Target vehicle determination method, device and intelligent driving automobile

Abstract

This application relates to a target vehicle determination method, apparatus, and intelligent driving vehicle. The method includes: acquiring initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information of the vehicle; then determining a boundary correction amount based on the environmental information; and determining corrected vehicle boundary data and corrected lane line boundary data based on the boundary correction amount, the initial vehicle boundary data, and the initial lane line boundary data; finally, determining the target vehicle of the vehicle based on the corrected vehicle boundary data and the corrected lane line boundary data. This method can accurately grasp the distribution of vehicles around the vehicle, thereby solving the problem of timely and accurate selection of target vehicles around the vehicle in complex driving environments and improving the safety of the vehicle during driving.

Description

Technical Field

[0001] This application relates to the field of autonomous driving, and in particular to a method, apparatus and intelligent driving vehicle for determining a target vehicle. Background Technology

[0002] With the rapid development of autonomous driving technology, people are placing higher demands on the safety, reliability, and comfort of vehicles during autonomous driving. During autonomous driving, the driving behavior of surrounding vehicles can seriously interfere with the driving safety of the vehicle itself. For example, when surrounding vehicles rapidly enter or exit the planned driving path, their sudden approach poses a serious threat to the driving safety of the vehicle.

[0003] In existing technologies, to address the aforementioned issues, vehicle information, lane information, and road information acquired by sensors installed inside the vehicle are typically used to determine the target vehicle selection area corresponding to the vehicle. Then, the corresponding target vehicle is selected within this area for tracking. However, in complex road environments, the information acquired by sensors may contain data errors, leading to inaccuracies in the distribution information of surrounding vehicles within the target vehicle selection area. This makes it impossible to accurately select nearby target vehicles in a timely manner, affecting the safety of driving the vehicle.

[0004] Currently, there is no effective solution for how to accurately and timely select target vehicles around the vehicle in complex driving environments. Summary of the Invention

[0005] Therefore, it is necessary to provide a target vehicle determination method, device, and intelligent driving vehicle that can promptly and accurately select target vehicles around the vehicle in complex driving environments to address the aforementioned technical problems.

[0006] Firstly, this application provides a method for determining a target vehicle. The method includes:

[0007] Acquire the vehicle's initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information;

[0008] The boundary correction amount is determined based on the environmental information. The boundary correction amount includes a first boundary correction amount corresponding to the initial vehicle boundary data and a second boundary correction amount corresponding to the initial lane line boundary data.

[0009] Based on the boundary correction amount, the initial vehicle boundary data, and the initial lane line boundary data, the corrected vehicle boundary data and the corrected lane line boundary data are determined.

[0010] The target vehicle is determined based on the corrected vehicle boundary data and the corrected lane line boundary data.

[0011] In one embodiment, the environmental information includes at least one of the following: lane width, road curvature, vehicle type of surrounding vehicles, and movement intention of surrounding vehicles. Determining the boundary correction amount based on the environmental information includes:

[0012] Obtain the longitudinal distance between the surrounding vehicles and the vehicle;

[0013] Based on the environmental information and the longitudinal distance, a first boundary correction amount corresponding to the initial vehicle boundary data and a second boundary correction amount corresponding to the initial lane line boundary data are determined.

[0014] In one embodiment, determining the target vehicle based on the corrected vehicle boundary data and the corrected lane line boundary data includes:

[0015] The vehicle distribution information of surrounding vehicles is determined based on the corrected vehicle boundary data and the corrected lane line boundary data.

[0016] The target vehicle is determined based on the vehicle distribution information.

[0017] In one embodiment, the vehicle distribution information includes whether the surrounding vehicles belong to the vehicle's lane, adjacent lane, or next-next lane, and determining the target vehicle of the vehicle based on the vehicle distribution information includes:

[0018] At least one target vehicle is identified in each of the voluntary lane, the adjacent lane, and the next adjacent lane.

[0019] In one embodiment, identifying at least one target vehicle in each of the vehicular lane, the adjacent lane, and the next adjacent lane includes:

[0020] Obtain the longitudinal distances between all surrounding vehicles and the vehicle itself, sort them longitudinally based on the longitudinal distances, and determine the longitudinal sorting results of the vehicle's lane, the longitudinal sorting results of adjacent lanes, and the longitudinal sorting results of the next adjacent lane.

[0021] Based on the longitudinal sorting results of the vehicle lane, the longitudinal sorting results of the adjacent lanes, and the longitudinal sorting results of the next adjacent lane, at least one target vehicle is determined from each of the vehicle lane, the adjacent lane, and the next adjacent lane.

[0022] In one embodiment, the environmental information includes second vehicle boundary data of surrounding vehicles, and the step of determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data includes:

[0023] Determine the lane-changing status of the vehicle;

[0024] If the lane change state is no lane change or before the lane change is completed, then the first driving range of the vehicle is determined according to the corrected vehicle boundary data, and the second driving range of the surrounding vehicles is determined according to the second vehicle boundary data.

[0025] Based on the first driving section and the second driving section, it is determined whether there is lateral overlap, wherein the lateral overlap means that the above driving sections have projection overlap in the direction perpendicular to the lane centerline;

[0026] If so, then it is determined that the surrounding vehicles belong to the bicycle lane.

[0027] In one embodiment, determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data further includes:

[0028] If the lane change status is "lane change completed", then determine the lane where the vehicle is located after the lane change and obtain the lane line corresponding to the lane where the vehicle is located after the lane change.

[0029] The first lane interval of the lane after the lane change is determined based on the corrected lane line boundary data.

[0030] Determine whether there is lateral overlap between the first lane section and the second driving section;

[0031] If so, then it is determined that the surrounding vehicles belong to the bicycle lane.

[0032] In one embodiment, determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data further includes:

[0033] The adjacent lanes of the vehicle are determined based on the rear axle center coordinates and the initial lane line boundary data.

[0034] Obtain the lane lines of the adjacent lanes, and determine the second lane interval of the adjacent lanes based on the corrected lane line boundary data;

[0035] Determine whether there is lateral overlap between the second lane section and the second driving section;

[0036] If so, then the surrounding vehicles are determined to belong to the adjacent lane.

[0037] In one embodiment, determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data further includes:

[0038] The next adjacent lane of the vehicle is determined based on the rear axle center coordinates of the vehicle and the initial lane line boundary data.

[0039] Determine the lane lines of the next adjacent lane, and determine the third lane section of the next adjacent lane based on the corrected lane line boundary data;

[0040] Determine whether there is lateral overlap between the third lane section and the second driving section;

[0041] If so, then the surrounding vehicles are determined to belong to the next adjacent lane.

[0042] Secondly, this application also provides a target vehicle identification device. The device includes:

[0043] The acquisition module is used to acquire the initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information of the vehicle.

[0044] An optimization module is used to determine a boundary correction amount based on the environmental information. The boundary correction amount includes a first boundary correction amount corresponding to the initial vehicle boundary data and a second boundary correction amount corresponding to the initial lane line boundary data.

[0045] The decision module is used to determine the target vehicle of the vehicle based on the corrected vehicle boundary data and the corrected lane line boundary data.

[0046] Thirdly, this application also provides an intelligent driving vehicle. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0047] Acquire the vehicle's initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information;

[0048] The boundary correction amount is determined based on the environmental information. The boundary correction amount includes a first boundary correction amount corresponding to the initial vehicle boundary data and a second boundary correction amount corresponding to the initial lane line boundary data.

[0049] Based on the boundary correction amount, the initial vehicle boundary data, and the initial lane line boundary data, the corrected vehicle boundary data and the corrected lane line boundary data are determined.

[0050] The target vehicle is determined based on the corrected vehicle boundary data and the corrected lane line boundary data.

[0051] The aforementioned target vehicle selection method, device, and intelligent driving vehicle acquire initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information. Then, based on the environmental information, a boundary correction amount is determined. Next, based on the boundary correction amount, the initial vehicle boundary data, and the initial lane line boundary data, corrected vehicle boundary data and corrected lane line boundary data are determined. Finally, based on the corrected vehicle boundary data and corrected lane line boundary data, the target vehicle for the vehicle is determined. This allows for accurate understanding of the distribution of vehicles around the vehicle, thus solving the problem of timely and accurate selection of target vehicles in complex driving environments and improving driving safety. Attached Figure Description

[0052] Figure 1 This is an application environment diagram of the target vehicle determination method in one embodiment;

[0053] Figure 2 This is a flowchart illustrating a target vehicle determination method in one embodiment;

[0054] Figure 3 This is a schematic diagram illustrating the result of correcting vehicle boundary data in one embodiment;

[0055] Figure 4 This is a schematic diagram of the target vehicle selection results in one embodiment;

[0056] Figure 5 This is a schematic diagram of the target vehicle selection results in another embodiment;

[0057] Figure 6 This is a schematic diagram illustrating the determination of lateral overlap between the vehicle to be determined and the unicar in one embodiment.

[0058] Figure 7 This is a schematic diagram of the distribution of surrounding vehicles during a lane change process in one embodiment.

[0059] Figure 8 This is a structural block diagram of a target vehicle determination device in one embodiment;

[0060] Figure 9 This is a structural block diagram of the target vehicle determination device in another embodiment;

[0061] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] The target vehicle determination method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Specifically, terminal 102 can acquire initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information of its own vehicle and transmit the acquired data to server 104. Server 104 can determine boundary correction amounts based on the environmental information. These boundary correction amounts include a first boundary correction amount corresponding to the initial vehicle boundary data and a second boundary correction amount corresponding to the initial lane line boundary data. Based on the boundary correction amounts, initial vehicle boundary data, and initial lane line boundary data, server 104 determines corrected vehicle boundary data and corrected lane line boundary data. Based on the corrected vehicle boundary data and corrected lane line boundary data, server 104 determines the target vehicle of its own vehicle. The determined target vehicle result is returned to terminal 102. Terminal 102 can be, but is not limited to, various visual sensors, positioning elements, vehicle body sensing elements, and other intelligent driving vehicle-mounted devices. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0064] In one embodiment, such as Figure 2 As shown, a target vehicle determination method is provided, which is applied to... Figure 1 The method for determining the target vehicle in the example is explained below, including the following steps:

[0065] Step S201: Obtain the initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information of the vehicle.

[0066] The initial vehicle boundary data consists of the vehicle's outline boundary data, including the coordinate arrays of the vehicle's left and right boundaries. The initial lane line boundary data consists of the coordinate data of each lane line in the road segment where the vehicle is located. The environmental information includes road environment information and surrounding vehicle information. The road information includes lane width, road curvature, etc., and the surrounding vehicle information includes the vehicle type, vehicle movement intention, and vehicle outline boundary data of the surrounding vehicles.

[0067] Specifically, the vehicle's sensing elements can first obtain information about the vehicle types and movement intentions of surrounding vehicles, as well as road traffic light information and lane marking information.

[0068] For example, sensing elements include, but are not limited to, vehicle body sensors such as vehicle cameras, radar, and lidar. Global path, road information, vehicle and surrounding vehicle location information, and lane centerline information can be obtained during the driving process through navigation or high-precision maps. Driver's driving requests, driving settings, and vehicle speed, among other vehicle information, can be obtained through user input units.

[0069] The data obtained above is then fused to obtain the required initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information.

[0070] Preferably, in this embodiment, the initial vehicle boundary data and initial lane boundary data are coordinate data in the SL coordinate system (also known as the Frenet frame). Therefore, during data fusion, the vehicle and surrounding vehicles can be abstracted as two-dimensional bounding boxes. Then, the Cartesian coordinate data obtained through sensors, navigation, high-precision maps, etc., including lane marking information, vehicle and surrounding vehicle positioning information, and lane centerline information, are converted into data in the SL coordinate system. The left boundary x-coordinate PL and right boundary x-coordinate PR of the vehicle's bounding box relative to the surrounding vehicles in the SL coordinate system are determined, corresponding to the initial vehicle boundary data (EPL, EPR) of the vehicle and the boundary x-coordinate array (OPL, OPR) of the surrounding vehicle's bounding box. The SL coordinate system is a coordinate system established with the road centerline as a reference, where S represents the direction of the road centerline and L represents the direction perpendicular to the road centerline. It is known that when driving on structured roads, the SL coordinate system is more in line with actual needs than the XY coordinate system. In the process of establishing the SL coordinate system in this embodiment, the SL coordinate system can be established with the lane centerline of the vehicle as the reference.

[0071] Step S202: Determine the boundary correction amount based on the environmental information. The boundary correction amount includes a first boundary correction amount corresponding to the initial vehicle boundary data and a second boundary correction amount corresponding to the initial lane line boundary data.

[0072] It is understandable that, since the attitude information of the target vehicle directly acquired by the sensors generally contains errors, it is unreliable to determine whether a collision with surrounding vehicles is possible solely based on the vehicle's left and right boundaries as its driving range. Therefore, it is necessary to determine the corresponding first boundary correction amount for the acquired initial vehicle boundary data. Furthermore, when surrounding vehicles have the same lane-changing intention as the vehicle, it is unreliable to determine whether a surrounding vehicle is a safety hazard during the lane-changing process solely based on the actual lane it is in, and the safety of the vehicle's lane-changing cannot be guaranteed. Therefore, in this embodiment, the initial lane line boundary data also needs to be corrected to determine its corresponding second boundary correction amount.

[0073] The first boundary correction is a vehicle boundary correction that takes into account the influence of surrounding vehicles and environmental information. Optionally, the value of the first boundary correction may vary depending on the surrounding vehicles. Specifically, when determining the first boundary correction, one vehicle to be determined can be selected from the multiple sensed surrounding vehicles. Based on the vehicle information of the vehicle to be determined and the road information of the road where the vehicle is located, the corresponding first boundary correction can be determined. Then, each surrounding vehicle is traversed, and the first boundary correction of the vehicle relative to each surrounding vehicle is determined using the above method.

[0074] The second boundary correction is the boundary correction of the lane line that takes into account the influence of surrounding vehicles and environmental information. Similarly, the second boundary correction of the same lane line will be different for different surrounding vehicles. It is necessary to determine the second boundary correction of each lane line for each surrounding vehicle.

[0075] Step S203: Determine the corrected vehicle boundary data and the corrected lane line boundary data based on the boundary correction amount, the initial vehicle boundary data, and the initial lane line boundary data.

[0076] Understandably, the corrected initial vehicle boundary data and initial lane line boundary data can more accurately reflect the road division under different environmental information, so as to more accurately select the corresponding target vehicle from the surrounding vehicles.

[0077] Step S204: Determine the target vehicle of the self-vehicle based on the corrected vehicle boundary data and the corrected lane line boundary data.

[0078] Preferably, a virtual lane distribution map can be constructed based on the corrected vehicle boundary data and the corrected lane boundary data, the lanes of the surrounding vehicles in the current road segment virtual lane distribution map can be determined, and then the target vehicle can be selected from multiple surrounding vehicles.

[0079] Optionally, before selecting the target vehicle, it is also necessary to determine the target detection area. Specifically, the target selection area can be determined based on preset selection rules to identify the detection areas in front of and behind the vehicle, thus obtaining the target detection area. For example, the detection distances in front of and behind the vehicle can be preset. If the preset detection distance in front of the vehicle is 100 meters and the detection distance behind the vehicle is 50 meters, then the target detection area is the road range between 100 meters in front of the vehicle and 50 meters behind it. In another example, the current lane width can be obtained first, and then the target detection area can be determined based on preset ratio parameters and lane width.

[0080] The target vehicles include at least one of the following: vehicles surrounding the vehicle in its own lane, vehicles surrounding the vehicle in the adjacent lane of the vehicle's own lane, and vehicles surrounding the vehicle in the next adjacent lane of the vehicle's own lane.

[0081] In the aforementioned target vehicle determination method, initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information are acquired. Based on the acquired environmental information, the boundary correction amount for the initial vehicle boundary data and initial lane line boundary data is determined. Then, the boundary data is corrected and compensated to obtain corrected vehicle boundary data and corrected lane line boundary data to determine the target vehicle. This method can accurately obtain the real-time distribution of vehicles around the vehicle, avoiding target vehicle selection errors caused by sensor data errors. Therefore, it can accurately select target vehicles even in complex road environments, thereby improving driving safety.

[0082] In one embodiment, the environmental information includes at least one of the following: lane width, road curvature, vehicle type of surrounding vehicles, and movement intention of surrounding vehicles. Determining the boundary correction amount based on the environmental information includes: obtaining the longitudinal distance between surrounding vehicles and the vehicle; determining a first boundary correction amount corresponding to the initial vehicle boundary data and a second boundary correction amount corresponding to the initial lane line boundary data based on the environmental information and the longitudinal distance.

[0083] Understandably, the safe driving range required for a vehicle is affected by various driving environments, such as weather conditions, light intensity, and road conditions. Therefore, the corresponding safe driving range differs depending on the driving environment. Consequently, when selecting target vehicles for safety tracking and monitoring, the impact of different driving environments on the selection process must also be considered.

[0084] In this embodiment, the environmental information includes at least one of lane width, road curvature, vehicle type of surrounding vehicles, and the movement intention of surrounding vehicles. In another embodiment, the environmental information may also include road type, weather conditions, road surface conditions, etc., wherein the road type may be road attribute information such as highway, first-class highway, second-class highway, third-class highway, fourth-class highway, and on / off ramp types; the weather conditions may be natural weather information such as sunny, rainy, snowy, or foggy weather; and the road surface conditions may include information such as the slipperiness of the current driving surface and the road gradient.

[0085] Preferably, in determining the first boundary correction amount corresponding to the initial vehicle boundary data based on environmental information, a surrounding vehicle within the target detection area can be selected as the vehicle to be determined, and then the longitudinal distance between the surrounding vehicle and the vehicle can be obtained. Next, the lane width and road curvature of the road where the vehicle is currently located are obtained, and the vehicle type and motion intention of the vehicle to be determined are obtained. Then, the lane compensation weight K1 corresponding to the obtained current lane width is determined by looking up a table based on the preset lane width and longitudinal distance. The road compensation weight K2 corresponding to the obtained current road curvature is determined by looking up a table based on the preset road curvature and longitudinal distance. The vehicle compensation weight K3 corresponding to the obtained current vehicle type is determined by looking up a table based on the preset vehicle type and longitudinal distance. The motion compensation weight K4 corresponding to the obtained current motion intention is determined by looking up a table based on the preset motion intention and longitudinal distance. Finally, the first inner boundary correction amount G1 is determined by combining the above four compensation weights, and the first outer boundary correction amount G2 is determined based on the first inner boundary correction amount combined with a preset gain coefficient. The first inner and outer boundary correction amounts are parameters used to correct the initial vehicle boundary under different conditions. The specific formulas for determining the first inner boundary correction amount G1 and the first outer boundary correction amount G2 are as follows:

[0086] G1 = K1 * K2 * K3 * K4

[0087] G2=α*G1

[0088] Where α is a preset gain coefficient that is not less than 1.

[0089] Furthermore, iterate through all surrounding vehicles within the target detection area and determine the first boundary correction amount of the vehicle relative to each surrounding vehicle.

[0090] After obtaining the first boundary correction amount, the initial vehicle boundary data can be corrected and compensated to obtain corrected vehicle outer boundary data and corrected vehicle inner boundary data. The determination formula is as follows:

[0091] D1 = G1 * (EPL, EPR)

[0092] =(DL1, DR1)

[0093] D2 = G2 * (EPL, EPR)

[0094] =(DL2, DR2)

[0095] Wherein, D1 is the corrected vehicle inner boundary data, DL1 is the corrected vehicle inner boundary data with left side boundary data, DR1 is the corrected vehicle inner boundary data with right side boundary data, D2 is the corrected vehicle outer boundary data, DL2 is the corrected vehicle outer boundary data with left side boundary data, and DR2 is the corrected vehicle outer boundary data with right side boundary data.

[0096] In one exemplary embodiment, Figure 3 This diagram illustrates the results of correcting vehicle boundary data. Curves A1 and A2 represent the corrected outer and inner boundary data when the vehicle to be determined is a small passenger car, respectively. Curves B1 and B2 represent the corrected outer and inner boundary data when the vehicle to be determined is a small commercial vehicle, respectively. Figure 3 As shown, the corrected vehicle boundary data has been extended outwards by an appropriate amount compared to the vehicle width.

[0097] Similarly, when determining the second boundary correction amount for the initial lane line boundary data, a surrounding vehicle within the target detection area can be selected as the vehicle to be determined, along with its corresponding longitudinal distance. Then, the lane width and road curvature of adjacent lanes, the vehicle type and motion intention of the vehicle to be determined are obtained. Based on the aforementioned environmental information and longitudinal distance, a table is consulted to determine the lane compensation weight W1 corresponding to the lane width, the road compensation weight W2 corresponding to the road curvature, the vehicle compensation weight W3 corresponding to the vehicle type, and the motion compensation weight W4 corresponding to the motion intention. Finally, the second boundary correction amount for the initial lane line boundary data is determined based on the following formula.

[0098] F1 = W1 * W2 * W3 * W4

[0099] F2=β*F1

[0100] Where F1 is the second inner boundary correction amount, F2 is the second outer boundary correction amount, β is a preset gain coefficient not less than 1, and the second inner and outer boundary correction amounts are parameters used to correct the initial lane line boundary under different conditions.

[0101] Optionally, when determining the second boundary correction amount corresponding to the initial lane line boundary data, the lookup table used for the environmental information and longitudinal distance can be the same as or different from the lookup table used when determining the first boundary correction amount, and α can be the same as or different from β. Therefore, in this embodiment, F1 and G1 can be the same data or different data, and F2 and G2 can be the same data or different data.

[0102] Furthermore, the formula for determining the corrected lane boundary data is as follows:

[0103] B1 = F1 * (SL, SR)

[0104] =(BL1, BR1)

[0105] B2 = F2 * (SL, SR)

[0106] =(BL2, BR2)

[0107] Wherein, (SL, SR) are the initial lane line boundary data, B1 is the corrected inner lane line boundary data, BL1 is the left boundary data of the corrected inner lane line boundary data, BR1 is the right boundary data of the corrected inner lane line boundary data, B2 is the corrected outer lane line boundary data, BL2 is the left boundary data of the corrected outer lane line boundary data, and BR2 is the right boundary data of the corrected outer lane line boundary data.

[0108] In this embodiment, by considering the impact of different environmental factors on vehicle driving safety, the boundary correction amount of vehicle boundary data and lane line boundary data relative to different surrounding vehicles is determined to correct and compensate the acquired initial vehicle boundary data and initial lane line boundary data. This achieves a certain expansion based on the actual acquired data, eliminates the safety hazards caused by inaccurate sensor data, and increases the reserve for the vehicle's safe driving range and the lane line's coverage range. It can provide early warning in emergency situations and understand the impact of surrounding vehicles on the vehicle's safe driving even when sensor data is inaccurate, thereby improving the safety of the vehicle's driving.

[0109] In one embodiment, determining the target vehicle of the vehicle based on the corrected vehicle boundary data and the corrected lane line boundary data includes: determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data; and determining the target vehicle of the vehicle based on the vehicle distribution information.

[0110] Specifically, a virtual driving road for the vehicle can be constructed based on the corrected vehicle boundary data and the corrected lane line boundary data, and the distribution of each virtual lane line in the virtual driving road can be determined. The vehicle distribution information of the surrounding vehicles in the virtual road can be determined based on the positioning information of the surrounding vehicles. Finally, based on the vehicle distribution information, the target vehicle of the vehicle can be determined according to the corresponding target vehicle selection rules.

[0111] In this embodiment, the vehicle distribution information of surrounding vehicles is determined based on the corrected vehicle boundary data and lane line boundary data. This can more accurately determine the distribution of surrounding vehicles relative to the vehicle itself. Consequently, when selecting a target vehicle, surrounding vehicles that have a greater impact on the vehicle itself can be prioritized as target vehicles, thereby improving the safety of driving the vehicle.

[0112] In one embodiment, the vehicle distribution information includes whether the surrounding vehicles belong to the vehicle's own lane, the adjacent lane, or the next adjacent lane. Determining the target vehicle of the vehicle based on the vehicle distribution information includes: determining at least one target vehicle in each of the vehicle's own lane, the adjacent lane, and the next adjacent lane.

[0113] Optionally, when determining vehicle distribution information, in the vehicle's own lane, three surrounding vehicles can be selected from directly in front of the vehicle and one surrounding vehicle can be selected from directly behind the vehicle as target vehicles in the vehicle's own lane. In adjacent lanes, four surrounding vehicles can be selected from each of the adjacent lanes on both sides of the vehicle as adjacent target vehicles. In the next adjacent lane, two surrounding vehicles can be selected from each of the next adjacent lanes on both sides of the vehicle as next adjacent target vehicles.

[0114] In another exemplary embodiment, when the vehicle distribution information does not meet the above selection rules, the target vehicle can also be selected based on the actual vehicle distribution information. For example, when there are only two surrounding vehicles directly in front of the vehicle in its lane and no surrounding vehicles directly behind, the two surrounding vehicles directly in front can be selected as the target vehicle for the lane. If the road where the vehicle is currently located is a two-way four-lane secondary highway, there is at most one adjacent lane. In this case, the target vehicle can be selected from the adjacent lane based on the actual surrounding vehicle distribution information.

[0115] Optionally, during actual driving, there may be situations where there are no surrounding vehicles in the current driving segment. In this case, the system can directly report to the corresponding driver assistance system that there are no target vehicles in the current segment. For example, when driving on a Class IV highway at night, if the geographical location of the driving road is relatively remote, it is very likely that there will be a scenario where only the vehicle itself is driving in the current driving segment.

[0116] In this embodiment, by analyzing the distribution of surrounding vehicles in the vehicle's lane, adjacent lanes, and next-next lanes, a corresponding target vehicle is selected in each lane. This allows for the simultaneous identification of multiple target vehicles, meeting the requirements of advanced autonomous driving systems for the number of target vehicles selected. Consequently, the driving environment of the vehicle can be monitored more comprehensively, enabling the advanced autonomous driving system to plan the vehicle's driving path more comprehensively.

[0117] In one embodiment, determining at least one target vehicle in each of the vehicle lane, the adjacent lane, and the next adjacent lane includes: obtaining the longitudinal distances between all surrounding vehicles and the vehicle, sorting them longitudinally based on the longitudinal distances, and determining the longitudinal sorting results for the vehicle lane, the adjacent lane, and the next adjacent lane; and determining at least one target vehicle from each of the vehicle lane, the adjacent lane, and the next adjacent lane based on the obtained corrected vehicle boundary data according to the longitudinal sorting results for the vehicle lane, the adjacent lane, and the next adjacent lane.

[0118] Preferably, when obtaining the longitudinal arrangement result of the vehicle lane, the set of surrounding vehicles included in the vehicle lane can be determined, the longitudinal distances of all surrounding vehicles in the set can be obtained, and they can be sorted longitudinally to determine the longitudinal arrangement result of the vehicle lane. The three surrounding vehicles with the closest longitudinal distance in front and the one surrounding vehicle with the closest longitudinal distance behind are selected as the target vehicles of the vehicle lane. Similarly, for adjacent lanes, the set of surrounding vehicles included in the adjacent lane can be determined first, the longitudinal distances of all surrounding vehicles in the set can be obtained, and they can be sorted longitudinally to determine the longitudinal arrangement result of the adjacent lanes. Based on the sorting result, the four surrounding vehicles with the closest longitudinal distance in the adjacent lane are selected as the target vehicles. For the next adjacent lane, the set of surrounding vehicles included in the next adjacent lane can be determined first, the longitudinal distances of all surrounding vehicles in the set can be obtained, and they can be sorted longitudinally to determine the longitudinal arrangement result of the next adjacent lane. Based on the sorting result, the two surrounding vehicles with the closest longitudinal distance in the next adjacent lane are selected as the target vehicles. Figure 4 This is a schematic diagram of the target vehicle selection result in this embodiment, where vehicle A is the vehicle itself.

[0119] Optionally, in one embodiment, if the vehicle distribution information in the vehicle lane indicates that the number of vehicles in front of the vehicle is no more than 3 and the number of vehicles behind the vehicle is no more than 1, then there is no need for vertical sorting; all surrounding vehicles in the current vehicle lane are directly identified as target vehicles for that lane. Similarly, if the number of surrounding vehicles in the adjacent lane is no more than 4 and the number of surrounding vehicles in the next adjacent lane is no more than 2, then there is no need for vertical sorting; the surrounding vehicles in the adjacent lane are directly identified as adjacent target vehicles, and the surrounding vehicles in the next adjacent lane are identified as next adjacent target vehicles. Figure 5 This is a schematic diagram of the target vehicle selection results in this embodiment.

[0120] In this embodiment, the target vehicle selection result is determined based on the longitudinal distance between the surrounding vehicles and the vehicle itself. When there are many surrounding vehicles, the vehicle with the closest longitudinal distance to the vehicle itself can be selected as the target vehicle first. Then, when the target vehicle cuts into the front of the vehicle at close range, the dangerous target can be selected in advance to the corresponding decision module, so as to change the driving speed or driving path of the vehicle in time, thereby realizing safe driving.

[0121] In one embodiment, the environmental information includes second vehicle boundary data of surrounding vehicles. Determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and corrected lane line boundary data includes: determining the lane-changing state of the vehicle; if the lane-changing state is no lane change or before lane change is completed, determining a first driving range of the vehicle based on the corrected vehicle boundary data, and determining a second driving range of surrounding vehicles based on the second vehicle boundary data; determining whether there is lateral overlap based on the first driving range and the second driving range, wherein the lateral overlap indicates that the driving ranges have projected overlap in the direction perpendicular to the lane centerline; if so, determining that the surrounding vehicles belong to the vehicle's lane.

[0122] The vehicle's lane-changing status includes not changing lanes, before lane change completion, and after lane change completion. When the vehicle has not received a lane-changing instruction, it is in a lane-holding driving state by default; that is, the vehicle's lane-changing status at this time is not changing lanes. After receiving a lane-changing instruction, the vehicle's current posture information can determine whether it is in the pre-lane-change, during-lane-change, or post-lane-change stage. At this point, "before lane change completion" includes both the pre-lane-change and during-lane-change stages, and "after lane change completion" includes the post-lane-change stage.

[0123] Preferably, the relevant data of all surrounding vehicles uploaded by the sensors are compiled into a surrounding vehicle set. From this set, one surrounding vehicle is selected as the vehicle to be determined, and then the first driving interval of the vehicle relative to the vehicle to be determined is determined. The first driving interval of the vehicle is the safe driving interval of the vehicle during safe driving, determined based on the corrected vehicle boundary data D1 and D2 obtained in the above embodiment. Optionally, if the selected vehicle to be determined does not belong to the overlapping vehicle set of the vehicle lane, the first driving interval can be determined as (DL1, DR1) based on the corrected vehicle inner boundary data D1. The second vehicle boundary data is determined as (OPL, OPR) based on the boundary horizontal coordinate array of the bounding box of the vehicle to be determined, and then the second driving interval is determined as (OPL, OPR). Then, it is determined whether the first driving interval (DL1, DR1) and the second driving interval (OPL, OPR) have lateral overlap to determine whether the vehicle to be determined belongs to the vehicle lane. Then, each surrounding vehicle in the surrounding vehicle set is traversed to determine the surrounding vehicles included in the vehicle lane, and the vehicle ID of the surrounding vehicle is recorded in the overlapping vehicle set of the vehicle lane.

[0124] For example, Figure 6This diagram illustrates the determination of lateral overlap between the vehicle to be determined and the vehicle being tested. Vehicle A is the vehicle being tested, and vehicle B is the vehicle to be tested. When determining the corresponding driving interval, the coordinates in the SL coordinate system are defined as positive on the left and negative on the right, as shown in the diagram. The left and right boundary arrays for vehicle A are determined to be (0.75, -1), and the left and right boundary arrays for vehicle B are determined to be (1, -0.75). The corresponding first driving interval is (0.75, -1), and the second driving interval is (1, -0.75). At this point, there is lateral overlap between vehicle B and the vehicle being tested, and the lateral overlap interval is (0.75, -0.75). The vehicle ID of vehicle B is recorded in the set of overlapping vehicles in the vehicle's lane.

[0125] Furthermore, for vehicles already included in the set of vehicles overlapping in their own lanes, when determining them at the next time step, the corrected vehicle outer boundary data D2 needs to be used to determine the first driving section, and then to determine whether there is any lateral overlap between the first driving section and the second driving section. If so, it is determined that the corresponding surrounding vehicles belong to the vehicle's own lane, and the vehicle ID corresponding to that vehicle is retained in the set of vehicles overlapping in their own lanes. If not, it is determined that the corresponding surrounding vehicles do not belong to the vehicle's own lane, and the vehicle ID of that vehicle is removed from the set of vehicles overlapping in their own lanes.

[0126] Due to limitations in sensor accuracy and data errors in real-world applications, the lateral position of the target vehicle directly uploaded by the sensor may fluctuate. This fluctuation can cause data instability for target vehicles near the inner boundary of the corrected vehicle, affecting the target vehicle selection result. For example, in the current frame, the target vehicle and the vehicle may overlap laterally, but in the next frame, due to fluctuations in sensor data, the target vehicle and the vehicle may no longer overlap laterally, resulting in target jumps and leading to incorrect target vehicle selection. Therefore, this embodiment uses the outer boundary data of the corrected vehicle as the criterion for determining whether surrounding vehicles with existing overlap records still overlap laterally with the vehicle. Specifically, the inner boundary data of the corrected vehicle is used as the inclusion criterion for determining whether surrounding vehicles belong to the set of overlapping vehicles in the vehicle's lane, while the outer boundary data of the corrected vehicle is used as the exclusion criterion for determining whether surrounding vehicles belong to the set of overlapping vehicles in the vehicle's lane, thereby increasing the stability of target vehicle selection.

[0127] Optionally, the vehicle lane in this application is not equivalent to the lane the vehicle is in on an actual road, but rather a virtual lane constructed in the SL coordinate system based on the vehicle's current attitude and position. When the vehicle is in a lane-holding driving state, such as... Figure 6 As shown, the width of the vehicle's lane is smaller than the actual lane width of the lane the vehicle is in on the road. When the vehicle is changing lanes, the lane section of the vehicle's lane lies between the actual lanes before and after the lane change, such as... Figure 4As shown, when the vehicle is changing lanes from lane 4 to lane 3, its lane is not actually part of either lane 4 or lane 3, but rather a virtual lane located between them. During the lane change, the system can promptly adjust the selection of the target vehicle. If the target vehicle is in the lane before the lane change and its lateral coordinate has not changed significantly, the system can promptly exclude that target vehicle from the selection of following targets and preemptively select a vehicle in the target lane that might affect the vehicle's driving safety as the vehicle in the lane change lane, thereby improving the driving safety during lane changes.

[0128] Preferably, when the vehicle is performing a lane change, it is also necessary to predict the trajectory of a target vehicle marked as longitudinally following ahead. Based on the time required for the vehicle to complete the lane change and the speeds of surrounding vehicles, the position of the target vehicle at the moment of lane change completion is predicted. Specifically, the prediction formula is as follows:

[0129]

[0130] Where V0 is the speed of surrounding vehicles, a is the acceleration determined by a two-dimensional lookup table based on the relative distance and relative speed between the vehicle and surrounding vehicles, which can be obtained through actual vehicle calibration, and t is the time required for the vehicle to complete the lane change.

[0131] Furthermore, based on the predicted position X of the autonomous vehicle at the moment of lane change completion determined by the autonomous vehicle lane change planning, it is determined whether to continue longitudinally following the target vehicle. If the difference between the predicted position Y of the target vehicle and the predicted position X of the autonomous vehicle is greater than or equal to a preset safety threshold, longitudinal following of the target vehicle will cease; otherwise, target following of the target vehicle will continue.

[0132] In this embodiment, during the process of determining the surrounding vehicles included in the vehicle's lane, the vehicle's lane interval is determined based on the vehicle's safe driving space. This then determines whether surrounding vehicles belong to the vehicle's lane, and vehicles that laterally overlap with the vehicle's lane interval are identified as vehicles included in the vehicle's lane. This allows for accurate knowledge of the vehicle distribution in front of and behind the vehicle, preventing the accidental selection of vehicles driving close to the lane line in adjacent lanes as vehicles in the vehicle's lane at curves, and facilitating the subsequent planning of a safe driving path for the vehicle. Furthermore, this embodiment also considers the vehicle's lane-changing status as basic data for determining whether surrounding vehicles belong to the vehicle's lane, which to some extent reduces the acceleration and deceleration jerks caused by the slow release of the original lane target during lane changes.

[0133] In one embodiment, determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data further includes: if the lane change status is that the lane change is completed, determining the lane where the vehicle is located after the lane change, and obtaining the lane line corresponding to the lane where the vehicle is located after the lane change; determining a first lane interval of the lane where the vehicle is located after the lane change based on the corrected lane line boundary data; determining whether there is lateral overlap between the first lane interval and the second driving interval; if so, determining that the surrounding vehicles belong to the vehicle's lane.

[0134] Specifically, the lane after the lane change can be determined based on the received lane change instruction. In an exemplary embodiment, if the lane change instruction is to change from lane 3 to lane 2, then the first lane interval needs to be determined based on the corrected lane line boundary data of lane 2. The corresponding first lane interval is the driving lane. Similarly, when determining whether a surrounding vehicle belongs to the driving lane, it is necessary to determine whether there is lateral overlap between the second driving interval of the surrounding vehicle and the first lane interval. If so, it is determined that the surrounding vehicle belongs to the driving lane, and the vehicle number of the surrounding vehicle is recorded in the set of overlapping vehicles in the driving lane.

[0135] Preferably, in another embodiment, whether a surrounding vehicle belongs to the driving lane can also be determined based on the lateral overlap rate between the second driving zone and the first lane zone of surrounding vehicles and a preset threshold. Specifically, the formula for calculating the preset threshold is as follows:

[0136] N = γ * W1 * W2 * W3 * W4

[0137] Here, γ is a constant value, which serves as the reference value for the preset threshold, causing the value of the preset threshold to fluctuate around γ.

[0138] First, determine the overlap rate between each surrounding vehicle in the overlapping vehicle set of the self-lane and the first lane interval. Then, select surrounding vehicles with an overlap rate greater than a preset threshold and add them to the self-lane vehicle set. When selecting a target vehicle in the self-lane later, select surrounding vehicles that meet the requirements from the self-lane vehicle set as the target vehicle for the self-lane.

[0139] In this embodiment, by using the lane boundary of the target lane as the first lane interval and calculating the overlap rate with the driving intervals of surrounding vehicles, the surrounding vehicles included in the voluntary lane are determined. This can optimize the update delay of the target vehicle in the voluntary lane to a certain extent, and quickly select vehicles driving close to the edge of the target lane into the voluntary lane. This provides more accurate data for the subsequent determination of the target vehicle in the voluntary lane, improving the safety of voluntary lane changes.

[0140] In one embodiment, determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data further includes: obtaining the rear axle center coordinates of the vehicle; determining the adjacent lanes of the vehicle based on the rear axle center coordinates and the initial lane line boundary data; obtaining the lane lines of the adjacent lanes; determining the second lane interval of the adjacent lanes based on the corrected lane line boundary data; determining whether there is lateral overlap between the second lane interval and the second driving interval; if so, determining that the surrounding vehicles belong to the adjacent lanes.

[0141] Specifically, during a lane change, the vehicle needs to cross lane lines to change lanes, which alters the vehicle's lane position. At this point, the actual vehicle distribution needs to be determined based on the vehicle's rear axle center coordinates to identify the adjacent lanes, obtain corrected lane line data for those adjacent lanes, and ultimately determine the surrounding vehicles in those adjacent lanes. For example, Figure 7 The diagram shows the distribution of surrounding vehicles during the lane change process of the vehicle. As shown in the figure, the vehicle changes from lane 4 to lane 3, and the rear axle center coordinates of the vehicle are located within lane 3. Therefore, the corrected lane line boundary data of lane 4 and lane 2 can be used as the basis for determining the second lane interval of the adjacent lane of the vehicle.

[0142] Preferably, before determining the surrounding vehicles included in adjacent lanes, the vehicle to be determined can be obtained based on the set of surrounding vehicles and the set of vehicles overlapping with the lane. Corrected lane line boundary data of the adjacent lane relative to the lane to be determined can be obtained, and the second lane interval of the adjacent lane can be determined based on the corrected lane line boundary data. Similarly, it can be determined whether there is lateral overlap between the second lane interval and the second driving interval of the vehicle to be determined. If lateral overlap exists, the vehicle to be determined is determined to belong to the adjacent lane, and the vehicle to be determined is added to the set of vehicles overlapping with the adjacent lane. Finally, all surrounding vehicles to be determined are traversed to determine the surrounding vehicles included in the adjacent lanes.

[0143] Furthermore, before the autonomous vehicle executes a lane change, because the movement intentions of surrounding vehicles are considered when correcting the initial lane boundary data to determine the corresponding boundary correction amount, in this embodiment, before or at the initial stage of the autonomous vehicle's lane change, surrounding vehicles in the next adjacent lane that are entering the target lane can be identified as vehicles in the target lane. This allows the autonomous vehicle to timely consider the movement of surrounding vehicles when planning its driving path, avoiding collisions and improving safety during lane changes. Figure 5 As shown, when a vehicle plans to move from lane 4 to lane 3 in the initial stage, vehicle B in lane 2 that intends to change lanes to lane 3 can be identified as a surrounding vehicle in the adjacent lane of the vehicle.

[0144] In this embodiment, the vehicle's adjacent lanes are determined by the rear axle center coordinates and initial lane boundary data. This allows for the determination of the second lane interval corresponding to the adjacent lanes, accurately determining whether surrounding vehicles are located in those lanes and thus accurately assessing the vehicle distribution. This enables timely adjustments to the vehicle's speed when surrounding vehicles in adjacent lanes intend to enter the vehicle's lane. Furthermore, when the vehicle needs to change lanes, the planned path is updated promptly based on the road conditions in the adjacent lanes. Simultaneously, the movement intentions of surrounding vehicles in the next adjacent lane are considered during lane changes, and vehicles in the next adjacent lane are pre-selected as adjacent lane vehicles. This optimizes scenarios where the vehicle and a target in the next adjacent lane simultaneously change lanes, reducing the risk of collision.

[0145] Optionally, when determining surrounding vehicles in adjacent lanes, it is also possible to determine whether a surrounding vehicle belongs to an adjacent lane based on the lateral overlap rate between the second driving section and the second lane section of the surrounding vehicle and a preset threshold N. The formula for determining the preset threshold N is the same as described above.

[0146] First, determine the overlap rate between each surrounding vehicle in the adjacent lane overlapping vehicle set and the second lane interval. Then, select surrounding vehicles with an overlap rate greater than a preset threshold N and add them to the adjacent lane vehicle set. When selecting target vehicles in adjacent lanes later, select qualified surrounding vehicles from the adjacent lane vehicle set as adjacent target vehicles.

[0147] In one embodiment, determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data further includes: determining the second adjacent lane of the vehicle based on the rear axle center coordinates of the vehicle and the initial lane line boundary data; determining the lane line of the second adjacent lane; determining the third lane interval of the second adjacent lane based on the corrected lane line boundary data; determining whether there is lateral overlap between the third lane interval and the second driving interval; if so, determining that the surrounding vehicles belong to the second adjacent lane.

[0148] Similarly, when determining the next adjacent lane, the vehicle's next adjacent lane and its initial lane line boundary data can be determined based on the rear axle center coordinates and initial lane line boundary data. Before determining the surrounding vehicles included in the next adjacent lane, the vehicle to be determined can be obtained based on the surrounding vehicle set, the vehicle overlapping in the vehicle's own lane set, and the vehicle overlapping in adjacent lane sets. Based on the initial lane line boundary data of the next adjacent lane, the corrected lane line boundary data of the next adjacent lane relative to the vehicle to be determined is determined, thereby determining the third lane interval corresponding to the next adjacent lane. Then, it is determined whether the third lane interval overlaps with the second driving interval of the vehicle to be determined. If so, the vehicle to be determined is determined to belong to the next adjacent lane, and the vehicle is recorded in the next adjacent lane overlapping vehicle set. Finally, all surrounding vehicles to be determined are traversed to determine the surrounding vehicles in the next adjacent lane.

[0149] In this embodiment, the vehicle's second-next lane is determined by the rear axle center coordinates and the initial lane boundary data. Then, the third lane interval corresponding to the second-next lane is determined to accurately obtain whether the surrounding vehicles are located in the second-next lane. This allows for accurate acquisition of the vehicle distribution in the second-next lane, which is more convenient for subsequent planning of the vehicle's driving path by taking into account the vehicle distribution in the surrounding lanes and making reasonable plans to ensure the vehicle's safety.

[0150] Preferably, in the process of determining surrounding vehicles included in adjacent lanes, if the vehicle to be determined does not belong to the overlapping vehicle set of adjacent lanes, the corresponding second lane interval can be determined based on the boundary data within the corrected lane line corresponding to the adjacent lane, thereby determining whether the vehicle to be determined belongs to a vehicle in the adjacent lane. If the vehicle to be determined already belongs to the overlapping vehicle set of adjacent lanes, when determining whether the vehicle to be determined belongs to an adjacent lane again, the corresponding second lane interval needs to be determined based on the boundary data outside the corrected lane line. If the second driving interval corresponding to the vehicle to be determined overlaps with the second lane interval, it indicates that the vehicle to be determined is still driving in the adjacent lane. Otherwise, it indicates that the vehicle to be determined has left the adjacent lane. This prevents fluctuations in sensor data from interfering with the selection of the target vehicle, thereby increasing the stability of the target vehicle selection.

[0151] Furthermore, in the process of determining the surrounding vehicles included in the next adjacent lane, it is also necessary to use the corrected vehicle inner boundary data as the selection criterion for whether the surrounding vehicles belong to the overlapping vehicle set of the next adjacent lane, and use the corrected vehicle outer boundary data as the exclusion criterion for whether the surrounding vehicles belong to the overlapping vehicle set of the next adjacent lane.

[0152] In a preferred embodiment, the method for determining a target vehicle when the vehicle is in a lane-holding driving state includes the following steps:

[0153] Step 1: Obtain the initial vehicle boundary data, initial lane boundary line data, and corresponding environmental information of the vehicle to determine the set of vehicles surrounding the vehicle.

[0154] The environmental information includes at least one of the following: lane width, road curvature, vehicle type of surrounding vehicles, vehicle movement intention, and second vehicle boundary data of surrounding vehicles.

[0155] Step 2: Identify a vehicle to be determined from the surrounding vehicle set, determine the first boundary correction amount of the initial vehicle boundary data based on the environmental information table, and obtain the corrected vehicle boundary data of the vehicle relative to the vehicle to be determined based on the first boundary correction amount.

[0156] Step 3: Determine the first driving range of the vehicle based on the corrected vehicle boundary data, and determine the second driving range of the vehicle to be determined based on the second vehicle boundary data.

[0157] Step 4: Determine whether there is any lateral overlap between the first driving section and the second driving section. If so, determine that the vehicle to be determined belongs to the self-vehicle lane and add the vehicle to be determined to the set of self-vehicle lane overlapping vehicles.

[0158] Step 5: Repeat steps 2 to 4 until all surrounding vehicles have been traversed, identify all surrounding vehicles in your lane, and record them in the set of overlapping vehicles in your lane.

[0159] Step 6: Determine the adjacent lanes of the vehicle. Based on the surrounding vehicle set and the overlapping vehicle set of the vehicle in the vehicle's lane, determine a vehicle to be determined. Based on the environmental information, determine the second boundary correction amount of the initial lane line boundary data. Based on the second boundary correction amount, obtain the corrected vehicle boundary data of the adjacent lanes relative to the vehicle to be determined.

[0160] Step 7: Based on the above-mentioned corrected vehicle boundary data, determine the second lane interval of the adjacent lane, and determine whether the second lane interval and the second driving interval have lateral overlap. If so, determine that the vehicle to be determined belongs to the adjacent lane and add the vehicle to be determined to the set of vehicles with overlapping adjacent lanes.

[0161] Step 8: Repeat steps 6 and 7 until all remaining undetermined surrounding vehicles have been traversed, determine all surrounding vehicles in adjacent lanes, and record them in the set of overlapping vehicles in adjacent lanes.

[0162] Step 9: Determine the next adjacent lane of the vehicle. Based on the surrounding vehicle set, the vehicle set overlapping with the vehicle in the vehicle's lane, and the vehicle set overlapping with the adjacent lane, determine a vehicle to be determined. Based on the environmental information, determine the second boundary correction amount of the initial lane line boundary data. Based on the second boundary correction amount, obtain the corrected vehicle boundary data of the next adjacent lane relative to the vehicle to be determined.

[0163] Step 10: Based on the above-mentioned corrected vehicle boundary data, determine the third lane section of the next adjacent lane, and determine whether the third lane section overlaps laterally with the second driving section. If so, determine that the vehicle to be determined belongs to the next adjacent lane, and add the vehicle to be determined to the set of overlapping vehicles in the next adjacent lane.

[0164] Step 11: Repeat steps 9 to 10 until all remaining undetermined surrounding vehicles are traversed, determine all surrounding vehicles in the next adjacent lane, and record them in the set of overlapping vehicles in the next adjacent lane.

[0165] Step 12: Based on the longitudinal distances between the vehicle and each surrounding vehicle in the set of overlapping vehicles in the vehicle's own lane, the set of overlapping vehicles in the adjacent lane, and the set of overlapping vehicles in the next adjacent lane, select the target vehicle in the vehicle's own lane, the target vehicle in the adjacent lane, and the target vehicle in the next adjacent lane, respectively.

[0166] In this embodiment, by considering the influence of factors such as the vehicle type, lane width, road curvature, and the movement intentions of surrounding vehicles, the sensor data is compensated for, thereby enabling a more accurate acquisition of the distribution of vehicles around the vehicle. This allows for the precise selection of target vehicles for tracking, preventing surrounding vehicles from suddenly cutting in front of the vehicle and posing a safety hazard. Furthermore, determining the vehicle's lane based on its safe driving zone can also, to some extent, prevent the selection of vehicles driving close to the lane lines as target vehicles during curves, thus improving the smoothness of the driving process and enhancing both user safety and user experience.

[0167] In another preferred embodiment, the method for determining the target vehicle when the vehicle is in a lane-changing driving state includes the following steps:

[0168] S1: Obtain the initial vehicle boundary data, initial lane boundary line data, and corresponding environmental information of the vehicle, and determine the set of surrounding vehicles of the vehicle.

[0169] The environmental information includes at least one of the following: lane width, road curvature, vehicle type of surrounding vehicles, vehicle movement intention, and second vehicle boundary data of surrounding vehicles.

[0170] S2, obtain the lane change status of the vehicle. If the vehicle is before the lane change is completed, determine the set of overlapping vehicles in the vehicle lane through the following steps S3-S4. If the vehicle is after the lane change is completed, determine the set of overlapping vehicles in the vehicle lane through the following steps S6-S8.

[0171] S3: Based on the surrounding vehicle set, obtain a vehicle to be determined; based on the environmental information table, determine the first boundary correction amount of the initial vehicle boundary data; based on the first boundary correction amount, obtain the corrected vehicle boundary data of the self-vehicle relative to the vehicle to be determined; based on the corrected vehicle boundary data, determine the first driving range of the self-vehicle; based on the second vehicle boundary data, determine the second driving range of the vehicle to be determined.

[0172] S4, determine whether there is lateral overlap between the first driving section and the second driving section. If so, determine that the vehicle to be determined belongs to the self-vehicle lane and add the vehicle to be determined to the self-vehicle lane overlapping vehicle set.

[0173] S5. Repeat S3 to S4 until all surrounding vehicles are traversed, identify all surrounding vehicles in the vehicle's lane, and record them in the set of overlapping vehicles in the vehicle's lane.

[0174] S6, obtain the lane where the vehicle is located after changing lanes, confirm that the lane where the vehicle is located after changing lanes is the vehicle's lane, obtain the lane line corresponding to the lane where the vehicle is located after changing lanes, obtain a vehicle to be determined based on surrounding vehicles, determine the second boundary correction amount of the initial lane line boundary data based on environmental information, and obtain the corrected lane line boundary data of the vehicle's lane relative to the vehicle to be determined based on the second boundary correction amount.

[0175] S7. Based on the above-mentioned corrected lane line boundary data, determine the first lane section of the vehicle lane, determine whether the first lane section and the second driving section have lateral overlap, and if so, determine that the vehicle to be determined belongs to the vehicle lane and record the vehicle to be determined in the set of overlapping vehicles in the vehicle lane.

[0176] S8. Repeat S6 to S7 until all surrounding vehicles are traversed, identify all surrounding vehicles in the vehicle's lane, and record them in the set of overlapping vehicles in the vehicle's lane.

[0177] S9, determine the adjacent lanes of the vehicle, obtain a vehicle to be determined based on the surrounding vehicle set and the overlapping vehicle set of the vehicle lane, determine the second boundary correction amount of the initial lane line boundary data based on environmental information, and obtain the corrected vehicle boundary data of the adjacent lanes relative to the vehicle to be determined based on the second boundary correction amount.

[0178] S10, based on the above-mentioned corrected vehicle boundary data, determine the second lane interval of the adjacent lane, determine whether the second lane interval and the second driving interval have lateral overlap, if so, determine that the vehicle to be determined belongs to the adjacent lane, and record the vehicle to be determined in the set of vehicles with overlapping adjacent lanes.

[0179] S11, repeat S9 to S10 until all remaining undetermined surrounding vehicles are traversed, determine all surrounding vehicles in adjacent lanes, and organize and record them into the set of overlapping vehicles in adjacent lanes.

[0180] S12, determine the next adjacent lane of the vehicle, obtain a vehicle to be determined based on the surrounding vehicle set, the vehicle overlapping vehicle set of the vehicle's own lane and the vehicle overlapping vehicle set of the adjacent lane, determine the second boundary correction amount of the initial lane line boundary data based on environmental information, and obtain the corrected vehicle boundary data of the next adjacent lane relative to the vehicle to be determined based on the second boundary correction amount.

[0181] S13. Based on the above-mentioned corrected vehicle boundary data, determine the third lane section of the next adjacent lane, and determine whether the third lane section and the second driving section have lateral overlap. If so, determine that the vehicle to be determined belongs to the next adjacent lane, and record the vehicle to be determined in the set of vehicles overlapping in the next adjacent lane.

[0182] S14, repeat steps 12 to 13 until all remaining undetermined surrounding vehicles are traversed, determine all surrounding vehicles in the next adjacent lane, and organize and record them into the set of overlapping vehicles in the next adjacent lane.

[0183] S15. Based on the longitudinal distance between each surrounding vehicle and the vehicle in the set of overlapping vehicles in the vehicle lane, the set of overlapping vehicles in the adjacent lane, and the set of overlapping vehicles in the next adjacent lane, select the target vehicle in the vehicle lane, the target vehicle in the adjacent lane, and the target vehicle in the next adjacent lane, respectively.

[0184] In this embodiment, by considering the lane-changing situation of the vehicle and setting different target vehicle selection methods for the lane-changing state, it is possible to clearly understand the distribution of surrounding vehicles in different lane-changing stages of the vehicle. During the vehicle's lane-changing process, it can promptly detect surrounding vehicles in adjacent lanes that intend to enter the vehicle's lane and adjust the vehicle's driving speed. When the vehicle needs to change lanes, it can also update the planned path of the vehicle in a timely manner based on the road conditions of adjacent lanes. At the same time, the movement intentions of surrounding vehicles in the next adjacent lane are considered during the vehicle's lane-changing process, and vehicles in the next adjacent lane are selected as adjacent lane vehicles in advance, thereby optimizing the scenario where the vehicle and the target in the next adjacent lane change lanes simultaneously and are prone to collision.

[0185] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0186] Based on the same inventive concept, this application also provides a target vehicle determination device for implementing the target vehicle determination method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more target vehicle determination device embodiments provided below can be found in the limitations of the target vehicle determination method described above, and will not be repeated here.

[0187] exist Figure 8 Here is a structural block diagram of a target vehicle determination device in one embodiment, such as... Figure 8 As shown, it includes: an acquisition module 81, an optimization module 82, and a decision module 83, wherein:

[0188] The acquisition module 81 is used to acquire the initial vehicle boundary data, initial lane line boundary data and corresponding environmental information of the vehicle.

[0189] The optimization module 82 is used to determine the boundary correction amount based on the environmental information. The boundary correction amount includes a first boundary correction amount corresponding to the initial vehicle boundary data and a second boundary correction amount corresponding to the initial lane line boundary data.

[0190] The decision module 83 is used to determine the target vehicle of the vehicle based on the corrected vehicle boundary data and the corrected lane line boundary data.

[0191] In the target vehicle determination device of this embodiment, initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information of the vehicle are acquired. Based on the acquired environmental information, the boundary correction amount of the initial vehicle boundary data and the initial lane line boundary data is determined. Then, the boundary data is corrected and compensated to obtain corrected vehicle boundary data and corrected lane line boundary data to determine the target vehicle of the vehicle. This device can accurately obtain the real-time distribution of vehicles around the vehicle, avoiding target vehicle selection errors caused by sensor data errors. Therefore, it can accurately select the target vehicle even in complex road environments, thereby improving the driving safety of the vehicle.

[0192] Furthermore, the optimization module 82 is also used to obtain the longitudinal distance between the surrounding vehicles and the vehicle; and to determine the first boundary correction amount corresponding to the initial vehicle boundary data and the second boundary correction amount corresponding to the initial lane line boundary data based on the environmental information and the longitudinal distance.

[0193] Furthermore, the decision module 83 is also used to determine the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data; and to determine the target vehicle of the vehicle based on the vehicle distribution information.

[0194] Furthermore, the vehicle distribution information includes whether the surrounding vehicles belong to the vehicle's own lane, the adjacent lane, or the next adjacent lane. The decision module 83 is also used to determine at least one target vehicle in each of the vehicle's own lane, the adjacent lane, and the next adjacent lane.

[0195] Furthermore, the decision module 83 is also used to obtain the longitudinal distance between all the surrounding vehicles and the vehicle, perform longitudinal sorting based on the longitudinal distance, and determine the longitudinal sorting result of the vehicle lane, the longitudinal sorting result of the adjacent lane, and the longitudinal sorting result of the next adjacent lane; and determine at least one target vehicle from the vehicle lane, the adjacent lane, and the next adjacent lane according to the longitudinal sorting result of the vehicle lane, the longitudinal sorting result of the adjacent lane, and the longitudinal sorting result of the next adjacent lane.

[0196] Furthermore, the decision module 83 is also used to determine the lane-changing state of the vehicle; if the lane-changing state is no lane change or before the lane change is completed, then the first driving range of the vehicle is determined according to the corrected vehicle boundary data, and the second driving range of the surrounding vehicles is determined according to the second vehicle boundary data; based on the first driving range and the second driving range, it is determined whether there is lateral overlap, wherein the lateral overlap indicates that the above driving ranges have projection overlap in the direction perpendicular to the lane centerline; if so, then it is determined that the surrounding vehicles belong to the vehicle lane.

[0197] Furthermore, the decision module 83 is also used to determine the lane where the vehicle is located after the lane change if the lane change status is completed, and obtain the lane line corresponding to the lane where the vehicle is located after the lane change; determine the first lane interval of the lane where the vehicle is located after the lane change based on the corrected lane line boundary data; determine whether there is lateral overlap based on the first lane interval and the second driving interval; if so, determine that the surrounding vehicles belong to the vehicle's lane.

[0198] Furthermore, the decision module 83 is also used to obtain the rear axle center coordinates of the vehicle, determine the adjacent lanes of the vehicle based on the rear axle center coordinates and the initial lane line boundary data; obtain the lane lines of the adjacent lanes, determine the second lane section of the adjacent lanes based on the corrected lane line boundary data; determine whether there is lateral overlap based on the second lane section and the second driving section; if so, determine that the surrounding vehicles belong to the adjacent lanes.

[0199] Furthermore, the decision module 83 is also used to obtain the rear axle center coordinates of the vehicle, determine the next adjacent lane of the vehicle based on the rear axle center coordinates and the initial lane line boundary data; determine the lane line of the next adjacent lane, determine the third lane section of the next adjacent lane based on the corrected lane line boundary data; determine whether there is lateral overlap between the third lane section and the second driving section; if so, determine that the surrounding vehicles belong to the next adjacent lane.

[0200] Preferred, Figure 9The diagram below illustrates the structure of a target vehicle determination device in another embodiment. It includes a system input module 91, an information processing module 92, a decision-making and planning module 93, and an execution module 94. The system input module 91 acquires environmental information, including a navigation and positioning unit, a perception unit, and a vehicle body unit. The navigation and positioning unit acquires high-precision map information, visual lane line information, positioning information, and lane centerline information. The perception unit acquires information about surrounding vehicles, lane markings, and traffic lights. The vehicle body unit acquires information such as driver requests, settings, and vehicle speed. The information processing module 92 includes a fusion unit and a target selection unit. The fusion unit performs fusion processing on the output information to obtain lane line information, surrounding information, global path information including route selection information, lane information, and lane priority requests. The target selection unit determines the target vehicle based on the fused data. The decision-making and planning module 93 processes the information from the fusion unit and the target selection unit to obtain steering wheel angle requests, acceleration / deceleration requests, and turn signal requests. The execution module 94 executes the aforementioned request commands. Furthermore, parameter transmission between the various modules includes, but is not limited to, transmission via CAN bus, Ethernet, etc.

[0201] Each module in the aforementioned target vehicle selection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0202] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores surrounding vehicle data, environmental information, and the device's own vehicle data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a target vehicle selection method.

[0203] Those skilled in the art will understand that Figure 10The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0204] In one embodiment, an intelligent driving vehicle is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0205] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0206] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0207] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0208] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A target vehicle determination method characterized by comprising: The method includes: Acquire the vehicle's initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information; The boundary correction amount is determined based on the environmental information. The boundary correction amount includes a first boundary correction amount corresponding to the initial vehicle boundary data and a second boundary correction amount corresponding to the initial lane line boundary data. Based on the boundary correction amount, the initial vehicle boundary data, and the initial lane line boundary data, the corrected vehicle boundary data and the corrected lane line boundary data are determined. The target vehicle of the vehicle is determined based on the corrected vehicle boundary data and the corrected lane line boundary data. The environmental information includes at least one of the following: lane width, road curvature, vehicle type of surrounding vehicles, and movement intention of surrounding vehicles; the first boundary correction amount is the vehicle boundary correction amount of the vehicle under the influence of surrounding vehicles and environmental information, and the second boundary correction amount is the lane line boundary correction amount under the influence of surrounding vehicles and environmental information. The step of determining the target vehicle based on the corrected vehicle boundary data and the corrected lane line boundary data includes: The vehicle distribution information of surrounding vehicles is determined based on the corrected vehicle boundary data and the corrected lane line boundary data. The target vehicle of the vehicle is determined based on the vehicle distribution information; The vehicle distribution information includes whether the surrounding vehicles belong to their own lane, adjacent lane, or next-next lane. The step of determining the target vehicle of the vehicle based on the vehicle distribution information includes: obtaining the longitudinal distance between all the surrounding vehicles and the vehicle, sorting them longitudinally based on the longitudinal distance, and determining the longitudinal sorting result of the vehicle's lane, the longitudinal sorting result of the adjacent lane, and the longitudinal sorting result of the next adjacent lane. Based on the longitudinal sorting results of the vehicle lane, the longitudinal sorting results of the adjacent lanes, and the longitudinal sorting results of the next adjacent lane, at least one target vehicle is determined from each of the vehicle lane, the adjacent lane, and the next adjacent lane. Determining the first boundary correction amount based on the environmental information includes: selecting a surrounding vehicle within the target detection area as the vehicle to be determined; obtaining the longitudinal distance between the surrounding vehicle and the vehicle, the lane width of the road where the vehicle is currently located, the road curvature of the road where the vehicle is currently located, the vehicle type of the vehicle to be determined, and the motion intention of the vehicle to be determined; determining the lane compensation weight corresponding to the obtained current lane width by looking up a table based on a preset lane width and longitudinal distance; determining the road compensation weight corresponding to the obtained current road curvature by looking up a table based on a preset road curvature and longitudinal distance; determining the vehicle compensation weight corresponding to the obtained current vehicle type by looking up a table based on a preset vehicle type and longitudinal distance; determining the motion compensation weight corresponding to the obtained current motion intention by looking up a table based on a preset motion intention and longitudinal distance; determining the first inner boundary correction amount based on the lane compensation weight, road compensation weight, vehicle compensation weight, and motion compensation weight; and determining the first outer boundary correction amount based on the first inner boundary correction amount combined with a preset gain coefficient.

2. The method according to claim 1, characterized in that, Determining the boundary correction amount based on the environmental information includes: Obtain the longitudinal distance between the surrounding vehicles and the vehicle; Based on the environmental information and the longitudinal distance, a first boundary correction amount corresponding to the initial vehicle boundary data and a second boundary correction amount corresponding to the initial lane line boundary data are determined.

3. The method according to claim 1, characterized in that, The step of determining the target vehicle of the self-vehicle based on the vehicle distribution information includes: At least one target vehicle is identified in each of the voluntary lane, the adjacent lane, and the next adjacent lane.

4. The method according to claim 1, characterized in that, The environmental information includes second vehicle boundary data of surrounding vehicles. The process of determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and corrected lane line boundary data includes: Determine the lane-changing status of the vehicle; If the lane change state is no lane change or before the lane change is completed, then the first driving range of the vehicle is determined according to the corrected vehicle boundary data, and the second driving range of the surrounding vehicles is determined according to the second vehicle boundary data. Based on the first driving section and the second driving section, it is determined whether there is lateral overlap, wherein the lateral overlap means that the above driving sections have projection overlap in the direction perpendicular to the lane centerline; If so, then it is determined that the surrounding vehicles belong to the bicycle lane.

5. The method according to claim 4, characterized in that, The step of determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data further includes: If the lane change status is "lane change completed", then determine the lane where the vehicle is located after the lane change and obtain the lane line corresponding to the lane where the vehicle is located after the lane change. The first lane interval of the lane after the lane change is determined based on the corrected lane line boundary data. Determine whether there is lateral overlap between the first lane section and the second driving section; If so, then it is determined that the surrounding vehicles belong to the bicycle lane.

6. The method according to claim 4, characterized in that, The step of determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data further includes: Obtain the rear axle center coordinates of the vehicle, and determine the adjacent lanes of the vehicle based on the rear axle center coordinates and the initial lane line boundary data; Obtain the lane lines of the adjacent lanes, and determine the second lane interval of the adjacent lanes based on the corrected lane line boundary data; Determine whether there is lateral overlap between the second lane section and the second driving section; If so, then the surrounding vehicles are determined to belong to the adjacent lane.

7. The method according to claim 4, characterized in that, The step of determining the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data further includes: The next adjacent lane of the vehicle is determined based on the rear axle center coordinates of the vehicle and the initial lane line boundary data. Determine the lane lines of the next adjacent lane, and determine the third lane section of the next adjacent lane based on the corrected lane line boundary data; Determine whether there is lateral overlap between the third lane section and the second driving section; If so, then the surrounding vehicles are determined to belong to the next adjacent lane.

8. A target vehicle identification device, characterized in that, The device includes: The acquisition module is used to acquire the initial vehicle boundary data, initial lane line boundary data, and corresponding environmental information of the vehicle. An optimization module is used to determine a boundary correction amount based on the environmental information. The boundary correction amount includes a first boundary correction amount corresponding to the initial vehicle boundary data and a second boundary correction amount corresponding to the initial lane line boundary data. The decision module is used to determine the target vehicle of the vehicle based on the corrected vehicle boundary data and the corrected lane line boundary data. The environmental information includes at least one of the following: lane width, road curvature, vehicle type of surrounding vehicles, and movement intention of surrounding vehicles; the first boundary correction amount is the vehicle boundary correction amount of the vehicle under the influence of surrounding vehicles and environmental information, and the second boundary correction amount is the lane line boundary correction amount under the influence of surrounding vehicles and environmental information. The decision module is also used to determine the vehicle distribution information of surrounding vehicles based on the corrected vehicle boundary data and the corrected lane line boundary data; and to determine the target vehicle of the vehicle based on the vehicle distribution information. The vehicle distribution information includes whether the surrounding vehicles belong to the vehicle's own lane, adjacent lane, or next-next lane. The decision module is further configured to obtain the longitudinal distance between all the surrounding vehicles and the vehicle, perform longitudinal sorting based on the longitudinal distance, and determine the longitudinal sorting results of the vehicle's own lane, adjacent lane, and next-next lane. Based on the longitudinal sorting results of the vehicle's own lane, adjacent lane, and next-next lane, at least one target vehicle is determined from each of the vehicle's own lane, adjacent lane, and next-next lane. The optimization module is also used to select a surrounding vehicle within the target detection area as the vehicle to be determined; obtain the longitudinal distance between the surrounding vehicle and the vehicle itself, the lane width of the road where the vehicle is currently located, the road curvature of the road where the vehicle is currently located, the vehicle type of the vehicle to be determined, and the motion intention of the vehicle to be determined; determine the lane compensation weight corresponding to the obtained current lane width by looking up a table based on the preset lane width and longitudinal distance; determine the road compensation weight corresponding to the obtained current road curvature by looking up a table based on the preset road curvature and longitudinal distance; determine the vehicle compensation weight corresponding to the obtained current vehicle type by looking up a table based on the preset vehicle type and longitudinal distance; determine the motion compensation weight corresponding to the obtained current motion intention by looking up a table based on the preset motion intention and longitudinal distance; determine the first inner boundary correction amount based on the lane compensation weight, road compensation weight, vehicle compensation weight, and motion compensation weight; and determine the first outer boundary correction amount based on the first inner boundary correction amount combined with a preset gain coefficient.

9. An intelligent driving vehicle, comprising a memory and a processor, wherein the memory stores an executable program, characterized in that, When the processor executes the executable program, it implements the steps of the method according to any one of claims 1 to 7.

Images