Autonomous driving system and method for a vehicle

Abstract

The application relates to an automatic driving system and method of a vehicle, wherein the system comprises: an automatic driving hardware platform, which acquires sensing information and corresponding control actions in a driving process and / or a parking process in an automatic driving mode; a whole vehicle information modular component, which is used for classifying the sensing information to obtain classified sensing information; an automatic driving software platform, which is used for controlling the automatic driving vehicle to perform corresponding driving actions and / or parking actions; a driving and parking function state component, which is used for controlling the automatic driving vehicle to enter corresponding driving working conditions of the driving process and / or the parking process according to a current driving scene and the control actions; and an automatic driving function scheduling component, which is used for driving the automatic driving software platform to work. The embodiment of the application can integrate the driving and the parking into an integrated setting, adaptively controls the vehicle according to changes of scenes, improves the intelligence and applicability of the vehicle, is more intelligent and reliable, and improves the driving experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to an automatic driving system and method of a vehicle. BACKGROUND

[0002] With the improvement of the function of the automatic driving system, it has developed from the previous single independent function of high-speed cruise, adaptive cruise, automatic parking to point-to-point full-automatic driving function integration. Since the high-speed driving function, urban automatic driving and parking lot and parking garage are relatively independent automatic driving scenes, they have different software strategies in perception, fusion, planning, control and the like, and how to integrate different algorithms of different scenes into the same automatic driving controller to meet the automatic driving of the line and parking function on one platform is a current difficult problem.

[0003] In the related art, the preview distance parallel to the driving direction of the vehicle can be calculated according to the current vehicle speed and driving direction, and the preview point is selected, and when the vehicle speed is negative, i.e. parking is requested, the preview point is selected at the rear of the vehicle, which realizes that the same control method meets the needs of the automatic driving vehicle in different working conditions, occupies less controller computing power, has high real-time calculation and good control effect.

[0004] However, although the control integration is realized in the related art, only the steering wheel angle control in different forward and reverse gears can be realized, and the problem of compatibility and switching of the control algorithm of the subsystem in the automatic driving system in different scene changes cannot be solved, and improvement is needed. SUMMARY

[0005] The present application provides an automatic driving system and method of a vehicle to solve the technical problem in the related art that only the steering wheel angle control in different forward and reverse gears can be realized, and the compatibility and switching of the control algorithm of the subsystem in the automatic driving system in different scene changes cannot be solved.

[0006] The first aspect of the present application provides an automatic driving system of a vehicle, comprising: an automatic driving hardware platform, the automatic driving hardware platform comprising a plurality of automatic driving controllers and a plurality of sensors arranged correspondingly to obtain perception information and corresponding control actions in a driving process and / or a parking process in an automatic driving mode; a whole vehicle information modular component for classifying the perception information to obtain classified perception information; an automatic driving software platform for controlling an automatic driving vehicle to perform corresponding driving actions and / or parking actions based on a preset operating system and the classified perception information; a line and parking function state component for controlling the automatic driving vehicle to enter corresponding driving conditions of the driving process and / or the parking process according to a current driving scene and the control actions; and an automatic driving function scheduling component for driving the automatic driving software platform to work according to the corresponding driving conditions of the driving process and / or the parking process.

[0007] According to the technical means, the perception information and corresponding control actions of the vehicle in the autonomous driving mode can be obtained based on the sensors, actuators, controllers and other devices of the autonomous vehicle, so that the vehicle can complete the autonomous driving action by using the autonomous driving function scheduling component in combination with the current driving scene, thereby solving the compatibility and switching of the subsystems in different scenes and control algorithms in the autonomous driving system, and realizing the integration of the driving and / or parking functions.

[0008] Optionally, in an embodiment of the present application, the autonomous driving hardware platform includes a plurality of at least one front millimeter wave radar, at least one corner millimeter wave radar, at least one front-view camera, at least one surround-view camera, at least one fisheye camera, at least one ultrasonic sensor, an autonomous driving domain controller, a steering controller, a brake controller, a vehicle domain controller, a chassis power controller, a vehicle body domain controller and a cabin domain controller.

[0009] According to the technical means, the perception information and corresponding control actions of the vehicle in the autonomous driving mode can be obtained based on the sensors, actuators, controllers and other devices of the autonomous vehicle, so that the vehicle can complete the autonomous driving action by using the autonomous driving function scheduling component in combination with the current driving scene, thereby solving the compatibility and switching of the subsystems in different scenes and control algorithms in the autonomous driving system, and realizing the integration of the driving and / or parking functions.

[0010] Optionally, in an embodiment of the present application, the at least one front millimeter wave radar, the at least one front camera and the autonomous driving domain controller are connected to transmit the first target information perceived; the at least one corner millimeter wave radar and the autonomous driving domain controller are connected to transmit the target and drivable area information; the at least one surround-view camera and the autonomous driving domain controller are connected to transmit the second target information perceived; the at least one fisheye camera and the vehicle domain controller are connected to input the original perception image; the at least one ultrasonic sensor and the autonomous driving domain controller are connected to input the ultrasonic echo signal; and the autonomous driving domain controller is respectively connected to the chassis power controller, the vehicle body domain controller and the cabin domain controller to respectively transmit the control signal, the network information and the video information.

[0011] According to the technical means, the communication between the plurality of autonomous driving controllers and the plurality of sensors correspondingly arranged in the autonomous driving hardware platform can be realized, and the corresponding information can be output.

[0012] Optionally, in an embodiment of the present application, the vehicle information modular assembly comprises: an external system information modular unit configured to classify information of a power domain, a cabin domain and a body domain of the vehicle according to a first preset classification rule; an intelligent sensor output information modular unit configured to classify perception information collected by the plurality of sensors according to a second preset classification rule; and an automatic driving domain controller information modular unit configured to classify software modules of the automatic driving software platform according to a third preset classification rule.

[0013] According to the above technical means, the embodiment of the present application can realize classification of output information of all application modules based on the vehicle information modular assembly.

[0014] Optionally, in an embodiment of the present application, the first preset classification rule comprises at least one of a change frequency, a signal attribute, a transceiving relationship, an application module and a data volume; the second preset classification rule comprises at least one of a sensing source, a sensor characteristic and a sensing result type; and the third preset classification rule comprises at least one of a fusion function, an environment reconstruction function, a prediction function, a decision function, a path planning function and a vehicle control function.

[0015] According to the above technical means, the embodiment of the present application can realize detailed classification of output information of all application modules.

[0016] Optionally, in an embodiment of the present application, the automatic driving function scheduling assembly is specifically configured to identify a current scene based on the control action, automatic driving map information, vehicle positioning information, perceived road surface identification information, traffic sign information, garage information, parking space information and vehicle driving information, so as to drive the automatic driving software platform to work in combination with the corresponding driving working condition.

[0017] According to the above technical means, the embodiment of the present application can identify the current scene of the automatic driving vehicle, thereby realizing vehicle action control based on the current scene.

[0018] The second aspect embodiment of the present application provides an automatic driving method of a vehicle, comprising the following steps: acquiring perception information and corresponding control actions in a driving process and / or a parking process in an automatic driving mode; classifying the perception information to obtain classified perception information; controlling the automatic driving vehicle to enter a corresponding driving working condition of the driving process and / or the parking process according to a current driving scene and the control actions; and controlling the automatic driving vehicle to perform corresponding driving actions and / or parking actions based on a preset operating system and the classified perception information.

[0019] Optionally, in an embodiment of the present application, the classifying the perception information to obtain classified perception information comprises: classifying information of a power domain, a cabin domain and a body domain of the whole vehicle according to a first preset classification rule; classifying perception information collected by the information of the plurality of sensors according to a second preset classification rule; and classifying software modules of the automatic driving software platform according to a third preset classification rule.

[0020] Optionally, in an embodiment of the present application, the first preset classification rule comprises at least one of a change frequency, a signal attribute, a transceiving relationship, an application module and a data volume; the second preset classification rule comprises at least one of a sensing source, a sensor characteristic and a sensing result type; and the third preset classification rule comprises at least one of a fusion function, an environment reconstruction function, a prediction function, a decision function, a path planning function and a vehicle control function.

[0021] An embodiment of 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 automatic driving method of the vehicle as described in the above embodiments.

[0022] An embodiment of the fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the automatic driving method of the vehicle as described above.

[0023] The beneficial effects of the embodiments of the present application are as follows:

[0024] (1) The embodiments of the present application can obtain perception information and corresponding control actions of a vehicle in an automatic driving mode based on sensors, actuators, controllers and other devices of an automatic driving vehicle, so as to control the vehicle to complete automatic driving actions by combining a current driving scene and using an automatic driving function scheduling component, integrate driving and parking into an integrated setting, adaptively control the vehicle according to changes in the scene, improve the intelligence and applicability of the vehicle, be more intelligent and reliable, and improve the driving experience.

[0025] (2) The embodiments of the present application can realize detailed classification of output information of all application modules based on a whole vehicle information modular component.

[0026] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0027] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the appended drawings.

[0028] Figure 1 FIG. 1 is a structural schematic diagram of an automatic driving system of a vehicle according to an embodiment of the present application;

[0029] Figure 2 FIG. 1 is a structural schematic diagram of an automatic driving system of a vehicle according to an embodiment of the present application;

[0030] Figure 3 FIG. 2 is a schematic diagram of automatic driving function state jumping of an automatic driving system of a vehicle according to another embodiment of the present application;

[0031] Figure 4 FIG. 3 is a schematic diagram of automatic driving function time-sharing calling of an automatic driving system of a vehicle according to another embodiment of the present application;

[0032] Figure 5 FIG. 4 is a flowchart of an automatic driving method of a vehicle according to an embodiment of the present application;

[0033] Figure 6 FIG. 5 is a structural schematic diagram of a vehicle according to an embodiment of the present application.

[0034] wherein, 10-automatic driving system of a vehicle; 100-automatic driving hardware platform, 101-front millimeter wave radar, 102-left front corner radar, 103-front ultrasonic radar, 104-right front corner radar, 105-left periphery view camera, 106-side surround view camera, 107-right periphery view camera, 108-rear ultrasonic radar, 109-right rear corner millimeter wave radar, 110-rear periphery view camera, 111-left rear corner millimeter wave radar, 112-peripheral view rear camera, 113-front camera, 114-front surround view camera, 200-vehicle information modular assembly, 300-automatic driving software platform, 400-parking function state component, 500-automatic driving function scheduling component. DETAILED DESCRIPTION

[0035] Embodiments of the present application are described in detail below with reference to the accompanying drawings. Examples of the embodiments are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by reference to the drawings are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application.

[0036] An automatic driving system and method of a vehicle according to embodiments of the present application are described below with reference to the accompanying drawings. In the related art mentioned in the background section above, only the control of steering wheel angle in different forward and reverse gears can be achieved, and the technical problem of compatibility and switching of subsystems in different scene changes and control algorithms in an automatic driving system cannot be solved. The present application provides an automatic driving system of a vehicle, in which the system can obtain perception information and corresponding control actions of a driving process and / or a parking process in an automatic driving mode based on an automatic driving hardware platform, a plurality of automatic driving controllers and a plurality of sensors arranged accordingly, so as to classify the perception information by using a vehicle information modular component, control the automatic driving vehicle to enter the corresponding driving working condition of the driving process and / or the parking process by using a driving and parking function state component in combination with the current driving scene, and drive the automatic driving software platform to work by using an automatic driving function scheduling component, so as to integrate the driving and parking into an integrated setting, adapt to changes in the scene to control the vehicle, improve the intelligence and applicability of the vehicle, be more intelligent and reliable, and improve the driving experience. Thus, the technical problem of compatibility and switching of subsystems in different scene changes and control algorithms in an automatic driving system cannot be solved in the related art, and only the control of steering wheel angle in different forward and reverse gears can be achieved.

[0037] Specifically, Figure 1 A structural schematic diagram of an automatic driving system of a vehicle provided by embodiments of the present application is shown.

[0038] As Figure 1 shown, the automatic driving system 10 of the vehicle includes an automatic driving hardware platform 100, a vehicle information modular component 200, an automatic driving software platform 300, a driving and parking function state component 400, and an automatic driving function scheduling component 500.

[0039] Specifically, the automatic driving hardware platform 100 includes a plurality of automatic driving controllers and a plurality of sensors arranged accordingly, so as to obtain perception information and corresponding control actions of a driving process and / or a parking process in an automatic driving mode.

[0040] In actual execution, the automatic driving hardware platform 100 can include a plurality of automatic driving controllers and a plurality of sensors arranged accordingly, so as to obtain control actions of a driving process and / or a parking process of the vehicle in an automatic driving mode based on the plurality of automatic driving controllers, and obtain perception information of the driving process and / or the parking process in the automatic driving mode based on the plurality of sensors arranged accordingly.

[0041] Optionally, in an embodiment of the present application, the automatic driving hardware platform 100 comprises a plurality of at least one front millimeter wave radar, at least one corner millimeter wave radar, at least one front-view camera, at least one surround-view camera, at least one fisheye camera, at least one ultrasonic sensor, an automatic driving domain controller, a steering controller, a brake controller, a vehicle domain controller, a chassis power controller, a vehicle body domain controller, and a cabin domain controller.

[0042] Specifically, in an embodiment of the present application, the plurality of automatic driving controllers in the automatic driving hardware platform 100 can comprise a plurality of an automatic driving domain controller, a steering controller, a brake controller, a vehicle domain controller, a chassis power controller, a vehicle body domain controller, and a cabin domain controller; and the plurality of sensors can comprise a plurality of at least one front millimeter wave radar, at least one corner millimeter wave radar, at least one front-view camera, at least one surround-view camera, at least one fisheye camera, and at least one ultrasonic sensor. The embodiment of the present application can combine the plurality of automatic driving controllers and the plurality of sensors based on the configuration of the actual vehicle, thereby increasing the flexibility and practicality of the application of the embodiment of the present application.

[0043] Optionally, in an embodiment of the present application, the at least one front millimeter wave radar, the at least one front camera, and the automatic driving domain controller are connected to transmit the first target information perceived; the at least one corner millimeter wave radar is connected with the automatic driving domain controller to transmit the target and drivable area information; the at least one surround-view camera is connected with the automatic driving domain controller to transmit the second target information perceived; the at least one fisheye camera is connected with the vehicle domain controller to input the original perception image; the at least one ultrasonic sensor is connected with the automatic driving domain controller to input the ultrasonic echo signal; and the automatic driving domain controller is connected with the chassis power controller, the vehicle body domain controller, and the cabin domain controller respectively to transmit the control signal, the network information, and the video information respectively.

[0044] As a possible implementation manner, the at least one front millimeter wave radar, the at least one front camera and the automatic driving domain controller can be connected through a CAN (Controller Area Network) and an Ethernet to transmit target information perceived; the at least one corner millimeter wave radar can be connected with the automatic driving domain controller through the CAN to transmit target and drivable area information; the at least one panoramic camera and the automatic driving domain controller can be connected through the Ethernet to transmit target information perceived; the at least one fisheye camera can be connected with the domain controller through DSI (digital-speech interpolation) after video compression and deserialization to input original perception images; the at least one ultrasonic sensor and the automatic driving domain controller can be connected through a standard IO (Input / Output) port to input ultrasonic echo signals; the automatic driving domain controller and a chassis power controller and a vehicle body domain controller can be connected through the CAN, and the automatic driving domain controller and a cabin domain controller can be connected through the CAN, the Ethernet and the LVDS (Low-Voltage Differential Signaling) to respectively transmit control signals, network information and video information.

[0045] The automatic driving domain controller can include a power management, an external communication chip (ETH-Switch, CAN-PHY), a real-time task processor, a memory (DDR and eMMC), a surround view image deserializer, an AI (Artificial Intelligence) computing unit and a system on chip (SOC), can output rendered images to a vehicle display screen through a video encoder, and the external communication chip can realize communication between the automatic driving domain controller and a cabin domain controller, a vehicle domain controller, a front camera intelligent sensor, a front radar intelligent sensor and a panoramic intelligent sensor; the real-time task processor can calculate control instructions according to planning results and output the control instructions to an external controller; the AI computing unit can process images, operate a deep learning network model and output target detection results; and the system on chip can output planning results to the real-time processor after performing operation fusion algorithm, prediction, decision and planning processing.

[0046] The vehicle information modularized component 200 is used for classifying perception information to obtain classified perception information.

[0047] In some embodiments, the vehicle information modularized component 200 can be used to classify perception information obtained by the automatic driving hardware platform 100 to obtain classified perception information.

[0048] Optionally, in an embodiment of the present application, the vehicle information modular assembly 200 comprises: an external system information modular unit, an intelligent sensor output information modular unit, and an autonomous driving domain controller information modular unit.

[0049] The external system information modular unit is configured to classify information of a power domain, a cabin domain, and a body domain of the vehicle according to a first preset classification rule.

[0050] The intelligent sensor output information modular unit is configured to classify perception information collected by a plurality of sensors according to a second preset classification rule.

[0051] The autonomous driving domain controller information modular unit is configured to classify software modules of the autonomous driving software platform 300 according to a third preset classification rule.

[0052] In actual implementation, the vehicle information modular assembly 200 can comprise the external system information modular unit, the intelligent sensor output information modular unit, and the autonomous driving domain controller information modular unit, so as to classify output information of all application modules, and facilitate the autonomous driving software platform 300 to control the autonomous driving vehicle to perform corresponding driving actions and / or parking actions based on the classified perception information.

[0053] The external system information modular unit can classify information of a power domain, a cabin domain, a body domain, and an intelligent sensor of the vehicle according to a first preset classification rule.

[0054] The intelligent sensor output information modular unit can classify perception information collected by a plurality of sensors according to a second preset classification rule.

[0055] The autonomous driving domain controller information modular unit can classify software modules of the autonomous driving software platform 300 according to a third preset classification rule.

[0056] Optionally, in an embodiment of the present application, the first preset classification rule comprises at least one of a change frequency, a signal attribute, a transceiving relationship, an application module, and a data volume; the second preset classification rule comprises at least one of a sensing source, a sensor characteristic, and a sensing result type; and the third preset classification rule comprises at least one of a fusion function, an environment reconstruction function, a prediction function, a decision function, a path planning function, and a vehicle control function.

[0057] As one possible implementation, the external system information modular unit can classify information of a power domain, a cabin domain, a body domain, and an intelligent sensor of the vehicle according to a first preset classification rule, i.e., a change frequency, a signal attribute, a transceiving relationship, an application module, a data volume, etc., to complete classification of 92 vehicle subsystem information.

[0058] The intelligent sensor output information modular unit can be classified according to a second preset classification rule, that is, according to a sensor source, a sensor characteristic, and a sensing result type, and a total of 25 intelligent sensing information classifications are completed.

[0059] The automatic driving domain controller information modular unit can divide application software modules of automatic driving according to a third preset classification rule, that is, according to different functions (fusion, environment reconstruction, prediction, decision, path planning, and vehicle control), perform detailed classification on outputs of all application modules, a total of 48 application information classifications are completed, and meanwhile, during actual software running of the automatic driving domain controller, each modular information can output a corresponding state or request other sub-functions according to application requirements.

[0060] The automatic driving software platform 300 is configured to control an automatic driving vehicle to perform corresponding driving actions and / or parking actions based on a preset operating system and classified perception information.

[0061] In some embodiments, the automatic driving software platform 300 can include a driver, an operating system, and middleware. The real-time task processor in the embodiment of the application can use a real-time operating system (AutoSar), the AI computing unit can use a dedicated driver, the system on chip can use a soft real-time operating system (Linux) and a real-time operating system (QNX), and the middleware can satisfy special requirements of the automatic driving system, such as inter-chip communication, monitoring and diagnosis, OTA (Over-the-Air Technology, over-the-air technology) upgrade, execution management, network communication, and configuration management.

[0062] The driving and parking function state component 400 is configured to control the automatic driving vehicle to enter a corresponding driving working condition of a driving process and / or a parking process according to a current driving scene and a control action.

[0063] In actual execution, the driving and parking function state component 400 of the embodiment of the application can globally analyze specific states of driving modes in different scenes according to actual automatic driving function requirements, and a total of 5 large states and 24 small states are formed. The embodiment of the application can enter different driving working conditions according to different driving scenes and driver operations during actual running, and then control software modules to work in corresponding states.

[0064] The automatic driving function scheduling component 500 is configured to drive the automatic driving software platform 300 to work according to the corresponding driving working condition of the driving process and / or the parking process.

[0065] As a possible implementation manner, the automatic driving function scheduling component 500 in the embodiment of the present application can drive the automatic driving software platform 300 to work according to the corresponding driving conditions of the driving process and / or the parking process, so as to realize the judgment of different driving conditions through perception and scene recognition and driver operation, and then activate the corresponding software module to output specific external control and interaction instruction, and finally realize different automatic driving user requirements while reducing the number of controllers.

[0066] Optionally, in an embodiment of the present application, the automatic driving function scheduling component 500 is specifically used to identify the current scene based on the control action, the automatic driving map information, the vehicle positioning information, the perceived road surface identification information, the traffic sign information, the garage information, the parking space information, and the vehicle driving information, so as to drive the automatic driving software platform 300 to work in combination with the corresponding driving conditions.

[0067] Specifically, the automatic driving function scheduling component 500 can judge the current driving condition and driving target based on the perception information, the driver operation, call different software module functions, and in particular, the automatic driving function scheduling component 500 can give the current specific scene based on the current driver operation, the automatic driving map information, the vehicle positioning, the perceived road surface identification, the traffic sign, the garage information, the parking space information, and the vehicle driving information, so as to drive the automatic driving software platform 300 to work in combination with the corresponding driving conditions, so that the software module works in different states such as running, hibernation, and suspension. When the scene and the condition change, the automatic driving function scheduling component 500 can control the corresponding module to work in the corresponding state according to the set order, so as to drive the automatic driving software platform 300 to work, and then realize the automatic driving function in different conditions.

[0068] In combination Figure 2 to Figure 4 As shown in the figure, the working principle of the automatic driving system of the vehicle of the embodiment of the present application is described in detail.

[0069] As Figure 2 shown, the system 10 of the embodiment of the present application can include: an automatic driving hardware platform 100, a front millimeter wave radar 101, a left front corner radar 102, a front ultrasonic wave radar 103, a right front corner radar 104, a left peripheral view camera 105, a side peripheral view camera 106, a right peripheral view camera 107, a rear ultrasonic wave radar 108, a right rear corner millimeter wave radar 109, a rearward peripheral view camera 110, a left rear corner millimeter wave radar 111, a peripheral view rear camera 112, a front camera 113, a front peripheral view camera 114, a vehicle information modular component 200, an automatic driving software platform 300, a driving and parking function state component 400, and an automatic driving function scheduling component 500.

[0070] Specifically, as Figure 2As shown, the front millimeter wave radar 101 can be installed below the front bumper of the vehicle to detect long-distance targets; the left front corner radar 102 and the right front corner radar 104 are respectively installed inside the bumper to identify medium and long-distance moving targets and extract a drivable area according to radar echo information; the front ultrasonic radar 103 has six units installed at different positions of the front bumper to detect the position of a near-distance echo and cluster to obtain the boundary of an obstacle; the five omnidirectional cameras include the left omnidirectional camera 105 and the right omnidirectional camera 107, which are respectively installed on the front wing panel and the B-pillar, and the rear omnidirectional camera 112, which is installed below the roof of the vehicle to perceive medium-distance targets on the left and right sides of the vehicle, drivable area information, and lane lines; the four ring cameras include the left and right side ring cameras 106, the front ring camera 114, and the rear ring camera 110, which are respectively installed below the left and right rearview mirrors, the front bumper mesh, and the trunk lid to perceive near-distance targets, drivable area information, and lane line information; the front camera 113 is installed at the rearview mirror in the vehicle to perceive front moving targets, drivable area and lane line information, traffic signs, and the like.

[0071] It should be noted that the sensor configuration scheme of the embodiments of the present application is only a typical engineering example, and actual configuration can be increased or optimized according to the functional needs of the project, such as adding a laser radar and using a 3D millimeter wave radar instead of an ultrasonic wave.

[0072] For example, the embodiments of the present application can include three parts of sensors, external subsystems, and automatic driving domain controllers.

[0073] The sensors include ring cameras, ultrasonic sensors, front millimeter wave radars, front view cameras / smart sensors, omnidirectional cameras, positioning units, and corner millimeter wave radars.

[0074] Among them, the ring cameras and ultrasonic sensors are directly connected to the automatic driving domain controller and output raw images and ultrasonic echo information, respectively; the front millimeter wave radars, front view cameras / smart sensors, omnidirectional cameras, and corner millimeter wave radars can directly access raw perception information (images or echoes) or access identified target information (obstacles, drivable areas, semantic information), and the second kind can be used in the embodiments of the present application.

[0075] The external subsystems can include a cabin domain controller, a vehicle domain controller, and steering and brake redundant actuators. The vehicle domain controller is responsible for outputting power-related information and responding to control requests from the automatic driving domain controller. The cabin domain controller provides network communication, vehicle image display, and vehicle screen operation for automatic driving auxiliary function development. The steering and brake redundant actuators provide real-time vehicle information related to braking and steering and respond to control requests from the automatic driving controller. The vehicle body domain controller is similar and provides vehicle body-related information while responding to vehicle body control instructions.

[0076] The automatic driving domain controller includes four main chips: a domain control on-board Ethernet gateway, a real-time controller, a first chip, and a second chip. The Ethernet switch enables communication between the vehicle domain controller, the front corner radar, the real-time controller, the first chip, and the second chip. The real-time controller obtains vehicle external CAN information and path planning results from the system on chip, runs control algorithms to output control instructions. The first chip includes an Ethernet switch, a real-time controller, and a system on chip. The Ethernet switch connects multiple surround view cameras and multiple front cameras and switches. The real-time controller performs redundant control and issues control instructions through the redundant system when an anomaly occurs to meet functional safety requirements. The system on chip is responsible for high-speed functional application software. The second chip is responsible for low-speed functional application software, network communication, surround view image processing, rendering pictures, and output.

[0077] The real-time controller can run the AutoSar system, process external CAN information, and handle horizontal and vertical control algorithms. The system on chip of the first chip and the system on chip of the second chip handle complex and computationally intensive algorithms such as perception, fusion, positioning, prediction, decision-making, planning, and function scheduling, running QNX and Linux systems. The first chip embeds a real-time processor and deploys redundant control algorithms, running the AutoSar system.

[0078] The modular classification information input and output by the domain controller can be as shown in Table 1 and Table 2.

[0079] Table 1

[0080] Serial number Chassis domain Serial number Cabin domain Serial number Body domain 1 Switch state 1 Navigation map information 1 Remote control information 2 Power information 2 Car machine state 2 Tire pressure information 3 Gear information 3 Surround view setting information 3 Thermal management information 4 Pedal information 4 Driving function setting information 4 Seat state 5 Motion information 5 Parking function setting information 5 Body state 6 Braking state 6 Driving function switch setting 6 Light state 7 Energy recovery state 7 Recorder setting information 7 Door state 8 Steering state 8 Voice request information 8 Window state 9 GNSS information 9 Screen information 9 Handheld steering wheel state … … … … … …

[0081] Table 2

[0082]

[0083] The input part can divide the vehicle into three parts: chassis domain, cabin domain, and vehicle body domain. The chassis domain includes power, braking, steering, and other subsystems.

[0084] According to the actual situation of the vehicle, the vehicle information can be sorted and combined to form 18 sub-information, each of which contains similar related signals, such as vehicle switch state, pedal state, vehicle gear information, steering wheel angle.

[0085] The cockpit domain includes instruments, car machines and vehicle network modules. According to the actual characteristics of the cockpit information, the vehicle cockpit domain related information is divided into 15 sub-information, each of which contains similar related signals, such as navigation information, car machine switch state information, instrument information, screen setting information.

[0086] The vehicle body domain contains vehicle body control, keyless entry, keyless start, vehicle body switch and other information. According to the characteristics of each signal and the characteristics of the controller, a total of 11 sub-information is divided, such as tire pressure state information, power state, vehicle light state, vehicle door state, horn state, etc.

[0087] The output part can classify and combine the output signals of the automatic driving domain controller according to the receiver and functional characteristics, and a total of five types of information are divided, including display, chassis control, vehicle body control, system state and information state.

[0088] Among them, the display information includes 12 information, including information about reconstruction target, signboard, lane line, ultrasonic sector, etc. The chassis control class includes a total of 5 information, including brake, steering control, gear, power control, etc. The vehicle body control class includes a total of 5 information, including light, window, door, power and other vehicle body control interfaces. The state class includes a total of 12 information, including high-speed function state, low-speed function state and other function state related information. The information class includes a total of 15 information interfaces, mainly used for prompting the state of internal modules, such as parking space state, low-speed function information, high-speed function information.

[0089] As shown in Figure 3 , the controller has five big states, which are high-speed driving, human driving, function activation, low-speed cruise and parking.

[0090] Among them, high-speed driving can include cruise driving, lane-changing driving, congestion assistance and navigation driving according to different sensor information. The activation state represents that the function is turned on but not in the horizontal and vertical control of the vehicle. The low-speed cruise state is mainly the automatic driving state before reaching the parking space or after leaving the parking space. According to the actual application requirements, it can be further divided into driver driving to search for parking space, searching for parking space along lane line, searching for parking space based on map and cruising to reach the pickup point after leaving the parking space. Except for the driver driving to search for parking space, all of them are in the horizontal and vertical control state.

[0091] The parking state includes two sub-states of parking in and parking out. According to the input of the driver in different scenarios, the embodiments of the present application can use different perception information to call the parking in or parking out planning algorithm to complete the in and out of the garage function.

[0092] As shown in Figure 4 , when the autonomous vehicle drives to different areas, it can judge the current working condition according to different perception information, and then call the algorithm module corresponding to the working condition for control.

[0093] The embodiments of the present application can be divided into 25 categories according to the actual application scenario. Different software modules are used according to different application scenarios and corresponding functional requirements. The state machine is used to switch different software modules to realize the switching of corresponding perception, positioning, fusion, prediction, decision, planning and control algorithms in different working conditions, and then the corresponding control instruction information is sent to the external controller.

[0094] It should be noted that the function algorithm scheduling switching can be soft switched by the software level, that is, all software modules in the entire controller are powered on. In different states, different algorithm modules or working states are switched, and the dynamic controller calculation load is adjusted in time to realize the function switching while improving the hardware resource utilization. It can also be realized by hard switching through the operating system level, that is, different software modules are dynamically started or stopped in different states, and the calculation and storage resources are completely released to further improve the hardware resource utilization. The two methods can be determined according to the actual situation of the hardware resources.

[0095] The automatic driving system of the vehicle according to the embodiments of the present application can be based on an automatic driving hardware platform, use multiple automatic driving controllers and multiple sensors set accordingly, obtain perception information and corresponding control actions in the driving process and / or parking process in the automatic driving mode, use the whole vehicle information modular assembly to classify the perception information, use the driving and parking function state assembly to control the automatic driving vehicle to enter the corresponding driving working condition in the driving process and / or parking process according to the current driving scene, and use the automatic driving function scheduling assembly to drive the automatic driving software platform to work, thereby integrating the driving and parking into an integrated setting, adaptively changing the vehicle control according to the scene, improving the intelligence and applicability of the vehicle, and making the vehicle more intelligent and reliable, and improving the driving experience. Therefore, the technical problem that the steering wheel angle control in different forward and reverse gears cannot be solved in the automatic driving system, and the compatibility and switching of the subsystem in different scene changes and control algorithms cannot be solved in the related art are solved.

[0096] Next, the automatic driving method of the vehicle according to the embodiments of the present application is described with reference to the accompanying drawings.

[0097] Figure 5 is a flowchart of the automatic driving method of the vehicle according to the embodiments of the present application.

[0098] As Figure 5 shown, the automatic driving method of the vehicle comprises the following steps:.

[0099] In step S501, the perception information and corresponding control actions of the vehicle in the driving process and / or parking process in the automatic driving mode are acquired.

[0100] In step S502, the perception information is classified to obtain classified perception information.

[0101] In step S503, the automatic driving vehicle is controlled to enter the corresponding driving working condition of the driving process and / or parking process according to the current driving scene and control actions.

[0102] In step S504, the automatic driving vehicle is controlled to perform corresponding driving actions and / or parking actions based on the preset operating system and the classified perception information.

[0103] Optionally, in an embodiment of the present application, classifying the perception information to obtain classified perception information comprises: classifying information of a power domain, a cabin domain and a body domain of the vehicle according to a first preset classification rule; classifying perception information collected by information of a plurality of sensors according to a second preset classification rule; and classifying software modules of an automatic driving software platform according to a third preset classification rule.

[0104] Optionally, in an embodiment of the present application, the first preset classification rule comprises at least one of change frequency, signal attribute, transceiving relationship, application module and data volume; the second preset classification rule comprises at least one of sensing source, sensor characteristic and sensing result type; and the third preset classification rule comprises at least one of fusion function, environment reconstruction function, prediction function, decision function, path planning function and vehicle control function.

[0105] It should be noted that the foregoing explanation and description of the automatic driving system embodiment of the vehicle also apply to the automatic driving method of the vehicle of this embodiment, which will not be described here.

[0106] According to the vehicle automatic driving method provided by the embodiment of the present application, the perception information and corresponding control actions of the driving process and / or parking process in the automatic driving mode can be obtained based on the automatic driving hardware platform, by using the plurality of automatic driving controllers and the plurality of sensors arranged correspondingly, so that the perception information is classified by using the whole vehicle information modular assembly, the automatic driving vehicle is controlled to enter the corresponding driving working condition of the driving process and / or parking process by the driving and parking function state assembly in combination with the current driving scene, and the automatic driving software platform is driven to work by using the automatic driving function scheduling assembly, so that the driving and parking are integrated in an integrated setting, the vehicle control is adaptively changed according to the scene, the intelligence and applicability of the vehicle are improved, the vehicle is more intelligent and reliable, and the driving experience is improved. Therefore, the technical problem that the steering wheel angle control in different forward and reverse gears cannot be realized and the subsystems in the automatic driving system cannot be compatible and switched in different scene changes and control algorithms in the related art is solved.

[0107] Figure 6 The vehicle structure schematic diagram provided by the embodiment of the present application is provided. The vehicle can include:

[0108] The memory 601, the processor 602, and the computer program stored in the memory 601 and executable on the processor 602.

[0109] The processor 602 implements the vehicle automatic driving method provided in the above embodiment when executing the program.

[0110] Further, the vehicle further includes:

[0111] The communication interface 603 is used for communication between the memory 601 and the processor 602.

[0112] The memory 601 is used to store the computer program executable on the processor 602.

[0113] The memory 601 can include a high-speed RAM memory, and can also include a non-volatile memory, for example, at least one disk memory.

[0114] 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 with each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 6 Only one thick line is used to represent the bus in the figure, but it does not mean that there is only one bus or only one type of bus.

[0115] 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 complete communication between each other through an internal interface.

[0116] The processor 602 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the present application.

[0117] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the automatic driving method of the vehicle.

[0118] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does 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, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0119] Moreover, the terms "first", "second", "third", etc. are used herein only to describe different steps or categories of steps in a claim for patent purposes, and are not to be construed as indicating or implying relative importance of one step to another or a quantity of steps. Thus, features defined with "first", "second" or "third" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as, for example, two, three, etc., unless specifically defined otherwise.

[0120] Any process or method descriptions or blocks in flow charts herein, and elsewhere, can be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process, and alternate implementations are possible. In some embodiments, the processes or methods described herein can be accomplished by one or more hardware devices or modules or in changing wired or wireless connections between hardware devices. For example, one or more processors can be configured with one or more software applications or referred to as "programs" to carry out the processes or methods as described herein.

[0121] Logic and / or steps represented in flow charts herein, and elsewhere, can be embodied in computer-readable media, for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or a combination thereof. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can specifically include a hardware apparatus, such as a portable computer diskette, a hard disk, a computer memory, a programmable logic device, or a chip or chip set, or the like. The computer-readable medium can also include a hardware apparatus connected, whether wired or wireless, to the instruction execution system, apparatus, or device, or to a hardware apparatus that is in communication with the instruction execution system, apparatus, or device. The computer-readable medium can also be specifically a medium that transmits the program, such as through a wireless channel, over an electrical conduit, over the Internet, or on a telephone line, and the like. The computer-readable medium can also be specifically a medium that receives the program and records the program on the medium, such as a portable computer diskette or a hard disk or a computer memory, or the like.

[0122] It should be understood that parts of the present application can be realized in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be realized by software or firmware stored in a memory and executed by a suitable instruction execution system. If realized in hardware and in another embodiment, any one or a combination of the following technologies known in the art can be used: discrete logic circuit with logic gate circuit for implementing logic functions on data signals, application specific integrated circuit with suitable combination logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA), etc.

[0123] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by a program instructing the relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0124] In addition, each functional unit in each embodiment of the present application can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-mentioned integrated module can be realized in the form of hardware or in the form of a software functional module. The integrated module, if realized in the form of a software functional module and sold or used as an independent product, can also be stored in a computer readable storage medium.

[0125] The above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. An automatic driving system of a vehicle, characterized by comprising: The application relates to an automatic driving hardware platform, a vehicle information modular assembly, an automatic driving software platform, a driving and parking function state assembly and an automatic driving function scheduling assembly. The automatic driving hardware platform comprises a plurality of automatic driving controllers and a plurality of corresponding sensors arranged to obtain perception information and corresponding control actions in an automatic driving mode during driving and / or parking. The vehicle information modular assembly is used for classifying the perception information to obtain classified perception information. The vehicle information modular assembly comprises: An external system information modular unit is used for classifying information of a power domain, a cabin domain and a body domain of a vehicle according to a first preset classification rule. An intelligent sensor output information modular unit is used for classifying perception information collected by the plurality of sensors according to a second preset classification rule. An automatic driving domain controller information modular unit is used for classifying software modules of the automatic driving software platform according to a third preset classification rule. The first preset classification rule comprises at least one of variation frequency, signal attribute, transceiving relationship, application module and data volume; the second preset classification rule comprises at least one of sensing source, sensor characteristic and sensing result type; and the third preset classification rule comprises at least one of fusion function, environment reconstruction function, prediction function, decision function, path planning function and vehicle control function. The automatic driving software platform is used for controlling an automatic driving vehicle to perform corresponding driving actions and / or parking actions based on a preset operating system and the classified perception information. The driving and parking function state assembly is used for controlling the automatic driving vehicle to enter corresponding driving working conditions of the driving and / or parking process according to a current driving scene and the control actions. The automatic driving function scheduling assembly is used for driving the automatic driving software platform to work according to corresponding driving working conditions of the driving and / or parking process. The automatic driving function scheduling assembly judges the current driving working condition and driving target based on the classified perception information and driver operation to drive the automatic driving software platform to work in combination with the corresponding driving working condition.

2. The system of claim 1, wherein, The automatic driving hardware platform comprises a plurality of at least one front millimeter wave radar, at least one corner millimeter wave radar, at least one forward-looking camera, at least one surround-view camera, at least one fisheye camera, at least one ultrasonic sensor, an automatic driving domain controller, a steering controller, a brake controller, a vehicle domain controller, a chassis power controller, a body domain controller and a cabin domain controller.

3. The system of claim 2, wherein, The at least one front millimeter wave radar, the at least one forward-looking camera and the automatic driving domain controller are connected to transmit first target information perceived. The at least one corner millimeter wave radar and the automatic driving domain controller are connected to transmit target and drivable area information. The at least one surround-view camera and the automatic driving domain controller are connected to transmit second target information perceived. The at least one fisheye camera and the vehicle domain controller are connected to input original perception images. The at least one ultrasonic sensor and the automatic driving domain controller are connected to input ultrasonic echo signals. ​ The automatic driving domain controller is connected with the chassis power controller, the vehicle body domain controller and the cabin domain controller respectively to transmit control signals, network information and video information.

4. The system of claim 1, wherein, The automatic driving function scheduling component is specifically configured to identify a current scene based on the control action, automatic driving map information, vehicle positioning information, perceived road identification information, traffic sign information, garage information, parking space information and vehicle driving information, so as to drive the automatic driving software platform to work in combination with the corresponding driving working condition.

5. An automatic driving method of a vehicle, characterized by, The system of any one of claims 1-4, wherein the method comprises the steps of: obtaining perception information and corresponding control actions in a driving process and / or a parking process in an automatic driving mode; classifying the perception information to obtain classified perception information; the classifying the perception information to obtain classified perception information comprises: classifying information of a power domain, a cabin domain and a vehicle body domain according to a first preset classification rule; classifying perception information collected by the information of the plurality of sensors according to a second preset classification rule; classifying software modules of the automatic driving software platform according to a third preset classification rule; the first preset classification rule comprises at least one of a change frequency, a signal attribute, a transceiving relationship, an application module and a data volume; the second preset classification rule comprises at least one of a sensing source, a sensor characteristic and a sensing result type; the third preset classification rule comprises at least one of a fusion function, an environment reconstruction function, a prediction function, a decision function, a path planning function and a vehicle control function; controlling the automatic driving vehicle to enter a corresponding driving working condition of the driving process and / or the parking process according to a current driving scene and the control action; and controlling the automatic driving vehicle to perform corresponding driving actions and / or parking actions based on a preset operating system and the classified perception information; The automatic driving function scheduling component judges a current driving working condition and a driving target based on the classified perception information and driver operation, so as to drive the automatic driving software platform to work in combination with the corresponding driving working condition.

6. A vehicle characterized by comprising: comprise: a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the automatic driving method of the vehicle according to claim 5.

7. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the automatic driving method of the vehicle according to claim 5.

Images