Vehicle trajectory restoration method, device and storage medium

Abstract

The embodiment of the present application provides a vehicle trajectory restoration method, device and storage medium. In the embodiment of the present application, the existing position sensing device can be used to sense the position of the vehicle, and based on the sensed vehicle position information, the driving fleet on each incoming lane of the target intersection can be dynamically maintained; the driving fleet can be simulated according to the traffic control signal of the target intersection, thereby determining the driving parameters of the vehicles in the driving fleet within the perception blind spot of the position sensing device, and then restoring the vehicle trajectory of the vehicle within the perception blind spot. In this way, in the embodiment of the present application, the vehicle trajectory of the vehicle in the perception area can be determined by using the position sensing device; the vehicle trajectory of the vehicle in the perception blind spot can also be predicted by performing simulated communication control on the fleet where the vehicle is located, thereby generating a complete trajectory of the vehicle. This can achieve full restoration of the vehicle trajectory occurring in the target intersection without adding position sensing devices.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a vehicle trajectory restoration method, device, and storage medium. Background Art

[0002] As an important node in traffic management, intersections’ traffic data can be used for refined traffic management tasks such as intersection channeling optimization, signal control optimization, congestion relief, and global traffic operation status perception.

[0003] At present, vehicle trajectories within intersections are mainly sensed by position sensing devices such as coils, geomagnetism, radars, and cameras. However, due to the limitations of the installation density and cost of these position sensing devices, most intersections have perception blind spots, resulting in the loss of vehicle trajectories within the intersections. This has seriously restricted the development of refined traffic management. Summary of the Invention

[0004] Various aspects of the present application provide a vehicle trajectory environment method, device, and storage medium for fully restoring vehicle trajectories occurring at an intersection.

[0005] The present invention provides a method for restoring a vehicle trajectory, including:

[0006] Using a position sensing device corresponding to a target intersection, sensing position information of a vehicle that appears in a target entry lane at the target intersection;

[0007] Determining relative positions of vehicles appearing on the target entry lane based on the position information to generate a moving convoy on the target entry lane;

[0008] Performing simulated traffic control on the traveling convoy according to the traffic control signal of the target intersection within the perception blind spot of the position sensing device to determine driving parameters of the vehicles in the traveling convoy within the perception blind spot;

[0009] The vehicle trajectories of the vehicles in the driving fleet within the perception blind spot are restored according to the driving parameters.

[0010] An embodiment of the present application further provides a computing device, including a memory, a processor, and a communication component;

[0011] The memory is used to store one or more computer instructions;

[0012] The processor is coupled to the memory and the communication component and is configured to execute the one or more computer instructions for:

[0013] Using the position sensing device corresponding to the target intersection through the communication component, the position information of the vehicle appearing in the target entry lane at the target intersection is sensed;

[0014] Determining relative positions of vehicles appearing on the target entry lane based on the position information to generate a moving convoy on the target entry lane;

[0015] Performing simulated traffic control on the traveling convoy according to the traffic control signal of the target intersection within the perception blind spot of the position sensing device to determine driving parameters of the vehicles in the traveling convoy within the perception blind spot;

[0016] The vehicle trajectories of the vehicles in the driving fleet within the perception blind spot are restored according to the driving parameters.

[0017] An embodiment of the present application also provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed by one or more processors, the one or more processors are caused to execute the aforementioned vehicle trajectory restoration method.

[0018] In an embodiment of the present application, existing position sensing equipment can be used to sense the position of vehicles entering the target intersection. Based on the sensed vehicle position information, the driving fleet on each lane entering the target intersection can be dynamically maintained. On this basis, simulated traffic control can be performed on the driving fleet on each lane entering the target intersection according to the traffic control signal of the target intersection, thereby determining the driving parameters of the vehicles in the driving fleet within the perception blind spot of the position sensing equipment, and then restoring the vehicle trajectory of the vehicle within the said perception blind spot. In this way, in an embodiment of the present application, the vehicle trajectory of the vehicle within the perception area can be determined by using the position sensing equipment. The vehicle trajectory of the vehicle within the perception blind spot can also be predicted by performing simulated communication control on the vehicle's fleet, thereby generating a complete trajectory of the vehicle. This can achieve a full restoration of the vehicle trajectory occurring in the target intersection without the need for additional position sensing equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 A flow chart of a vehicle trajectory restoration method provided by an exemplary embodiment of the present application;

[0021] Figure 2 A logical diagram of a vehicle trajectory restoration solution provided by an exemplary embodiment of the present application;

[0022] Figure 3 A schematic diagram of an installation location of a location awareness device provided by an exemplary embodiment of the present application;

[0023] Figure 4 A logical diagram of a solution for correcting vehicle location information provided by an exemplary embodiment of the present application;

[0024] Figure 5 A schematic structural diagram of a computing device is provided as another exemplary embodiment of the present application. DETAILED DESCRIPTION

[0025] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0026] Currently, the position sensing devices installed at intersections have perception blind spots, resulting in the loss of vehicle trajectories within the intersection. To this end, in some embodiments of the present application: existing position sensing devices can be used to perform position sensing of vehicles entering the target intersection, and based on the perceived vehicle position information, the driving fleet on each incoming lane of the target intersection can be dynamically maintained; on this basis, the driving fleet on each incoming lane can be simulated for traffic control according to the traffic control signal of the target intersection, thereby determining the driving parameters of the vehicles in the driving fleet within the perception blind spot of the position sensing device, and then restoring the vehicle trajectory of the vehicle within the perception blind spot. In this way, in the embodiments of the present application, the position sensing device can be used to determine the vehicle trajectory of the vehicle within the perception area; the vehicle trajectory of the vehicle within the perception blind spot can also be predicted by performing simulated communication control on the fleet where the vehicle is located, thereby combining and generating the complete trajectory of the vehicle, which can achieve full restoration of the vehicle trajectory occurring within the target intersection without the need to add position sensing devices.

[0027] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0028] Figure 1 A flow chart of a vehicle trajectory restoration method provided by an exemplary embodiment of the present application is provided. Figure 2 This is a logical diagram of a vehicle trajectory restoration solution provided by an exemplary embodiment of the present application. The vehicle trajectory restoration method can be executed by a vehicle trajectory restoration device, which can be implemented as a combination of software and / or hardware, and can be integrated into a computing device. Figure 1 , the method comprising:

[0029] Step 100: Using a position sensing device corresponding to a target intersection, sensing position information of a vehicle that appears in a target entry lane at the target intersection;

[0030] Step 101: Determine the relative positions of vehicles on the target entry lane based on the position information to generate a moving convoy on the target entry lane.

[0031] Step 102: within the blind spot of the position sensing device, simulate traffic control of the convoy according to the traffic control signal of the target intersection to determine the driving parameters of the vehicles in the convoy within the blind spot.

[0032] Step 103: Restore the vehicle trajectories of the vehicles in the convoy within the perception blind spot based on the driving parameters.

[0033] The vehicle trajectory restoration method provided in this embodiment can be applied to various application scenarios that require determining the vehicle trajectory occurring at an intersection, such as routing channelization optimization scenarios, signal control optimization scenarios, congestion relief scenarios, and global traffic permission status perception scenarios. This embodiment does not limit the application scenarios.

[0034] Currently, intersections are often equipped with location-sensing devices, including but not limited to coils, geomagnetic sensors, radars, and cameras. In practice, to save equipment costs, the density of location-sensing devices at intersections is typically low. Furthermore, the sensing area of these devices often cannot cover the entire intersection. Figure 3 A schematic diagram of the installation location of a location awareness device provided by an exemplary embodiment of the present application. Figure 3 , the position sensing device has a large area of perception blind spot, in which the position sensing device cannot perceive the vehicle's position information.

[0035] refer to Figure 1 and Figure 2 In step 100, the location information of the vehicle appearing in the target entry lane at the target intersection can be sensed by using the location sensing device corresponding to the target intersection. In this embodiment, only the location sensing device already installed at the target intersection can be used without adding additional location sensing devices to avoid increasing equipment costs. The location information can be latitude and longitude information, etc. Figure 3 The target entry lane can be any of the multiple entry lanes at the target intersection. An entry lane refers to the lane that leads into the target intersection. In practical applications, unique identification information such as license plates can be used to identify vehicles to distinguish them. During the entire vehicle trajectory restoration process, the identification information of the same vehicle remains unchanged.

[0036] In this embodiment, the location sensing device may perform location sensing operations periodically, for example, once per second. Thus, for a vehicle, the location sensing device may provide the vehicle's location information once per second while the vehicle is within the sensing area. This generates a trajectory of the vehicle within the sensing area every second, thereby constructing a vehicle trajectory within the sensing area. Of course, this embodiment is not limited to performing location sensing periodically; the location sensing device may also perform location sensing operations according to other time schedules. Herein, the time slice corresponding to each location sensing operation is referred to as a sensing time slice.

[0037] Furthermore, in practical applications, considering that there may be multiple location sensing devices corresponding to the target intersection, and that different location sensing devices may have different sensing operating frequencies, in this embodiment, if multiple candidate location information for the same vehicle exists within a single sensing time slice, the vehicle's location information is determined based on the multiple candidate location information. For example, if multiple candidate location information corresponding to different time points exists within a single sensing time slice, the candidate location information corresponding to the time point closest to the end of the sensing time slice may be used as the vehicle's location information. For another example, if a single sensing time slice contains a single time point, but candidate location information is sensed by multiple different location sensing devices at that time point, a midpoint position may be determined based on the multiple candidate location information as the vehicle's location information. It should be understood that these are merely exemplary and this embodiment is not limited thereto. Other implementations may also be used in this embodiment to fuse multiple candidate location information for the same vehicle within a single sensing time slice to determine the vehicle's location information.

[0038] For the position sensing device corresponding to the target intersection, the position information of several vehicles may be sensed within its sensing area. Therefore, in this embodiment, the lanes in which these vehicles are located can be determined to determine the driving directions of these vehicles. An exemplary lane determination scheme may be: the position information of several known lanes can be pre-recorded, and on this basis, the position sensing device can be used to sense the position information of the first vehicle; if it is determined based on the position information of the first vehicle that the first vehicle is closest to the target entry lane among several known lanes, then the first vehicle is determined to be in the target entry lane; the first vehicle is any one of the vehicles that the position sensing device can sense. In this exemplary scheme, a traversal method can be used to traverse the distance between the first vehicle and several known lanes to determine the lane in which the first vehicle is located. In addition, the position information of several known lanes can be represented by the longitude and latitude of the lane centerline.

[0039] In actual applications, after determining that the first vehicle is closest to a target entry lane among several known lanes, the system can further determine whether the distance between the first lane and the target entry lane is less than a preset distance threshold. If so, the first vehicle can be determined to be in the target entry lane; if not, the position information of the first vehicle sensed this time can be determined to be invalid. This effectively avoids perception errors such as position drift during the position sensing process.

[0040] In this way, the position information of the vehicle appearing in the target lane can be obtained, and on this basis, the reference Figure 1 and Figure 2 In step 101, the relative positions of the vehicles appearing on the target entry lane can be determined based on the position information to generate a moving convoy on the target entry lane.

[0041] It should be understood that the position sensing device continuously senses vehicles entering the target entry lane. This is a continuous sensing process, and the number of vehicles entering the sensing area corresponding to the target entry lane changes dynamically over time. Therefore, the position sensing device can sense all vehicles currently or historically present in the target entry lane, as well as the relative positions of these vehicles, thereby obtaining a convoy in the target entry lane. It should be understood that over time, vehicles in the convoy in the target entry lane continue to advance, and vehicles at the front of the convoy gradually disappear (for example, a vehicle entering the sensing area of the exit lane of the target intersection can be determined to have disappeared from the convoy), while more vehicles enter the rear of the convoy. In this embodiment, it is assumed that the relative positions of vehicles in the target entry lane remain consistent within the sensing area corresponding to the target entry lane (i.e., the area covered by the position sensing device in the target entry lane) and within the sensing blind spot of the target intersection (i.e., the area not covered by the position sensing device in the target intersection).

[0042] In addition, in this embodiment, when there are multiple driving directions in the target entry lane, the driving directions corresponding to the vehicles appearing in the target entry lane are determined to obtain the vehicles in each driving direction respectively; based on the position information, the relative positions of the vehicles in different driving directions are determined respectively to generate a driving fleet in different driving directions in the target entry lane.

[0043] Based on this, reference Figure 1 and Figure 2In step 102, simulated traffic control can be performed on the convoy in the target incoming lane according to the traffic control signal of the target intersection within the perception blind spot of the position sensing device corresponding to the target intersection. The traffic control signal can be a traffic light timing signal used to control the start and stop of the convoy. By simulating the traffic control of the convoy, driving parameters of the vehicles in the convoy within the perception blind spot can be generated. The driving parameters include but are not limited to driving speed, driving acceleration, driving deceleration, driving time, driving position, etc. In actual applications, a vehicle following model can be applied to the convoy. During the process of simulating traffic control of the convoy, the driving parameters of the vehicles in the convoy within the perception blind spot can be determined according to the principles of the vehicle following model.

[0044] In addition, for the aforementioned situation where there are multiple driving directions of the target entering lane, in step 102, simulated traffic control can be performed separately for the driving fleets with different driving directions on the target entering lane, and driving parameters of the vehicles in each driving fleet within the perception blind spot can be generated.

[0045] In this way, the driving parameters of each vehicle in the driving fleet corresponding to the target entering lane can be obtained. Figure 1 and Figure 2 In step 103, the vehicle trajectory of each vehicle in the fleet within the blind spot can be restored based on the driving parameters. From the perspective of a single vehicle, the vehicle's trajectory position can be restored based on the driving parameters of the vehicle within each sensing time slice according to the aforementioned sensing time slices. Consequently, multiple trajectory positions of the vehicle can be obtained after several sensing time slices. The vehicle trajectory of the vehicle can be constructed based on these multiple trajectory positions.

[0046] In addition, the vehicle trajectories occurring at the target intersection can also be output. It should be understood that the use of vehicle trajectories at the target intersection may vary depending on the application scenario. For example, in some application scenarios, the vehicle trajectories at the target intersection can be graphically displayed. In other application scenarios, various data contained in the vehicle trajectories at the target intersection can also be used for data analysis, statistics, further calculations, etc. This embodiment does not limit the application process of vehicle trajectories.

[0047] In summary, in this embodiment, the existing position sensing equipment can be used to sense the position of vehicles entering the target intersection. Based on the sensed vehicle position information, the driving fleet on each entering lane of the target intersection can be dynamically maintained. On this basis, the driving fleet on each entering lane can be simulated and controlled according to the traffic control signal of the target intersection, thereby determining the driving parameters of the vehicles in the driving fleet within the perception blind spot of the position sensing equipment, and then restoring the vehicle trajectory of the vehicle within the perception blind spot. In this way, in this embodiment of the present application, the vehicle trajectory of the vehicle within the perception area can be determined by using the position sensing equipment. The vehicle trajectory of the vehicle within the perception blind spot can also be predicted by performing simulated communication control on the vehicle's fleet, thereby generating a complete trajectory of the vehicle. This can achieve a full restoration of the vehicle trajectory occurring in the target intersection without the need for additional position sensing equipment.

[0048] In the above or below embodiments, the moving vehicle fleet corresponding to the target entering lane may be updated according to the aforementioned sensing time slice.

[0049] The update of the driving fleet may include at least two dimensions: which vehicles are included in the driving fleet and the relative positions between the vehicles in the driving fleet.

[0050] For the dimension of "which vehicles are included in the driving fleet", vehicles that are newly sensed by the position sensing device to appear in the target entry lane within a single sensing time slice can be added to the driving fleet; vehicles that are within the sensing area corresponding to the exit lane of the target intersection and are determined based on simulated communication control of the driving fleet corresponding to the target entry lane can be deleted from the driving fleet.

[0051] Regarding the dimension of "relative positions between vehicles in a moving convoy," as mentioned above, in this embodiment, the relative positions between vehicles appearing in the target entry lane can be assumed to remain consistent within the perception area corresponding to the target entry lane and within the perception blind spot of the target intersection. To this end, in this embodiment, the relative positions between perceived vehicles can be determined within the perception area corresponding to the target entry lane within the current perception time slice based on the position information of the vehicles perceived by the position sensing device. For blind spot vehicles in the moving convoy located within the perception blind spot of the position sensing device, the relative positions between blind spot vehicles determined within the historical perception time slice prior to the current perception time slice can be used.

[0052] Based on the above two dimensions, a driving fleet can be constructed within a single perception time slice based on the vehicles appearing in the target entry lane perceived by the position sensing device. The vehicles in the driving fleet will be divided into two categories. One category is vehicles located within the perception area. The relative positions of these vehicles can be determined based on the position information of the vehicles perceived by the position sensing device; the other category is vehicles located in the perception blind spot. The relative positions of these vehicles can use their corresponding relative positions in the historical perception time slice.

[0053] An exemplary approach for determining the relative positions of vehicles within a perception area corresponding to a target entry lane within a single perception time slice may include: utilizing a position sensing device to sense the position information of a second vehicle and other vehicles within its perception area located in the target entry lane; determining the second vehicle's preceding and following vehicles among the other vehicles; and correcting the second vehicle's position information to determine the relative positions of the second vehicle and its preceding and following vehicles, with the goal of ensuring that the distances between the second vehicle and its preceding and following vehicles meet the following vehicle requirement. The second vehicle may be any vehicle in the target entry lane. Thus, based on the following vehicle requirement, the second vehicle's position information can be corrected to determine the relative positions of the second vehicle and its preceding and following vehicles, effectively improving the accuracy of the relative positions between vehicles. Consequently, the relative positions of all vehicles in the moving convoy corresponding to the target entry lane can be determined.

[0054] Figure 4 A logical diagram of a solution for correcting vehicle location information provided by an exemplary embodiment of the present application, in which:

[0055] When the distance between the vehicle in front of and behind the second vehicle is greater than twice the safe following distance, if the distance between the second vehicle and the vehicle in front or behind it is less than the safe following distance, the position information of the second vehicle may be corrected until the distance between the second vehicle and the vehicle in front and behind it is no less than the safe following distance;

[0056] In a case where the distance between the vehicle in front of the second vehicle and the vehicle behind it is less than twice the safe following distance but greater than twice the minimum following distance, if the distance between the second vehicle and the vehicle in front of it or the vehicle behind it is less than the minimum following distance, the position information of the second vehicle may be corrected until the distance between the second vehicle and the vehicle in front of it and the vehicle behind it is no less than the minimum following distance;

[0057] When the distance between the vehicle in front of the second vehicle and the vehicle behind the second vehicle is less than twice the minimum following distance, the position information of the second vehicle may be deleted within the sensing time slice.

[0058] refer to Figure 4, the distance between the second vehicle and the vehicle in front of it can be expressed as hl, and the distance between the second vehicle and the vehicle behind it can be expressed as hf. Based on this, the above exemplary solution can be specifically implemented as follows:

[0059] Case 1: hl + hf ≥ 2 * hsafe (following safety distance)

[0060] If hl < hSafe, move the position of the second vehicle backward by hsafe - hl;

[0061] If hf < hsafe, move the position of the second vehicle forward by hsafe - hf.

[0062] Case 2: hl + hf ≤ 2 * hsafe, and hl + hf ≥ 2 * hmin (minimum following distance)

[0063] Let hmid = (hl + hf) / 2, and adjust the second vehicle to the position of hmid.

[0064] Case 3: If hl + hf ≤ 2 * hmin

[0065] Delete the position information of the second vehicle and wait to determine whether it can be in the driving fleet in the next sensing time slice.

[0066] Of course, this is only exemplary, and this embodiment is not limited to this. In addition, for the case where the distances between the second vehicle and the vehicle in front of it and the vehicle behind it are both greater than the following safety distance, there is no need to correct the position information of the second vehicle. This can provide a basis for applying the following model to the driving fleet subsequently.

[0067] In this embodiment, within a single sensing time slice, the vehicles existing on the target entry lane and the relative positions that meet the following requirements between these vehicles can be determined, so as to generate the driving fleet corresponding to the target entry lane within a single sensing time slice. Furthermore, as time goes by, the driving fleet corresponding to the target entry lane can be dynamically updated, and the relative positions between the vehicles located in the sensing blind area can be defined by沿用 the relative positions determined in the historical sensing time slices. This can ensure the real-time performance and accuracy of the driving fleet and prepare for applying the following model.

[0068] In the above or following embodiments, a following vehicle model can be applied to a moving convoy. During the process of simulating traffic control for a moving convoy, the driving parameters of the vehicles in the convoy within the perception blind spot are determined according to the principles of the following vehicle model. The following vehicle model reflects the stimulus-response behavior of the driver of the following vehicle after obtaining relevant information about the leading vehicle. The driver's stimulus-response behavior refers to the reaction to the acceleration or deceleration actions made by the driver in order to track the leading vehicle. There are many factors that affect the driver's reaction behavior, the most important of which are the speed difference between the leading and trailing vehicles, the distance between the leading and trailing vehicles, the current speed of the following vehicle, and the degree of aggressiveness of the driver. Therefore, based on the following vehicle model, the driving parameters of the current vehicle can be calculated based on the leading vehicle's speed, acceleration, deceleration, driving position, and other driving parameters. For the specific calculation process of the following vehicle model, please refer to relevant public information and will not be elaborated here.

[0069] Based on this, in this embodiment, the relevant vehicles in the driving fleet corresponding to the target entry lane can be controlled to start or stop according to the traffic control signal of the target intersection, so that the traffic control status can be transmitted to other vehicles in the driving fleet through the following model, thereby obtaining the corresponding driving parameters of all vehicles in the driving fleet.

[0070] Specifically, in this embodiment, when the traffic control signal is switched to no traffic, the lead vehicle that needs to stop can be determined in the traveling fleet; simulated parking control is performed on the lead vehicle that needs to stop to obtain the driving parameters of the lead vehicle that needs to stop; based on the following vehicle model, the driving parameters of other vehicles in the traveling fleet that are located behind the lead vehicle that needs to stop and in the perception blind spot are calculated according to the driving parameters of the lead vehicle that needs to stop.

[0071] During the perception time slice corresponding to the moment the traffic control signal switches to a no-traffic signal, the position information of each vehicle in the convoy can be obtained. The vehicle located behind and closest to the start-stop line of the target entry lane can be identified as the lead vehicle requiring a stop. During the simulated parking control process for the lead vehicle requiring a stop, the speed of the lead vehicle requiring a stop can be set to zero at the moment the traffic control signal switches to a no-traffic signal, thereby generating driving parameters for the lead vehicle requiring a stop. In one exemplary approach, a virtual vehicle can be deployed at the start-stop line of the target entry vehicle and configured with driving parameters that match the traffic control signal at the target intersection. Specifically, when the traffic control signal switches to a no-traffic signal, the virtual vehicle's current speed is configured to be zero. Based on this, when the traffic control signal switches to a no-traffic signal, the virtual vehicle can be used as the leading vehicle of the lead vehicle requiring a stop, and the driving parameters of the lead vehicle requiring a stop can be calculated based on the driving parameters of the virtual vehicle. In actual applications, the specific position of the virtual vehicle at the start-stop line of the target entering vehicle can be determined by aiming at ensuring that the distance between the virtual vehicle and the leading vehicle that needs to stop meets the following vehicle requirement. Of course, this embodiment does not limit this.

[0072] Afterwards, based on the vehicle-following model, the driving parameters of other vehicles in the driving convoy that are located behind the lead vehicle that needs to stop and are within the perception blind spot can be calculated.

[0073] In this embodiment, when the traffic control signal is switched to allow passage, the lead vehicle that needs to be started can be determined in the traveling fleet; the lead vehicle that needs to be started is simulated and started to obtain the driving parameters of the lead vehicle that needs to be started; based on the following vehicle model, the driving parameters of other vehicles in the traveling fleet that are located behind the lead vehicle that needs to be started and in the perception blind spot are calculated according to the driving parameters of the lead vehicle that needs to be started.

[0074] During the sensing time slice corresponding to the moment the traffic control signal switches to allow passage, the position information of each vehicle in the convoy can be obtained, and the vehicle located behind and closest to the start-stop line of the target entry lane can be identified as the lead vehicle to be started. During the simulated start-up control of the lead vehicle to be started, the starting speed of the lead vehicle to be started at the moment the traffic control signal switches to allow passage can be set to 0, and other driving parameters such as the acceleration and deceleration of the lead vehicle to be started can be set, thereby generating the driving parameters of the lead vehicle to be started. In an exemplary embodiment, following the aforementioned virtual vehicle, when the traffic control signal switches to allow passage, the current speed of the virtual vehicle can be configured to 0, and other driving parameters such as the acceleration and deceleration of the virtual vehicle can be configured based on experience. Based on this, when the traffic control signal switches to allow passage, the virtual vehicle can be used as the leading vehicle of the lead vehicle to be started, and the driving parameters of the lead vehicle to be started can be calculated based on the driving parameters of the virtual vehicle. In actual applications, the specific position of the virtual vehicle at the start-stop line of the target entering vehicle can be determined by aiming at ensuring that the distance between the virtual vehicle and the lead vehicle to be started meets the following vehicle requirement. Of course, this embodiment does not limit this.

[0075] Afterwards, based on the vehicle-following model, the driving parameters of other vehicles in the driving convoy that are located behind the lead vehicle that needs to be started and are within the perception blind spot can be calculated.

[0076] In addition, in the above-mentioned process of simulating traffic control for the driving fleet corresponding to the target entry lane, the virtual vehicle configured for the target entry lane can be used only to represent the traffic control signal of the target intersection, and there is no need to follow the vehicles in the driving fleet. To this end, the driving parameters of the virtual vehicle can be used only in the following model to transmit the traffic control signal in the driving fleet, thereby generating the driving parameters of each vehicle in the driving fleet.

[0077] Furthermore, in this embodiment, the vehicle following model can be dynamically optimized. An exemplary optimization scheme may be:

[0078] When the position information of the third vehicle in the traveling convoy is sensed again by the position sensing device corresponding to the target intersection, if the position information of the third vehicle sensed again is inconsistent with the vehicle trajectory restored for the third vehicle, the model parameters of the following model are adjusted according to the position information of the third vehicle sensed again, so as to perform the operation of calculating the driving parameters using the adjusted following model; wherein the third vehicle can be any one of the vehicles in the traveling convoy corresponding to the target entry lane.

[0079] That is, the position sensing device corresponding to the target intersection may again sense the position of a third vehicle in the convoy corresponding to the target entry lane. For example, if the sensing area of the position sensing device covers the exit lane of the target intersection, the position information of the third vehicle may be sensed again in the exit lane. Of course, the sensing area of the position sensing device may also cover other locations of the target intersection, which is not limited here. The re-perceived position information of the third vehicle is inconsistent with the vehicle trajectory restored for the third vehicle, which may mean that the perceived position information of the third vehicle and the driving position of the third vehicle restored within the same sensing time slice are inconsistent within the same sensing time slice. In this case, it can be considered that the vehicle trajectory restoration of the third vehicle contains an error. To this end, the re-perceived position information of the third vehicle can optionally be used to replace the driving position of the third vehicle restored within the corresponding sensing time slice, and the model parameters of the vehicle following model can be adjusted until, during the vehicle following model's determination of the driving parameters of the third vehicle, the driving position output within the corresponding sensing time slice when the position information of the third vehicle is re-perceived is consistent with the re-perceived position information of the third vehicle. On this basis, the adjusted vehicle following model can be used to perform the operation of calculating the driving parameters in subsequent perception time slices, and the vehicle trajectory of the third vehicle in other perception time slices is no longer adjusted.

[0080] Of course, the above solution is implemented in a scenario where the vehicle trajectory is restored in real time based on the vehicle's real-time position changes. This real-time calculation method has higher real-time performance, but the accuracy of the vehicle trajectory may be sacrificed. In other cases, the vehicle's driving parameters can also be calculated with a lag based on the following model. For example, based on experience, the time required for a vehicle to pass the target intersection is typically within 30 seconds. In this case, a 30-second lag can be used to restore the vehicle trajectory. In this method, the position information of the third vehicle can usually be re-perceived before the following model is used. Therefore, if the re-perceived position information of the third vehicle does not match the restored vehicle trajectory for the third vehicle, the re-perceived position information of the third vehicle can be used to replace the driving position of the third vehicle restored within the corresponding perception time slice, and the model parameters of the following model can be adjusted until, during the following model's determination of the third vehicle's driving parameters, the driving position output within the corresponding perception time slice upon re-perceiving the third vehicle's position information is consistent with the re-perceived position information of the third vehicle. Based on this, the adjusted following model can be used to recalculate the driving parameters of the third vehicle to regain the third vehicle's trajectory. This delayed calculation method can obtain a more accurate vehicle trajectory, but it requires sacrificing real-time performance. In practice, real-time calculation or delayed calculation can be selected according to needs.

[0081] In summary, this embodiment allows for the determination of the driving parameters of vehicles in the convoy within the blind spot of the perception system, based on the principles of the vehicle-following model, during the simulated traffic control process for a convoy according to the traffic control signals at the target intersection. This not only ensures that the simulated traffic control procedures adhere to the actual traffic control signals at the target intersection, but also enables the accurate transmission of traffic control signals to the vehicles in the convoy based on the vehicle-following model, thereby accurately reconstructing the driving states of the vehicles within the blind spot of the position sensing device. This allows for the accurate determination of the vehicles' driving parameters, thereby ensuring the accuracy of the reconstructed vehicle trajectories.

[0082] It should be noted that the execution entity of each step of the method provided in the above embodiment can be the same device, or the method can be executed by different devices. For example, the execution entity of steps 101 to 103 can be device A; for another example, the execution entity of steps 101 and 102 can be device A, and the execution entity of step 103 can be device B; and so on.

[0083] In addition, some of the processes described in the above embodiments and the accompanying drawings include multiple operations that appear in a specific order, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", "third", etc. in this article are used to distinguish different vehicles, etc., and do not represent a sequential order, nor do they limit "first", "second", and "third" to being different types.

[0084] Figure 5 A schematic diagram of a computing device provided as another exemplary embodiment of the present application is shown in FIG. Figure 5 As shown, the computing device includes a memory 50 , a processor 51 and a communication component 52 .

[0085] The processor 51 is coupled to the memory 50 and is configured to execute the computer program in the memory 50 to:

[0086] The traffic component 52 uses the position sensing device corresponding to the target intersection to sense the position information of the vehicle that appears in the target entry lane at the target intersection;

[0087] Determine the relative positions of the vehicles appearing on the target entry lane based on the position information to generate a moving convoy on the target entry lane;

[0088] Within the blind spot of the position sensing device, simulate traffic control of the convoy according to the traffic control signal of the target intersection to determine the driving parameters of the vehicles in the convoy within the blind spot;

[0089] Based on driving parameters, the vehicle trajectories of vehicles in the driving fleet within the perception blind spot are restored.

[0090] In an optional embodiment, when the processor 51 uses the position sensing device to sense the position information of a vehicle that appears in the target entry lane at the target intersection, it is configured to:

[0091] Sense the location information of the first vehicle using a location sensing device;

[0092] If it is determined based on the position information of the first vehicle that the first vehicle is closest to the target entry lane among the known lanes, then it is determined that the first vehicle is in the target entry lane;

[0093] The first vehicle is any one of the vehicles that can be sensed by the position sensing device.

[0094] In an optional embodiment, when determining the relative positions of vehicles appearing on the target entering lane based on the position information, the processor 51 is configured to:

[0095] Within a single sensing time slice, the position sensing device senses the position information of the second vehicle and other vehicles that appear in the target entering lane within its sensing area;

[0096] determining, among other vehicles, a preceding vehicle and a following vehicle of the second vehicle;

[0097] With the goal of ensuring that the distances between the second vehicle and its preceding and following vehicles meet the following vehicle requirement, the position information of the second vehicle is corrected to generate the relative positions of the second vehicle and its preceding and following vehicles;

[0098] The second vehicle is any one of the vehicles appearing on the target entering lane.

[0099] In an optional embodiment, when the processor 51 corrects the position information of the second vehicle with the goal of satisfying the following vehicle requirement with the distance between the second vehicle and the preceding and following vehicles, it is configured to:

[0100] If the distance between the vehicle in front of the second vehicle and the vehicle behind it is greater than twice the safe following distance, and if the distance between the second vehicle and the vehicle in front of or behind it is less than the safe following distance, the position information of the second vehicle is corrected until the distance between the second vehicle and the vehicle in front of or behind it is no less than the safe following distance.

[0101] In a case where the distance between the vehicle in front of the second vehicle and the vehicle behind it is less than twice the safe following distance but greater than twice the minimum following distance, if the distance between the second vehicle and the vehicle in front of it or the vehicle behind it is less than the minimum following distance, correct the position information of the second vehicle until the distance between the second vehicle and the vehicle in front of it and the vehicle behind it is no less than the minimum following distance;

[0102] When the distance between the vehicle in front of the second vehicle and the vehicle behind the second vehicle is less than twice the minimum following distance, the position information of the second vehicle is deleted within the sensing time slice.

[0103] In an optional embodiment, the processor 51 is further configured to:

[0104] In a single perception time slice, for blind spot vehicles in a traveling fleet that are within the perception blind spot of the position perception device, the relative positions between the blind spot vehicles determined in the historical perception time slice before the current perception time slice are used.

[0105] In an optional embodiment, when the processor 51 simulates traffic control on the convoy according to the traffic control signal of the target intersection to determine the driving parameters of the vehicles in the convoy within the perception blind spot, it is configured to:

[0106] When the traffic control signal switches to no-travel, determine the lead vehicle in the moving convoy that needs to stop;

[0107] Perform simulated parking control on the lead vehicle that needs to stop to obtain the driving parameters of the lead vehicle that needs to stop;

[0108] Based on the vehicle-following model, the driving parameters of other vehicles in the convoy that are located behind the lead vehicle that needs to stop and are within the perception blind spot are calculated according to the driving parameters of the lead vehicle that needs to stop.

[0109] In an optional embodiment, when the processor 51 simulates traffic control on the convoy according to the traffic control signal of the target intersection to determine the driving parameters of the vehicles in the convoy within the perception blind spot, it is configured to:

[0110] When the traffic control signal switches to allowing traffic, determine the lead vehicle that needs to be started in the moving fleet;

[0111] Perform simulated start control on the lead vehicle to be started to obtain the driving parameters of the lead vehicle to be started;

[0112] Based on the vehicle-following model, the driving parameters of the leading vehicle to be started are calculated according to the driving parameters of the leading vehicle to be started. The driving parameters of other vehicles in the driving convoy that are located behind the leading vehicle to be started and are within the perception blind spot are calculated.

[0113] In an optional embodiment, the processor 51 is further configured to:

[0114] A virtual vehicle is deployed at the start-stop line of the target entry lane, and the driving parameters of the virtual vehicle are adapted to the traffic control signal of the target intersection;

[0115] Based on the vehicle-following model, a virtual vehicle is used as the leading vehicle of the leading vehicle that needs to stop or the leading vehicle that needs to start, and the driving parameters of the leading vehicle that needs to stop or the leading vehicle that needs to start are calculated according to the driving parameters of the virtual vehicle.

[0116] In an optional embodiment, the processor 51 is further configured to:

[0117] When the position information of the third vehicle in the traveling fleet is sensed again by the position sensing device corresponding to the target intersection, if the position information of the third vehicle sensed again is inconsistent with the vehicle trajectory restored for the third vehicle, the model parameters of the following model are adjusted according to the position information of the third vehicle sensed again, so as to use the adjusted following model to perform the operation of calculating the driving parameters.

[0118] In an optional embodiment, when determining the relative positions of vehicles appearing on the target entry lane based on the position information to generate a moving convoy on the target entry lane, the processor 51 is configured to:

[0119] In the case where the target entering lane has multiple driving directions, determining the driving directions corresponding to the vehicles appearing in the target entering lane, so as to obtain the vehicles in each driving direction respectively;

[0120] According to the position information, the relative positions of the vehicles in different driving directions are determined respectively to generate a driving convoy in different driving directions on the target entering lane.

[0121] In an optional embodiment, the processor 51 is further configured to:

[0122] If there are multiple candidate position information of the same vehicle within a single sensing time slice, the vehicle position information is determined based on the multiple candidate position information.

[0123] Further, if Figure 5 As shown, the computing device also includes: a display 53, a power supply component 54, an audio component 55 and other components. Figure 5 Only some components are shown schematically, and it does not mean that the computing device only includes Figure 5 Components shown.

[0124] It is worth noting that the technical details in the above-mentioned embodiments of the computing device can be referred to the relevant description in the aforementioned method embodiment. In order to save space, they will not be repeated here, but this should not cause any loss of the scope of protection of this application.

[0125] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed, can implement the steps that can be executed by a computing device in the above method embodiment.

[0126] above Figure 5 The memory in the computing platform is used to store computer programs and can be configured to store various other data to support operations on the computing platform. Examples of such data include instructions for any application or method operating on the computing platform, contact data, phone book data, messages, pictures, videos, etc. The memory can be implemented by any type of volatile or non-volatile storage device or a combination of them, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0127] above Figure 5 The communication component in is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0128] above Figure 5 The display in the embodiment includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0129] above Figure 5 The power supply component in a device provides power to various components of the device in which the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which the power supply component is located.

[0130] above Figure 5The audio component in the device may be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal may be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0131] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0132] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0135] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0136] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0137] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0138] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0139] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included in the protection scope of the present application.

Claims

1. A vehicle trajectory restoration method, characterized in that: include: Using a position sensing device corresponding to a target intersection, within its sensing area, sensing position information of a vehicle that appears in a target entry lane at the target intersection; Determining relative positions of vehicles appearing on the target entering lane based on the position information to generate a moving convoy on the target entering lane; wherein the relative positions remain consistent within a sensing area and a sensing blind area corresponding to the position sensing device; Within the blind spot of the position sensing device, simulated traffic control is performed on the moving convoy according to the traffic control signal of the target intersection to determine driving parameters of vehicles in the moving convoy within the blind spot; the traffic control signal is used to control the start and stop of the moving convoy; The vehicle trajectories of the vehicles in the driving fleet within the perception blind spot are restored according to the driving parameters.

2. The method according to claim 1, characterized in that The method of using a position sensing device to sense position information of a vehicle located in a target entry lane at the target intersection includes: Using the position sensing device to sense the position information of the first vehicle; If it is determined based on the position information of the first vehicle that the first vehicle is closest to a target entry lane among the known lanes, then it is determined that the first vehicle is in the target entry lane; The first vehicle is any one of the vehicles that can be sensed by the position sensing device.

3. The method according to claim 1, characterized in that The determining, based on the position information, the relative positions of the vehicles appearing on the target entering lane includes: Within a single sensing time slice, using the position sensing device to sense position information of a second vehicle and other vehicles that appear in the target entering lane within its sensing area; determining a preceding vehicle and a following vehicle of the second vehicle among the other vehicles; With the goal of ensuring that the distances between the second vehicle and its preceding and following vehicles meet the following vehicle requirement, the position information of the second vehicle is corrected to generate the relative positions of the second vehicle and its preceding and following vehicles; The second vehicle is any one of the vehicles appearing on the lane where the target enters.

4. The method according to claim 3, characterized in that The step of correcting the position information of the second vehicle with the goal of the distance between the second vehicle and the preceding and following vehicles satisfying the following vehicle requirement includes: When the distance between the vehicle in front of and behind the second vehicle is greater than twice the safe following distance, if the distance between the second vehicle and the vehicle in front or behind is less than the safe following distance, correct the position information of the second vehicle until the distance between the second vehicle and the vehicle in front and behind is no less than the safe following distance; In a case where the distance between the vehicle in front of and behind the second vehicle is less than twice the safe following distance but greater than twice the minimum following distance, if the distance between the second vehicle and the vehicle in front or behind is less than the minimum following distance, correcting the position information of the second vehicle until the distance between the second vehicle and both the vehicle in front and the vehicle behind is no less than the minimum following distance; When the distance between the vehicle in front and the vehicle behind the second vehicle is less than twice the minimum following distance, the position information of the second vehicle is deleted within the sensing time slice.

5. The method according to claim 3, characterized in that Also includes: In a single sensing time slice, for blind spot vehicles in the traveling fleet that are within the sensing blind spot of the position sensing device, the relative positions between the blind spot vehicles determined in the historical sensing time slice before the current sensing time slice are used.

6. The method according to claim 1, characterized in that The simulated traffic control is performed on the traveling vehicle fleet according to the traffic control signal of the target intersection to determine the driving parameters of the vehicles in the traveling vehicle fleet within the perception blind spot, including: When the passage control signal is switched to a prohibition of passage, determining a lead vehicle in the traveling convoy that needs to stop; Performing simulated parking control on the lead vehicle that needs to stop to obtain driving parameters of the lead vehicle that needs to stop; Based on the vehicle following model, the driving parameters of other vehicles in the traveling fleet that are located behind the lead vehicle that needs to stop and within the perception blind spot are calculated according to the driving parameters of the lead vehicle that needs to stop.

7. The method according to claim 1, characterized in that The simulated traffic control is performed on the traveling vehicle fleet according to the traffic control signal of the target intersection to determine the driving parameters of the vehicles in the traveling vehicle fleet within the perception blind spot, including: When the passage control signal is switched to allow passage, determining a lead vehicle in the traveling fleet that needs to be started; Performing simulated start control on the lead vehicle that needs to be started to obtain driving parameters of the lead vehicle that needs to be started; Based on the vehicle following model, the driving parameters of the other vehicles in the traveling fleet that are located behind the lead vehicle that needs to be started and within the perception blind spot are calculated according to the driving parameters of the lead vehicle that needs to be started.

8. The method according to claim 6 or 7, characterized in that Also includes: Deploy a virtual vehicle at the start-stop line of the target entry lane, wherein the driving parameters of the virtual vehicle are adapted to the traffic control signal of the target intersection; Based on the vehicle following model, the virtual vehicle is used as the leading vehicle of the leading vehicle that needs to stop or the leading vehicle that needs to start, and the driving parameters of the leading vehicle that needs to stop or the leading vehicle that needs to start are calculated according to the driving parameters of the virtual vehicle.

9. The method according to claim 6, characterized in that Also includes: When the position information of the third vehicle in the traveling fleet is perceived again by the position sensing device corresponding to the target intersection, if the position information of the third vehicle perceived again is inconsistent with the vehicle trajectory restored for the third vehicle, the model parameters of the following model are adjusted according to the position information of the third vehicle perceived again, so as to perform the operation of calculating the driving parameters using the adjusted following model.

10. The method according to claim 1, characterized in that Determining the relative positions of the vehicles appearing on the target entry lane according to the position information to generate a moving convoy on the target entry lane includes: In the case where there are multiple driving directions of the target entering lane, determining the driving directions corresponding to the vehicles appearing in the target entering lane, so as to obtain the vehicles in each driving direction respectively; The relative positions of the vehicles in different driving directions are determined according to the position information to generate a driving convoy in different driving directions on the target entry lane.

11. The method according to claim 1, wherein Also includes: If there are multiple candidate position information of the same vehicle within a single sensing time slice, the position information of the vehicle is determined based on the multiple candidate position information.

12. A computing device, characterized in that including memory, processor, and communication components; The memory is used to store one or more computer instructions; The processor is coupled to the memory and the communication component and is configured to execute the one or more computer instructions for: Using the position sensing device corresponding to the target intersection through the communication component, sensing the position information of the vehicle appearing in the target entry lane at the target intersection within its sensing area; Determining relative positions of vehicles appearing on the target entering lane based on the position information to generate a moving convoy on the target entering lane; wherein the relative positions remain consistent within a sensing area and a sensing blind area corresponding to the position sensing device; Within the blind spot of the position sensing device, simulated traffic control is performed on the moving convoy according to the traffic control signal of the target intersection to determine driving parameters of vehicles in the moving convoy within the blind spot; the traffic control signal is used to control the start and stop of the moving convoy; The vehicle trajectories of the vehicles in the driving fleet within the perception blind spot are restored according to the driving parameters.

13. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed by one or more processors, the one or more processors are caused to execute the vehicle trajectory restoration method according to any one of claims 1 to 11.

Images