WO2019047642A1

WO2019047642A1 - Control method and device applicable to self-driving car

Info

Publication number: WO2019047642A1
Application number: PCT/CN2018/098624
Authority: WO
Inventors: 郑超; 郁浩; 姜雨; 闫泳杉; 唐坤; 张云飞
Original assignee: 百度在线网络技术（北京）有限公司
Priority date: 2017-09-05
Filing date: 2018-08-03
Publication date: 2019-03-14
Also published as: CN107499258A

Abstract

Disclosed is a control method applicable to a self-driving car, the method comprising: generating, on the basis of acquired sensor information, a control instruction used to control a component on a controller area network bus of a self-driving car, and generating a controller area network bus signal corresponding to the control instruction (step 201); and inputting the controller area network bus signal to a controller area network bus, and generating monitoring data corresponding to a controller area network bus signal inputted by the component on the controller area network bus of the self-driving car to the controller area network bus (step 202). Further disclosed is a control device applicable to a self-driving car. The control method enables both control of components on a controller area network bus of a self-driving car and monitoring of operation of the components on the controller area network bus of the self-driving car during a driving process of the self-driving car at the same time, thus providing efficient control of the self-driving car while ensuring safety.

Description

Control method and device applied to self-driving car

This patent application claims Chinese patent application filed on September 5, 2017, with the application number of 201710792107.8, the applicant is Baidu Online Network Technology (Beijing) Co., Ltd., and the invention is entitled "Control Method and Device for Self-driving Cars" The priority of this application is hereby incorporated by reference in its entirety.

Technical field

The present application relates to the field of vehicles, and in particular to the field of automatic driving, and more particularly to a control method and apparatus for driving an autonomous vehicle.

Background technique

The safety of self-driving cars and the control efficiency of self-driving cars are the most critical indicators for autonomous vehicles. Therefore, how to design a control mode for autonomous vehicles with high efficiency and safety has become one of the key links in the development of the entire control system for autonomous vehicles.

Summary of the invention

The present application provides a control method and apparatus applied to an autonomous vehicle for solving the technical problems existing in the above background art.

The present application provides a control method applied to an autonomous driving vehicle, the method comprising: generating, based on the collected sensor information, a control instruction for controlling a component on a controller area network bus of the self-driving vehicle, and generating a control instruction corresponding to the Controller area network bus signal; input controller area network bus signal to controller area network bus, and generate controller on the controller area network bus of the self-driving car to the controller area network bus on the controller area network bus The monitoring data corresponding to the signal.

The present application provides a control device for an autonomous driving vehicle, the device comprising: a decision unit for generating a control command for controlling a component on a controller area network bus of the self-driving car based on the collected sensor information, and Generating a controller area network bus signal corresponding to the control instruction; an interaction unit for inputting the controller area network bus signal to the controller area network bus, and generating a component input to the controller on the controller area network bus of the self-driving vehicle The monitoring data corresponding to the controller area network bus signal on the local area network bus.

The control method and device for autonomous driving vehicle provided by the present application generates control commands for controlling components on a controller area network bus of an autonomous driving vehicle based on the collected sensor information, and generates control corresponding to the control command Local area network bus signal; input the controller area network bus signal to the controller area network bus, and generate a controller on the controller area network bus of the self-driving car to input the controller area network bus signal on the controller area network bus Corresponding monitoring data. Realizing the control of the components on the controller area network bus of the self-driving car at the same time and monitoring the operation of the components on the controller area network bus of the self-driving car driving the car during driving, thereby ensuring safety Control the self-driving car more efficiently.

DRAWINGS

Other features, objects, and advantages of the present application will become more apparent from the detailed description of the accompanying drawings.

1 shows a schematic diagram of a hardware structure of an autonomous vehicle suitable for use in the present application;

2 is a schematic structural view showing an embodiment of a control method applied to an autonomous driving vehicle according to the present application;

FIG. 3 illustrates an exemplary flowchart of a control method applied to an autonomous driving vehicle according to the present application;

Fig. 4 shows a schematic structural view of an embodiment of a control device applied to an autonomous vehicle according to the present application.

Detailed ways

The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention, rather than the invention. It is also to be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings.

FIG. 1 shows a schematic diagram of a hardware structure of an autonomous vehicle suitable for use in the present application.

As shown in FIG. 1, the self-driving car includes a CPU 101, a memory 102, a camera 103, a GPS 104, and an inertial navigation device 105. The CPU 101, the memory 102, the camera 103, the GPS 104, and the inertial navigation device 105 are connected to each other by a bus 106.

The engine control unit, brake unit, steering unit, and the like of the self-driving vehicle are connected via a CAN (Controller Area Network) bus. In other words, the components such as the engine control unit, the brake unit, and the steering unit of the self-driving automobile are components on the CAN bus of the self-driving automobile. When a component on the CAN bus of the self-driving car outputs a CAN bus signal, other components on the CAN bus of the self-driving car can receive the CAN bus signal, and the CAN bus signal is required on the CAN bus of the self-driving car. The component can process the CAN bus signal.

Please refer to FIG. 2, which shows a flow of one embodiment of a control method applied to an autonomous driving vehicle according to the present application. The control method applied to the self-driving automobile provided by the embodiment of the present application can be performed by an autonomous driving vehicle. The method includes the following steps:

Step 201: Generate a control instruction based on the sensor information, and generate a controller area network bus signal corresponding to the control instruction.

In the present embodiment, a control command for controlling a component on the CAN bus of the self-driving car of the self-driving car may be first generated based on the acquired sensor information. Components on the CAN bus of a self-driving car of an autonomous vehicle may include, but are not limited to, an engine control component, a brake component, and a steering component. The control commands for controlling components on the CAN bus of the self-driving car of the self-driving car may include, but are not limited to, an acceleration command, a deceleration command, a brake command, and a steering command. Control commands such as acceleration commands, deceleration commands, brake commands, and steering commands correspond to components on the CAN bus of different self-driving cars. For example, the brake command is an instruction for controlling a brake component on the CAN bus of the self-driving car, and the steering command is an instruction for controlling a steering component on the CAN bus of the self-driving car.

For example, the sensor information is a road condition image collected by the camera, and according to the multi-frame road condition image collected by the camera, before the auto-driving car drives to the traffic light on the driving route, the state of the traffic light is recognized as red, and the auto-driving car can be used. When the traffic light is within a preset distance, a control command for controlling a brake component in a component on the CAN bus of the self-driving car to perform a braking operation is generated.

In the present embodiment, after generating a control command for controlling a component on the CAN bus of the self-driving car of the self-driving car, a CAN bus signal corresponding to the control command may be generated.

For example, the sensor information is a road condition image collected by the camera, and according to the multi-frame road condition image collected by the camera, before the auto-driving car drives to the traffic light on the driving route, the state of the traffic light is recognized as red, and the auto-driving car can be used. Within a preset distance from the traffic light, a control command is generated for controlling the braking component in the components on the CAN bus of the self-driving car to perform the braking operation. The control command for controlling the brake operation of the brake component in the component on the CAN bus of the self-driving car can be converted into a CAN bus signal and input to the CAN bus, so that the brake component on the CAN bus of the self-driving car can be The CAN bus signal input to the CAN bus is received to perform a braking operation.

For another example, the sensor information is a position where the GPS collects the self-driving car, and the high-precision map determines that the road ahead of the self-driving car is a curve, and when the self-driving car travels to the start position of the curve, it can be generated for control. The steering component on the CAN bus of the self-driving car performs a control command for the steering operation. The control command for controlling the steering operation of the steering component in the component on the CAN bus of the self-driving car can be converted into a CAN bus signal input to the CAN bus, so that the steering component of the self-driving car can receive the CAN bus CAN bus signal, performing steering operation.

In some optional implementations of this embodiment, generating a CAN bus signal corresponding to a control command for controlling a component on the CAN bus of the self-driving car includes: generating a component on the CAN bus for controlling the self-driving car a control signal corresponding to the control command; smoothing a control signal corresponding to a control command for controlling a component on the CAN bus of the self-driving car; and a control command based on the CAN bus for controlling a component on the CAN bus of the self-driving car The corresponding relationship of the signals generates a CAN bus signal corresponding to the control signal.

The control signal corresponding to the control instruction for controlling the components on the CAN bus of the self-driving automobile may be generated by the CPU of the self-driving automobile, and the control signal corresponding to the control command may be output, and the PID (proportional-integral-derivative controller) algorithm may be used. The control signal corresponding to the output control command is smoothed, and then the conversion unit connected to the CPU can generate a CAN bus signal corresponding to the control signal based on the correspondence between the control signal and the controller area network bus signal. The conversion unit can be an FPGA (Field Programmable Gate Array).

For example, the sensor information is a position where the self-driving car is collected by the GPS, and the road ahead of the self-driving car is determined by the high-precision map as a curve, and when the self-driving car travels to the starting position of the curve, the self-driving car can be used. The CPU generates a control command for controlling a steering component on the CAN bus of the self-driving car to perform a steering operation. Then, the control command for performing the steering operation of the steering component in the component on the CAN bus for controlling the self-driving car can be converted into a CAN bus signal by the FPGA connected to the CPU, and input to the CAN bus through the CAN bus interface, thereby automatically The steering unit driving the car can receive the CAN bus signal on the CAN bus and perform a steering operation.

In some optional implementation manners of the embodiment, generating the CAN bus signal corresponding to the control instruction includes: generating a control instruction based on a correspondence between a control instruction for controlling a component on the CAN bus of the self-driving automobile and a CAN bus instruction Corresponding CAN bus command; generate CAN bus signal corresponding to CAN bus command.

A CAN bus command corresponding to a control command for controlling a component on the CAN bus of an autonomous vehicle such as an engine control component, a brake component, a steering component, or the like may be determined in advance, and is established to control an engine control component, a brake component, a steering component, and the like. The correspondence between the control commands of the components on the CAN bus of the self-driving car and the CAN bus commands. When it is necessary to generate a CAN bus signal corresponding to the control command, the control relationship between the control command of the component on the CAN bus for controlling the engine control component, the brake component, the steering component, and the like, and the CAN bus command may be generated to generate the control. The CAN bus command corresponding to the instruction.

For example, the sensor information is a position where the self-driving car is collected by GPS, and the road ahead of the self-driving car is determined by a high-precision map as a curve, and can be generated for control when the self-driving car travels to the start position of the curve. The steering component on the CAN bus of the self-driving car performs a control command for the steering operation. The steering component on the CAN bus for controlling the self-driving car can be generated according to the correspondence between the control command of the component on the CAN bus for controlling the engine control component, the brake component, the steering component, and the like, and the CAN bus command. The CAN bus command corresponding to the control command of the steering operation is executed, and then the CAN bus signal corresponding to the CAN bus command can be generated, and the CAN bus signal is input to the CAN bus, so that the steering component of the self-driving car can be received on the CAN bus. The CAN bus signal performs a steering operation.

Step 202: Input a CAN bus signal to the CAN bus, and generate monitoring data.

In the present embodiment, after the CAN bus signal corresponding to the control command for controlling the components on the CAN bus of the self-driving automobile of the self-driving automobile is generated by the step 201, the CAN bus signal can be input to the CAN bus. At the same time, the CAN bus signal on the CAN bus can be converted into monitoring data.

In this embodiment, the CAN bus signal on the CAN bus can be obtained, and the CAN bus signal on the CAN bus is parsed to obtain a CAN bus command, and the CAN bus command includes a command field or a data field, thereby generating a command field or data. The monitoring information of the preset format of the field.

For example, when the engine control unit on the CAN bus of the self-driving car sends a command for controlling the fuel injection amount to the oil quantity injection control unit, the CAN bus command corresponding to the command and the CAN bus signal corresponding to the CAN bus command are first generated in sequence. Then, the CAN bus signal corresponding to the CAN bus command is input to the CAN bus. The CAN bus signal can be obtained, and the CAN bus signal is parsed to obtain a CAN bus command. The CAN bus command includes a command field or a data field, that is, a field indicating a command of the fuel injection amount, thereby generating a command field or Monitoring information for the preset format of the data field. From the monitoring information, it is possible to determine a command for the engine control unit to transmit the controlled injection amount to the oil amount injection control unit.

In this embodiment, by inputting the CAN bus signal to the CAN bus and converting the CAN bus signal on the CAN bus into monitoring data, it is possible to simultaneously control the auto-driving car and the CAN bus of each self-driving car that monitors the self-driving car. The operation of each control unit realizes the monitoring of the self-driving car.

In some optional implementation manners of the embodiment, the monitoring data corresponding to the CAN bus signal input to the CAN bus by the component on the CAN bus of the self-driving automobile includes: receiving the CAN bus signal on the CAN bus through the CAN bus interface. And decoding the CAN bus signal to obtain a CAN command corresponding to the CAN bus signal; extracting a command field or a data field in the CAN bus command, and generating monitoring data including the command field or the data field.

For example, when a component on the CAN bus of an autonomous vehicle transmits commands or data to other components on the CAN bus of the self-driving car, firstly, a CAN bus command corresponding to the command or data, and a CAN corresponding to the CAN bus command are sequentially generated. The bus signal is then input to the CAN bus, and the CAN bus signal can be received through the CAN bus interface by using a conversion component such as an FPGA, the CAN bus signal is decoded, the CAN bus command corresponding to the CAN bus signal is obtained, and the CAN bus is extracted. A command field or data field in an instruction, and a monitoring data that contains a command field or data field.

In some optional implementation manners of the embodiment, the monitoring data corresponding to the CAN bus signal input to the CAN bus by the component on the CAN bus of the self-driving automobile includes: receiving the CAN bus signal on the CAN bus through the CAN bus interface. Then, the CAN bus controller can be used to parse the CAN bus signal to obtain a CAN bus command corresponding to the CAN bus signal; the command field or data field in the CAN bus command is extracted, and the monitoring data including the command field or the data field is generated.

For example, when a component on the CAN bus of an autonomous vehicle transmits commands or data to other components on the CAN bus of the self-driving car, firstly, a CAN bus command corresponding to the transmitted command or data is sequentially generated, and the CAN bus command corresponds to The CAN bus signal is then input to the CAN bus, and the CAN bus signal on the CAN bus can be received through the CAN bus interface. Then, the CAN bus signal can be analyzed by the CAN bus controller to obtain the CAN bus command corresponding to the CAN bus signal. The command field or data field in the CAN bus instruction is extracted, and the monitoring data including the command field or the data field is generated.

In some optional implementation manners of this embodiment, a single wide-angle camera may be used to collect road condition images in real time. Since the real-time road condition image can be used to identify the state of the obstacle during the driving process of the self-driving car, and input into the model predicting the driving behavior within the preset time period to predict the driving behavior within the preset time period, the self-driving car is When the environment is perceived, it needs to be applied to a large number of road condition images. The massive road condition image will occupy a large amount of bandwidth of the entire data transmission system of the self-driving car during the transmission process. Therefore, by using a single wide-angle camera to collect road condition images in real time, the environment is satisfied. At the same time of the perceived demand, the problem that the bandwidth of the entire data transmission system occupying the self-driving car is sharply increased due to the acquisition of the road condition image by the plurality of cameras is avoided.

Please refer to FIG. 3, which shows an exemplary flowchart of a control method applied to an autonomous driving vehicle according to the present application.

In Fig. 3, an in-vehicle brain, a camera, a GPS, an inertial navigation device IMU, a PID control unit, an autobox unit, and a CAN bus are shown. The vehicle brain can generate engine control components and brakes on the CAN bus for controlling the self-driving car according to the position of the self-driving car collected by the GPS, the attitude of the self-driving car collected by the inertial navigation device, and the road condition image captured by the camera. Control instructions for components and steering components. The autobox component can generate the CAN bus signal corresponding to the control command, input to the CAN bus through the CAN bus interface, and finally control the auto-driving car to perform operations such as acceleration, deceleration, braking, and steering. At the same time, the autobox component can convert the CAN bus signals input to the CAN bus from the engine control components, brake components and steering components on the CAN bus of the self-driving car into monitoring data.

Referring to FIG. 4, as an implementation of the method shown in the above figures, the present application provides an embodiment of a control device applied to an autonomous vehicle, the embodiment corresponding to the method embodiment shown in FIG. 2.

As shown in FIG. 4, the control device applied to the self-driving car includes: a decision unit 401, and an interaction unit 402. The determining unit 401 is configured to generate, according to the collected sensor information, a control instruction for controlling a component on a controller area network bus of the self-driving vehicle, and generate a controller area network bus signal corresponding to the control instruction; The interaction unit 402 is configured to input a controller area network bus signal to the controller area network bus, and generate a controller area network bus signal input to the controller area network bus by a component on the controller area network bus of the self-driving vehicle. Corresponding monitoring data.

In some optional implementation manners of the embodiment, the determining unit includes: a signal conversion subunit configured to generate a control signal corresponding to the control instruction; smoothing a control signal corresponding to the control instruction; and based on the control signal and the controller The corresponding relationship of the local area network bus signals generates a controller area network bus signal corresponding to the control signal.

In some optional implementation manners of the embodiment, the interaction unit includes: a signal decoding subunit configured to receive a controller area network bus signal on the controller area network bus through the controller area network bus interface, and to control The local area network bus signal is decoded to obtain a controller area network bus command corresponding to the controller area network bus signal; the command field or data field in the controller area network bus command is extracted, and the monitoring including the command field or the data field is generated. data.

In some optional implementation manners of the embodiment, the determining unit includes: an instruction conversion subunit configured to generate a controller local area network corresponding to the control instruction based on a correspondence between the control instruction and the controller area network bus instruction Bus command; generates a controller area network bus signal corresponding to the controller area network bus command.

In some optional implementation manners of the embodiment, the interaction unit includes: an instruction parsing subunit configured to receive, by using a controller area network bus interface, a controller area network bus signal on the controller area network bus, and using the control The local area network bus controller parses the controller area network bus signal to obtain a controller area network bus command corresponding to the controller area network bus signal; extracts a command field or a data field in the controller area network bus command, and generates a command including Monitoring data for fields or data fields.

In some optional implementation manners of the embodiment, the control device applied to the self-driving automobile further includes: an image acquisition unit configured to collect the road condition image in real time by using a single wide-angle camera.

The present application also provides an autonomous vehicle that can be configured with one or more processors; a memory for storing one or more programs, and one or more programs can include steps 201 for performing the above steps. The instruction of the operation described in -202. When one or more programs are executed by one or more processors, cause one or more processors to perform the operations described in steps 201-202 above.

The present application also provides a computer readable medium, which may be included in an autonomous vehicle, or may be separately present, not incorporated into an autonomous vehicle. The computer readable medium carries one or more programs that, when executed by an autonomous vehicle, cause the self-driving vehicle to generate a controller area network for controlling the self-driving vehicle based on the collected sensor information. Control instructions for components on the bus, and controller local area network bus signals corresponding to the generated control commands; inputting controller area network bus signals to the controller area network bus, and generating components on the controller area network bus of the self-driving vehicle The monitoring data corresponding to the controller area network bus signal input to the controller area network bus.

It should be noted that the computer readable medium described herein may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain or store a program, which can be used by or in connection with an instruction execution system, apparatus or device. In the present application, a computer readable signal medium may include a data signal that is propagated in the baseband or as part of a carrier, carrying computer readable program code. Such propagated data signals can take a variety of forms including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer readable signal medium can also be any computer readable medium other than a computer readable storage medium, which can transmit, propagate, or transport a program for use by or in connection with the instruction execution system, apparatus, or device. . Program code embodied on a computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality and operation of possible implementations of systems, methods and computer program products in accordance with various embodiments of the present application. In this regard, each block of the flowchart or block diagram can represent a module, a program segment, or a portion of code that includes one or more of the logic functions for implementing the specified. Executable instructions. It should also be noted that in some alternative implementations, the functions noted in the blocks may also occur in a different order than that illustrated in the drawings. For example, two successively represented blocks may in fact be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts, can be implemented in a dedicated hardware-based system that performs the specified function or operation. Or it can be implemented by a combination of dedicated hardware and computer instructions.

The units involved in the embodiments of the present application may be implemented by software or by hardware. The described unit may also be provided in a processor, for example, as a processor comprising a decision unit, an interaction unit. Wherein, the names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the decision unit may also be described as "for generating a controller for controlling an autonomous driving vehicle based on the collected sensor information. A control command for a component on the local area network bus, and a unit for generating a controller area network bus signal corresponding to the control command.

The above description is only a preferred embodiment of the present application and a description of the principles of the applied technology. It should be understood by those skilled in the art that the scope of the invention referred to in the present application is not limited to the specific combination of the above technical features, and should also be covered by the above technical features without departing from the inventive concept. Other technical solutions formed by any combination of their equivalent features. For example, the above features are combined with the technical features disclosed in the present application, but are not limited to the technical features having similar functions.

Claims

A control method for an autonomous driving vehicle, characterized in that the method comprises:

Generating, according to the collected sensor information, a control instruction for controlling a component on a controller area network bus of the self-driving vehicle, and generating a controller area network bus signal corresponding to the control instruction;

Inputting the controller area network bus signal to the controller area network bus, and generating the monitoring data corresponding to the controller area network bus signal input to the controller area network bus by the component on the controller area network bus of the self-driving vehicle .
The method according to claim 1, wherein the generating the controller area network bus signal corresponding to the control instruction comprises:

Generating a control signal corresponding to the control instruction;

Smoothing a control signal corresponding to the control instruction;

And generating a controller area network bus signal corresponding to the control signal based on a correspondence between the control signal and the controller area network bus signal.
The method according to claim 2, wherein the monitoring data corresponding to the controller area network bus signal input to the controller area network bus of the controller local area network bus of the self-driving vehicle comprises:

Receiving, by the controller area network bus interface, a controller area network bus signal on the controller area network bus, and decoding the controller area network bus signal to obtain a controller area network corresponding to the controller area network bus signal Bus instruction

Extracting command fields or data fields from the controller area network bus instructions and generating monitoring data containing the command fields or data fields.
The method according to claim 1, wherein the generating the controller area network bus signal corresponding to the control instruction comprises:

Generating a controller area network bus instruction corresponding to the control instruction based on a correspondence between the control instruction and the controller area network bus command;

Generating a controller area network bus signal corresponding to the controller area network bus command.
The method according to claim 4, wherein the monitoring data corresponding to the controller area network bus signal input to the controller area network bus of the controller local area network bus of the self-driving vehicle comprises:

Receiving, by the controller area network bus interface, a controller area network bus signal on the controller area network bus, and parsing the controller area network bus signal by using a controller area network bus controller to obtain the controller area network bus signal Corresponding controller area network bus command;

Extracting command fields or data fields from the controller area network bus instructions and generating monitoring data containing the command fields or data fields.
The method according to any one of claims 1 to 5, wherein the method further comprises:

A single wide-angle camera captures road conditions in real time.
A control device for an autonomous driving vehicle, characterized in that the control device applied to an autonomous driving vehicle comprises:

a decision unit, configured to generate, according to the collected sensor information, a control instruction for controlling a component on a controller area network bus of the self-driving vehicle, and generate a controller area network bus signal corresponding to the control instruction;

An interaction unit for inputting the controller area network bus signal to the controller area network bus, and generating a controller area network bus on the controller area network bus of the self-driving vehicle to be input to the controller area network bus on the controller area network bus The monitoring data corresponding to the signal.
The control device for an autonomous vehicle according to claim 7, wherein the decision unit comprises:

a signal conversion subunit configured to generate a control signal corresponding to the control instruction; perform a smoothing process on the control signal corresponding to the control instruction; and generate the control signal based on a correspondence between the control signal and a controller area network bus signal Corresponding controller area network bus signal.
The control device for an autonomous driving vehicle according to claim 8, wherein the interaction unit comprises:

a signal decoding subunit configured to receive a controller area network bus signal on a controller area network bus through a controller area network bus interface, and decode the controller area network bus signal to obtain the controller area network A controller area network bus command corresponding to the bus signal; extracting a command field or a data field in the controller area network bus command, and generating monitoring data including the command field or data field.
The control device for an autonomous vehicle according to claim 7, wherein the decision unit comprises:

The instruction conversion subunit is configured to generate a controller area network bus instruction corresponding to the control instruction based on a correspondence between the control instruction and the controller area network bus instruction; and generate a controller area network corresponding to the controller area network bus instruction Network bus signal.
The control device for an autonomous driving vehicle according to claim 10, wherein the interaction unit comprises:

An instruction parsing subunit configured to receive a controller area network bus signal on a controller area network bus through a controller area network bus interface, and to parse the controller area network bus signal by using a controller area network bus controller to obtain The controller area network bus signal corresponding to the controller area network bus command; extracting a command field or a data field in the controller area network bus command, and generating monitoring data including the command field or the data field.
The control device for autonomously driving a vehicle according to any one of claims 7-11, wherein the control device applied to the self-driving car further comprises:

The image acquisition unit is configured to collect road condition images in real time using a single wide-angle camera.
An autonomous vehicle characterized in that it comprises:

One or more processors;

Memory for storing one or more programs,

The one or more processors are caused to perform the method of any of claims 1-6 when the one or more programs are executed by the one or more processors.
A computer readable storage medium having stored thereon a computer program, wherein the program is executed by a processor to implement the method of any of claims 1-6