Vehicle driving data prediction method, device, electronic device and readable medium

Abstract

An embodiment of the present invention provides a vehicle driving data prediction method, device, electronic device and readable medium, the method comprising: identifying and recording at least one vehicle and the block occupied by the vehicle body to obtain a global vehicle map, analyzing the drivable direction of each lane, and setting each lane to correspond to a block, recording each block and the drivable direction on the block to obtain a driving direction map, and collecting driving data of at least one vehicle in an identifiable area of ​​an intelligent traffic roadside unit, so that the driving data of the vehicle to be predicted in the blind spot can be predicted based on the global vehicle map, the driving direction map and the driving data of at least one vehicle in the identifiable area. The driving data of the vehicle to be predicted in the blind spot predicted by using this method has higher accuracy and is more in line with the actual situation, thereby better assisting driving or providing support for automatic driving, and avoiding the occurrence of traffic accidents.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a vehicle driving data prediction method, a vehicle driving data prediction device, an electronic device, and a computer-readable medium. Background Art

[0002] An intelligent traffic roadside unit (RSU) is a sensor that integrates radar and cameras. It is usually deployed on poles on both sides of the road to sense road traffic conditions to assist driving or provide support for autonomous driving.

[0003] In actual applications, factors such as cost constraints, insufficient installation points, and mutual obstruction by obstacles create permanent and temporary blind spots, leading to gaps in observation data from intelligent roadside units. Using this incomplete observation data to assist driving or support autonomous driving can lead to serious traffic problems. Therefore, it is necessary to predict the missing observation data in blind spots to obtain complete data.

[0004] Traditional methods use the last observed data before a vehicle enters the blind spot as the direction of travel for vehicles with lost observation data. Their speed is also predicted based on the last observed data before entering the blind spot. This method can lead to vehicles running off the road or running over others when encountering curves or when the vehicle ahead slows down. Summary of the Invention

[0005] The embodiments of the present invention provide a vehicle driving data prediction method, device, electronic device and computer-readable medium to solve the problem that using the last observation data before entering a blind spot as the driving data of the blind spot can easily lead to traffic accidents.

[0006] An embodiment of the present invention discloses a vehicle driving data prediction method, comprising:

[0007] Identifying and recording at least one vehicle and the area occupied by the vehicle to obtain a global vehicle map;

[0008] Analyze the drivable direction of each lane, set each lane to correspond to a block, record each block and the drivable direction on the block to obtain a driving direction map;

[0009] Collecting driving data of the at least one vehicle in an identifiable area of ​​the intelligent transportation roadside unit;

[0010] The driving data of the vehicle to be predicted in the blind spot is predicted based on the global vehicle map, the driving direction map and the driving data of the at least one vehicle in the identifiable area.

[0011] Optionally, the step of predicting the driving data of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving data of the at least one vehicle in the identifiable area includes:

[0012] The driving direction and speed of the vehicle to be predicted in the blind spot are predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area.

[0013] Optionally, the step of predicting the driving direction and driving speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and driving speed of the at least one vehicle in the identifiable area includes:

[0014] Searching the global vehicle map for a block occupied by the vehicle body to be predicted;

[0015] According to the block occupied by the vehicle body to be predicted, searching the driving direction map for a possible driving direction on the block occupied by the vehicle body to be predicted;

[0016] The driving direction of the vehicle to be predicted in the blind spot is determined according to the driving direction of the vehicle to be predicted in the identifiable area and the drivable directions in the block occupied by the body of the vehicle to be predicted.

[0017] Optionally, the step of predicting the driving direction and driving speed of the to-be-predicted vehicle in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and driving speed of the at least one vehicle in the identifiable area further includes:

[0018] Determining the speed of the preceding vehicle of the to-be-predicted vehicle and the maximum drivable speed of the to-be-predicted vehicle in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0019] Based on a preset car-following model, the driving speed of the vehicle in front of the vehicle to be predicted and the maximum drivable speed of the vehicle to be predicted in the blind spot are used to predict the driving speed of the vehicle to be predicted in the blind spot.

[0020] Optionally, the step of determining the driving speed of the preceding vehicle of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and driving speed of the at least one vehicle in the identifiable area includes:

[0021] Determining a deduced direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0022] Deducing the deduced position of the vehicle to be predicted using the deduced direction of the vehicle to be predicted, a preset driving speed, and a preset time interval;

[0023] Searching for vehicles other than the vehicle to be predicted in the block corresponding to the deduced position from the global map information and counting the number of times each vehicle appears;

[0024] Determining a preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position;

[0025] The driving speed of the preceding vehicle of the vehicle to be predicted is found from the driving speed of the at least one vehicle in the identifiable area.

[0026] Optionally, the step of determining the preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position includes:

[0027] Based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position, the probability of each vehicle becoming the preceding vehicle of the vehicle to be predicted is calculated, and the vehicle with a probability greater than that of other vehicles is taken as the preceding vehicle of the vehicle to be predicted.

[0028] Optionally, the step of determining the maximum drivable speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and driving speed of the at least one vehicle in the identifiable area includes:

[0029] Determining a deduced direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0030] Using the first preset distance as a constraint condition, the deduced trajectory of the vehicle to be predicted is deduced using the deduced direction of the vehicle to be predicted and a preset driving speed;

[0031] Calculating the angle between the starting direction and the ending direction of the predicted trajectory of the vehicle to be predicted;

[0032] The maximum drivable speed of the vehicle to be predicted in the blind spot is determined according to the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted.

[0033] Optionally, the step of determining the maximum drivable speed of the vehicle to be predicted in the blind spot based on the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted includes:

[0034] Determining whether an angle between a starting driving direction and an ending driving direction of the deduced trajectory of the vehicle to be predicted exceeds a first preset threshold;

[0035] If the angle between the starting direction and the ending direction of the predicted trajectory of the vehicle to be predicted does not exceed a first preset threshold, the maximum drivable speed of the current lane is used as the maximum drivable speed of the vehicle to be predicted in the blind spot;

[0036] If the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted exceeds a first preset threshold, the maximum drivable speed of the vehicle to be predicted in the blind spot is determined based on the size of the angle; the size of the angle has a corresponding relationship with the maximum drivable speed.

[0037] The embodiment of the present invention further discloses a vehicle driving data prediction device, comprising:

[0038] A global vehicle map generation module, configured to identify and record at least one vehicle and the area occupied by the vehicle body to obtain a global vehicle map;

[0039] A driving direction map generation module is used to analyze the drivable direction of each lane, set each lane to correspond to a block, record each block and the drivable direction on the block to obtain a driving direction map;

[0040] a collection module, configured to collect driving data of the at least one vehicle in an identifiable area of ​​the intelligent transportation roadside unit;

[0041] The prediction module is used to predict the driving data of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map and the driving data of the at least one vehicle in the identifiable area.

[0042] Optionally, the prediction module includes:

[0043] The prediction submodule is used to predict the driving direction and speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map and the driving direction and speed of the at least one vehicle in the identifiable area.

[0044] Optionally, the prediction submodule includes:

[0045] A first search unit is configured to search the global vehicle map for a block occupied by the vehicle body to be predicted;

[0046] A second search unit is configured to search the driving direction map for a possible driving direction on the block occupied by the vehicle body to be predicted according to the block occupied by the vehicle body to be predicted;

[0047] The driving direction determining unit is used to determine the driving direction of the vehicle to be predicted in the blind spot according to the driving direction of the vehicle to be predicted in the identifiable area and the drivable directions in the block occupied by the body of the vehicle to be predicted.

[0048] Optionally, the prediction submodule further includes:

[0049] a first determining unit, configured to determine a driving speed of a preceding vehicle of the to-be-predicted vehicle and a maximum drivable speed of the to-be-predicted vehicle in a blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0050] The driving speed determination unit is used to predict the driving speed of the vehicle to be predicted in the blind spot based on a preset car-following model and the driving speed of the preceding vehicle of the vehicle to be predicted and the maximum drivable speed of the vehicle to be predicted in the blind spot.

[0051] Optionally, the first determining unit includes:

[0052] a first deduction direction determination subunit, configured to determine a deduction direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0053] a deduced position determination subunit, configured to deduce the deduced position of the vehicle to be predicted using the deduced direction of the vehicle to be predicted, a preset driving speed, and a preset time interval;

[0054] A first search subunit is configured to search the global map information for vehicles other than the vehicle to be predicted in the block corresponding to the deduced position and to count the number of occurrences of each vehicle;

[0055] a preceding vehicle determining subunit, configured to determine a preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position;

[0056] The second searching subunit is configured to search for a driving speed of a preceding vehicle of the vehicle to be predicted from the driving speeds of the at least one vehicle in the identifiable area.

[0057] Optionally, the preceding vehicle determining subunit includes:

[0058] The preceding vehicle determination component is used to calculate the probability of each vehicle becoming the preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position, and to select the vehicle with a probability greater than that of other vehicles as the preceding vehicle of the vehicle to be predicted.

[0059] Optionally, the first determining unit includes:

[0060] a second deduction direction determination subunit, configured to determine a deduction direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0061] a deduction trajectory determination subunit, configured to deduce a deduction trajectory of the vehicle to be predicted using a first preset distance as a constraint condition, a deduction direction of the vehicle to be predicted, and a preset driving speed;

[0062] An angle calculation subunit, used to calculate the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted;

[0063] The first determining subunit is configured to determine a maximum drivable speed of the vehicle to be predicted in the blind spot according to an angle between a starting driving direction and an ending driving direction of a deduced trajectory of the vehicle to be predicted.

[0064] Optionally, the first determining subunit includes:

[0065] a judgment component, configured to judge whether an angle between a starting driving direction and an ending driving direction of the deduced trajectory of the vehicle to be predicted exceeds a first preset threshold;

[0066] a first maximum drivable speed determining component, configured to use the maximum drivable speed of the current lane as the maximum drivable speed of the vehicle to be predicted in the blind spot if the angle between the starting and ending directions of the deduced trajectory of the vehicle to be predicted does not exceed a first preset threshold;

[0067] a second maximum drivable speed determination component for determining, if the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted exceeds a first preset threshold, the maximum drivable speed of the vehicle to be predicted in the blind spot based on the size of the angle; the size of the angle having a corresponding relationship with the maximum drivable speed.

[0068] An embodiment of the present invention further discloses an electronic device, comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0069] The memory is used to store computer programs;

[0070] The processor is configured to implement the vehicle driving data prediction method according to an embodiment of the present invention when executing the program stored in the memory.

[0071] An embodiment of the present invention further discloses a computer-readable medium having instructions stored thereon, which, when executed by one or more processors, enables the processors to execute the vehicle driving data prediction method as described in the embodiment of the present invention.

[0072] The embodiments of the present invention include the following advantages:

[0073] In an embodiment of the present invention, a global vehicle map is obtained by identifying and recording at least one vehicle and a block occupied by the vehicle body, the drivable direction of each lane is analyzed, and each lane is set to correspond to a block, each block and the drivable direction on the block are recorded to obtain a driving direction map, and driving data of at least one vehicle in an identifiable area of ​​an intelligent traffic roadside unit are collected, so that the driving data of the vehicle to be predicted in the blind spot can be predicted based on the global vehicle map, the driving direction map and the driving data of at least one vehicle in the identifiable area. The driving data of the vehicle to be predicted in the blind spot can be predicted by using this method, and the driving data of the vehicle to be predicted in the blind spot predicted by using this method has higher accuracy and is more in line with the actual situation, so that it can better assist driving or provide support for automatic driving, thereby avoiding the occurrence of traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a schematic diagram of a permanent blind spot;

[0075] Figure 2 It is a short-term blind spot diagram;

[0076] Figure 3 This is a flowchart of the steps of a vehicle driving data prediction method provided in an embodiment of the present invention;

[0077] Figure 4 This is a schematic diagram of lanes in a high-precision map provided in an embodiment of the present invention;

[0078] Figure 5 is a flowchart of another vehicle driving data prediction method provided in an embodiment of the present invention;

[0079] Figure 6 This is a schematic diagram of a driving direction map provided in an embodiment of the present invention;

[0080] Figure 7 This is a flow chart for determining a preceding vehicle of a vehicle to be predicted provided in an embodiment of the present invention;

[0081] Figure 8 This is a schematic diagram of the change in the angle of the travel direction of a trajectory from the starting point to the end point provided in an embodiment of the present invention;

[0082] Figure 9 This is a structural block diagram of a vehicle driving data prediction device provided in an embodiment of the present invention;

[0083] Figure 10 is a block diagram of an electronic device provided in an embodiment of the present invention;

[0084] Figure 11 is a schematic diagram of a computer-readable medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0085] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0086] Due to factors such as cost constraints, insufficient installation points, and mutual obstruction by obstacles, permanent and short-term blind spots are generated, resulting in a gap in the observation data of the intelligent transportation roadside unit. Figure 1 , shows a schematic diagram of a permanent blind spot. In the figure, 101 is the area that the intelligent traffic roadside unit can identify, and 102 is the area that the intelligent traffic roadside unit cannot identify, that is, the blind spot of the intelligent traffic roadside unit. The blind spot on this road is caused by insufficient installation points and is called a permanent blind spot. Figure 2 , shows a schematic diagram of a short-term blind spot. 201 in the figure represents the area that the intelligent roadside unit can identify, while 202 represents the area that the intelligent roadside unit cannot identify, i.e., the blind spot of the intelligent roadside unit. 203 in the figure represents vehicles with observations, while 204 represents vehicles to be predicted without observations. This intersection waiting area is not a blind spot for the intelligent roadside unit, but some vehicles still have no observations. This is caused by obstruction by other vehicles and is called a short-term blind spot.

[0087] In the existing technology, the driving direction and speed of the predicted vehicle last observed before entering the blind spot are directly used as the driving direction and speed of the predicted vehicle in the blind spot. The actual driving direction of the lane is not taken into account, and the driving data of other vehicles around the predicted vehicle and the actual road conditions are not taken into account. Therefore, using the data obtained by this method to guide vehicle driving is prone to the risk of running out of the lane and colliding with the vehicle in front.

[0088] To address the problem that using the last observation data before entering a blind spot as driving data for the blind spot can easily lead to traffic accidents, the present invention provides a vehicle driving data prediction method, which obtains a global vehicle map by identifying and recording at least one vehicle and the block occupied by the vehicle body, analyzes the drivable direction of each lane, sets each lane to correspond to a block, records each block and the drivable direction on the block to obtain a driving direction map, and collects driving data of at least one vehicle in an identifiable area of ​​an intelligent traffic roadside unit, so that the driving data of the vehicle to be predicted in the blind spot can be predicted based on the global vehicle map, the driving direction map, and the driving data of at least one vehicle in the identifiable area. The method can predict the driving data of the vehicle to be predicted in the blind spot, and because the present invention uses the actual drivable direction of the lane to determine the driving direction of the vehicle to be predicted, and determines the driving speed of the vehicle to be predicted based on the driving data of other vehicles around the vehicle to be predicted and the actual road conditions, the driving data of the vehicle to be predicted in the blind spot predicted by the method has higher accuracy and is more in line with the actual situation, thereby better assisting driving or providing support for automatic driving, thereby avoiding the occurrence of traffic accidents.

[0089] Reference Figure 3 , shows a flowchart of a vehicle driving data prediction method provided in an embodiment of the present invention, which may specifically include the following steps:

[0090] A Digital Roadside Unit (DRSU) is a sensor system that integrates radar and cameras. These sensors are typically deployed on poles along the road to monitor road traffic conditions. The cameras transmit images to the roadside computing unit, which identifies various traffic entities, including motor vehicles, non-motor vehicles, and pedestrians, and calculates their type, size, position, and speed. Radar is used to detect the position and speed of these entities. The roadside computing unit then fuses the visual and radar information for output.

[0091] Step 301, identifying and recording at least one vehicle and the area occupied by the vehicle body to obtain a global vehicle map;

[0092] Usually, there may be at least one vehicle on the road. In order to obtain a complete traffic situation, the vehicles on the road and the coordinate information corresponding to each vehicle may be collected first.

[0093] In an embodiment of the present invention, an intelligent traffic roadside unit can be used to identify vehicles on the road and record the identified vehicles. The recorded vehicle information can include vehicle identification information and vehicle coordinate information. The vehicle identification information can be a vehicle ID.

[0094] Each coordinate may be set to correspond to a block to obtain block information occupied by the vehicle body, so that in a subsequent prediction process, block information occupied by at least one vehicle body may be found.

[0095] Specifically, after identifying at least one vehicle ID and the coordinate information of each vehicle, the vehicle information can be recorded in a hash table with (vehicle coordinates as key, vehicle ID as value) to obtain a global vehicle map, so that the block information occupied by the vehicle body can be found later according to the vehicle ID.

[0096] Step 302: Analyze the drivable direction of each lane, set each lane to correspond to a block, record each block and the drivable direction on the block to obtain a drivable direction map;

[0097] During vehicle driving, the drivable direction provided by the lane itself imposes certain restrictions on the vehicle's drivable direction. Therefore, in order to improve the accuracy of the prediction of the driving direction of the vehicle to be predicted in the blind spot, the driving direction provided by the lane can be considered. Therefore, in an embodiment of the present invention, each lane can be analyzed to obtain the drivable direction of each lane, and each lane can be set to correspond to a block. Each block and the drivable direction on the block are recorded to obtain a driving direction map, which can be used to determine the drivable direction of the vehicle to be predicted later.

[0098] Specifically, a mapping vehicle can be used to collect high-precision maps of the road, from which all lanes can be extracted. The drivable direction of each lane can be calculated, and each lane can be set to correspond to a block. Each block and the drivable direction on the block can be recorded to obtain a driving direction map.

[0099] The calculation method for the drivable direction of each lane is as follows:

[0100] In a high-precision map, a road can be composed of at least one lane, and each lane line can be composed of a point set. Figure 4 , shows a lane diagram in a high-precision map provided in an embodiment of the present invention. In the figure, 401 represents the road direction, 402 represents the point set for the left side of the road, and 403 represents the point set for the right side of the road. Assuming the initial coordinates of the road are used as the starting point, the subscript of the first lane line is set to 0, and so on.

[0101] The number of midpoints of the left and right lanes of a road can be the same or different. Figure 4As an example, the number of midpoints on the left and right sides of a road is different, with the left side having two more midpoints than the right side. The line segment 404 between the black and gray points connects the points with the same subscript in the two point sets. The two extra points on the left side are both connected to the last point on the right side. The square 405 between the line segments is the midpoint of a line segment.

[0102] Connect the blocks starting from index 0, and perform the following processing on the line segment between every two blocks:

[0103] Let the first purple point be mid0(x0,y0) and the second purple point be mid1(x1,y1). Given two points, according to the formula:

[0104] A=y1-y0(1)

[0105] B=x1-x0(2)

[0106] C=x1×y0-x0×y1(3)

[0107] You can get the general straight line equation from mid0 to mid1:

[0108] A×x+B×y+C=0(4)

[0109] Using mid1-mid0, we can find the direction vector (x, y) of the line and use the inverse tangent function:

[0110] θ=atan2(y,x)(5)

[0111] The direction angle θ (radians) of the line segment from mid0 to mid1 can be obtained.

[0112] Next, calculate the absolute value of the x difference △x and the absolute value of the y difference △y between mid0 and mid1. If △x is greater than △y, start at x = x0, step 1, and use the obtained line equation to find the set of direction angles S from mid0 to mid1. Traverse the set of direction angles S and record them according to the defined JSON structure. If △y is greater than △x, start at y = y0, step 1, and use the obtained line equation to find the set of direction angles S from mid0 to mid1. Traverse the set of direction angles S and record them according to the defined JSON structure. This will determine the drivable direction of the first lane. The drivable direction of each lane is calculated using the above method.

[0113] Step 303: collecting driving data of the at least one vehicle in the identifiable area of ​​the intelligent transportation roadside unit;

[0114] If all vehicles on the road travel in any direction and at any speed, there is a high probability of collision between them. To ensure vehicle safety, the driving data of other vehicles around the vehicle can be used to limit the vehicle's driving data, so that there is a safe driving distance between vehicles, thus avoiding collisions.

[0115] Therefore, in an embodiment of the present invention, an intelligent traffic roadside unit can be used to collect driving data of at least one vehicle, so that the driving data of at least one vehicle can be subsequently used to limit the driving data of the vehicle to be predicted, thereby avoiding collisions between the vehicle to be predicted and other vehicles.

[0116] Step 304 : predicting the driving data of the to-be-predicted vehicle in the blind spot based on the global vehicle map, the driving direction map, and the driving data of the at least one vehicle in the identifiable area.

[0117] In order to obtain the driving data of the vehicle to be predicted in the blind spot, after obtaining the global vehicle map, the driving direction map and the driving data of at least one vehicle in the identifiable area, the driving data of the vehicle to be predicted in the blind spot can be predicted using the global vehicle map, the driving direction map and the driving data of at least one vehicle in the identifiable area to obtain the driving data of the vehicle to be predicted in the blind spot, and then the driving data of the vehicle to be predicted in the blind spot can be associated with the vehicle to be predicted, so that the vehicle to be predicted uses the predicted driving data to drive, avoiding the vehicle to be predicted from running out of the lane or colliding with other vehicles, and can guide other vehicles around it to adjust their own driving direction and driving speed according to the driving data of the vehicle to be predicted, avoiding other vehicles from colliding with the vehicle to be predicted.

[0118] The vehicle driving data prediction method of the embodiment of the present invention is adopted to obtain a global vehicle map by identifying and recording at least one vehicle and the block occupied by the vehicle body, analyze the drivable direction of each lane, set each lane to correspond to a block, record each block and the drivable direction on the block to obtain a driving direction map, and collect driving data of at least one vehicle in the identifiable area of ​​the intelligent traffic roadside unit, so that the driving data of the vehicle to be predicted in the blind spot can be predicted based on the global vehicle map, the driving direction map and the driving data of at least one vehicle in the identifiable area. The method can be used to predict the driving data of the vehicle to be predicted in the blind spot, and because the present invention uses the actual drivable direction of the lane to determine the driving direction of the vehicle to be predicted, and determines the driving speed of the vehicle to be predicted based on the driving data of other vehicles around the vehicle to be predicted and the actual road conditions, the driving data of the vehicle to be predicted in the blind spot predicted by the method has higher accuracy and is more in line with the actual situation, so that it can better assist driving or provide support for automatic driving, thereby avoiding the occurrence of traffic accidents.

[0119] Reference Figure 5 , shows a flowchart of another vehicle driving data prediction method provided in an embodiment of the present invention, which may specifically include the following steps:

[0120] Step 501: Identify and record at least one vehicle and the area occupied by the vehicle to obtain a global vehicle map;

[0121] In an embodiment of the present invention, an intelligent transportation roadside unit can be used to identify vehicles on the road and record the identified vehicles. The recorded vehicle information may include vehicle identification information and vehicle coordinate information. Each coordinate can be set to correspond to a block, and the block information occupied by the vehicle body can be obtained. The identified vehicle identification information and the block information occupied by the vehicle body are recorded to obtain a global vehicle map, so that the block information occupied by the vehicle body can be subsequently searched based on the vehicle identification information.

[0122] Step 502: Analyze the drivable direction of each lane, set each lane to correspond to a block, record each block and the drivable direction on the block to obtain a drivable direction map;

[0123] In an embodiment of the present invention, a mapping vehicle can be used to collect high-precision maps of roads, from which all lanes are extracted, the drivable direction of each lane is calculated, and each lane is set to correspond to a block. Each block and the drivable direction on the block are recorded to obtain a driving direction map.

[0124] Step 503: collecting driving data of the at least one vehicle in the identifiable area of ​​the intelligent transportation roadside unit;

[0125] In an embodiment of the present invention, an intelligent traffic roadside unit can be used to collect driving data of at least one vehicle so that the driving data of at least one vehicle can be used to restrict the driving data of the vehicle to be predicted, thereby avoiding collision between the vehicle to be predicted and other vehicles.

[0126] Step 504 : predicting the driving direction and speed of the to-be-predicted vehicle in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area.

[0127] In order to obtain the driving direction and driving speed of the vehicle to be predicted in the blind spot, after obtaining the global vehicle map, the driving direction map, and the driving direction and driving speed of at least one vehicle in the identifiable area, the global vehicle map, the driving direction map, and the driving direction and driving speed of at least one vehicle in the identifiable area can be used to predict the driving direction and driving speed of the vehicle to be predicted in the blind spot to obtain the driving direction and driving speed of the vehicle to be predicted in the blind spot.

[0128] In one embodiment of the present invention, the step of predicting the driving direction and speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area includes:

[0129] S11, searching the global vehicle map for a block occupied by the vehicle body to be predicted;

[0130] In order to make the predicted driving direction of the vehicle in the blind spot more realistic and avoid the vehicle running out of the lane, the driving direction of the vehicle can be restricted by the drivable direction of the lane, so that the predicted vehicle can adopt an appropriate driving direction.

[0131] In an embodiment of the present invention, the drivable direction of the lane is used to restrict the driving direction of the vehicle. First, the lane in which the vehicle to be predicted is located can be determined. Specifically, the block occupied by the body of the vehicle to be predicted can be searched from the global vehicle map according to the vehicle ID of the vehicle to be predicted, so as to further determine the drivable direction of the vehicle.

[0132] S12, searching, from the driving direction map, for a drivable direction in the block occupied by the vehicle body to be predicted according to the block occupied by the vehicle body to be predicted;

[0133] After determining the block occupied by the vehicle body to be predicted, the drivable directions on the block occupied by the vehicle body to be predicted can be found from the driving direction map, thereby obtaining at least one direction in which the vehicle to be predicted can travel.

[0134] S13 , determining the driving direction of the vehicle to be predicted in the blind spot according to the driving direction of the vehicle to be predicted in the identifiable area and the drivable directions in the block occupied by the body of the vehicle to be predicted.

[0135] The possible driving directions in the block occupied by the vehicle to be predicted may be the same as the vehicle's current direction, may differ by a certain angle, or may be completely opposite to the vehicle's current direction. However, a possible driving direction in the block occupied by the vehicle to be predicted that is completely opposite to the vehicle's current direction clearly violates the laws of motion. A vehicle cannot directly change from one driving direction to the opposite direction. Therefore, the vehicle's current direction can be used to restrict its next driving direction.

[0136] As an example, see Figure 6 , shows a schematic diagram of a driving direction map provided in an embodiment of the present invention. In the figure, 601 represents the area occupied by the vehicle to be predicted, 602 represents the current driving direction of the vehicle to be predicted, and 603 represents the possible driving directions on the driving direction map. If the current driving direction of the vehicle to be predicted is not used to constrain the predicted driving direction, in this case, the vehicle's next driving direction will be downward, not right. Therefore, it is necessary to use the current driving direction of the vehicle to be predicted to constrain the predicted driving direction and exclude driving directions that clearly violate the laws of motion.

[0137] Specifically, the system can traverse the possible driving directions within the block occupied by the vehicle to be predicted, searching for a direction angle whose difference from the direction of the vehicle's last observed movement before it entered the blind spot is less than a first preset threshold. The found direction angle is then recorded in a driving direction list. Furthermore, to ensure that the predicted driving direction is more accurate than actual driving direction, the direction angle that appears most frequently in the driving direction list can be used as the predicted vehicle's driving direction in the blind spot.

[0138] The first threshold may be 20°, 30°, 40°, 45°, 50°, 60°, 90°, and so on.

[0139] As a preferred example, the first threshold may be 40°. Setting it to 40° allows the vehicle to be predicted to maintain a reasonable direction and continue to move forward in an area with multiple driving directions, such as an intersection.

[0140] In one embodiment of the present invention, the step of predicting the driving direction and speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area further includes:

[0141] S21, determining a driving speed of a preceding vehicle of the to-be-predicted vehicle and a maximum drivable speed of the to-be-predicted vehicle in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0142] In order to make the predicted speed of the vehicle to be predicted in the blind spot more in line with reality and avoid the vehicle to be predicted from colliding with other vehicles, the speed of other vehicles can be used to limit the speed of the vehicle to be predicted, especially the vehicle in front of the vehicle to be predicted. The speed of the vehicle to be predicted can be used to limit the speed of the vehicle to be predicted, so as to ensure a safe driving distance between the two and avoid the occurrence of collision accidents. At the same time, the maximum drivable speed of the vehicle to be predicted can be determined according to the shape of the road, so as to further use the maximum drivable speed of the vehicle to be predicted to limit the speed of the vehicle to be predicted, so that the vehicle to be predicted can travel at an appropriate speed.

[0143] In an embodiment of the present invention, a global vehicle map, a driving direction map, and the driving direction and speed of at least one vehicle in an identifiable area can be used to determine the driving speed of the vehicle ahead of the predicted vehicle and the maximum possible driving speed of the predicted vehicle in the blind spot.

[0144] S22 , based on a preset car-following model, using the driving speed of the preceding vehicle of the vehicle to be predicted and the maximum drivable speed of the vehicle to be predicted in the blind spot, predicting the driving speed of the vehicle to be predicted in the blind spot.

[0145] After determining the speed of the vehicle ahead of the predicted vehicle and the maximum drivable speed of the predicted vehicle in the blind spot, the speed of the vehicle ahead of the predicted vehicle and the maximum drivable speed of the predicted vehicle in the blind spot can be substituted into the preset following model to obtain the speed of the predicted vehicle in the blind spot by calculation.

[0146] Specifically, the preset car-following model includes two situations:

[0147] If the preceding vehicle can be found, the vehicle can be considered to be in a congested traffic state. The following model under congested traffic state is used to calculate the speed of the vehicle to be predicted:

[0148]

[0149]

[0150] Where, a(t): acceleration of the vehicle at time t; a start : vehicle's starting acceleration; v max: Maximum speed limit of the vehicle; v(t): Speed ​​of the vehicle at time t; δ: Speed ​​sensitivity index. The smaller the value, the smoother the effect of speed change on acceleration; s * : the expected minimum distance from the vehicle in front; Δv(t): the speed difference between the last observed speed before entering the blind spot and the speed of the vehicle in front; Δx(t): the distance difference between the last observed speed before entering the blind spot and the vehicle in front; s0: the safety distance at rest; s1: the safety distance related to speed; T: the safe headway distance; a max : maximum acceleration of the vehicle; b exp : Expected deceleration.

[0151] If no preceding vehicle is found, the vehicle can be considered to be in a free state in traffic flow and is not constrained by other vehicles. The following model in a free state in traffic flow is used to calculate the speed of the vehicle to be predicted:

[0152] Because there is no preceding vehicle, that is, Δx(t) tends to infinity, Tends to 0.

[0153] The formula of the car-following model (traffic flow free state) is as follows:

[0154]

[0155] In one embodiment of the present invention, the step of determining the driving speed of the preceding vehicle of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and driving speed of the at least one vehicle in the identifiable area includes:

[0156] S31, determining a deduced direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0157] In order to make the predicted speed of the vehicle to be predicted in the blind spot more realistic and avoid collision between the vehicle to be predicted and other vehicles, the speed of the vehicle to be predicted is limited by the speed of the vehicle in front of the vehicle to be predicted.

[0158] In the embodiment of the present invention, the preceding vehicle of the vehicle to be predicted may be determined first, and then the driving speed of the preceding vehicle may be searched from the collected driving data of at least one vehicle.

[0159] The preceding vehicle of the predicted vehicle is determined through deduction. Specifically, the deduced direction of the predicted vehicle can be determined based on the global vehicle map, the driving direction map, and the driving direction and speed of at least one vehicle in the identifiable area. Specifically, the block occupied by the predicted vehicle is first searched in the global vehicle map based on the predicted vehicle ID. Then, based on the block occupied by the predicted vehicle, the possible driving directions for the block occupied by the predicted vehicle are searched in the driving direction map. The deduced direction of the predicted vehicle is determined based on the driving direction of the predicted vehicle in the identifiable area and the possible driving directions for the block occupied by the predicted vehicle.

[0160] S32, deducing the deduced position of the vehicle to be predicted using the deduced direction of the vehicle to be predicted, a preset driving speed, and a preset time interval;

[0161] After determining the predicted direction of the vehicle to be predicted, the predicted position of the vehicle to be predicted can be predicted at a preset speed and time interval, so that the preceding vehicle can be determined based on the predicted position. The preset speed can be 5m / s, 10m / s, 20m / s, 30m / s, etc.; the time interval can be 0.1s, 0.15s, 0.2s, 0.25s, 0.3s, 0.5s, etc.

[0162] As a preferred example, the preset driving speed can be 20m / s, and the preset time interval can be 0.1s. Driving at this speed for 0.1s can basically cover half of the vehicle body, thereby shortening the number of deductions and avoiding deducing too far and missing the effective vehicle in front.

[0163] S33, searching the global map information for vehicles other than the vehicle to be predicted in the block corresponding to the deduced position and counting the number of times each vehicle appears;

[0164] The vehicle that appears at the deduced position of the vehicle to be predicted may be the preceding vehicle of the vehicle to be predicted. Therefore, after the deduced position of the vehicle to be predicted is obtained, the vehicles other than the vehicle to be predicted in the block corresponding to the deduced position can be searched from the global map information and the number of times each vehicle appears can be counted, so as to determine the preceding vehicle of the vehicle to be predicted from the vehicles in the deduced position of the vehicle to be predicted.

[0165] S34, determining a preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position;

[0166] There may be more than one vehicle appearing at the deduced position of the vehicle to be predicted, and the number of times these vehicles appear may also be different. However, the number of blocks of the deduced position of the vehicle to be predicted is limited. Therefore, the probability that the vehicle that appears more times at the deduced position is the preceding vehicle of the vehicle to be predicted is relatively high. Therefore, the preceding vehicle of the vehicle to be predicted can be determined based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position.

[0167] S35 , searching for the driving speed of the preceding vehicle of the vehicle to be predicted from the driving speeds of the at least one vehicle in the identifiable area.

[0168] After determining the vehicle preceding the vehicle to be predicted, the driving speed of the vehicle preceding the vehicle to be predicted can be searched from the driving speeds of at least one vehicle in the identifiable area, thereby obtaining the driving speed of the vehicle preceding the vehicle to be predicted, which can be used to calculate the driving speed of the vehicle to be predicted in the blind spot.

[0169] In one embodiment of the present invention, the step of determining the preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position includes:

[0170] S41, calculating the probability of each vehicle being the preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position, and taking the vehicle with a higher probability than other vehicles as the preceding vehicle of the vehicle to be predicted.

[0171] The number of blocks of the deduced position of the vehicle to be predicted is limited. Among the limited number of blocks, the vehicle that appears the most times has the highest probability of becoming the preceding vehicle of the vehicle to be predicted. Therefore, in an embodiment of the present invention, the probability of each vehicle becoming the preceding vehicle of the vehicle to be predicted can be calculated based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position, and the vehicle with a probability greater than that of other vehicles is used as the preceding vehicle of the vehicle to be predicted.

[0172] As an example, the vehicle with the highest number of appearances and a number of appearances greater than a preset multiple of the number of blocks corresponding to the deduction position can be used as the preceding vehicle of the vehicle to be predicted. Specifically, it can be determined whether the number of appearances of the vehicle with the highest number of appearances is greater than a preset multiple of the number of blocks corresponding to the deduction position. If the number of appearances of the vehicle with the highest number of appearances is greater than a preset multiple of the number of blocks corresponding to the deduction position, the vehicle with the highest number of appearances can be used as the preceding vehicle of the vehicle to be predicted. Taking a second preset distance as a constraint, if the number of appearances of the vehicle with the highest number of appearances within the second preset distance is less than or equal to a preset multiple of the number of blocks corresponding to the deduction position, it is determined that the vehicle to be predicted has no preceding vehicle. For example, if the number of blocks corresponding to the deduction position is N, and the number of appearances of the vehicle with the highest number of appearances is b, if b>1 / 3N, then the vehicle can be used as the preceding vehicle of the vehicle to be predicted. Taking 60 meters as a preset distance, if the number of appearances of the vehicle with the highest number of appearances at all deduction positions deduced within 60 meters is c, and c≤1 / 3N, then it can be determined that the vehicle to be predicted has no preceding vehicle.

[0173] As an example, see Figure 7 , shows a flowchart of determining a preceding vehicle of a vehicle to be predicted provided in an embodiment of the present invention.

[0174] The method for finding the preceding vehicle is a looping process, with the input parameters being the current vehicle information and the current loop count. First, the loop checks whether the current loop count is greater than 30. If it is, the preceding vehicle is considered unavailable and the loop exits. If it is less than 30, the loop continues. Looping 30 times means searching for the preceding vehicle within a 60-meter radius. Next, the IDs of all vehicles (excluding the vehicle's own ID) within the block occupied by the deduced vehicle are obtained and counted. The vehicle B with the greatest number of occurrences (i.e., the vehicle occupying the most blocks) is identified. Its occurrence count is compared with 1 / 3 of the total number of blocks occupied by the deduced vehicle, U. If the occurrence count is greater than 1 / 3U, B is considered the preceding vehicle. If the occurrence count is less than 1 / 3U, the loop continues. If the preceding vehicle is not found in this loop, the loop continues, first obtaining the direction θ for the next iteration. If θ cannot be obtained, a recursive process is performed. If θ can be found, the next position of the deduced vehicle is calculated at a speed of 20 m / s and a time interval of 0.1 s, and the current number of loops is increased by 1 to proceed to the next position to find the preceding vehicle.

[0175] In one embodiment of the present invention, the step of determining the maximum drivable speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and driving speed of the at least one vehicle in the identifiable area includes:

[0176] S51, determining a deduced direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0177] In order to make the predicted speed of the vehicle to be predicted in the blind spot more close to reality and avoid traffic accidents such as speeding and violating traffic regulations or running out of the lane by the predicted vehicle, the shape of the road is used to limit the maximum drivable speed of the vehicle to be predicted, so that the maximum drivable speed of the vehicle to be predicted can be further used to limit the speed of the vehicle to be predicted.

[0178] In the embodiment of the present invention, the shape of the road may be determined first, and then the maximum drivable speed of the vehicle to be predicted may be determined according to the different shapes of the road.

[0179] The shape of the road is also determined by deduction. Specifically, the deduced direction of the vehicle to be predicted can be determined based on the global vehicle map, the driving direction map, and the driving direction and speed of at least one vehicle in the identifiable area.

[0180] S52, using a first preset distance as a constraint condition, using the deduced direction of the vehicle to be predicted and a preset driving speed to deduce a deduced trajectory of the vehicle to be predicted;

[0181] After determining the predicted direction of the vehicle to be predicted, a trajectory of the vehicle to be predicted within the first preset distance can be derived using the predicted direction and a preset driving speed, with a first preset distance as a constraint. After the predicted trajectory of the vehicle to be predicted within the first preset distance is derived, the shape of the road can be determined based on the derived trajectory. The first preset distance can be 10 meters, 20 meters, 50 meters, 60 meters, 100 meters, etc.; the preset driving speed can be 5 m / s, 10 m / s, 20 m / s, 30 m / s, etc.

[0182] S53, calculating the angle between the starting direction and the ending direction of the deduced trajectory of the vehicle to be predicted;

[0183] Road shapes can generally be divided into two types: straight and curved. If the road is straight, the initial and final directions of a vehicle traveling on the straight road generally do not differ significantly, that is, the angle between the initial and final directions is small. However, for a vehicle traveling on a curved road, the initial and final directions will change significantly, that is, the angle between the initial and final directions is large.

[0184] In an embodiment of the present invention, after the deduced trajectory of the vehicle to be predicted within the first preset distance is obtained, the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted can be calculated, and the shape of the road can be determined based on the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted.

[0185] Reference Figure 8 , shows a schematic diagram of the change in the driving direction angle of a trajectory from the starting point to the end point provided in an embodiment of the invention, recording the angle of the driving direction after each movement from the starting point to the end point of the trajectory.

[0186] S54: Determine the maximum drivable speed of the vehicle to be predicted in the blind spot according to the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted.

[0187] On a straight road, a vehicle can usually travel at a higher speed. However, on a curve, if the vehicle travels at a higher speed, it is very likely to roll over due to centrifugal force. To ensure safe driving of the vehicle, different maximum driving speeds can be set for the vehicle on straight roads and curves.

[0188] Specifically, after determining the shape of the road based on the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted, the maximum drivable speed of the vehicle to be predicted in the blind spot can be determined based on the shape of the road.

[0189] In one embodiment of the present invention, the step of determining the maximum drivable speed of the vehicle to be predicted in the blind spot based on the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted includes:

[0190] S61, determining whether the angle between the starting direction and the ending direction of the deduced trajectory of the vehicle to be predicted exceeds a first preset threshold;

[0191] When driving on a straight road, there may be a difference between the vehicle's starting direction and the ending direction, but the difference is smaller than that on a curve. Therefore, a threshold can be set, and roads with a difference less than the threshold are regarded as straight roads, and roads with a difference greater than the threshold are regarded as curves.

[0192] After calculating the angle between the starting and ending directions of the predicted vehicle's trajectory, it is determined whether the angle exceeds a first preset threshold to determine whether the road is straight or curved. The first preset threshold can be 10°, 20°, 30°, 45°, 60°, and so on.

[0193] S62: If the angle between the starting direction and the ending direction of the predicted trajectory of the vehicle to be predicted does not exceed a first preset threshold, the maximum drivable speed of the current lane is used as the maximum drivable speed of the vehicle to be predicted in the blind spot.

[0194] If the angle between the starting and ending directions of the predicted trajectory of the vehicle to be predicted does not exceed a first preset threshold, it indicates that the vehicle's trajectory is straight. In this case, the road shape can be considered to be a straight road. For a straight road, the vehicle can travel at a higher speed. Therefore, the maximum drivable speed of the current lane can be used as the maximum drivable speed of the predicted vehicle in the blind spot.

[0195] S63: If the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted exceeds a first preset threshold, the maximum drivable speed of the vehicle to be predicted in the blind spot is determined based on the size of the angle; the size of the angle has a corresponding relationship with the maximum drivable speed.

[0196] If the angle between the starting driving direction and the ending driving direction of the predicted trajectory of the vehicle exceeds a first preset threshold, it means that the vehicle will enter a curve. At this time, the shape of the road can be considered to be a curve. For a curve, the larger the curve angle, the smaller the maximum drivable speed of the vehicle.

[0197] Specifically, different included angles may be set to correspond to different maximum drivable speeds, so that the maximum drivable speed of the vehicle to be predicted in the blind spot may be determined according to the calculated size of the included angle.

[0198] The vehicle driving data prediction method of the embodiment of the present invention is adopted to obtain a global vehicle map by identifying and recording at least one vehicle and the block occupied by the vehicle body, analyze the drivable direction of each lane, set each lane to correspond to a block, record each block and the drivable direction on the block to obtain a driving direction map, and collect driving data of at least one vehicle in the identifiable area of ​​the intelligent traffic roadside unit, so that the driving data of the vehicle to be predicted in the blind spot can be predicted based on the global vehicle map, the driving direction map and the driving data of at least one vehicle in the identifiable area. The method can be used to predict the driving data of the vehicle to be predicted in the blind spot, and because the present invention uses the actual drivable direction of the lane to determine the driving direction of the vehicle to be predicted, and determines the driving speed of the vehicle to be predicted based on the driving data of other vehicles around the vehicle to be predicted and the actual road conditions, the driving data of the vehicle to be predicted in the blind spot predicted by the method has higher accuracy and is more in line with the actual situation, so that it can better assist driving or provide support for automatic driving, thereby avoiding the occurrence of traffic accidents.

[0199] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0200] Reference Figure 9 , shows a structural block diagram of a vehicle driving data prediction device provided in an embodiment of the present invention, which may specifically include the following modules:

[0201] A global vehicle map generating module 901 is configured to identify and record at least one vehicle and the area occupied by the vehicle to obtain a global vehicle map;

[0202] A driving direction map generation module 902 is configured to analyze the drivable direction of each lane, assign each lane to a corresponding block, and record each block and the drivable direction on the block to obtain a driving direction map;

[0203] The collection module 903 is used to collect the driving data of the at least one vehicle in the identifiable area of ​​the intelligent transportation roadside unit;

[0204] The prediction module 904 is configured to predict the driving data of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving data of the at least one vehicle in the identifiable area.

[0205] In one embodiment of the present invention, the prediction module includes:

[0206] The prediction submodule is used to predict the driving direction and speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map and the driving direction and speed of the at least one vehicle in the identifiable area.

[0207] In one embodiment of the present invention, the prediction submodule includes:

[0208] A first search unit is configured to search the global vehicle map for a block occupied by the vehicle body to be predicted;

[0209] A second search unit is configured to search the driving direction map for a possible driving direction on the block occupied by the vehicle body to be predicted according to the block occupied by the vehicle body to be predicted;

[0210] The driving direction determining unit is used to determine the driving direction of the vehicle to be predicted in the blind spot according to the driving direction of the vehicle to be predicted in the identifiable area and the drivable directions in the block occupied by the body of the vehicle to be predicted.

[0211] In one embodiment of the present invention, the prediction submodule further includes:

[0212] a first determining unit, configured to determine a driving speed of a preceding vehicle of the to-be-predicted vehicle and a maximum drivable speed of the to-be-predicted vehicle in a blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0213] The driving speed determination unit is used to predict the driving speed of the vehicle to be predicted in the blind spot based on a preset car-following model and the driving speed of the preceding vehicle of the vehicle to be predicted and the maximum drivable speed of the vehicle to be predicted in the blind spot.

[0214] In one embodiment of the present invention, the first determining unit includes:

[0215] a first deduction direction determination subunit, configured to determine a deduction direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0216] a deduced position determination subunit, configured to deduce the deduced position of the vehicle to be predicted using the deduced direction of the vehicle to be predicted, a preset driving speed, and a preset time interval;

[0217] A first search subunit is configured to search the global map information for vehicles other than the vehicle to be predicted in the block corresponding to the deduced position and to count the number of occurrences of each vehicle;

[0218] a preceding vehicle determining subunit, configured to determine a preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position;

[0219] The second searching subunit is configured to search for a driving speed of a preceding vehicle of the vehicle to be predicted from the driving speeds of the at least one vehicle in the identifiable area.

[0220] In one embodiment of the present invention, the preceding vehicle determining subunit includes:

[0221] The preceding vehicle determination component is used to calculate the probability of each vehicle becoming the preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position, and to select the vehicle with a probability greater than that of other vehicles as the preceding vehicle of the vehicle to be predicted.

[0222] In one embodiment of the present invention, the first determining unit includes:

[0223] a second deduction direction determination subunit, configured to determine a deduction direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0224] a deduction trajectory determination subunit, configured to deduce a deduction trajectory of the vehicle to be predicted using a first preset distance as a constraint condition, a deduction direction of the vehicle to be predicted, and a preset driving speed;

[0225] An angle calculation subunit, used to calculate the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted;

[0226] The first determining subunit is configured to determine a maximum drivable speed of the vehicle to be predicted in the blind spot according to an angle between a starting driving direction and an ending driving direction of a deduced trajectory of the vehicle to be predicted.

[0227] In one embodiment of the present invention, the first determining subunit includes:

[0228] a judgment component, configured to judge whether an angle between a starting driving direction and an ending driving direction of the deduced trajectory of the vehicle to be predicted exceeds a first preset threshold;

[0229] a first maximum drivable speed determining component, configured to use the maximum drivable speed of the current lane as the maximum drivable speed of the vehicle to be predicted in the blind spot if the angle between the starting and ending directions of the deduced trajectory of the vehicle to be predicted does not exceed a first preset threshold;

[0230] a second maximum drivable speed determination component for determining, if the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted exceeds a first preset threshold, the maximum drivable speed of the vehicle to be predicted in the blind spot based on the size of the angle; the size of the angle having a corresponding relationship with the maximum drivable speed.

[0231] As for the device 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.

[0232] In addition, an embodiment of the present invention further provides an electronic device, such as Figure 10 As shown, it includes a processor 1001, a communication interface 1002, a memory 1003 and a communication bus 1004, wherein the processor 1001, the communication interface 1002, and the memory 1003 communicate with each other through the communication bus 1004.

[0233] Memory 1003, used for storing computer programs;

[0234] The processor 1001 is configured to execute the program stored in the memory 1003 by performing the following steps:

[0235] Identifying and recording at least one vehicle and the area occupied by the vehicle to obtain a global vehicle map;

[0236] Analyze the drivable direction of each lane, set each lane to correspond to a block, record each block and the drivable direction on the block to obtain a driving direction map;

[0237] Collecting driving data of the at least one vehicle in an identifiable area of ​​the intelligent transportation roadside unit;

[0238] The driving data of the vehicle to be predicted in the blind spot is predicted based on the global vehicle map, the driving direction map and the driving data of the at least one vehicle in the identifiable area.

[0239] In one embodiment of the present invention, the step of predicting the driving data of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving data of the at least one vehicle in the identifiable area includes:

[0240] The driving direction and speed of the vehicle to be predicted in the blind spot are predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area.

[0241] In one embodiment of the present invention, the step of predicting the driving direction and speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area includes:

[0242] Searching the global vehicle map for a block occupied by the vehicle body to be predicted;

[0243] According to the block occupied by the vehicle body to be predicted, searching the driving direction map for a possible driving direction on the block occupied by the vehicle body to be predicted;

[0244] The driving direction of the vehicle to be predicted in the blind spot is determined according to the driving direction of the vehicle to be predicted in the identifiable area and the drivable directions in the block occupied by the body of the vehicle to be predicted.

[0245] In one embodiment of the present invention, the step of predicting the driving direction and speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area further includes:

[0246] Determining the speed of the preceding vehicle of the to-be-predicted vehicle and the maximum drivable speed of the to-be-predicted vehicle in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0247] Based on a preset car-following model, the driving speed of the vehicle in front of the vehicle to be predicted and the maximum drivable speed of the vehicle to be predicted in the blind spot are used to predict the driving speed of the vehicle to be predicted in the blind spot.

[0248] In one embodiment of the present invention, the step of determining the driving speed of the preceding vehicle of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and driving speed of the at least one vehicle in the identifiable area includes:

[0249] Determining a deduced direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0250] Deducing the deduced position of the vehicle to be predicted using the deduced direction of the vehicle to be predicted, a preset driving speed, and a preset time interval;

[0251] Searching for vehicles other than the vehicle to be predicted in the block corresponding to the deduced position from the global map information and counting the number of times each vehicle appears;

[0252] Determining a preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position;

[0253] The driving speed of the preceding vehicle of the vehicle to be predicted is found from the driving speed of the at least one vehicle in the identifiable area.

[0254] In one embodiment of the present invention, the step of determining the preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position includes:

[0255] Based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position, the probability of each vehicle becoming the preceding vehicle of the vehicle to be predicted is calculated, and the vehicle with a probability greater than that of other vehicles is taken as the preceding vehicle of the vehicle to be predicted.

[0256] In one embodiment of the present invention, the step of determining the maximum drivable speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and driving speed of the at least one vehicle in the identifiable area includes:

[0257] Determining a deduced direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area;

[0258] Using the first preset distance as a constraint condition, the deduced trajectory of the vehicle to be predicted is deduced using the deduced direction of the vehicle to be predicted and a preset driving speed;

[0259] Calculating the angle between the starting direction and the ending direction of the predicted trajectory of the vehicle to be predicted;

[0260] The maximum drivable speed of the vehicle to be predicted in the blind spot is determined according to the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted.

[0261] In one embodiment of the present invention, the step of determining the maximum drivable speed of the vehicle to be predicted in the blind spot based on the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted includes:

[0262] Determining whether an angle between a starting driving direction and an ending driving direction of the deduced trajectory of the vehicle to be predicted exceeds a first preset threshold;

[0263] If the angle between the starting direction and the ending direction of the predicted trajectory of the vehicle to be predicted does not exceed a first preset threshold, the maximum drivable speed of the current lane is used as the maximum drivable speed of the vehicle to be predicted in the blind spot;

[0264] If the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted exceeds a first preset threshold, the maximum drivable speed of the vehicle to be predicted in the blind spot is determined based on the size of the angle; the size of the angle has a corresponding relationship with the maximum drivable speed.

[0265] The communication bus mentioned in the terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0266] The communication interface is used for communication between the above terminal and other devices.

[0267] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0268] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0269] like Figure 11 As shown, in another embodiment provided by the present invention, a computer-readable medium 1101 is also provided, which stores instructions. When the computer-readable medium is run on a computer, the processor executes the vehicle driving data prediction method described in the above embodiment.

[0270] In another embodiment of the present invention, a computer program product including instructions is provided. When the computer program product is run on a computer, the computer executes the vehicle driving data prediction method described in the above embodiment.

[0271] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable medium or transmitted from one computer-readable medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0272] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0273] Each embodiment in this specification is described in a related manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiment is generally similar to the method embodiment, so the description is relatively simple. For related parts, refer to the description of the method embodiment.

[0274] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the scope of protection of the present invention.

Claims

1. A vehicle driving data prediction method, characterized in that: include: Identifying and recording at least one vehicle and the area occupied by the vehicle to obtain a global vehicle map; Analyze the drivable direction of each lane, set each lane to correspond to a block, record each block and the drivable direction on the block to obtain a driving direction map; Collecting driving data of the at least one vehicle in an identifiable area of ​​the intelligent transportation roadside unit; Predicting driving data of a vehicle to be predicted in a blind spot based on the global vehicle map, the driving direction map, and the driving data of the at least one vehicle in the identifiable area; The step of predicting the driving data of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving data of the at least one vehicle in the identifiable area includes: Predicting the driving direction and speed of the to-be-predicted vehicle in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area; The step of predicting the driving direction and speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area further includes: Determining the speed of the preceding vehicle of the to-be-predicted vehicle and the maximum drivable speed of the to-be-predicted vehicle in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area; Based on a preset car-following model, the speed of the vehicle ahead of the vehicle to be predicted and the maximum drivable speed of the vehicle to be predicted in the blind spot are used to predict the speed of the vehicle to be predicted in the blind spot; The step of determining the maximum drivable speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and driving speed of the at least one vehicle in the identifiable area includes: Determining a deduced direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area; Using the first preset distance as a constraint condition, the deduced trajectory of the vehicle to be predicted is deduced using the deduced direction of the vehicle to be predicted and a preset driving speed; Calculating the angle between the starting direction and the ending direction of the predicted trajectory of the vehicle to be predicted; The maximum drivable speed of the vehicle to be predicted in the blind spot is determined according to the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted.

2. The method according to claim 1, characterized in that The step of predicting the driving direction and driving speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and driving speed of the at least one vehicle in the identifiable area comprises: Searching the global vehicle map for a block occupied by the vehicle body to be predicted; According to the block occupied by the vehicle body to be predicted, searching the driving direction map for a possible driving direction on the block occupied by the vehicle body to be predicted; The driving direction of the vehicle to be predicted in the blind spot is determined according to the driving direction of the vehicle to be predicted in the identifiable area and the drivable directions in the block occupied by the body of the vehicle to be predicted.

3. The method according to claim 1, characterized in that The step of determining the driving speed of the preceding vehicle of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and driving speed of the at least one vehicle in the identifiable area comprises: Determining a deduced direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area; Deducing the deduced position of the vehicle to be predicted using the deduced direction of the vehicle to be predicted, a preset driving speed, and a preset time interval; Searching for vehicles other than the vehicle to be predicted in the block corresponding to the deduced position from the global map information and counting the number of times each vehicle appears; Determining a preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position; The driving speed of the preceding vehicle of the vehicle to be predicted is found from the driving speed of the at least one vehicle in the identifiable area.

4. The method according to claim 3, characterized in that The step of determining the preceding vehicle of the vehicle to be predicted based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position includes: Based on the number of times each vehicle appears and the number of blocks corresponding to the deduced position, the probability of each vehicle becoming the preceding vehicle of the vehicle to be predicted is calculated, and the vehicle with a probability greater than that of other vehicles is taken as the preceding vehicle of the vehicle to be predicted.

5. The method according to claim 1, wherein The step of determining the maximum drivable speed of the vehicle to be predicted in the blind spot based on the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted comprises: Determining whether an angle between a starting driving direction and an ending driving direction of the deduced trajectory of the vehicle to be predicted exceeds a first preset threshold; If the angle between the starting direction and the ending direction of the predicted trajectory of the vehicle to be predicted does not exceed a first preset threshold, the maximum drivable speed of the current lane is used as the maximum drivable speed of the vehicle to be predicted in the blind spot; If the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the predicted vehicle exceeds a first preset threshold, the maximum drivable speed of the predicted vehicle in the blind spot is determined based on the size of the angle; the size of the angle has a corresponding relationship with the maximum drivable speed.

6. A vehicle driving data prediction device, characterized in that: include: A global vehicle map generation module, configured to identify and record at least one vehicle and the area occupied by the vehicle body to obtain a global vehicle map; A driving direction map generation module is used to analyze the drivable direction of each lane, set each lane to correspond to a block, record each block and the drivable direction on the block to obtain a driving direction map; a collection module, configured to collect driving data of the at least one vehicle in an identifiable area of ​​the intelligent transportation roadside unit; a prediction module, configured to predict driving data of a vehicle to be predicted in a blind spot based on the global vehicle map, the driving direction map, and the driving data of the at least one vehicle in the identifiable area; The prediction module includes: a prediction submodule, configured to predict the driving direction and speed of the vehicle to be predicted in the blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area; The prediction submodule includes: a first determining unit, configured to determine a driving speed of a preceding vehicle of the to-be-predicted vehicle and a maximum drivable speed of the to-be-predicted vehicle in a blind spot based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area; a driving speed determining unit, configured to predict the driving speed of the vehicle to be predicted in the blind spot based on a preset car-following model and the driving speed of the preceding vehicle of the vehicle to be predicted and the maximum drivable speed of the vehicle to be predicted in the blind spot; The first determining unit includes: a second deduction direction determination subunit, configured to determine a deduction direction of the vehicle to be predicted based on the global vehicle map, the driving direction map, and the driving direction and speed of the at least one vehicle in the identifiable area; a deduction trajectory determination subunit, configured to deduce a deduction trajectory of the vehicle to be predicted using a first preset distance as a constraint condition, a deduction direction of the vehicle to be predicted, and a preset driving speed; An angle calculation subunit, used to calculate the angle between the starting driving direction and the ending driving direction of the deduced trajectory of the vehicle to be predicted; The first determining subunit is configured to determine a maximum drivable speed of the vehicle to be predicted in the blind spot according to an angle between a starting driving direction and an ending driving direction of a deduced trajectory of the vehicle to be predicted.

7. An electronic device, characterized in that: comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is configured to implement the vehicle driving data prediction method according to any one of claims 1 to 5 when executing the program stored in the memory.

8. A computer-readable medium, characterized in that Instructions are stored thereon, which, when executed by one or more processors, enable the processors to execute the vehicle driving data prediction method according to any one of claims 1 to 5.

Images