light ends, k y is the weight coefficient during the yellow light period, T y0 is the starting time of the yellow light, T y1 The yellow light ends at k g is the weight coefficient during the green light period, T g0 is the green light start time, T g1 is the green light end time, and T is the merging time.

[0162] Step 2072: Generate a left-turn pedestrian impact factor by calculating based on the preset left-turn path parameters and the dynamic information of pedestrians on the crosswalk where the confluence point on the left-turn path is located and the dynamic information of pedestrians on the non-motorized vehicle lane where the confluence point on the left-turn path is located.

[0163] In the embodiment of the present invention, the left turn path parameters include but are not limited to the influence weight of pedestrians and the total width of the road.

[0164] like Figure 3 As shown, when the current navigation path of the vehicle SV is the left-turn driving path I1I6, the main scene elements that cause path interference include: the current traffic light state, the dynamic information of pedestrians on the crosswalk at the confluence point on the left-turn path (pedestrian P7 at the crosswalk at intersection I6), and the dynamic information of pedestrians on the non-motorized vehicle lane at the confluence point on the left-turn path (pedestrian B1 riding a bicycle).

[0165] It is worth noting that the influence function of the cyclist B1 is the same as P in the above right-turn path weight model. pi (t), the influence function of pedestrian P7 is the same as P in the above right-turn driving path weight model pj (t).

[0166] Step 2073: Generate a left-turn path weight according to the traffic light influence factor and the left-turn pedestrian influence factor.

[0167] In an embodiment of the present invention, the left-turn pedestrian impact factor includes the impact of pedestrians at the exit point and the entrance point on the current navigation path when the pedestrian walks from the edge of the left lane road as the starting point to the opposite road, and the impact of pedestrians at the exit point and the entrance point on the current navigation path when the pedestrian riding a bicycle walks from the edge of the right lane road as the starting point to the opposite road.

[0168] In the embodiment of the present invention, the weight model of the left-turn driving path I1I6 is:

[0169]

[0170] Among them, S(t) is the traffic light influence factor; P pi (t) is the impact of pedestrians at the exit and entry points on the current navigation path when a cyclist walks from the edge of the right lane to the opposite road; P pj (t) is the impact of pedestrians at the exit and entry points on the current navigation path when the pedestrians start from the edge of the left lane and walk towards the opposite road; I 6,7 represents the set of pedestrians moving from the right side to the left side of the vehicle SV at the crosswalk at the intersection of I6 and I7, J 6,7Represents the set of pedestrians moving from the left side to the right side of the vehicle SV on the crosswalk at the intersection of I6 and I7.

[0171] In summary, the left-turn driving path weight model is:

[0172]

[0173] Among them, I m I n (t) is path I m I n The left-turn path weight; S(t) is the traffic light influence factor; P pi (t) is the impact of pedestrians at the exit and entry points on the current navigation path when a cyclist walks from the edge of the right lane to the opposite road; P pj (t) is the impact of pedestrians at the exit and entry points on the current navigation path when the pedestrian walks from the edge of the left lane to the opposite road.

[0174] Step 208: Generate a left turn path weight through a left turn driving path weight model according to a traffic light weight coefficient, vehicle driving parameters, a vehicle at an exit point, a vehicle at an entry point, and a current traffic light status.

[0175] In the embodiment of the present invention, the vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light.

[0176] like Figure 3 As shown, when the current navigation path of vehicle SV is the left-turn U-turn path I1I8, according to traffic rules, the U-turn vehicle has the lowest right of way. Therefore, the scene elements that interfere with path I1I8 include: vehicle V3 turning left at intersection I3, vehicle V2 going straight at intersection I5, and vehicle V1 turning right at intersection I7, among which vehicles V3 and V2 need to drive according to the traffic light status.

[0177] In the embodiment of the present invention, step 208 specifically includes:

[0178] Step 2081: Generate a first left-turn U-turn vehicle impact factor by calculating based on the preset left-turn U-turn path parameters, the start and end times of the traffic light, and the merging time according to the driving information of the vehicle on the motor vehicle lane where the merging point on the left-turn U-turn path is located.

[0179] In the embodiment of the present invention, the left turn path parameters include but are not limited to the influence weight of the vehicle, the influence weight of the specified driving conditions of the specified traffic light, and the distance between the intersection and the crossroad of each path.

[0180] like Figure 3As shown, the impact of the left-turning vehicle V3 on the vehicle SV traveling along the path I1I8 is analyzed:

[0181] According to traffic rules, when the green light at the I6 intersection comes on, vehicle V3 goes straight to the center point O of the intersection before turning left. Before vehicle V3 reaches the center point O, vehicle SV's left turn is not affected by vehicle V3. After vehicle V3 passes the center point O, vehicle V3 has priority over vehicle SV. Right of way at intersection.

[0182] Specifically, if the driving position of vehicle V3 exceeds the center point O of the intersection, the impact factor of vehicle V3 The value is the preset weight coefficient of the impact of vehicle V3 on other vehicles; if the driving position of vehicle V3 does not exceed the center point O of the intersection, the impact factor of vehicle V3 The value of is 0.

[0183] like Figure 3 As shown, in the embodiment of the present invention, when the yellow light or red light at the I6 intersection is on, when the vehicle V3 stops at the I8 intersection, it has no effect on the driving path I1I8. Therefore, after considering the state of the traffic light at the I6 intersection, the influence function of the left turn of the vehicle V3 on the driving path I1I8 of the vehicle SV is as follows:

[0184]

[0185] Among them, C3(t) is the influence factor of the vehicle V3 after the traffic light on the left-turning vehicle; T y06 T is the time when the yellow light of the traffic light at the I6 intersection starts to turn on; r16 The time when the red light of the I6 intersection ends; T g06 T is the time when the green light starts at the I6 intersection; g16 The green light ends at the I6 intersection; k S6 is the weight coefficient of the driving path I1I8 when the traffic light is yellow and red and the vehicle V3 stops at the intersection I3; T is the merging time; d O3 is the distance between the intersection I3 and the center point O of the intersection; v3 is the speed of vehicle V3 when passing through the intersection; k V3 It is the weight coefficient of the influence of the preset vehicle V3 on other vehicles.

[0186] In the embodiment of the present invention, the first left-turn U-turn vehicle impact factor includes the vehicle V3 impact factor And the impact factor C3(t) of the vehicle V3 behind the traffic light on the left-turning vehicle.

[0187] Step 2082: Generate a second left-turn U-turn vehicle impact factor according to the preset left-turn U-turn path parameters, the start and end times of the traffic light, and the merging time.

[0188] like Figure 3 As shown, in the embodiment of the present invention, since the straight vehicle V2 has the highest right of way, when the traffic light at the I8 intersection is green, the vehicle SV stops turning left and needs to give way to the vehicle V2; when the traffic light at the I8 intersection is yellow or red, the straight vehicle V2 does not affect the path I1I8. Therefore, the influence function of the straight vehicle V2 on the driving path I1I8 of the vehicle SV is:

[0189]

[0190] Where C2(t) is the impact factor of the second left-turn U-turn vehicle; k V2 is the weight coefficient of the impact of the straight-moving vehicle V2 on other vehicles; T y08 T is the time when the yellow light of the traffic light at intersection I8 starts; r18 The time when the red light of the traffic light at the I8 intersection ends; T g08 T is the time when the green light starts at the I8 intersection; g18 is the time when the green light ends at the I8 intersection; T is the merging time.

[0191] Step 2083: Generate a third left-turn U-turn vehicle impact factor by calculating based on the preset left-turn U-turn path parameters and the merging time and according to the driving information of the vehicle on the motor vehicle lane where the merging point on the left-turn U-turn path is located.

[0192] like Figure 3 As shown, the impact of the right-turning vehicle V1 on the driving path of the vehicle SV along the path I1I8 is analyzed:

[0193] Since the right turn of vehicle V1 is not affected by traffic lights and has a higher priority than the left-turning vehicle SV, vehicle SV needs to stop and give way to vehicle V1 during the right turn of vehicle V1; only after vehicle V1 turns right and passes through intersection I7 can vehicle SV continue to travel along path I1I8.

[0194] Assume that the length of the right turn path of vehicle V1 is L V1 , the speed of right turn is v1, and the influence function of right turn vehicle V1 on the driving path I1I8 of vehicle SV is:

[0195]

[0196] Among them, C1(t) is the impact factor of the third left-turn U-turn vehicle; is the starting time of vehicle V1 turning right; k V1 is the weight coefficient of the driving path I1I8 obtained after the vehicle V1 turns right through the intersection I7; T is the merging time; L V1 is the length of the path of vehicle V1 turning right; v1 is the speed of vehicle V1 turning right.

[0197] It is worth noting that the length of the right turn path of vehicle V1 is L V1 It is the distance between vehicle V1 and the confluence point I8.

[0198] Step 2084: Generate a left-turn U-turn path weight according to the first left-turn U-turn vehicle influence factor, the second left-turn U-turn vehicle influence factor, and the third left-turn U-turn vehicle influence factor.

[0199] In the embodiment of the present invention, the first left-turn U-turn vehicle influence factor includes the vehicle influence factor and the influence factor C of vehicles behind the traffic lights on left-turning vehicles 1i (t).

[0200] like Figure 3 As shown, the weight model of the left turn path I1I8 is:

[0201]

[0202] Among them, I1I8(t) is the left turn path weight of path I1I8, is the vehicle impact factor, C 1i (t) is the impact factor of the first left-turn U-turn vehicle, C 2j (t) is the impact factor of the second left-turn U-turn vehicle, C 3n (t) is the impact factor of the third left-turn U-turn vehicle, I 7,8 is the set of vehicles turning right from intersection I7 to intersection I8, J 5,8 is the set of vehicles going straight from intersection I5 to intersection I8, N 3,8 It is a collection of vehicles turning left from intersection I3 to intersection I8.

[0203] In summary, the left turn path weight is:

[0204]

[0205] Among them, I m I n (t) is path I m I n The left turn path weight, is the vehicle impact factor, C 1i (t) is the impact factor of the first left-turn U-turn vehicle, C 2j (t) is the impact factor of the second left-turn U-turn vehicle, C 3n (t) is the impact factor of the third left-turn U-turn vehicle.

[0206] Furthermore, the vehicle SV is placed at the intersections I3, I5 and I7 respectively. According to the above process and analysis method, the weight models of the driving paths I3I2, I3I4, I3I6, I3I8, I5I2, I5I4, I5I6, I5I8, I7I2, I7I4, I7I6 and I7I8 can be established as shown below, and the meanings of the repeated parameters are not repeated here:

[0207]

[0208] Among them, I 1,2 is the set of vehicles turning right from intersection I1 to intersection I2, J 7,2 represents the set of vehicles going straight from intersection I7 to intersection I2, N 5,2 It is a collection of vehicles turning left from intersection I5 to intersection I2.

[0209]

[0210] Among them, I 3,4 is the set of pedestrians moving from the right side to the left side of the vehicle SV on the I3 crosswalk and the I4 crosswalk, J 3,4 is the set of pedestrians moving from the left side to the right side of the vehicle SV on the I3 crosswalk and the I4 crosswalk, N 1,4 The gathering place is for vehicles going straight from intersection I1 to intersection I4.

[0211] I3I6(t)=S6(t)

[0212] Among them, S6(t) is the traffic light model of intersection I6.

[0213]

[0214] Among them, I 1,8 is the set of pedestrians moving from the right side to the left side of the vehicle SV at the crosswalk at the intersection of I1 and I8, J 1,8 It is the set of pedestrians moving from the left side to the right side of the vehicle SV on the crosswalk at the intersection of I1 and I8.

[0215] Similarly, other driving path weight models are as follows:

[0216]

[0217]

[0218]

[0219]

[0220]

[0221]

[0222]

[0223]

[0224] It is worth noting that the same and similar parameters can refer to the above specific embodiments, and the embodiments of the present invention will not be described in detail here.

[0225] Step 209: Determine a target path from the paths of different driving directions according to the path weights corresponding to the different driving directions.

[0226] In the embodiment of the present invention, the path weights corresponding to different driving directions include a right turn path weight, a straight path weight, a left turn path weight, and a left turn path weight.

[0227] In the embodiment of the present invention, a target path can be determined according to path weights corresponding to different driving directions through a preset path selection strategy.

[0228] It is worth noting that the path selection strategy can be set according to actual conditions, and the embodiment of the present invention does not limit this. As an optional solution, the path selection strategy is that the path corresponding to the maximum path weight is the target path.

[0229] Furthermore, based on the target path, the autonomous driving system can formulate corresponding driving strategies, such as deceleration, acceleration, braking, maintaining the current path, etc. According to the determined driving strategy, the autonomous driving system can send control signals to the vehicle's actuators, such as the braking system, power system, etc., so as to control the vehicle to perform corresponding driving actions, such as controlling the vehicle to brake first and then drive normally according to the current navigation path, or only controlling the vehicle to brake, or only controlling the vehicle to drive normally according to the current navigation path.

[0230] The present invention uses a path weight model to perform weight evaluation on the navigation path, thereby solving the problem that the traditional vehicle automatic driving control strategy cannot be flexibly formulated according to the real-time traffic conditions, resulting in low safety of vehicle automatic driving. It can more accurately determine the vehicle's driving strategy and improve the accuracy of decision-making.

[0231] It is worth noting that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of laws and regulations. The user information in the embodiments of this application is obtained through legal and compliant channels, and the acquisition, storage, use, and processing of user information are authorized and agreed by the customer.

[0232] It is worth noting that the information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0233] It is worth noting that the technical solution provided in this application provides users with corresponding operation entrances for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0234] In the technical solution of the target path determination method based on the path weight model provided in the embodiment of the present invention, the target scene element of the current driving scene of the driving vehicle is obtained; the path weight model corresponding to different preset driving directions is used to calculate the path weight according to the target scene element, and the path weights corresponding to different driving directions are generated; according to the path weights corresponding to different driving directions, the target path is determined from the paths in different driving directions, and the vehicle's automatic driving control strategy can be flexibly formulated according to the real-time traffic conditions, thereby improving the safety of the vehicle's automatic driving; the vehicle's driving strategy can be determined more accurately, thereby improving the accuracy of decision-making.

[0235] Figure 5 A schematic diagram of the structure of a target path determination device based on a path weight model provided by an embodiment of the present invention, wherein the device is used to execute the target path determination method based on the path weight model, such as Figure 5 As shown, the device includes: a target scene element acquisition unit 11, a path weight generation unit 12 and a target path determination unit 13.

[0236] The target scene element acquisition unit 11 is used to acquire the target scene element of the current driving scene of the driving vehicle.

[0237] The path weight generating unit 12 is used to calculate the path weight according to the target scene elements through the preset path weight models corresponding to different driving directions, and generate the path weights corresponding to different driving directions.

[0238] The target path determining unit 13 is used to determine the target path from the paths in different driving directions according to the path weights corresponding to the different driving directions.

[0239] In the embodiment of the present invention, the device further includes: a current navigation path acquisition unit 14 , a driving distance generation unit 15 and a determination unit 16 .

[0240] The current navigation path acquisition unit 14 is used to acquire the current navigation path of the traveling vehicle.

[0241] The driving distance generating unit 15 is used to generate the driving distance between the driving vehicle and the current intersection according to the current navigation path.

[0242] The judgment unit 16 is used to judge whether the driving distance is less than a preset distance threshold; if so, the target scene element acquisition unit 11 is triggered to continue to execute the step of acquiring the target scene element of the current driving scene of the driving vehicle; if not, the current navigation path acquisition unit 14 is triggered to continue to execute the step of acquiring the current navigation path of the driving vehicle until the driving distance is less than the distance threshold.

[0243] In an embodiment of the present invention, the target scene element acquisition unit 11 is specifically used to construct a path directed graph of the crossroad according to the current crossroad in the current navigation path, with the confluence point and the confluence point of each intersection as vertices, and the connection line between the confluence point and the confluence point as a directed connection edge; through the recognition device, scene elements are recognized according to the path directed graph of the crossroad to generate target scene elements.

[0244] In the embodiment of the present invention, the path weight models corresponding to different driving directions include a right-turn driving path weight model, a straight-through driving path signal light model, a left-turn driving path weight model and a left-turn U-turn driving path weight model; the target scene elements include pedestrians at the confluence point, vehicles at the confluence point, pedestrians at the confluence point, vehicles at the confluence point and the current signal light status; the path weight generation unit 12 is specifically used to generate the right-turn path weight through the right-turn driving path weight model according to the preset signal light weight coefficient, vehicle driving parameters, pedestrians at the confluence point, vehicles at the confluence point, pedestrians at the confluence point, vehicles at the confluence point and the current signal light status; generate the straight-through path weight through the straight-through driving path signal light model according to the signal light weight coefficient, vehicle driving parameters and the current signal light status; generate the left-turn path weight through the left-turn driving path weight model according to the signal light weight coefficient, vehicle driving parameters, pedestrians at the confluence point and the current signal light status; generate the left-turn U-turn path weight through the left-turn U-turn driving path weight model according to the signal light weight coefficient, vehicle driving parameters, vehicles at the confluence point, vehicles at the confluence point and the current signal light status.

[0245] In an embodiment of the present invention, the vehicle driving parameters include the merging time; the current traffic light state includes the start and end time of the traffic light; the path weight generation unit 12 is specifically used to generate a right-turn pedestrian impact factor through calculation based on the preset right-turn path parameters and the dynamic information of pedestrians on the crosswalk where the merging point on the right-turn path is located and the pedestrians on the crosswalk where the exit point on the right-turn path is located; generate a traffic light impact factor based on the merging time through the traffic light weight coefficient and the traffic light start and end time; calculate based on the driving information of the vehicle on the motor vehicle lane where the exit point on the right-turn path is located to generate a right-turn vehicle impact factor; generate a right-turn path weight based on the right-turn pedestrian impact factor, the traffic light impact factor and the vehicle impact factor.

[0246] In the embodiment of the present invention, the vehicle driving parameters include the merging time; the current signal light state includes the signal light start and end time; the path weight generation unit 12 is specifically used to generate the straight path weight according to the merging time through the signal light weight coefficient and the signal light start and end time.

[0247] In an embodiment of the present invention, the vehicle driving parameters include the merging time; the current signal light state includes the start and end time of the signal light; the path weight generation unit 12 is specifically used to generate a signal light influence factor according to the merging time through the signal light weight coefficient and the start and end time of the signal light; through the preset left turn path parameters, the dynamic information of pedestrians on the crosswalk where the merging point on the left turn path is located and the dynamic information of pedestrians on the non-motorized vehicle lane where the merging point on the left turn path is located is calculated to generate a left turn pedestrian influence factor; based on the signal light influence factor and the left turn pedestrian influence factor, a left turn path weight is generated.

[0248] In an embodiment of the present invention, the vehicle driving parameters include the merging time; the current signal light state includes the signal light start and end time; the path weight generating unit 12 is specifically used to generate a first left-turn U-turn vehicle impact factor by calculating according to the preset left-turn U-turn path parameters, the signal light start and end time and the merging time, based on the driving information of the vehicle on the motor vehicle lane where the confluence point on the left-turn U-turn path is located; generate a second left-turn U-turn vehicle impact factor according to the preset left-turn U-turn path parameters, the signal light start and end time and the merging time; generate a third left-turn U-turn vehicle impact factor by calculating according to the preset left-turn U-turn path parameters and the merging time, based on the driving information of the vehicle on the motor vehicle lane where the confluence point on the left-turn U-turn path is located; generate a left-turn U-turn path weight according to the first left-turn U-turn vehicle impact factor, the second left-turn U-turn vehicle impact factor and the third left-turn U-turn vehicle impact factor.

[0249] In the scheme of the embodiment of the present invention, the target scene element of the current driving scene of the moving vehicle is obtained; the path weight model corresponding to different preset driving directions is used to calculate the path weight according to the target scene element, and the path weights corresponding to different driving directions are generated; according to the path weights corresponding to different driving directions, the target path is determined from the paths of different driving directions, and the vehicle's automatic driving control strategy can be flexibly formulated according to the real-time traffic conditions to improve the safety of the vehicle's automatic driving; the vehicle's driving strategy can be determined more accurately to improve the accuracy of decision-making.

[0250] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer device, and specifically, the computer device may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0251] An embodiment of the present invention provides a computer device, including a memory and a processor, the memory is used to store information including program instructions, the processor is used to control the execution of the program instructions, and when the program instructions are loaded and executed by the processor, the steps of the embodiment of the above-mentioned target path determination method based on the path weight model are implemented. For a specific description, please refer to the embodiment of the above-mentioned target path determination method based on the path weight model.

[0252] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer device 600 suitable for implementing an embodiment of the present application.

[0253] like Figure 6 As shown, the computer device 600 includes a central processing unit (CPU) 601, which can perform various appropriate tasks and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer device 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0254] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal feedback device (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed as needed as the storage section 608.

[0255] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 609, and / or installed from the removable medium 611.

[0256] 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.

[0257] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0258] 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.

[0259] 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.

[0260] 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.

[0261] 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.

[0262] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0263] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0264] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application 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.

[0265] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0266] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0267] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A target path determination method based on a path weight model, characterized in that: The method comprises: Obtaining a target scene element of a current driving scene of a moving vehicle; By using the preset path weight model corresponding to different driving directions, the path weight is calculated according to the target scene element to generate the path weight corresponding to different driving directions; Determining a target path from the paths in different driving directions according to the path weights corresponding to the different driving directions; The path weight models corresponding to different driving directions include a right-turn driving path weight model, a straight-through driving path signal light model, a left-turn driving path weight model, and a left-turn U-turn driving path weight model; the target scene elements include pedestrians at the confluence point, vehicles at the confluence point, pedestrians at the confluence point, vehicles at the confluence point, and the current signal light status; The path weight model corresponding to different driving directions is preset, and the path weight is calculated according to the target scene element to generate the path weight corresponding to different driving directions, including: Generate a right-turn path weight through a right-turn driving path weight model according to a preset signal light weight coefficient, vehicle driving parameters, the pedestrians at the confluence point, the vehicles at the confluence point, the pedestrians at the confluence point, the vehicles at the confluence point and the current signal light status; Generate a straight path weight through a straight driving path signal light model according to the signal light weight coefficient, vehicle driving parameters and current signal light status; Generate a left turn path weight through a left turn driving path weight model according to the traffic light weight coefficient, vehicle driving parameters, pedestrians at the confluence point and current traffic light status; Generate a left-turn U-turn path weight through a left-turn U-turn driving path weight model according to the traffic light weight coefficient, vehicle driving parameters, outgoing point vehicles, incoming point vehicles and current traffic light status; The vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light; The right-turn path weight model is used to generate the right-turn path weight according to the preset signal light weight coefficient, vehicle driving parameters, the pedestrians at the confluence point, the vehicles at the confluence point, the pedestrians at the confluence point, the vehicles at the confluence point and the current signal light status, including: By using the preset right-turn path parameters, the pedestrian influencing factor for right-turn pedestrians is generated by calculating according to the dynamic information of pedestrians on the crosswalk where the merging point on the right-turn path is located and pedestrians on the crosswalk where the merging point on the right-turn path is located; Generate a signal light influence factor according to the merging time by using the signal light weight coefficient and the start and end time of the signal light; Calculate according to the driving information of the vehicles on the motor vehicle lane where the exit point on the right-turn path is located, and generate the right-turn vehicle impact factor; The right-turn path weight is generated according to the right-turn pedestrian influence factor, the traffic light influence factor and the vehicle influence factor.

2. The target path determination method based on the path weight model according to claim 1 is characterized in that: Before obtaining the target scene element of the current driving scene of the driving vehicle, the method further includes: Get the current navigation path of the moving vehicle; generating a travel distance between the traveling vehicle and a current intersection according to the current navigation path; Determining whether the driving distance is less than a preset distance threshold; If yes, continue to execute the step of obtaining the target scene element of the current driving scene of the driving vehicle; If not, continue to execute the step of obtaining the current navigation path of the moving vehicle until the driving distance is less than the distance threshold.

3. The target path determination method based on the path weight model according to claim 1 is characterized in that: The step of obtaining the target scene element of the current driving scene of the driving vehicle includes: According to the current crossroad in the current navigation path, the confluence point and confluence point of each intersection are used as vertices, and the connection line between the confluence point and the confluence point is used as a directed connection edge to construct a path directed graph of the crossroad; The target scene element is generated by performing scene element recognition according to the path directed graph of the crossroad through the recognition device.

4. The target path determination method based on the path weight model according to claim 1 is characterized in that: The straight path signal light model is used to generate a straight path weight according to the signal light weight coefficient, the vehicle driving parameters and the current signal light state, including: The straight path weight is generated according to the merging time by using the traffic light weight coefficient and the traffic light start and end times.

5. The target path determination method based on the path weight model according to claim 1 is characterized in that: The left-turn path weight model is used to generate a left-turn path weight according to the traffic light weight coefficient, vehicle driving parameters, pedestrians at the confluence point and the current traffic light state, including: Generate a signal light influence factor according to the merging time by using the signal light weight coefficient and the start and end time of the signal light; By using the preset left-turn path parameters, the left-turn pedestrian impact factor is generated by calculating according to the dynamic information of pedestrians on the crosswalk where the confluence point on the left-turn path is located and the dynamic information of pedestrians on the non-motorized vehicle lane where the confluence point on the left-turn path is located; The left-turn path weight is generated according to the traffic light influence factor and the left-turn pedestrian influence factor.

6. The target path determination method based on the path weight model according to claim 1 is characterized in that: The left-turn U-turn path weight model is used to generate a left-turn U-turn path weight according to the traffic light weight coefficient, vehicle driving parameters, outgoing point vehicles, incoming point vehicles and current traffic light status, including: The first left-turn U-turn vehicle impact factor is generated by calculating the preset left-turn U-turn path parameters, the start and end times of the signal lights, and the merging time according to the driving information of the vehicles on the motor vehicle lane at the merging point on the left-turn U-turn path; Generate a second left-turn vehicle impact factor based on the preset left-turn path parameters, signal light start and end times, and merging time; The third left-turn U-turn vehicle impact factor is generated by calculating the preset left-turn U-turn path parameters and the merging time according to the driving information of the vehicle on the motor vehicle lane where the merging point on the left-turn U-turn path is located; The left-turn U-turn path weight is generated according to the first left-turn U-turn vehicle influence factor, the second left-turn U-turn vehicle influence factor and the third left-turn U-turn vehicle influence factor.

7. A target path determination device based on a path weight model, characterized in that: The device comprises: A target scene element acquisition unit, used to acquire a target scene element of a current driving scene of a driving vehicle; A path weight generating unit, configured to calculate the path weight according to the target scene element by using a preset path weight model corresponding to different driving directions, and generate path weights corresponding to different driving directions; a target path determining unit, configured to determine a target path from the paths in different driving directions according to the path weights corresponding to the different driving directions; The path weight models corresponding to different driving directions include a right-turn driving path weight model, a straight-through driving path signal light model, a left-turn driving path weight model, and a left-turn U-turn driving path weight model; the target scene elements include pedestrians at the confluence point, vehicles at the confluence point, pedestrians at the confluence point, vehicles at the confluence point, and the current signal light status; The path weight generating unit is specifically used to generate a right turn path weight according to a preset signal light weight coefficient, vehicle driving parameters, the pedestrians at the confluence point, the vehicles at the confluence point, the pedestrians at the confluence point, the vehicles at the confluence point, and the current signal light status through a right turn driving path weight model; generate a straight path weight according to the signal light weight coefficient, vehicle driving parameters, and the current signal light status through a straight driving path signal light model; generate a left turn path weight according to the signal light weight coefficient, vehicle driving parameters, the pedestrians at the confluence point, and the current signal light status through a left turn driving path weight model; generate a left turn U-turn path weight according to the signal light weight coefficient, vehicle driving parameters, the vehicles at the confluence point, the vehicles at the confluence point, and the current signal light status through a left turn U-turn driving path weight model; The vehicle driving parameters include the merging time; the current signal light status includes the start and end time of the signal light; The path weight generation unit is specifically used to generate a right-turn pedestrian impact factor by calculating based on the dynamic information of pedestrians on the crosswalk where the merging point on the right-turn path is located and the pedestrians on the crosswalk where the exit point on the right-turn path is located through preset right-turn path parameters; generate a signal light impact factor based on the merging time through the signal light weight coefficient and the signal light start and end time; generate a right-turn vehicle impact factor by calculating based on the driving information of the vehicle on the motor vehicle lane where the exit point on the right-turn path is located; generate the right-turn path weight based on the right-turn pedestrian impact factor, the signal light impact factor and the vehicle impact factor.

8. The target path determination device based on the path weight model according to claim 7, characterized in that: The device also includes: A current navigation path acquisition unit, used to acquire the current navigation path of the moving vehicle; A driving distance generating unit, used for generating a driving distance between the driving vehicle and a current intersection according to the current navigation path; A judgment unit is used to judge whether the driving distance is less than a preset distance threshold; if so, trigger the target scene element acquisition unit to continue to execute the step of acquiring the target scene element of the current driving scene of the driving vehicle; if not, trigger the current navigation path acquisition unit to continue to execute the step of acquiring the current navigation path of the driving vehicle until the driving distance is less than the distance threshold.

9. The target path determination device based on the path weight model according to claim 7, characterized in that: The target scene element acquisition unit is specifically used to construct a path directed graph of the cross intersection according to the current cross intersection in the current navigation path, with the confluence point and confluence point of each intersection as vertices, and the connection line between the confluence point and the confluence point as a directed connection edge; through the recognition device, scene element recognition is performed according to the path directed graph of the cross intersection to generate the target scene element.

10. The target path determination device based on the path weight model according to claim 7, characterized in that: The path weight generating unit is specifically configured to generate the straight path weight according to the merging time by using the signal light weight coefficient and the signal light start and end time.

11. The target path determination device based on the path weight model according to claim 7, characterized in that: The path weight generating unit is specifically used to generate a signal light influence factor according to the merging time by using the signal light weight coefficient and the start and end time of the signal light; and to generate a left-turn pedestrian influence factor by calculating according to the dynamic information of pedestrians on the crosswalk where the merging point on the left-turn path is located and the dynamic information of pedestrians on the non-motorized vehicle lane where the merging point on the left-turn path is located by using the preset left-turn path parameters; The left-turn path weight is generated according to the traffic light influence factor and the left-turn pedestrian influence factor.

12. The target path determination device based on the path weight model according to claim 7, characterized in that: The path weight generating unit is specifically used to generate a first left-turn U-turn vehicle impact factor by calculating the preset left-turn U-turn path parameters, the start and end times of the signal light, and the merging time according to the driving information of the vehicle on the motor vehicle lane where the merging point on the left-turn U-turn path is located; and generate a second left-turn U-turn vehicle impact factor according to the preset left-turn U-turn path parameters, the start and end times of the signal light, and the merging time; The third left-turn U-turn vehicle impact factor is generated by calculating the preset left-turn U-turn path parameters and the merging time according to the driving information of the vehicle on the motor vehicle lane where the merging point on the left-turn U-turn path is located; the left-turn U-turn path weight is generated according to the first left-turn U-turn vehicle impact factor, the second left-turn U-turn vehicle impact factor and the third left-turn U-turn vehicle impact factor.

13. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the target path determination method based on the path weight model described in any one of claims 1 to 6 is implemented.

14. A computer device comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, characterized in that: When the program instructions are loaded and executed by the processor, the target path determination method based on the path weight model described in any one of claims 1 to 6 is implemented.

15. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the target path determination method based on the path weight model described in any one of claims 1 to 6 is implemented.

Images