Disclosure of Invention
The application provides a vehicle controller, a vehicle and a vehicle control method, which are used for realizing the extension of computational power, so that the requirements of different automatic driving scenes can be met by using the same platform.
In a first aspect, the present application provides a vehicle controller comprising:
a baseboard and at least one core processor board located on the baseboard, the core processor board to provide corresponding computational power according to a scenario of autonomous driving, the scenario of autonomous driving including at least one of level L3 autonomous driving, level L4 autonomous driving, and level L5 autonomous driving;
the baseboard and each of the core arithmetic processor boards each include a communication interface, and the communication interface of the baseboard and the communication interface of the core arithmetic processor board are connected by a board-to-board connector.
Optionally, the communication interface includes one or more of a high-speed serial computer expansion bus interface, a camera serial interface, and a vehicle-mounted ethernet interface.
Optionally, the substrate further comprises a plurality of sensor interfaces.
Optionally, the sensor interface includes at least one of a camera interface, a millimeter wave radar interface, an ultrasonic radar interface, and a laser radar interface.
Optionally, the board-to-board connector is a floating board-to-board connector.
In a second aspect, the present application provides a vehicle comprising: the vehicle controller according to the first aspect and any one of the possible designs of the first aspect.
Optionally, the method further includes:
a plurality of sensors coupled to the vehicle controller.
Optionally, the sensor includes:
at least one of a camera, a millimeter wave radar, an ultrasonic radar, and a laser radar.
In a third aspect, the present application provides a vehicle control method for a microprocessor on a substrate of a vehicle controller according to the first aspect and any one of the possible designs of the first aspect, the method comprising:
the microprocessor acquires road information data around the vehicle;
the microprocessor processes the road information data under the calculation force and generates path information indicating a travel path of the vehicle.
Optionally, the microprocessor acquires road information data around the vehicle, and specifically includes:
the microprocessor acquires data acquired by the camera through a gigabit multimedia serial link technology;
and/or acquiring data acquired by the laser radar through a gigabit Ethernet;
and/or acquiring data collected by the millimeter wave radar through a controller area network with flexible data rate.
The application provides a vehicle controller, includes: the system comprises a baseboard and at least one core arithmetic processor board positioned on the baseboard, wherein the core arithmetic processor board is used for providing corresponding computing power according to an automatic driving scene, the automatic driving scene comprises at least one of L3-level automatic driving, L4-level automatic driving and L5-level automatic driving, the baseboard and each core arithmetic processor board comprise communication interfaces, and the communication interfaces of the baseboard and the core arithmetic processor board are connected through a board-to-board connector. Like this, divide into two kinds of plate layer structures with vehicle controller, two kinds of plate layer structures of standardized interface connection through board to board connector for the base plate can the different core operation processor boards of adaptation, realizes the nimble extension of calculation power, and can provide the required calculation power of different scenes of autopilot through the quantity of control core operation processor board, makes vehicle controller satisfy the demand of different autopilot scenes.
Detailed Description
To make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the drawings in the present application, and it is obvious that the described embodiments are some, but not all embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
An Automatic Driving Control Unit (ADCU) needs to have the capabilities of multi-sensor fusion, positioning, path planning, decision Control, and high-speed communication. For example, the autopilot domain controller may be provided with multiple capabilities by externally connecting multiple types of sensors.
The type and number of sensors are different for different levels of autopilot functionality. At present, a specific automatic driving domain controller corresponds to automatic driving functions of different levels, each specific automatic driving domain controller is provided with a specific core operation processor (System on Chip, SOC), and each core operation processor has fixed calculation power, so that the automatic driving domain controller cannot adapt to different core operation processors, cannot realize the expansion of the calculation power, and cannot meet the requirements of different automatic driving scenes by using the same platform.
And with the continuous development of the SOA (Service-Oriented Architecture) and OTA (Over-the-Air Technology), the requirements for upgrading and expanding the user software functions are increasing, so that the fixed computing power of the autopilot domain controller becomes a factor that restricts the autopilot domain controller.
In view of the above problem, the present application provides a vehicle controller including: the system comprises a baseboard and at least one core arithmetic processor board positioned on the baseboard, wherein the core arithmetic processor board is used for providing corresponding computing power according to an automatic driving scene, the automatic driving scene comprises at least one of L3-level automatic driving, L4-level automatic driving and L5-level automatic driving, the baseboard and each core arithmetic processor board comprise communication interfaces, and the communication interfaces of the baseboard and the core arithmetic processor board are connected through a board-to-board connector. Like this, divide into two kinds of plate layer structures with vehicle controller, two kinds of plate layer structures of standardized interface connection through board to board connector for the base plate can the different core operation processor boards of adaptation, realizes the nimble extension of calculation power, and can provide the required calculation power of different scenes of autopilot through the quantity of control core operation processor board, makes vehicle controller satisfy the demand of different autopilot scenes. Further, since the number of the core arithmetic processor boards is adjustable, the computational power of the vehicle controller is adjustable, thereby promoting the development of the vehicle controller.
The technical solution of the present application will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 1 shows a schematic structural diagram of a vehicle controller according to an embodiment of the present application. As shown in fig. 1, the vehicle controller of the present embodiment includes:
a base board 101 and at least one core processor board 102 located on the base board, the core processor board 102 being configured to provide a corresponding computational power according to a scenario of autonomous driving, the scenario of autonomous driving including at least one of level L3 autonomous driving, level L4 autonomous driving, and level L5 autonomous driving;
the baseboard 101 and each core processor board 101 include a communication interface, and the communication interface of the baseboard 101 and the communication interface of the core processor board 102 are connected by a board-to-board connector 103.
The vehicle controller is, for example, an automatic driving area controller, and is divided into a substrate 101 and a core arithmetic processor Board (SOC Board)102, where the substrate 101 can provide a Board level power supply, and a safety microprocessor (safety Microcontroller Unit) is designed on the substrate 101, and the realization of automatic driving needs to collect information of a road environment by depending on an environment sensing sensor, transmit the collected data to the safety microprocessor for processing, so as to identify obstacles, feasible roads, and the like, and plan a route, formulate a vehicle speed, automatically control the driving of an automobile, and the like according to an identification result.
Therefore, a plurality of cameras, millimeter wave radars, ultrasonic radars, laser radars and other devices can be externally connected, so that the safety processor can complete functions of image recognition, data processing and the like. Specifically, can include a plurality of sensor interfaces on the base plate 101, the sensor interface includes at least one in camera interface, millimeter wave radar interface, ultrasonic radar interface and the laser radar interface to make safe microprocessor carry out the interaction of data through camera interface and camera, carry out the interaction of data through millimeter wave radar interface and millimeter wave radar, carry out the interaction of data through ultrasonic radar interface and ultrasonic radar, carry out the interaction of data through laser radar interface and laser radar. For example, at least twelve camera interfaces, four lidar interfaces, six millimeter wave radar interfaces, and twelve ultrasonic radar interfaces are included, so that at least twelve cameras (cameras), four lidar, six millimeter wave radar, and twelve ultrasonic radar can be accessed. Two image interfaces may also be included to interface in two-way image displays.
As an implementation manner, the secure microprocessor on the substrate 101 is connected to the camera through a camera interface, for example, may be connected to the camera through a Low Voltage Differential Signaling (LVDS) video coaxial line. Low voltage differential signaling is a low swing differential signaling technique that enables signals to be transmitted at rates of several hundred Mbps on differential PCB lines or balanced cables, and its low voltage swing and low current drive output enable low noise and low power consumption. And then, a Gigabit Multimedia Serial Link (GMSL) technology can be adopted to perform data interaction and processing with the camera. The gigabit multimedia serial link is a transmission link formed by a serializer and a deserializer, and can simultaneously support four-way camera data transmission by using a four-channel deserializer of the gigabit multimedia serial link.
The ultrasonic radar Interface on the substrate 101 may be a Serial Peripheral Interface (SPI), so that the secure microprocessor performs data interaction and processing with the ultrasonic radar through the SPI. The serial peripheral interface is a synchronous peripheral interface, and can enable the single chip microcomputer to communicate with various peripheral devices in a serial mode to exchange information.
The millimeter-wave radar interface on the substrate 101 may be a Vehicle Ethernet (Vehicle Ethernet) interface, so that the secure microprocessor may perform Data interaction and processing with the millimeter-wave radar through the Vehicle Ethernet interface by using a Controller Area Network with Flexible Data rate (CAN-FD). The controller local area network bus adopts a two-wire serial communication protocol, is based on a non-destructive arbitration technology, is distributed and controlled in real time, and has high safety due to a reliable error processing and detecting mechanism, and the controller local area network with flexible data rate has flexible data rate on the basis of the controller local area network, thereby providing larger bandwidth.
The lidar interface on the substrate 101 may be a vehicle-mounted ethernet interface, so that the secure microprocessor performs data interaction and processing with the lidar via the vehicle-mounted ethernet interface by using a gigabit ethernet. The transmission speed of a gigabit ethernet network is 1000 megabits per second.
Due to the large amount of calculation, the automatic driving domain controller needs a processor with strong matching core calculation power, can provide support for automatic driving with calculation power of different levels, and the automatic driving level is increased by one level, and the calculation power needs to be increased by at least ten times, for example, 2 TOPS calculation power is needed for automatic driving of level L2, 24 TOPS calculation power is needed for automatic driving of level L3, 320 TOPS calculation power is needed for automatic driving of level L4, and 4000 TOPS calculation power is needed for automatic driving of level L5. The L2 level automatic driving refers to partial function automation, the basic operation is completed by the vehicle, the driver is responsible for peripheral monitoring and taking over the vehicle at any time, and the functions mainly include acc (adaptive Cruise control) automatic cruising, automatic car following, automatic parking and the like. The L3 level automatic driving refers to conditional automation, the vehicle can realize automatic acceleration and deceleration, steering, periphery monitoring and the like in a specific environment, the operation of a driver is not needed, but in the automatic driving process of the vehicle, the driver needs to prepare for taking over the vehicle at any time, and the system can give a prompt for taking over the vehicle to the driver. The L4 level automatic driving is highly automated, the system can autonomously perform all driving operations, and can completely autonomously go on the road, and the driver can do what he wants on the vehicle. Level L5 autopilot refers to full automation, and under all conditions, the autopilot system is able to complete all driving tasks.
The current automatic driving domain controller is limited by the hardware design and structure of the controller, all functions are usually integrated on a whole hardware single board, and the flexibility is low. For example, in the L2 level automatic driving, a safety microprocessor and a core operation processor are designed on a substrate, the core operation processor provides calculation force required by the L2 level automatic driving, the microprocessor performs data interaction and processing with a camera through a camera interface by adopting a gigabit multimedia serial link technology, performs data interaction and processing with an ultrasonic radar through an ultrasonic radar interface, and performs data interaction and processing with the millimeter radar through a millimeter radar interface by adopting a controller local area network with flexible data rate.
However, the existing autopilot domain controller cannot adapt to different core operation processors, and cannot realize the expansion of computational power, so that the requirements of different autopilot scenes cannot be met by using the same platform.
In the embodiment of the present application, at least one core arithmetic processor board 102 is designed on the substrate 101, the core arithmetic processor board 102 is used for bearing a core arithmetic processor, and the number of the core arithmetic processor boards 102 on the substrate 101 is controlled, so that the core arithmetic processor can provide corresponding computing power according to an automatic driving scene. The scenarios of the automatic driving may include at least one of L3 level automatic driving, L4 level automatic driving, and L5 level automatic driving.
For the L3 level automatic driving, referring to fig. 2, a core arithmetic processor board 102 may be designed on a substrate 101, the core arithmetic processor board 102 carries a core arithmetic processor to provide the computation power required by the L3 level automatic driving, a security microprocessor on the substrate 101 interacts data with a camera, a millimeter wave radar, an ultrasonic radar, a laser radar, and the like, and processes each received data under the support of the computation power provided by the core arithmetic processor, thereby implementing the L3 level automatic driving.
For the L4 level automatic driving, referring to fig. 3, two core arithmetic processor boards 102 may be designed on a substrate 101 to provide the computational power required by the L4 level automatic driving, and the safety microprocessing on the substrate 101 interacts data with a camera, a millimeter wave radar, an ultrasonic radar, a laser radar, and the like, and processes each received data with the support of the computational power provided by the two core arithmetic processors, thereby implementing the L4 level automatic driving.
For the L5-level automatic driving, referring to fig. 4, a plurality of core arithmetic processing boards 102 may be designed on a substrate 101 to provide the computational power required for the L5-level automatic driving, a security microprocessor of the substrate 101 performs data interaction with a camera, a millimeter wave radar, an ultrasonic radar, a laser radar, and the like, and processes each received data with the support of the computational power provided by the plurality of core arithmetic processing boards, thereby implementing the L5-level automatic driving.
The baseboard 101 and each core processor board 102 include a plurality of communication interfaces, which may include standardized interfaces such as a Peripheral Component Interconnect Express (PCIE) Interface, a Camera Serial Interface (CSI), a Vehicle Ethernet (Vehicle Ethernet) Interface, and the like, so as to be compatible with different combinations and numbers of sensors of L3-L5 level auto-driving.
The baseboard 101 and the core arithmetic processor board 102 perform data interaction through a communication interface, and the communication interface of the baseboard 101 and the communication interface of the core arithmetic processor board 102 are connected through a board-to-board connector 103. The board-to-board connector 103 may connect power and signals between boards to complete all connections, and the board-to-board connector 103 may be, for example, a floating board-to-board connector, which is a board-to-board connector having a function of absorbing and correcting errors in the ± X and ± Y directions when mounted on a substrate, and can eliminate substrate mounting misalignment and positional deviation when fitted, thereby accurately aligning the boards and enhancing shock resistance. And the board-to-board connector 103 integrates a single power pin, the maximum through-current of the single power pin can reach 3A, and the transmission rate of 8+ Gbps is supported.
The application provides a vehicle controller, includes: the system comprises a baseboard and at least one core arithmetic processor board positioned on the baseboard, wherein the core arithmetic processor board is used for providing corresponding computing power according to an automatic driving scene, the automatic driving scene comprises at least one of L3-level automatic driving, L4-level automatic driving and L5-level automatic driving, the baseboard and each core arithmetic processor board comprise communication interfaces, and the communication interfaces of the baseboard and the core arithmetic processor board are connected through a board-to-board connector. Like this, divide into two kinds of plate layer structures with vehicle controller, two kinds of plate layer structures of standardized interface connection through board to board connector for the base plate can the different core operation processor boards of adaptation, realizes the nimble extension of calculation power, and can provide the required calculation power of different scenes of autopilot through the quantity of control core operation processor board, makes vehicle controller satisfy the demand of different autopilot scenes.
The embodiment of the application also provides a vehicle, which comprises a vehicle controller.
The vehicle controller includes a base board and at least one core processor board on the base board, the core processor board providing corresponding computing power according to a scenario of autonomous driving including L3-level autonomous driving, L4-level autonomous driving, L5-level autonomous driving, and the like. The baseboard and each core arithmetic processor board include a communication interface, and the communication interface of the baseboard and the communication interface of the core arithmetic processor board are connected through a board-to-board connector.
The vehicle also comprises a plurality of sensor interfaces connected with the vehicle controller, the sensor interfaces are used for being connected with an external camera, a millimeter wave radar, an ultrasonic radar, a laser radar and the like, so that a microprocessor in the vehicle controller can receive road surface environment information and the like sent by the camera, the millimeter wave radar, the ultrasonic radar, the laser radar and other sensors, the vehicle controller has the capabilities of multi-sensor fusion, positioning, path planning, decision control, wireless communication, high-speed communication and the like, and the vehicle controller controls the vehicle to automatically drive.
The vehicle that this application provided includes vehicle controller, and vehicle controller includes the base plate and is located at least one core arithmetic processor on the base plate, provides the required computing power of different scenes of autopilot through the quantity of control core arithmetic processor board for vehicle controller satisfies the demand of different autopilot scenes.
An embodiment of the present application further provides a vehicle control method, shown with reference to fig. 5, including:
s101, the microprocessor acquires road surface information data around the vehicle.
The microprocessor acquires road information data around the vehicle through an external camera, a millimeter wave radar, an ultrasonic radar, a laser radar and the like.
S102, the microprocessor processes the road information data under the action of the computing force provided by the core computing processor to generate the path information.
After receiving the road information data around the vehicle, the microprocessor processes the road information data under the action of the computational force provided by the core arithmetic processor, identifies obstacles, feasible roads and the like, and generates path information according to the identification result, wherein the path information is used for indicating the driving path of the vehicle, so that the vehicle automatically drives according to the driving path generated by the microprocessor.
As one implementation, the microprocessor acquires data acquired by the camera through a gigabit multimedia serial link technology, and/or acquires data acquired by the laser radar through a gigabit Ethernet, and/or acquires data acquired by the millimeter wave radar through a controller area network with a flexible data rate.
According to the vehicle control method, the microprocessor generates the path information under the action of the calculation force provided by the core operation processor to indicate the automatic driving of the vehicle, and the number of the core operation processors is adjustable, so that the vehicle can meet different automatic driving scene requirements.
Fig. 6 shows a hardware structure diagram of an electronic device according to an embodiment of the present application. As shown in fig. 6, the electronic device 20 is configured to implement the operations corresponding to the electronic device in any of the method embodiments described above, where the electronic device 20 of this embodiment may include: memory 21, processor 22 and communication interface 23.
A memory 21 for storing computer instructions. The Memory 21 may include a Random Access Memory (RAM), a Non-Volatile Memory (NVM), at least one disk Memory, a usb disk, a removable hard disk, a read-only Memory, a magnetic disk or an optical disk.
A processor 22 for executing the computer instructions stored by the memory to implement the vehicle control method in the above-described embodiments. Reference may be made in particular to the description relating to the method embodiments described above. The Processor 22 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The communication interface 23 may be connected to the processor 212. Processor 22 may control communication interface 23 to perform the functions of receiving and transmitting signals.
The electronic device provided in this embodiment can be used to execute the vehicle control method, and its implementation manner and technical effect are similar, and this embodiment is not described herein again.
The present application also provides a computer readable storage medium, in which computer instructions are stored, and the computer instructions are executed by a processor to implement the methods provided by the above-mentioned various embodiments.
The present application also provides a computer program product comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read by at least one processor of the device from a computer-readable storage medium, and execution of the computer instructions by the at least one processor causes the device to perform the methods provided by the various embodiments described above.
The embodiment of the present application further provides a chip, which includes a memory and a processor, where the memory is used to store computer instructions, and the processor is used to call and execute the computer instructions from the memory, so that a device in which the chip is installed executes the method described in the above various possible embodiments.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. The true scope and spirit of the application, in which the specification and examples are considered to be exemplary only, is indicated by the following claims.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same. Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: it is also possible to modify the solutions described in the previous embodiments or to substitute some or all of them with equivalents. And the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.