Vehicle control method, device, vehicle and storage medium

Abstract

The present application relates to the field of autonomous driving technology, and more particularly to a vehicle control method, device, vehicle, and storage medium, wherein the method comprises: obtaining external environmental information; performing planning based on the external environmental information using a first preset algorithm, a second preset algorithm, and a third preset algorithm to generate a first planning boundary, a second planning boundary, and safety boundary information; generating first control information based on the first planning boundary and generating second control information based on the second planning boundary; controlling the vehicle based on the first control information when the first control information matches the second control information; determining a target boundary based on the first planning boundary, the second planning boundary, and the safety boundary information when the first control information does not match the second control information; and generating a control instruction based on the target boundary to control the vehicle. Thus, safety issues caused by vehicle system failures are resolved, and the continuity and user experience of intelligent driving are improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a vehicle control method, device, vehicle, and storage medium. Background Art

[0002] Intelligent vehicle technology holds enormous potential for reducing traffic accidents, alleviating congestion, and improving road and vehicle utilization, making it a hotly contested area for many companies. Intelligent connected vehicles (ICVs) are equipped with advanced onboard sensors, controllers, actuators, and other devices, integrating modern communications and networking technologies to seamlessly connect internal, external, and inter-vehicle networks. These vehicles feature control functions such as information sharing, complex environmental perception, intelligent decision-making, and automated collaboration. These intelligent mobility systems, combined with smart highways and auxiliary infrastructure, promise efficient, safe, comfortable, and energy-efficient driving. Autonomous driving, with the system largely or almost entirely controlling the vehicle, makes it crucial to avoid safety issues caused by system failures.

[0003] In related technologies, autonomous driving systems provide a redundancy mechanism to prevent threads from blocking the CPU (central processing unit) system, or provide a kinetic redundant software architecture to adapt to different application scenarios.

[0004] However, the redundancy mechanism of the relevant technology center does not take into account the safety mechanism in the event of a single point failure of the MCU (Microcontroller Unit), and the kinetic redundancy software architecture provided in the relevant technology does not consider how to ensure the correctness of the chip A / B calculation results. Moreover, the current autonomous driving domain controller has not yet achieved fully autonomous driving above level L4. When the vehicle is at level L1-L3 autonomous driving, the driver must still remain vigilant and take back control of the vehicle at any time. Summary of the Invention

[0005] The present application provides a vehicle control method, device, vehicle and storage medium, which solves safety and other problems caused by vehicle system failures and improves the continuity and experience of users' intelligent driving.

[0006] A first aspect of the present application provides a vehicle control method, comprising the following steps: obtaining external environmental information; performing planning according to the external environmental information through a first preset algorithm, a second preset algorithm, and a third preset algorithm, respectively, to generate a first planning boundary, a second planning boundary, and safety boundary information; generating first control information according to the first planning boundary and generating second control information according to the second planning boundary; controlling the vehicle according to the first control information when the first control information matches the second control information; or determining a target boundary according to the first planning boundary, the second planning boundary, and the safety boundary information when the first control information does not match the second control information; and generating a control instruction according to the target boundary to control the vehicle.

[0007] Based on the above technical means, safety and other issues caused by vehicle system failures are solved, and the continuity and experience of users' intelligent driving are improved.

[0008] Furthermore, the external environment information includes sensor collection information and high-precision map information, and the planning is performed according to the external environment information through a first preset algorithm, a second preset algorithm, and a third preset algorithm, respectively, to generate a first planning boundary, a second planning boundary, and safety boundary information, including: fusing the high-precision map information and the sensor collection information to generate target information; generating the first planning boundary and the second planning boundary according to the target information through the first preset algorithm and the second preset algorithm respectively; generating the safety boundary information according to the sensor collection information or the target information through the third preset algorithm.

[0009] According to the above technical means, the safety range is determined based on the generated safety boundary information, which ensures the safety of the driver and reduces the computing power requirements.

[0010] Furthermore, the fusion processing of the high-precision map information and the external environment information to generate target information includes: respectively processing the sensor collection information and the high-precision map information to obtain first scene perception information and second scene perception information; and fusing the first scene perception information and the second scene perception information to generate the target information.

[0011] According to the above technical means, the calculated planning boundary is made more accurate based on the target information generated by fusion.

[0012] Furthermore, the generating of the first planning boundary and the second planning boundary according to the target information by the first preset algorithm and the second preset algorithm respectively includes: planning the lateral and longitudinal control targets of the vehicle according to the target information; calculating the planned driving route of the vehicle according to the lateral and longitudinal control targets; generating the first planned route according to the driving state of the vehicle and the planned driving route by the first preset algorithm, and generating the second planned route according to the driving state of the vehicle and the planned driving route by the second preset algorithm.

[0013] According to the above technical means, the problem of misjudgment of the monitoring system is solved based on the two generated planning routes.

[0014] Furthermore, determining the target boundary based on the first planning boundary, the second planning boundary and the security boundary information includes: judging whether the first planning boundary and the second planning boundary are located within the security boundary information; when the first planning boundary is located within the security boundary information and the second planning boundary is not located within the security boundary information, using the first planning boundary as the target boundary; or when the second planning boundary is located within the security boundary information and the first planning boundary is not located within the security boundary information, using the second planning boundary as the target boundary; or when the first planning boundary and the second planning boundary are not located within the security boundary information, generating the target boundary according to the security boundary information.

[0015] Based on the above technical means, the multi-channel voting mechanism selects the target boundaries that meet the requirements by comparing the results of multiple parties, thereby improving the reliability of the system output results.

[0016] Furthermore, the vehicle control method also includes: obtaining fault information of the vehicle; and adjusting the automatic driving mode of the vehicle according to the fault information.

[0017] According to the above technical means, the vehicle's automatic driving mode is adjusted through fault information to improve the intelligence of vehicle driving.

[0018] Furthermore, adjusting the automatic driving mode of the vehicle according to the fault information includes: determining a fault attribute according to the fault information, the fault attribute including a critical fault and a non-critical fault; and when the fault attribute is a non-critical fault, adjusting the automatic driving mode of the vehicle after running for a preset time.

[0019] According to the above technical means, by setting the preset operation time of the self-driving system, the redundancy mechanism will not be switched immediately when the vehicle fails, thereby improving the consistency of autonomous driving.

[0020] Furthermore, the first preset algorithm and the second preset algorithm include heterogeneous algorithms, and the third preset algorithm includes a neural network algorithm.

[0021] Based on the above technical means, heterogeneous algorithms can simultaneously support a single independent computer in SIMD and MIMD modes, or use a group of independent computers interconnected by a high-speed network to complete computing tasks. The neural network algorithm can learn the driver's operating habits under different road conditions and continuously calculate to form a safety envelope.

[0022] A second aspect of the present application provides a vehicle control device, including: an acquisition module for acquiring external environment information; a planning module for planning according to the external environment information through a first preset algorithm, a second preset algorithm, and a third preset algorithm, respectively, to generate a first planning boundary, a second planning boundary, and safety boundary information; a generation module for generating first control information according to the first planning boundary and generating second control information according to the second planning boundary; a first control module for controlling the vehicle according to the first control information when the first control information matches the second control information; a determination module for determining a target boundary according to the first planning boundary, the second planning boundary, and the safety boundary information when the first control information does not match the second control information; and a second control module for generating a control instruction according to the target boundary to control the vehicle.

[0023] The third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle control method as described in the above embodiment.

[0024] Furthermore, the processor includes a first processor, a second processor, a third processor and a fourth processor, the first processor is used to obtain external environment information, and plan and generate a first planning boundary based on the external environment information through a first preset algorithm, the second processor is used to obtain external environment information, and plan and generate a second planning boundary based on the external environment information through a second preset algorithm, the third processor is used to generate first control information based on the first planning boundary, and the fourth processor is used to generate second control information based on the second planning boundary; the third processor or the fourth processor is also used to control the vehicle according to the first control information when the first control information matches the second control information; or, when the first control information does not match the second control information, determine the target boundary according to the first planning boundary, the second planning boundary and the safety boundary information, and generate control instructions according to the target boundary to control the vehicle.

[0025] The fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored. The program is executed by a processor to implement the vehicle control method as described in the above embodiment.

[0026] Therefore, the present application obtains external environmental information, performs planning based on the first preset algorithm, the second preset algorithm, and the third preset algorithm according to the external environmental information, generates a first planning boundary, a second planning boundary, and safety boundary information, generates first control information according to the first planning boundary, and generates second control information according to the second planning boundary, controls the vehicle according to the first control information when the first control information matches the second control information, and determines the target boundary according to the first planning boundary, the second planning boundary, and the safety boundary information when the first control information does not match the second control information, and generates control instructions according to the target boundary to control the vehicle. Thus, the safety and other problems caused by vehicle system failures are solved, and the L4-L5 fully automatic driving requirements are met. The takeover tasks when the self-driving system fails are completed by the self-driving system without the driver's participation, which improves the continuity and experience of the user's intelligent driving and reduces the time and manpower costs in development and subsequent maintenance and upgrades.

[0027] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0029] Figure 1 A flow chart of a vehicle control method provided according to an embodiment of the present application;

[0030] Figure 2 1 is a block diagram of the logic of a vehicle control system according to one embodiment of the present application;

[0031] Figure 3 1 is a schematic diagram of the architecture of an Advanced Driving System (ADS) according to one embodiment of the present application;

[0032] Figure 4 is a flow chart of a vehicle control method according to one embodiment of the present application;

[0033] Figure 5 is a block diagram of a vehicle control device according to an embodiment of the present application;

[0034] Figure 6 Schematic diagram of the structure of a vehicle according to an embodiment of the present application.

[0035] Explanation of the reference numerals: 10 - vehicle control device, 100 - acquisition module, 200 - planning module, 300 - generation module, 400 - first control module, 500 - determination module, 600 - second control module, 601 - memory, 602 - processor, 603 - communication interface. DETAILED DESCRIPTION

[0036] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0037] The following describes the vehicle control method, device, vehicle and storage medium of the embodiment of the present application with reference to the accompanying drawings. In response to the safety issues caused by vehicle system failures mentioned in the above background technology, the present application provides a vehicle control method, in which external environmental information is obtained, and planning is performed according to the external environmental information through a first preset algorithm, a second preset algorithm and a third preset algorithm to generate a first planning boundary, a second planning boundary and safety boundary information, and a first control information is generated according to the first planning boundary and a second control information is generated according to the second planning boundary. When the first control information matches the second control information, the vehicle is controlled according to the first control information. When the first control information does not match the second control information, the target boundary is determined according to the first planning boundary, the second planning boundary and the safety boundary information, and a control instruction is generated according to the target boundary to control the vehicle. In this way, the safety and other problems caused by vehicle system failures are solved, and the continuity and experience of the user's intelligent driving are improved.

[0038] Specifically, Figure 1 A flow chart of a vehicle control method provided in an embodiment of the present application.

[0039] like Figure 1 As shown, the vehicle control method includes the following steps:

[0040] In step S101, external environment information is acquired.

[0041] It can be understood that the embodiments of the present application collect external environmental information through sensors including lidar and cameras, including vehicle information, pedestrian information, and obstacle information around the vehicle, etc., or collect information such as traffic lights, buildings or lane lines around the vehicle through high-precision maps.

[0042] In step S102, planning is performed according to the external environment information using the first preset algorithm, the second preset algorithm, and the third preset algorithm to generate a first planning boundary, a second planning boundary, and safety boundary information.

[0043] Optionally, in some embodiments, the first preset algorithm and the second preset algorithm include heterogeneous algorithms, and the third preset algorithm includes a neural network algorithm.

[0044] Optionally, in some embodiments, the external environment information includes sensor acquisition information and high-precision map information, and planning is performed according to the external environment information through a first preset algorithm, a second preset algorithm, and a third preset algorithm, respectively, to generate a first planning boundary, a second planning boundary, and safety boundary information, including: fusing the high-precision map information and the sensor acquisition information to generate target information; generating a first planning boundary and a second planning boundary according to the target information through the first preset algorithm and the second preset algorithm, respectively; generating safety boundary information according to the sensor acquisition information or the target information through the third preset algorithm.

[0045] Among them, in some embodiments, high-precision map information and external environment information are fused and processed to generate target information, including: separately processing sensor collection information and high-precision map information to obtain first scene perception information and second scene perception information; fusing the first scene perception information and the second scene perception information to generate target information.

[0046] Those skilled in the art should understand that the acquired high-precision map information and sensor-collected information are fused and processed to generate target information, and the target information is used to generate a first planning boundary and a second planning boundary through a first preset algorithm and a second preset algorithm. The neural network algorithm is used to continuously learn based on the information collected by the sensor and / or the target information, and external sensor information is used to generate safety boundary information.

[0047] Specifically, the embodiment of the present application takes the information obtained from the high-precision map and the information collected by the sensor as input, and after a series of calculations and processing, accurately perceives the surrounding environment of the autonomous driving vehicle to obtain the first scene perception information, and fuses the vehicles, pedestrians, and obstacles identified by the sensors and internal algorithms to obtain the second scene perception information. The first scene perception information and the second scene perception information are fused and processed to generate target information.

[0048] Furthermore, in some embodiments, a first planning boundary and a second planning boundary are generated according to the target information through a first preset algorithm and a second preset algorithm, respectively, including: planning the lateral and longitudinal control targets of the vehicle according to the target information; calculating the planned driving route of the vehicle according to the lateral and longitudinal control targets; generating a first planned route according to the driving status and the planned driving route of the vehicle through the first preset algorithm, and generating a second planned route according to the driving status and the planned driving route of the vehicle through the second preset algorithm.

[0049] Among them, the lateral and longitudinal control targets include speed targets and acceleration targets, the vehicle's driving status includes automatic driving mode and non-automatic driving mode, and the user's planned driving route is obtained through the self-driving system.

[0050] Those skilled in the art should understand that the lateral and longitudinal control targets of the vehicle are planned based on the target information, and planning decision information is output according to the driving status of the vehicle and the planned driving route to generate a first planned route. Moreover, planning decision information is output according to the driving status of the vehicle and the planned driving route through a second preset algorithm to generate a second planned route.

[0051] In step S103 , first control information is generated according to the first planning boundary and second control information is generated according to the second planning boundary.

[0052] It can be understood that when generating the first control information, the embodiment of the present application can process the first planning boundary based on a preset heterogeneous algorithm to obtain the first control information, wherein the first control information can be a control instruction for the vehicle, such as controlling the vehicle to accelerate or decelerate, which is not specifically limited here.

[0053] It should be noted that the above-mentioned preset heterogeneous algorithm is only exemplary and does not limit the present application. Those skilled in the art may also adopt other algorithms when generating the first control information according to the first planning boundary. The embodiment of the present application generates the second control information according to the second planning boundary in a manner consistent with the above-mentioned strategy for generating the first control information according to the first planning boundary. To avoid redundancy, it will not be described in detail here.

[0054] In step S104 , when the first control information matches the second control information, the vehicle is controlled according to the first control information.

[0055] It can be understood that if the generated first control information is consistent with the second control information, it means that the chip of the vehicle's self-driving system has not failed, and the vehicle can maintain the current driving system state.

[0056] In step S105 , when the first control information does not match the second control information, a target boundary is determined according to the first planned boundary, the second planned boundary, and the safety boundary information.

[0057] In some embodiments, determining the target boundary based on the first planning boundary, the second planning boundary and the security boundary information includes: judging whether the first planning boundary and the second planning boundary are located within the security boundary information; using the first planning boundary as the target boundary when the first planning boundary is located within the security boundary information and the second planning boundary is not located within the security boundary information; or using the second planning boundary as the target boundary when the second planning boundary is located within the security boundary information and the first planning boundary is not located within the security boundary information; or generating the target boundary based on the security boundary information when the first planning boundary and the second planning boundary are not located within the security boundary information.

[0058] In step S106 , a control instruction is generated according to the target boundary to control the vehicle.

[0059] Specifically, the embodiment of the present application outputs the generated target boundary to the control monitoring, and the control monitoring generates control instructions to downgrade the vehicle's automatic driving system or to park the vehicle or perform emergency braking.

[0060] Therefore, the present application implements a method of acquiring external environmental information, performing planning based on the external environmental information based on the first preset algorithm, the second preset algorithm, and the third preset algorithm, generating a first planning boundary, a second planning boundary, and safety boundary information, generating first control information based on the first planning boundary, and generating second control information based on the second planning boundary, controlling the vehicle based on the first control information when the first control information matches the second control information, and determining a target boundary based on the first planning boundary, the second planning boundary, and safety boundary information when the first control information does not match the second control information, and generating control instructions based on the target boundary to control the vehicle. Thus, safety and other issues caused by vehicle system failures are resolved, as well as the problem of misjudgment caused by the monitoring system's own algorithmic defects, thereby improving the continuity and experience of users' intelligent driving.

[0061] Furthermore, in some embodiments, the vehicle control method further includes: obtaining fault information of the vehicle; and adjusting the automatic driving mode of the vehicle according to the fault information.

[0062] It should be understood that if the vehicle is unable to maintain a high level of autonomous driving, the self-driving system obtains vehicle fault information and adjusts the vehicle's autonomous driving mode based on the vehicle's fault information.

[0063] Among them, in some embodiments, adjusting the automatic driving mode of the vehicle according to the fault information includes: determining the fault attribute according to the fault information, the fault attribute includes a critical fault and a non-critical fault; when the fault attribute is a non-critical fault, adjusting the automatic driving mode of the vehicle after running for a preset time.

[0064] The fault attribute is determined based on the fault information. If the fault attribute is a non-critical fault, the self-driving system can continue to operate within the preset time. After running for the preset time, the vehicle's automatic driving mode is adjusted and switched to redundant control. If the fault attribute is a critical fault, the self-driving system function is downgraded to a safe state. If the self-driving system cannot enter a safe state even after being downgraded, the vehicle will be safely parked or emergency braked.

[0065] In order to enable those skilled in the art to further understand the vehicle control method of the embodiment of the present application, the following is combined with Figures 2 to 4 Elaborate in detail, Figure 2 This is a block diagram of the vehicle control system logic of an embodiment of the present application. Figure 3 This is a schematic diagram of the ADS architecture of an embodiment of the present application. Figure 3 This is a flow chart of a vehicle control method according to an embodiment of the present application.

[0066] In this embodiment, Figure 2 and Figure 3 As shown, the vehicle control system includes two chips (chip 1 and chip 2). Chip 1 is the main chip. Generally, the same system modules inside chip 1 and chip 2 monitor each other's heartbeats. If any system module inside the chip fails, the other same system module will report the fault status to the safety policy module for processing; if any system module inside chip 1 fails, chip 2 will detect the fault by monitoring the heartbeat, and the system will switch to chip 2 for control; if any system module inside chip 2 fails, the self-driving system function will be degraded, but it will not affect normal safe operation. The decision verification module derives the safety range through the input sensor information, and outputs the safety range based on the sensor information to the "safety policy"; the control arbitration module arbitrates the control results of the two chips to determine whether their output instructions are correct. The security strategy is responsible for handling faults in the dual-chip and its internal system modules, and for determining whether the results of dual-chip planning decisions 1 and 2 comply with the safety range calculated by the decision verification module based on external sensor information. If the results of planning decisions 1 and 2 are consistent, the output result of planning decision 1 can be used in the "security strategy"; if the results of planning decisions 1 and 2 are inconsistent, and planning decision 1 is within the safety range, the output result of planning decision 1 can be used in the "security strategy"; if planning decision 2 is within the safety range, the output result of planning decision 2 can be used in the "security strategy"; if the results of planning decisions 1 and 2 are inconsistent, and both are outside the safety range, the output results of planning decisions 1 / 2 cannot be used in the "security strategy".

[0067] Specifically, if Figure 4As shown, after the autonomous driving domain controller is activated, the dual chips use external sensor information based on heterogeneous algorithms to output perception fusion 11 and perception fusion 21 information, respectively, and use perception information based on heterogeneous algorithms to output corresponding target information to their respective planning decisions 12 and planning decisions 22. The planning decisions use target information based on heterogeneous algorithms to output planning decision information to control 13 and control 23 and decision verification 16.

[0068] Then, decision verification 16 is responsible for collecting fault information of the internal system modules of chip 1 and chip 2 and sending it to safety strategy 15 / 25 for processing. At the same time, decision verification 16 will output the safety range based on the neural network algorithm. Decision verification 16 passes the safety range and the planning decision information of chip 1 and chip 2 to safety strategy 15 / 25. Control 13 and control 23 use the planning decision information based on heterogeneous algorithms to output control information to control arbitration 14 / 24.

[0069] Then, security policy 15 / 25 respectively determines whether the first planning boundary and the second planning boundary of the planning decision information of chip 1 and chip 2 fall within the security boundary information. If chip 1 meets the requirements or the results of chip 1 and chip 2 are consistent, the security policy does not take any action; if chip 2 meets the requirements, the security policy selects the planning decision information of chip 2 as the security boundary; if both the planning decision 1 / 2 results received are unavailable or the arbitration results are inconsistent, the security boundary is output to "Control Arbitration" based on the security range.

[0070] If safety strategy 15 / 25 cannot maintain a high level of autonomous driving, a downgrade instruction will be sent to the state machine for downgrade processing. When safety strategy 15 / 25 cannot handle system failures and the system cannot enter a safe state after degradation, the vehicle will be controlled to stop safely and perform blind processing (emergency braking in an emergency).

[0071] Finally, the control arbitration 14 / 24 compares the control results of chip 1 and chip 2. If the results are inconsistent, it is reported to the "security policy". If the received security boundary is valid, control is carried out within the security boundary.

[0072] It should be noted that to avoid unexpected exit of the autonomous driving system due to common cause failure, Chip 1 and Chip 2 should be physically isolated and equipped with different power supplies to ensure complete independence from each other.

[0073] According to the vehicle control method proposed in the embodiment of the present application, by acquiring external environmental information, planning is performed based on the first preset algorithm, the second preset algorithm, and the third preset algorithm according to the external environmental information, generating a first planning boundary, a second planning boundary, and safety boundary information, generating a first control information according to the first planning boundary, and generating a second control information according to the second planning boundary, in the case where the first control information matches the second control information, controlling the vehicle according to the first control information, in the case where the first control information does not match the second control information, determining the target boundary according to the first planning boundary, the second planning boundary, and the safety boundary information, and generating a control instruction according to the target boundary to control the vehicle. In this way, the safety and other problems caused by vehicle system failures are solved, and the requirements for fully automatic driving of L4-L5 levels are met. When the self-driving system fails, the takeover tasks are completed by the self-driving system without the participation of the driver, which improves the continuity and experience of the user's intelligent driving and reduces the time and manpower costs in development and subsequent maintenance and upgrades.

[0074] Next, the vehicle control device proposed according to the embodiment of the present application is described with reference to the accompanying drawings.

[0075] Figure 5 It is a block diagram of a vehicle control device according to an embodiment of the present application.

[0076] like Figure 5 As shown, the vehicle control device 10 includes: an acquisition module 100 , a planning module 200 , a generation module 300 , a first control module 400 , a determination module 500 and a second control module 600 .

[0077] Among them, the acquisition module 100 is used to obtain external environmental information; the planning module 200 is used to plan according to the external environmental information through the first preset algorithm, the second preset algorithm and the third preset algorithm, and generate the first planning boundary, the second planning boundary and the safety boundary information; the generation module 300 is used to generate the first control information according to the first planning boundary and the second control information according to the second planning boundary; the first control module 400 is used to control the vehicle according to the first control information when the first control information matches the second control information; the determination module 500 is used to determine the target boundary according to the first planning boundary, the second planning boundary and the safety boundary information when the first control information does not match the second control information; the second control module 600 is used to generate a control instruction according to the target boundary to control the vehicle.

[0078] Furthermore, the external environment information includes sensor-collected information and high-precision map information. The planning module 200 is specifically used to: fuse the high-precision map information and the sensor-collected information to generate target information; generate a first planning boundary and a second planning boundary based on the target information through a first preset algorithm and a second preset algorithm respectively; and generate safety boundary information based on the sensor-collected information or the target information through a third preset algorithm.

[0079] Furthermore, the planning module 200 is also used to: respectively identify and process the sensor collection information and the high-precision map information to obtain first scene perception information and second scene perception information; and fuse the first scene perception information and the second scene perception information to generate target information.

[0080] Furthermore, the planning module 200 is also used to: plan the vehicle's lateral and longitudinal control targets based on the target information; calculate the vehicle's planned driving route based on the lateral and longitudinal control targets; generate a first planned route based on the vehicle's driving status and the planned driving route through a first preset algorithm, and generate a second planned route based on the vehicle's driving status and the planned driving route through a second preset algorithm.

[0081] Furthermore, the determination module 500 is used to determine whether the first planning boundary and the second planning boundary are located within the safety boundary information; when the first planning boundary is located within the safety boundary information and the second planning boundary is not located within the safety boundary information, the first planning boundary is used as the target boundary; or when the second planning boundary is located within the safety boundary information and the first planning boundary is not located within the safety boundary information, the second planning boundary is used as the target boundary; or when the first planning boundary and the second planning boundary are not located within the safety boundary information, the target boundary is generated according to the safety boundary information.

[0082] Furthermore, the vehicle control device 10 also includes: an adjustment module, which is used to obtain vehicle fault information and adjust the vehicle's automatic driving mode according to the fault information.

[0083] Furthermore, the adjustment module is specifically used to: determine the fault attribute based on the fault information, the fault attribute includes critical fault and non-critical fault; when the fault attribute is a non-critical fault, adjust the vehicle's automatic driving mode after running for a preset time.

[0084] Furthermore, the first preset algorithm and the second preset algorithm include heterogeneous algorithms, and the third preset algorithm includes a neural network algorithm.

[0085] It should be noted that the above explanation of the embodiment of the vehicle control method is also applicable to the vehicle control device of this embodiment and will not be repeated here.

[0086] According to the vehicle control device proposed in the embodiment of the present application, by acquiring external environmental information, planning is performed based on the first preset algorithm, the second preset algorithm, and the third preset algorithm according to the external environmental information, generating a first planning boundary, a second planning boundary, and safety boundary information, generating a first control information according to the first planning boundary, and generating a second control information according to the second planning boundary, in the case where the first control information matches the second control information, controlling the vehicle according to the first control information, in the case where the first control information does not match the second control information, determining the target boundary according to the first planning boundary, the second planning boundary, and the safety boundary information, and generating a control instruction according to the target boundary to control the vehicle. In this way, the safety and other problems caused by vehicle system failures are solved, and the requirements for fully automatic driving of L4-L5 levels are met. When the self-driving system fails, the takeover tasks are completed by the self-driving system without the participation of the driver, which improves the continuity and experience of the user's intelligent driving and reduces the time and manpower costs in development and subsequent maintenance and upgrades.

[0087] Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0088] A memory 601 , a processor 602 , and a computer program stored in the memory 601 and executable on the processor 602 .

[0089] When the processor 602 executes the program, the vehicle control method provided in the above embodiment is implemented.

[0090] Furthermore, the vehicle further comprises:

[0091] The communication interface 603 is used for communication between the memory 601 and the processor 602 .

[0092] The memory 601 is used to store computer programs that can be run on the processor 602 .

[0093] The memory 601 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0094] If the memory 601, the processor 602, and the communication interface 603 are implemented independently, the communication interface 603, the memory 601, and the processor 602 can be connected to each other via a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0095] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can communicate with each other through an internal interface.

[0096] The processor 602 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0097] Optionally, the processor 602 includes a first processor, a second processor, a third processor and a fourth processor, the first processor is used to obtain external environmental information, and plan and generate a first planning boundary based on the external environmental information through a first preset algorithm, the second processor is used to obtain external environmental information, and plan and generate a second planning boundary based on the external environmental information through a second preset algorithm, the third processor is used to generate first control information based on the first planning boundary, and the fourth processor is used to generate second control information based on the second planning boundary; the third processor or the fourth processor is also used to control the vehicle according to the first control information when the first control information matches the second control information; or, when the first control information does not match the second control information, determine the target boundary according to the first planning boundary, the second planning boundary and the safety boundary information, and generate control instructions according to the target boundary to control the vehicle.

[0098] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the above vehicle control method when executed by a processor.

[0099] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0100] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0101] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0102] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0103] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0104] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A vehicle control method, characterized in that: The vehicle control method includes: Obtaining external environment information; Performing planning based on the external environment information using a first preset algorithm, a second preset algorithm, and a third preset algorithm to generate a first planning boundary, a second planning boundary, and safety boundary information; generating first control information according to the first planning boundary and generating second control information according to the second planning boundary; If the first control information matches the second control information, controlling the vehicle according to the first control information; or In a case where the first control information does not match the second control information, determining a target boundary according to the first planning boundary, the second planning boundary, and the security boundary information; generating a control instruction to control the vehicle according to the target boundary; The external environment information includes sensor collection information and high-precision map information. The planning is performed according to the external environment information using a first preset algorithm, a second preset algorithm, and a third preset algorithm to generate a first planning boundary, a second planning boundary, and safety boundary information, including: fusing the high-precision map information and the sensor collected information to generate target information; generating the first planning boundary and the second planning boundary according to the target information using the first preset algorithm and the second preset algorithm respectively; Generate the safety boundary information according to the sensor collected information or the target information through the third preset algorithm; The fusing of the high-precision map information and the external environment information to generate target information includes: Respectively processing the sensor collected information and the high-precision map information to obtain first scene perception information and second scene perception information; fusing the first scene perception information and the second scene perception information to generate the target information; The generating the first planning boundary and the second planning boundary according to the target information by using the first preset algorithm and the second preset algorithm respectively includes: Planning the lateral and longitudinal control targets of the vehicle according to the target information; Calculating a planned driving route of the vehicle according to the lateral and longitudinal control targets; generating a first planned route according to the driving state of the vehicle and the planned driving route through the first preset algorithm, and generating a second planned route according to the driving state of the vehicle and the planned driving route using the second preset algorithm; The determining of the target boundary according to the first planning boundary, the second planning boundary, and the safety boundary information includes: Determining whether the first planning boundary and the second planning boundary are located within the security boundary information; In a case where the first planning boundary is within the safety boundary information and the second planning boundary is not within the safety boundary information, using the first planning boundary as the target boundary; or In a case where the second planning boundary is located within the safety boundary information and the first planning boundary is not located within the safety boundary information, using the second planning boundary as the target boundary; or In a case where the first planning boundary and the second planning boundary are not located within the safety boundary information, the target boundary is generated according to the safety boundary information.

2. The vehicle control method according to claim 1, characterized in that: The vehicle control method further includes: Obtaining fault information of the vehicle; Adjust the automatic driving mode of the vehicle according to the fault information.

3. The vehicle control method according to claim 2, characterized in that: The adjusting the automatic driving mode of the vehicle according to the fault information includes: Determining fault attributes according to the fault information, wherein the fault attributes include critical faults and non-critical faults; In the case where the fault attribute is a non-critical fault, the automatic driving mode of the vehicle is adjusted after running for a preset time.

4. The vehicle control method according to claim 1, wherein: The first preset algorithm and the second preset algorithm include heterogeneous algorithms, and the third preset algorithm includes a neural network algorithm.

5. A vehicle control device, suitable for using the vehicle control method according to any one of claims 1 to 4, characterized in that: include: Acquisition module, used to obtain external environment information; a planning module, configured to perform planning according to the external environment information using a first preset algorithm, a second preset algorithm, and a third preset algorithm, respectively, to generate a first planning boundary, a second planning boundary, and safety boundary information; a generating module, configured to generate first control information according to the first planning boundary and generate second control information according to the second planning boundary; a first control module, configured to control the vehicle according to the first control information when the first control information matches the second control information; a determination module, configured to determine a target boundary according to the first planning boundary, the second planning boundary, and the security boundary information when the first control information does not match the second control information; The second control module is configured to generate a control instruction according to the target boundary to control the vehicle.

6. A vehicle, characterized in that: The invention comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the vehicle control method according to any one of claims 1 to 4.

7. The vehicle according to claim 6, characterized in that The processor includes a first processor, a second processor, a third processor, and a fourth processor, wherein the first processor is configured to obtain external environment information, and perform planning based on the external environment information using a first preset algorithm to generate a first planning boundary, the second processor is configured to obtain external environment information, and perform planning based on the external environment information using a second preset algorithm to generate a second planning boundary, the third processor is configured to generate first control information based on the first planning boundary, and the fourth processor is configured to generate second control information based on the second planning boundary; The third processor or the fourth processor is further used to control the vehicle according to the first control information when the first control information matches the second control information; or, when the first control information does not match the second control information, determine the target boundary according to the first planning boundary, the second planning boundary and the safety boundary information, and generate control instructions according to the target boundary to control the vehicle.

8. A non-volatile computer-readable storage medium containing a computer program, characterized in that When the computer program is executed by a processor, the processor is caused to execute the vehicle control method according to any one of claims 1 to 4.

Images