Vehicle control method, device, apparatus, and storage medium

Abstract

This application discloses a vehicle control method, apparatus, device, and storage medium. It involves acquiring at least two preset spatiotemporal partitions corresponding to driving decisions. For each driving decision, upon reaching the corresponding decision cycle, decision driving data corresponding to the decision space range of the driving decision is determined from the driving data collected within the decision data acquisition cycle corresponding to that driving decision. Finally, based on the decision driving data, a driving instruction corresponding to the driving decision is planned and executed. According to an embodiment of this application, the vehicle is controlled to move according to the determined driving instruction. This driving instruction is planned based on the decision driving data collected within the decision data acquisition cycle corresponding to the spatiotemporal partition of the driving decision, achieving effective utilization of the data collected within each decision data acquisition cycle and improving efficiency.

Description

Technical Field

[0001] This application belongs to the field of automotive electronics technology, and in particular relates to a vehicle control method, device, equipment and storage medium. Background Technology

[0002] With the development of automation, computer technology and electronic technology, some service providers are already able to provide solutions for autonomous driving of vehicles.

[0003] During autonomous driving, the vehicle control center typically controls the vehicle's movement based on data collected by sensors such as radar sensors, image sensors, and sound sensors.

[0004] However, the above method makes it difficult to effectively utilize the data collected by the sensor, and the efficiency is low. Summary of the Invention

[0005] This application provides a vehicle control method, apparatus, and device that can improve the utilization rate of data collected by sensors.

[0006] On one hand, embodiments of this application provide a vehicle control method, the method comprising:

[0007] Obtain the spatiotemporal partitions corresponding to at least two preset driving decisions, wherein the spatiotemporal partitions include at least the decision data acquisition period, the decision period, and the decision space range.

[0008] For each driving decision, when the corresponding decision cycle is reached, the driving data determined within the completed decision data collection cycle for that driving decision is acquired.

[0009] From the driving data, determine the decision driving data corresponding to the decision space range of the driving decision.

[0010] Based on the driving decision data, plan the driving instructions corresponding to the driving decision.

[0011] Follow the driving instructions to control the vehicle's movement.

[0012] Optionally, the data collection cycle for decision-making can include:

[0013] For each driving decision, at least one target vehicle sensor corresponding to that driving decision is identified.

[0014] The data acquisition period of each of the at least one target vehicle sensor is obtained.

[0015] The largest data acquisition cycle among the at least one data acquisition cycle is determined as the decision data acquisition cycle.

[0016] Optionally, a preset decision-making cycle can be obtained, including:

[0017] Obtain vehicle information, which includes at least communication latency, decision latency, and data processing time.

[0018] When the sum of the communication delay, the decision delay, and the data processing duration is less than the unified data acquisition cycle, the decision multiple is determined to be the first character.

[0019] When it is determined that the sum of the communication delay, the decision delay, and the data processing duration is greater than or equal to the unified data acquisition cycle, the decision multiple is determined to be the second character, where the second character is greater than the first character.

[0020] For each driving decision, the decision period is determined by multiplying the decision multiplier by the decision data collection period corresponding to that driving decision.

[0021] Optionally, obtain the driving data determined within the decision data collection period corresponding to the completed driving decision, including:

[0022] Obtain the sensor data collected by the vehicle sensors within the decision data collection period corresponding to the completed driving decision with the smallest time interval to the current moment.

[0023] Based on the sensor data collected by the vehicle sensors within the unified data acquisition period, a linear interpolation algorithm is used to fit the sensor data to obtain fitted sensor data corresponding to the current moment.

[0024] The obtained fitted sensor data is identified as driving data.

[0025] Optionally, after acquiring the driving data determined within the decision data collection period corresponding to the completed driving decision, the following steps are included:

[0026] Based on the driving data corresponding to the driving decision and the decision data collection cycle, update the decision cycle and decision space range of the spatiotemporal partition corresponding to the driving decision.

[0027] Optionally, the decision period corresponding to the driving decision is updated based on the driving data and the decision data collection period, including:

[0028] Determine the primary and secondary influence locations within the decision space corresponding to this driving decision.

[0029] When, based on the driving data, it is determined that an influencing vehicle exists at a primary influence location within the decision space, the decision multiplier is determined to be the third character.

[0030] When, based on the driving data, it is determined that there are no influencing vehicles at the primary influence location within the decision space, but there are influencing vehicles at the secondary influence location within the decision space, the decision multiplier is determined to be the fourth character.

[0031] When, based on the driving data, it is determined that neither the primary nor secondary influence positions within the decision space contain any influencing vehicles, the decision multiplier is determined to be either the first character or the second character.

[0032] The product of the decision factor and the decision data collection period is used to determine the updated decision period.

[0033] Optionally, based on the driving data corresponding to the driving decision, the decision space range corresponding to the driving decision is updated, including:

[0034] Based on the driving data corresponding to this driving decision, determine the driving speed.

[0035] The braking distance corresponding to the driving speed within a preset braking distance standard is determined as the vehicle space length range.

[0036] The decision space range is updated based on the vehicle space length range.

[0037] The decision space range is composed of multiple vehicle space ranges, each of which is the product of the vehicle space length range and the lane width range.

[0038] Optionally, the braking distance corresponding to the driving speed in a preset braking distance standard is determined as the vehicle space length range, including:

[0039] In response to user actions, determine the safety level.

[0040] The product of the safety factor and the braking distance corresponding to the driving speed in the preset braking distance standard is determined as the vehicle space length range.

[0041] Optionally, based on the decision-making driving data, the driving instructions corresponding to the driving decision are planned, including:

[0042] When the driving decision is a lane-level driving decision, based on the decision driving data and the driving command being executed, the remaining distance to be traveled in the untraveled portion of the predicted driving distance of the driving command is determined.

[0043] When it is determined that the distance to be traveled is greater than a preset distance threshold, the driving instruction is determined as a re-planned driving instruction.

[0044] When it is determined that the distance to be traveled is less than or equal to the distance threshold, the driving instructions are replanned and executed based on the decision driving data corresponding to the lane machine driving decision.

[0045] Optionally, according to the driving command, control the vehicle's movement, including:

[0046] Obtain the vehicle's driving data.

[0047] Determine the predicted driving path corresponding to the driving command.

[0048] When it is determined, based on the driving data and the predicted driving path, that an object exists at the same location as the vehicle at the same time, the driving command is replanned and executed.

[0049] Optionally, after controlling the vehicle to drive according to the driving command, the method further includes:

[0050] Obtain the vehicle's driving data.

[0051] Based on the driving data and the driving instructions, the spatiotemporal deviation value between the vehicle's driving trajectory during the driving process and the predicted driving trajectory corresponding to the driving instructions is determined. The spatiotemporal deviation value includes a time deviation value and a spatial deviation value.

[0052] When the spatiotemporal deviation value is determined to be greater than a preset spatiotemporal error threshold, the driving instructions corresponding to the predicted driving trajectory are replanned based on the predicted driving trajectory.

[0053] Control the vehicle to drive according to the re-planned driving instructions.

[0054] Optionally, based on the decision-making driving data, the driving instructions corresponding to the driving decision are planned, including:

[0055] The system acquires the currently executing destination-level driving decisions, road-level driving decisions, and lane-level driving decisions, including destination-level driving decisions, road-level driving decisions, lane-level driving decisions, and action-level driving decisions.

[0056] When planning the road-level driving decisions, based on the decision driving data corresponding to the road-level driving decisions and the destination-level driving decisions, road-level driving decisions that do not conflict with the destination-level driving decisions are planned.

[0057] When planning the lane-level driving decision, based on the decision driving data corresponding to the lane-level driving decision and the road-level driving decision, a lane-level driving decision that does not conflict with the road-level driving decision is planned.

[0058] When planning the action-level driving decision, an action-level driving decision that does not conflict with the lane-level driving decision is planned based on the decision driving data corresponding to the action-level driving decision and the lane-level driving decision.

[0059] On the other hand, embodiments of this application provide a vehicle control device, the device comprising:

[0060] The acquisition unit is used to acquire at least two preset spatiotemporal partitions corresponding to driving decisions, wherein the spatiotemporal partitions include at least a decision data acquisition period, a decision period, and a decision space range.

[0061] The data acquisition unit is used to acquire, for each driving decision, the driving data determined within the completed decision data acquisition period corresponding to that driving decision when the corresponding decision period arrives.

[0062] The determining unit is used to determine, from the driving data, decision driving data corresponding to the decision space range of the driving decision.

[0063] The planning unit is used to plan the driving instructions corresponding to the driving decision based on the driving decision data.

[0064] The control unit is used to control the vehicle's movement according to the driving command.

[0065] Furthermore, embodiments of this application provide a vehicle control device, the device comprising:

[0066] The processor and the memory storing computer program instructions.

[0067] When the processor executes the computer program instructions, it implements the vehicle control method as provided in one aspect of this application.

[0068] In another aspect, embodiments of this application provide a computer-readable storage medium storing computer program instructions that, when executed by a processor, implement the vehicle control method as described in one aspect of this application.

[0069] In another aspect, embodiments of this application provide a vehicle control computer program product, wherein instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform the vehicle control method as described in one aspect of this application.

[0070] The vehicle control method, apparatus, device, and storage medium of this application embodiment can control vehicle movement according to a determined driving command. This driving command is planned based on driving data collected within the decision data collection period corresponding to the driving decision, achieving effective utilization of data collected within each decision data collection period. Furthermore, since different driving decisions correspond to different spatiotemporal partitions, when planning a certain driving decision, planning can be performed only based on the data corresponding to the spatiotemporal partition of that driving decision, thus improving efficiency. Attached Figure Description

[0071] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0072] Figure 1 This is a schematic flowchart of a vehicle control method provided in one embodiment of this application.

[0073] Figure 2 This is a schematic diagram of a nine-square grid provided in one embodiment of this application.

[0074] Figure 3 This is a schematic diagram of a 25-square grid provided in one embodiment of this application.

[0075] Figure 4 This is a schematic flowchart of a vehicle control method provided in another embodiment of this application.

[0076] Figure 5 This is a schematic diagram of the structure of a vehicle control device provided in one embodiment of this application.

[0077] Figure 6 This is a schematic diagram of the structure of a vehicle control device provided in one embodiment of this application. Detailed Implementation

[0078] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0079] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0080] To address the problems of the prior art, embodiments of this application provide a vehicle control method, apparatus, and device. The vehicle control method provided in this application embodiment will be described first below.

[0081] Figure 1 A schematic flowchart of a vehicle control method according to an embodiment of this application is shown. Figure 1 As shown, the vehicle control method provided in this application includes the following steps: S101 to S105.

[0082] S101 acquires at least two preset spatiotemporal partitions corresponding to driving decisions, wherein the spatiotemporal partitions include at least a decision data acquisition period, a decision period, and a decision space range.

[0083] In one or more embodiments of this application, the vehicle control method is applied to an autonomous vehicle, and thus, the vehicle control method can be executed by an electronic device. Of course, the electronic device can be a vehicle control center, computer, mobile phone, tablet computer, server, etc. This application does not limit the specific type of electronic device and it can be configured as needed.

[0084] Typically, when a vehicle is operating autonomously, it needs to plan its driving path. During path planning, the vehicle responds to user input and determines its destination. Then, based on maps and positioning systems, it selects the target route from multiple paths between its current location and the destination. During the journey, the vehicle needs to determine which lane to use based on road conditions and traffic rules. Furthermore, the vehicle also needs to plan driving maneuvers such as acceleration, deceleration, overtaking, and stopping.

[0085] However, the data required for different vehicle planning scenarios often varies, and the timeframes for these plans also differ. For example, determining a target driving route requires planning based on maps and positioning systems, and once the target route is determined, route planning is often no longer needed for a period of time (minutes or hours). Conversely, determining driving actions requires planning based on data collected by sensors, and once the driving action is determined, it often needs to be redefined within a short period (milliseconds to seconds).

[0086] Therefore, to improve efficiency and achieve effective data utilization, this electronic device can determine destination-level driving decisions, road-level driving decisions, lane-level driving decisions, and action-level driving decisions. As the names suggest, destination-level driving decisions involve planning the destination, typically requiring user input data, maps, and other information, with the time interval between two destination-level driving decisions often exceeding one hour. Road-level driving decisions involve planning the target driving route, typically requiring location information and maps, with the time interval between two road-level driving decisions often exceeding 10 minutes. Lane-level driving decisions involve planning the driving lane, typically requiring road condition data collected by sensors and maps, with the time interval between two road-level driving decisions often exceeding one minute. Action-level driving decisions involve planning driving actions, typically requiring road condition data collected by sensors and vehicle data, with the time interval between two action-level driving decisions often less than one minute.

[0087] Specifically, the electronic device can determine the spatiotemporal partitions corresponding to destination-level driving decisions, road-level driving decisions, lane-level driving decisions, and action-level driving decisions based on preset data. These spatiotemporal partitions include the decision data acquisition period, decision period, and decision spatial range, representing the spatial range and data acquisition time range that influence different driving decisions.

[0088] Since destination-level driving decisions and road-level driving decisions are usually determined based on user-input data, the electronic device can determine the spatiotemporal partition of the destination-level driving decision as a first preset value and the spatiotemporal partition of the road-level driving decision as a second preset value.

[0089] Regarding the data acquisition cycle for decision-making, the data required for planning driving instructions corresponding to different driving decisions typically varies. For example, planning driving instructions for action-level driving decisions requires information such as vehicle speed, inertial navigation information, and radar data. Planning driving instructions for destination-level driving decisions requires positioning data and maps. Since this data is usually acquired based on sensors, different driving decisions require different sensors.

[0090] Furthermore, planning a driving decision may require various data sets. For example, planning the driving command corresponding to an action-level driving decision requires information such as driving speed, inertial navigation information, and radar data. Therefore, each driving decision may correspond to one or more sensors. Typically, different sensors have different data acquisition periods. For instance, ultrasonic radar typically acquires data at a period of 50ms, while inertial navigation systems typically acquire data at a period of 5ms. Therefore, in order to plan the driving command corresponding to each driving decision based on newly acquired data, this electronic device can determine the decision data acquisition period for each driving decision.

[0091] As shown in Table 1, Table 1 is a sensor data acquisition cycle table provided by one or more embodiments of this application.

[0092] Table 1 Sensor Data Acquisition Cycle Table

[0093]

[0094]

[0095] The data acquisition cycle of the navigation sensor is 0.1s, with a maximum frequency of 200Hz and a minimum acquisition processing time of 5ms. The data acquisition cycle of the lidar sensor is 0.1s, with a maximum frequency of 10000Hz and a minimum acquisition processing time of 0.1ms. The data acquisition cycle of the image sensor is 0.1s, with a maximum frequency of 50Hz and a minimum acquisition processing time of 20ms. The data acquisition cycle of the ultrasonic radar sensor is 0.1s, with a maximum frequency of 20Hz and a minimum acquisition processing time of 50ms. The data acquisition cycle of the control sensor is 0.1s, with a maximum frequency of 100Hz and a minimum acquisition processing time of 10ms. The delay time of the roadside unit is 10ms.

[0096] Therefore, the electronic device can inspect each vehicle sensor and synchronize the time information of each sensor. Since the technology for inspecting sensors and synchronizing their time information is already quite mature in existing technologies, this application will not elaborate on the specific methods for detecting each vehicle sensor or synchronizing their time information.

[0097] This electronic device can determine at least one target vehicle sensor corresponding to each driving decision based on the data required for that decision. It then acquires the data acquisition period for each target vehicle sensor. Finally, the electronic device can determine the longest data acquisition period from the acquired data acquisition periods and set that period as the decision data acquisition period corresponding to that driving decision.

[0098] Regarding the decision cycle, in order to ensure that the driving instructions corresponding to each planned driving decision can be determined based on the real-time collected data, the electronic device can determine the decision cycle of each driving decision to be an integer multiple of the decision data collection cycle of that driving decision.

[0099] Specifically, after electronic devices collect data through sensors, they often need to process the collected data by fusion, filtering and other processes. There may be communication delays between different sensors and the electronic device. The driving instructions corresponding to the planning driving decisions also require a certain amount of time, i.e. decision delay.

[0100] Therefore, for each driving decision, the electronic device can obtain the vehicle information corresponding to that driving decision, including communication delay, decision delay, and data processing time.

[0101] The electronic device can determine whether the sum of the communication delay, the decision delay, and the data processing time is less than the decision data acquisition cycle corresponding to the driving decision. If yes, the decision multiple corresponding to the driving decision is determined to be a first character. If no, the decision multiple corresponding to the driving decision is determined to be a second character. The first character is less than the second character. In one or more embodiments of this application, the first character can be 1.

[0102] Finally, the electronic device can determine the product of the decision factor and the decision data acquisition period as the decision period corresponding to the driving decision.

[0103] Regarding the decision space range, since vehicles typically use sensors to determine the location information of other vehicles within a collection range centered on the vehicle when traveling on a road, in one or more embodiments of this application, the collection range is the range corresponding to a nine-square grid created centered on the vehicle, or the range corresponding to a twenty-five-square grid created centered on the vehicle, or other ranges. Figure 2 As shown, Figure 2 This is a nine-square grid diagram provided for one or more embodiments of this application. The vehicle is located at position 1, with position 9 in front, position 2 behind, position 7 to the left, and position 4 to the right.

[0104] Therefore, in one or more embodiments of this application, the electronic device can determine the decision space range for action-level driving decisions as the spatial range corresponding to a nine-square grid created centered on the vehicle. The width of each square within the nine-square grid is the width of the lane. The length of each square is a third preset character.

[0105] To reduce the probability of the vehicle colliding with other vehicles, the electronic device determines the vehicle's speed based on data collected by the speed sensor. Based on this speed, it then determines the corresponding safe following distance, which is the distance the vehicle would travel in 3 seconds at that speed. The length of each grid cell is then defined as this safe distance.

[0106] This electronic device can determine the decision space range corresponding to lane-level driving decisions based on preset spatial range parameters. Alternatively, when determining that the action-level spatial range corresponds to a nine-grid space created centered on the vehicle, this electronic device can determine the spatial range corresponding to a twenty-five-grid space created centered on the vehicle as the decision space range. Or, when determining that the action-level spatial range corresponds to a twenty-five-grid space created centered on the vehicle, this electronic device can determine the spatial range corresponding to an eighty-one-grid space created centered on the vehicle as the decision space range.

[0107] like Figure 3 As shown, Figure 3 This is a 25-grid diagram provided for one or more embodiments of this application. The vehicle is located at position 25, with positions 1 and 9 in front of it, positions 2 and 10 behind it, positions 7 and 22 to its left, and positions 4 and 17 to its right.

[0108] Using the above method, the electronic device can determine the spatiotemporal partitions corresponding to different driving decisions, such as lane-level driving decisions and action-level driving decisions, and then plan driving instructions corresponding to each driving decision based on each spatiotemporal partition.

[0109] S102: For each driving decision, when the decision cycle corresponding to the driving decision is reached, obtain the driving data determined within the decision data collection cycle corresponding to the completed driving decision.

[0110] In one or more embodiments of this application, the electronic device obtains driving data corresponding to each driving decision after determining the spatiotemporal partition corresponding to each driving decision.

[0111] Specifically, firstly, for each driving decision, when determining the decision cycle corresponding to the driving data, the electronic device acquires sensor data collected by the vehicle sensor within the completed decision data acquisition cycle corresponding to that driving decision, which has the shortest time interval to the current moment. In one or more embodiments of this application, the vehicle sensor is the target vehicle sensor corresponding to that driving decision. For example, if lane-level driving decision planning requires data from a roadside unit sensor, then the roadside unit sensor is the target vehicle sensor for that lane-level driving decision.

[0112] Secondly, the electronic device can, for each vehicle sensor, use a linear interpolation algorithm to fit the sensor data collected by that sensor during the decision data acquisition period to determine a fitted data curve. Then, from this fitted data curve, the fitted sensor data corresponding to the current moment can be determined.

[0113] Finally, the fitted sensor data corresponding to at least one vehicle sensor is subjected to data fusion processing to obtain processed data. This processed data is then identified as driving data.

[0114] Using the above method, the electronic device can determine the driving data corresponding to each driving decision, and then plan the driving instructions corresponding to each driving decision based on the driving data.

[0115] S103: Determine the decision driving data corresponding to the decision space range of the driving decision from the driving data.

[0116] In one or more embodiments of this application, for each driving decision, the driving data corresponding to the driving decision may include data outside the decision space range corresponding to the driving decision. For example, the high-precision map acquired by the map sensor may cover a large area. Therefore, in order to reduce computational complexity and improve efficiency, the electronic device can determine the decision driving data corresponding to the decision space range of the driving decision from the driving data.

[0117] Specifically, the electronic device can, for each driving decision, determine the driving data corresponding to the decision space range within the driving data as the decision driving data, and delete other driving data, based on the driving data corresponding to the decision driving space range and the driving data corresponding to the decision driving space range. Since determining the data of a small space from the data of a large space range is already a relatively mature technology in existing technology, this application will not elaborate on how to determine the decision driving data.

[0118] Using the above method, the electronic device can determine decision driving data based on the driving data corresponding to each driving decision, so as to plan the driving instructions corresponding to each driving decision.

[0119] S104: Based on the decision driving data, plan the driving instructions corresponding to the driving decision.

[0120] In one or more embodiments of this application, the electronic device can plan driving instructions corresponding to each driving decision after determining the decision driving data corresponding to each driving decision.

[0121] Specifically, the electronic device can plan driving instructions corresponding to each driving decision based on the corresponding driving data. Since planning driving instructions based on collected data is a relatively mature technology, this application will not elaborate on the specifics of how the driving instructions are planned.

[0122] Because this electronic device plans driving instructions separately for each driving decision, conflicts may arise between instructions for different decisions. For example, when a vehicle is traveling and there are roads ahead with both left and right turns, the path-level driving decision should dictate that the vehicle should travel in the right-turn lane. However, when the vehicle is not turning, the lane-level driving decision instructs the vehicle to travel in the left lane (left-turn lane). At an intersection, if the vehicle is in the left-turn lane, it needs to follow the lane markings to turn left, resulting in the vehicle traveling in the left lane, contradicting the lane-level driving decision instruction.

[0123] Therefore, in one or more embodiments of this application, when planning driving instructions corresponding to each driving decision, the electronic device can obtain the destination-level driving decision, road-level driving decision, and lane-level driving decision that are being executed.

[0124] When planning a road-level driving decision, the electronic device can plan a road-level driving decision that does not conflict with the destination-level driving decision, based on the decision driving data corresponding to the road-level driving decision and the destination-level driving decision. When planning a lane-level driving decision, the electronic device can plan a lane-level driving decision that does not conflict with the road-level driving decision, based on the decision driving data corresponding to the lane-level driving decision and the road-level driving decision. When planning an action-level driving decision, the electronic device can plan an action-level driving decision that does not conflict with the lane-level driving decision, based on the decision driving data corresponding to the action-level driving decision and the lane-level driving decision.

[0125] In one or more embodiments of this application, to improve data utilization and efficiency, when the electronic device determines that the driving decision is a lane-level driving decision, it can determine the predicted driving path of the driving instruction corresponding to the currently executed lane-level driving decision. Then, based on the distance data collected by vehicle sensors and the predicted driving distance of the predicted driving path, the untraveled portion of the predicted driving distance is determined as the remaining driving distance. When the remaining driving distance is determined to be greater than a preset distance threshold, the driving instruction is determined to be a re-planned driving instruction. When the remaining driving distance is determined to be less than or equal to the distance threshold, the driving instruction corresponding to the lane-level driving decision is re-planned based on the decision driving data corresponding to the lane-level driving decision.

[0126] Using the above method, the electronic device can plan driving instructions corresponding to each driving decision, thereby controlling the vehicle's movement.

[0127] S105: Control the vehicle's movement according to this driving instruction.

[0128] Specifically, the electronic device can control the vehicle to drive according to the determined driving instructions. Since the technology of controlling the vehicle to drive according to driving instructions is relatively mature in the existing technology, this application will not elaborate on how to control the vehicle to drive according to the driving instructions.

[0129] Because the vehicle has significant inertia during operation, errors may occur when controlling its movement; that is, the vehicle's actual trajectory may deviate from the trajectory corresponding to the driving command. Therefore, the electronic device can re-plan the driving command.

[0130] Specifically, after the electronic device determines the driving command, it can determine the predicted driving path corresponding to the driving command. When controlling the vehicle to drive according to the driving command, the electronic device can acquire the vehicle's driving data, which includes the vehicle's driving trajectory and the time when the vehicle arrives at each point within the driving trajectory.

[0131] The electronic device can determine the spatiotemporal deviation between the driving trajectory and the predicted driving trajectory based on the driving data and the predicted driving path. The spatiotemporal deviation includes both time deviation and spatial deviation.

[0132] When the spatiotemporal deviation value is determined to be greater than a preset spatiotemporal error threshold, the electronic device can re-plan the driving instructions corresponding to the predicted driving trajectory based on the predicted driving trajectory and the driving data, and control the vehicle to drive according to the re-planned driving instructions. That is, when the time deviation value is determined to be greater than a preset time error threshold, the electronic device can re-plan the driving instructions corresponding to the predicted driving trajectory based on the predicted driving trajectory and the driving data, and control the vehicle to drive according to the re-planned driving instructions. When the spatial deviation value is determined to be greater than a preset spatial error threshold, the electronic device can re-plan the driving instructions corresponding to the predicted driving trajectory based on the predicted driving trajectory and the driving data, and control the vehicle to drive according to the re-planned driving instructions.

[0133] To improve vehicle safety during operation, when the electronic device determines that the spatiotemporal deviation value exceeds a spatiotemporal error threshold, it can determine the likelihood of a collision based on the driving data and the predicted driving path, specifically whether an object is present in the same location as the vehicle at the same moment. If so, and the estimated collision time is greater than or equal to 3 seconds, the electronic device can replan and execute the driving instructions. If the estimated collision time is less than 3 seconds, the electronic device can follow emergency braking requirements, plan and execute emergency braking instructions. Otherwise, the driving instructions continue to be executed.

[0134] The driving data includes data collected by speed sensors and inertial navigation sensors. The data collection period for this driving data is shorter than the data collection period for the decision-making data corresponding to this action-level driving decision.

[0135] Using the above method, the electronic device can execute driving instructions corresponding to each driving decision to control the vehicle's movement.

[0136] The above describes the specific implementation of the vehicle control method provided in this application. Through these embodiments, the vehicle can be controlled to drive according to a determined driving instruction. This driving instruction is planned based on driving data collected within the decision data collection period corresponding to the driving decision, achieving effective utilization of data collected within each decision data collection period. Furthermore, since different driving decisions correspond to different spatiotemporal partitions, when planning a driving decision, planning can be performed solely based on data corresponding to the spatiotemporal partition of that driving decision, thus improving efficiency.

[0137] To improve the safety of the vehicle, as another implementation of this application, this application also provides another implementation of the vehicle control method, as detailed in the following embodiments.

[0138] Please see Figure 4 Another implementation of the vehicle control method provided in this application includes the following steps: steps S201 to S208.

[0139] S201: Obtain at least two preset spatiotemporal partitions corresponding to driving decisions, wherein the spatiotemporal partitions include at least the decision data acquisition period, the decision period, and the decision space range.

[0140] S202: For each driving decision, when the decision cycle corresponding to the driving decision is reached, obtain the driving data determined within the decision data collection cycle corresponding to the completed driving decision.

[0141] S203: Based on the driving data corresponding to the driving decision and the decision data collection cycle, update the decision cycle and decision space range of the spatiotemporal partition corresponding to the driving decision.

[0142] In one or more embodiments of this application, after determining the driving data, the electronic device can update the decision cycle and decision space range corresponding to each driving decision.

[0143] Specifically, for each driving decision's corresponding decision cycle, the electronic device can determine the primary and secondary influence locations based on the decision space range corresponding to that driving decision. For example, Figure 2 As shown, when the decision space of the action-level driving decision is determined to be a nine-square grid centered on the vehicle, the electronic device can determine positions 1, 4, and 7 as primary influence positions, and positions 3 and 6 as secondary influence positions.

[0144] Based on the driving data, determine whether there are any influencing vehicles at the primary and secondary impact locations. If it is determined that there are influencing vehicles at the primary impact location, the decision multiplier is set to the third character. If it is determined that there are no influencing vehicles at the primary impact location, but there are influencing vehicles at the secondary impact location, the decision multiplier is set to the fourth character.

[0145] When neither the primary nor secondary influence positions of the decision space for action-level and lane-level driving decisions affect the vehicle, the decision multiplier is determined to be either the first or second character. The third character is greater than the fourth character, and the fourth character is greater than the second character. The updated decision period is then determined by multiplying this decision multiplier by the decision data collection period for that driving decision.

[0146] Regarding the decision-making space range, the electronic device can determine the driving speed based on the driving data. Then, in response to user input, it determines a safety factor. Based on the braking distance corresponding to the driving speed in a preset braking distance standard and the safety factor, the product of the braking distance and the safety factor is determined as the vehicle's spatial length range. This braking distance standard can be a national standard or a braking distance standard determined in response to user settings. This application does not limit how the braking distance standard is specifically determined and can be set as needed.

[0147] The decision space range is updated based on the vehicle space length range. This decision space range consists of multiple vehicle space ranges, each being the product of the vehicle space length range and the lane width range. For example, when the decision space range is determined to be a nine-grid layout, the length of each grid cell is defined as the vehicle space length range.

[0148] S204: Determine the decision driving data corresponding to the decision space range of the driving decision from the driving data.

[0149] S205: Based on the decision driving data, plan the driving instructions corresponding to the driving decision.

[0150] S206: Control the vehicle's movement according to this driving instruction.

[0151] S201 to S202 are the same as S101 to S102 in the above embodiment, and S204 to S206 are the same as S103 to S105 in the above embodiment. For the sake of brevity, they will not be described in detail here.

[0152] In the above embodiments, the electronic device can update the decision cycle and decision space range corresponding to each driving decision, thereby improving vehicle safety.

[0153] First see Figure 5 The vehicle control device provided in this application embodiment includes the following units:

[0154] Acquisition unit 801 is used to acquire at least two preset spatiotemporal partitions corresponding to driving decisions, wherein the spatiotemporal partitions include at least a decision data acquisition period, a decision period, and a decision space range.

[0155] The acquisition unit 802 is used to acquire, for each driving decision, the driving data determined within the completed decision data acquisition period corresponding to that driving decision when the decision period corresponding to that driving decision is reached.

[0156] The determining unit 803 is used to determine, from the driving data, decision driving data corresponding to the decision space range of the driving decision.

[0157] Planning unit 804 is used to plan the driving instructions corresponding to the driving decision based on the decision driving data.

[0158] Control unit 805 is used to control the vehicle's movement according to the driving command.

[0159] Through the above embodiments, the vehicle control device can control the vehicle to drive according to the determined driving instructions. These driving instructions are planned based on driving data collected within the decision data collection period corresponding to the driving decision, achieving effective utilization of data collected within each decision data collection period. Furthermore, since different driving decisions correspond to different spatiotemporal partitions, when planning a certain driving decision, planning can be performed only based on the data corresponding to the spatiotemporal partition of that driving decision, thus improving efficiency.

[0160] As one implementation of this application, in order to improve data utilization and efficiency, the above-mentioned device may further include: an acquisition subunit 8011.

[0161] The acquisition subunit 8011 is used to determine at least one target vehicle sensor corresponding to each driving decision, acquire the data acquisition period of the at least one target vehicle sensor respectively, and determine the largest data acquisition period among the at least one data acquisition period as the decision data acquisition period.

[0162] As one implementation of this application, in order to improve data utilization and efficiency, the above-mentioned device may further include: an acquisition subunit 8012.

[0163] The acquisition subunit 8012 is used to acquire vehicle information, which includes at least communication delay, decision delay, and data processing time. When it is determined that the sum of the communication delay, decision delay, and data processing time is less than the unified data acquisition period, a decision multiple is determined as a first character. When it is determined that the sum of the communication delay, decision delay, and data processing time is greater than or equal to the unified data acquisition period, a decision multiple is determined as a second character, where the second character is greater than the first character. For each driving decision, the product of the decision multiple and the decision data acquisition period corresponding to the driving decision is determined as the decision period for that driving decision.

[0164] As one implementation of this application, in order to improve data utilization and efficiency, the above-mentioned device may further include: a data acquisition subunit 8021.

[0165] The acquisition subunit 8021 is used to acquire sensor data collected by vehicle sensors within the decision data acquisition period corresponding to the completed driving decision with the smallest time interval to the current moment. Based on the sensor data collected by vehicle sensors within the unified data acquisition period, the sensor data is fitted using a linear interpolation algorithm to obtain fitted sensor data corresponding to the current moment. The obtained fitted sensor data is then determined as driving data.

[0166] As one implementation of this application, in order to improve data utilization and efficiency, the above-mentioned device may further include: a data acquisition subunit 8022.

[0167] The acquisition subunit 8022 is used to update the decision period and decision space range of the spatiotemporal partition corresponding to the driving decision based on the driving data and decision data acquisition period corresponding to the driving decision.

[0168] As one implementation of this application, in order to improve data utilization and efficiency, the above-mentioned device may further include: a data acquisition subunit 8023.

[0169] The acquisition subunit 8023 is used to determine the primary and secondary influence positions within the decision space corresponding to the driving decision. When the driving data determines that a vehicle is influencing the primary influence position within the decision space, the decision multiple is determined to be the third character. When the driving data determines that a vehicle is not influencing the primary influence position within the decision space, but a vehicle is influencing the secondary influence position within the decision space, the decision multiple is determined to be the fourth character. When the driving data determines that neither a vehicle is influencing the primary nor a vehicle is influencing the secondary influence position within the decision space, the decision multiple is determined to be the first or second character. The product of the decision multiple and the decision data acquisition period is used to determine the updated decision period.

[0170] As one implementation of this application, in order to improve data utilization and efficiency, the above-mentioned device may further include: a data acquisition subunit 8024.

[0171] The acquisition subunit 8024 is used to determine the driving speed based on the driving data corresponding to the driving decision, determine the braking distance corresponding to the driving speed in the preset braking distance standard as the vehicle space length range, and update the decision space range based on the vehicle space length range. The decision space range is composed of multiple vehicle space ranges, and each vehicle space range is the product of the vehicle space length range and the lane width range.

[0172] As one implementation of this application, in order to improve data utilization and efficiency, the above-mentioned device may further include: a data acquisition subunit 8025.

[0173] The acquisition subunit 8025 is used to respond to the user's operation, determine the safety factor, and determine the product of the safety factor and the braking distance corresponding to the driving speed in the preset braking distance standard as the vehicle space length range.

[0174] As one implementation of this application, in order to improve data utilization and efficiency, the above-mentioned device may further include: a planning subunit 8041.

[0175] The planning subunit 8041 is used to determine the untraveled portion of the predicted driving distance of the driving instruction based on the decision driving data and the driving instruction being executed when the driving decision is a lane-level driving decision. When the untraveled distance is determined to be greater than a preset distance threshold, the driving instruction is determined to be a replanned driving instruction. When the untraveled distance is determined to be less than or equal to the distance threshold, the driving instruction is replanned and executed based on the decision driving data corresponding to the lane-level driving decision.

[0176] As one implementation of this application, in order to improve data utilization and efficiency, the above-mentioned device may further include a control subunit 8051.

[0177] The control subunit 8051 is used to acquire the vehicle's driving data, determine the predicted driving path corresponding to the driving command, and when it is determined, based on the driving data and the predicted driving path, that there is an object at the same position as the vehicle at the same time, replan and execute the driving command.

[0178] As one implementation of this application, in order to improve data utilization and efficiency, the above-mentioned device may further include a control subunit 8052.

[0179] The control subunit 8052 is used to acquire the vehicle's driving data, and based on the driving data and the driving command, determine the spatiotemporal deviation value between the vehicle's driving trajectory during the driving process and the predicted driving trajectory corresponding to the driving command. The spatiotemporal deviation value includes a time deviation value and a spatial deviation value. When it is determined that the spatiotemporal deviation value is greater than a preset spatiotemporal error threshold, the control subunit 8052 re-plans the driving command corresponding to the predicted driving trajectory based on the predicted driving trajectory, and controls the vehicle to drive according to the re-planned driving command.

[0180] As one implementation of this application, in order to improve data utilization and efficiency, the above-mentioned device may further include a control subunit 8053.

[0181] The control subunit 8053 is used to acquire the destination-level driving decision, road-level driving decision, and lane-level driving decision being executed, respectively. The driving decision includes destination-level driving decision, road-level driving decision, lane-level driving decision, and action-level driving decision. When planning the road-level driving decision, a road-level driving decision that does not conflict with the destination-level driving decision is planned based on the decision driving data corresponding to the road-level driving decision and the destination-level driving decision. When planning the lane-level driving decision, a lane-level driving decision that does not conflict with the road-level driving decision is planned based on the decision driving data corresponding to the lane-level driving decision and the road-level driving decision. When planning the action-level driving decision, an action-level driving decision that does not conflict with the lane-level driving decision is planned based on the decision driving data corresponding to the action-level driving decision and the lane-level driving decision.

[0182] Figure 6 A schematic diagram of the hardware structure of the vehicle control device provided in an embodiment of this application is shown.

[0183] The vehicle control device may include a processor 901 and a memory 902 storing computer program instructions.

[0184] Specifically, the processor 901 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0185] Memory 902 may include mass storage for data or instructions. For example, and not limitingly, memory 902 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 902 may include removable or non-removable (or fixed) media. Where appropriate, memory 902 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 902 is non-volatile solid-state memory.

[0186] In a particular embodiment, memory 902 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.

[0187] The processor 901 implements any of the vehicle control methods described in the above embodiments by reading and executing computer program instructions stored in the memory 902.

[0188] In one example, the vehicle control device may also include a communication interface 903 and a bus 910. Wherein, as... Figure 6 As shown, the processor 901, memory 902, and communication interface 903 are connected through bus 910 and complete communication with each other.

[0189] The communication interface 903 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0190] Bus 910 includes hardware, software, or both, that couples components of a vehicle control device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 910 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0191] The vehicle control device can execute the vehicle control method in this application embodiment based on currently blocked spam text messages and text messages reported by users, thereby achieving a combination of... Figure 1 and Figure 5 The vehicle control method and apparatus described.

[0192] Furthermore, in conjunction with the vehicle control methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions, which, when executed by a processor, implement any of the vehicle control methods in the above embodiments.

[0193] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0194] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0195] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0196] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0197] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A vehicle control method, characterized in that, include: Obtain the spatiotemporal partitions corresponding to at least two preset driving decisions, wherein the spatiotemporal partitions include at least the decision data acquisition period, the decision period, and the decision space range. For each driving decision, when the corresponding decision cycle is reached, the driving data determined within the completed decision data collection cycle for that driving decision is acquired. From the driving data, determine the decision driving data corresponding to the decision space range of the driving decision. Based on the driving decision data, plan the driving instructions corresponding to the driving decision. Follow the driving instructions to control the vehicle's movement; The data collection cycle for decision-making includes: For each driving decision, at least one target vehicle sensor corresponding to that driving decision is identified. The data acquisition period of each of the at least one target vehicle sensor is obtained. The largest data acquisition cycle among at least one data acquisition cycle is determined as the decision data acquisition cycle; Acquire the driving data determined within the decision data collection period corresponding to the completed driving decision, including: Obtain the sensor data collected by the vehicle sensors within the decision data collection period corresponding to the completed driving decision with the smallest time interval to the current moment. Based on the sensor data collected by the vehicle sensors within the decision data acquisition cycle corresponding to the driving decision that has ended with the shortest time interval to the current moment, the sensor data is fitted using a linear interpolation algorithm to obtain the fitted sensor data corresponding to the current moment. The obtained fitted sensor data is then identified as driving data. Based on the decision-making driving data, plan the driving instructions corresponding to the driving decision, including: When the driving decision is a lane-level driving decision, based on the decision driving data and the driving command being executed, the remaining distance to be traveled in the untraveled portion of the predicted driving distance of the driving command is determined. When it is determined that the distance to be traveled is greater than a preset distance threshold, the driving instruction is determined as a re-planned driving instruction. When it is determined that the distance to be traveled is less than or equal to the distance threshold, the driving instructions are replanned and executed based on the decision driving data corresponding to the lane-level driving decision.

2. The method according to claim 1, characterized in that, Obtain the preset decision-making cycle, including, Obtain vehicle information, which includes at least communication latency, decision latency, and data processing time. When the sum of the communication delay, the decision delay, and the data processing time is less than the decision data collection cycle corresponding to the driving decision, the decision multiplier is determined to be the first character. When the sum of the communication delay, the decision delay, and the data processing time is greater than or equal to the decision data acquisition cycle corresponding to the driving decision, the decision multiplier is determined to be the second character, where the second character is greater than the first character. For each driving decision, the decision period is determined by multiplying the decision multiplier by the decision data collection period corresponding to that driving decision.

3. The method according to claim 1, characterized in that, After acquiring the driving data determined within the decision data collection period corresponding to the completed driving decision, including: Based on the driving data corresponding to the driving decision and the decision data collection cycle, update the decision cycle and decision space range of the spatiotemporal partition corresponding to the driving decision.

4. The method according to claim 3, characterized in that, Based on the driving data corresponding to the driving decision and the decision data collection period, update the decision period corresponding to the driving decision, including: Determine the primary and secondary influence locations within the decision space corresponding to this driving decision. When, based on the driving data, it is determined that an influencing vehicle exists at a primary influence location within the decision space, the decision multiplier is determined to be the third character. When, based on the driving data, it is determined that there are no influencing vehicles at the primary influence location within the decision space, but there are influencing vehicles at the secondary influence location within the decision space, the decision multiplier is determined to be the fourth character. When, based on the driving data, it is determined that neither the primary nor secondary influence positions within the decision space contain any influencing vehicles, the decision multiplier is determined to be either the first character or the second character. The product of the decision factor and the decision data collection period is used to determine the updated decision period.

5. The method according to claim 3, characterized in that, Based on the driving data corresponding to the driving decision, update the decision space range corresponding to the driving decision, including: Based on the driving data corresponding to this driving decision, determine the driving speed. The braking distance corresponding to the driving speed within a preset braking distance standard is determined as the vehicle space length range. The decision space range is updated based on the vehicle space length range. The decision space range is composed of multiple vehicle space ranges, each of which is the product of the vehicle space length range and the lane width range.

6. The method according to claim 5, characterized in that, The braking distance corresponding to the driving speed in the preset braking distance standard is determined as the vehicle space length range, including: In response to user actions, determine the safety level. The product of the safety factor and the braking distance corresponding to the driving speed in the preset braking distance standard is determined as the vehicle space length range.

7. The method according to claim 1, characterized in that, Control the vehicle's movement according to the driving instructions, including: Obtain the vehicle's driving data. Determine the predicted driving path corresponding to the driving command. When it is determined, based on the driving data and the predicted driving path, that an object exists at the same location as the vehicle at the same time, the driving command is replanned and executed.

8. The method according to claim 1, characterized in that, After controlling the vehicle to drive according to the driving command, the method further includes: Obtain the vehicle's driving data. Based on the driving data and the driving instructions, the spatiotemporal deviation value between the vehicle's driving trajectory during the driving process and the predicted driving trajectory corresponding to the driving instructions is determined. The spatiotemporal deviation value includes a time deviation value and a spatial deviation value. When the spatiotemporal deviation value is determined to be greater than a preset spatiotemporal error threshold, the driving instructions corresponding to the predicted driving trajectory are replanned based on the predicted driving trajectory. Control the vehicle to drive according to the re-planned driving instructions.

9. The method according to claim 1, characterized in that, Based on the decision-making driving data, plan the driving instructions corresponding to the driving decision, including: The system acquires the currently executing destination-level driving decisions, road-level driving decisions, and lane-level driving decisions, including destination-level driving decisions, road-level driving decisions, lane-level driving decisions, and action-level driving decisions. When planning the road-level driving decisions, based on the decision driving data corresponding to the road-level driving decisions and the destination-level driving decisions, road-level driving decisions that do not conflict with the destination-level driving decisions are planned. When planning the lane-level driving decision, based on the decision driving data corresponding to the lane-level driving decision and the road-level driving decision, a lane-level driving decision that does not conflict with the road-level driving decision is planned. When planning the action-level driving decision, an action-level driving decision that does not conflict with the lane-level driving decision is planned based on the decision driving data corresponding to the action-level driving decision and the lane-level driving decision.

10. A vehicle control device, characterized in that, The device includes: The acquisition unit is used to acquire at least two preset spatiotemporal partitions corresponding to driving decisions, wherein the spatiotemporal partitions include at least a decision data acquisition period, a decision period, and a decision space range. The data acquisition unit is used to acquire, for each driving decision, the driving data determined within the completed decision data acquisition period corresponding to that driving decision when the corresponding decision period arrives. The determining unit is used to determine, from the driving data, decision driving data corresponding to the decision space range of the driving decision. The planning unit is used to plan the driving instructions corresponding to the driving decision based on the driving decision data. The control unit is used to control the vehicle's movement according to the driving command; The device further includes: an acquisition subunit, configured to determine at least one target vehicle sensor corresponding to each driving decision, acquire the data acquisition cycle of the at least one target vehicle sensor respectively, and determine the largest data acquisition cycle among the at least one data acquisition cycles as the decision data acquisition cycle; The acquisition subunit is used to acquire sensor data collected by vehicle sensors within the decision data acquisition period corresponding to the driving decision that has ended with the shortest time interval to the current time. Based on the sensor data collected by vehicle sensors within the decision data acquisition period corresponding to the driving decision that has ended with the shortest time interval to the current time, the sensor data is fitted using a linear interpolation algorithm to obtain fitted sensor data corresponding to the current time. The obtained fitted sensor data is then determined as driving data. The planning subunit is used to determine the untraveled portion of the predicted driving distance of the driving instruction based on the decision driving data and the driving instruction being executed when the driving decision is a lane-level driving decision. When the untraveled distance is determined to be greater than a preset distance threshold, the driving instruction is determined to be a replanned driving instruction. When the untraveled distance is determined to be less than or equal to the distance threshold, the driving instruction is replanned and executed based on the decision driving data corresponding to the lane-level driving decision.

Images