CN111599200A - Autonomous valet parking perception decision-making method, system and vehicle terminal - Google Patents

Abstract

The invention provides an autonomous passenger-riding parking perception decision method, an autonomous passenger-riding parking perception decision system and a vehicle-mounted terminal, wherein the autonomous passenger-riding perception decision method comprises the following steps: establishing a communication connection between a first vehicle-mounted terminal and at least one second vehicle-mounted terminal; the first vehicle-mounted terminal receives second perception target information sent by the second vehicle-mounted terminal; the method comprises the steps that a first vehicle-mounted terminal obtains first perception target information; the first vehicle-mounted terminal generates first route planning information according to the first perception target information and the second perception target information, and generates first direction control instruction information according to the first route planning information so as to control the vehicle to run. The autonomous passenger-riding parking perception decision method, the autonomous passenger-riding parking perception decision system and the vehicle-mounted terminal can realize detection of the target in the self-vehicle perception blind area, continuous tracking and motion situation prediction of the dynamic target in the super-perception range, earlier and more accurate planning control, reliability of a perception system is improved, and collision risk is reduced.

Description

Autonomous valet parking perception decision-making method, system and vehicle terminal

technical field

The invention relates to the technical field of communication networks, in particular to an autonomous valet parking perception decision-making method, system and vehicle terminal.

Background technique

In traffic accidents caused by many reasons, traffic problems caused by line of sight and blind spots account for a considerable proportion. Due to the structure of the vehicle itself, some positions on the vehicle will bring a certain range of visual blind spots to the driver, which will have a very serious impact on the driver's safe driving.

Under the condition of low-speed parking, the visual blind spot caused by the occlusion of the vehicle in front and surrounding vehicles is more serious. Due to the existence of the visual blind spot, the rear vehicle cannot detect obstacles such as vehicles and pedestrians in front and around it in time, which has a great impact on driving safety. hidden danger. The sensing scheme of the existing parking technology is generally a multi-sensor heterogeneous fusion sensing scheme. By installing two or more sensing sensors on the body to cover the unequal range around the vehicle, the perception of specific targets and environments is realized. However, even if the heterogeneous redundancy scheme is used, due to the large difference in the sensing range and applicable environment of different types of sensors, the detection performance of different types of targets is quite different, and there are obvious perception defects, which still cannot be used in the sensing range and Reliability reaches the expected level.

Therefore, there is an urgent need for a valet parking perception decision-making method, system and vehicle terminal that can combine the V2V technology to expand the perception range of the self-vehicle to the group perception range within the communication range, break through the limitation of the self-vehicle perception range, and greatly expand the perception area. , and realize the advance response to the target that is about to enter the perception area of the self-vehicle, and can also combine the decision-making information of the surrounding vehicles to realize the horizontal and vertical pre-control of the self-vehicle.

SUMMARY OF THE INVENTION

The technical problem solved by the present invention is to provide an autonomous valet parking perception decision-making method, system and vehicle terminal, which can realize the detection of the target in the blind area of the self-vehicle perception, and continuously obtain the dynamic target shared by other vehicles within the communication range. It can realize continuous tracking and motion situation prediction of dynamic targets in the super-perceptual range, judge the relative motion relationship between the target and the target based on the trajectory and route of the vehicle, and then respond to risky dynamic targets in advance, so as to achieve an earlier and faster response. Precise planning control improves the reliability of the perception system and reduces the risk of collision.

The present invention solves its technical problem by adopting the following technical scheme to realize:

An autonomous valet parking perception decision-making method, comprising: establishing a communication connection between a first vehicle-mounted terminal and at least one second vehicle-mounted terminal; the first vehicle-mounted terminal receiving second sensing target information sent by the second vehicle-mounted terminal; the first vehicle-mounted terminal Obtaining first sensing target information; the first vehicle-mounted terminal generates first route planning information according to the first sensing target information and the second sensing target information, and generates first direction control instruction information according to the first route planning information to control vehicle driving.

In a preferred embodiment of the present invention, the above-mentioned step of establishing a communication connection between the first vehicle-mounted terminal and at least one second vehicle-mounted terminal includes: acquiring location information of the first vehicle-mounted terminal; acquiring the first vehicle-mounted terminal within a preset range of the first vehicle-mounted terminal. Second vehicle-mounted terminal information, establish a communication connection between the first vehicle-mounted terminal and the second vehicle-mounted terminal.

In a preferred embodiment of the present invention, the step of acquiring the first sensing target information by the first vehicle-mounted terminal includes: the first vehicle-mounted terminal collects the first sensing target information through a vehicle-mounted sensor, and the vehicle-mounted sensor at least includes a camera, an ultrasonic radar, a millimeter wave One of radar and lidar.

In a preferred embodiment of the present invention, the above-mentioned first vehicle-mounted terminal generates first route planning information according to the first sensing target information and the second sensing target information, and generates first direction control instruction information according to the first route planning information, so as to The step of controlling the driving of the vehicle includes: the first vehicle-mounted terminal acquires third sensing target information in an area where the first vehicle-mounted terminal is located according to the first sensing target information and the second sensing target information.

In a preferred embodiment of the present invention, the above-mentioned first vehicle-mounted terminal generates first route planning information according to the first sensing target information and the second sensing target information, and generates first direction control instruction information according to the first route planning information, so as to The step of controlling the driving of the vehicle includes: the first vehicle terminal determines whether a collision will occur according to the first sensing target information, the second sensing target information and the current driving route information of the vehicle, and the first sensing target information and the second sensing target information include the sensing target information. Relative motion information of the target; when the first vehicle-mounted terminal collides with any target in the first sensing target information or the second sensing target information, the first route plan is generated according to the second sensing target information and the first sensing target information information.

In a preferred embodiment of the present invention, the above-mentioned first vehicle-mounted terminal generates first route planning information according to the first sensing target information and the second sensing target information, and generates first direction control instruction information according to the first route planning information, so as to The step of controlling the driving of the vehicle includes: the first vehicle-mounted terminal sending the first sensing target information, the first route planning information and the first direction control instruction information to the second vehicle-mounted terminal.

An autonomous valet parking perception decision-making method, comprising: establishing a communication connection between a first vehicle-mounted terminal and at least one second vehicle-mounted terminal; the first vehicle-mounted terminal receiving second sensing target information and second driving information sent by the second vehicle-mounted terminal , the second driving information includes the second route planning information and the second direction control instruction information; the first on-board terminal obtains the first sensing target information; the first on-board terminal obtains the first sensing target information, the second sensing target information and the second driving The information generates first route planning information, and generates first direction control instruction information according to the first route planning information, so as to control the driving of the vehicle.

In a preferred embodiment of the present invention, the above-mentioned first vehicle-mounted terminal generates the first route planning information according to the first sensing target information, the second sensing target information and the second driving information, and generates the first direction according to the first route planning information The step of controlling the instruction information to control the driving of the vehicle includes: the first vehicle-mounted terminal obtains third sensing target information in the area where the first vehicle-mounted terminal is located according to the first sensing target information and the second sensing target information, and the third sensing target information includes the sensing target information. relative motion information of the target; the first vehicle-mounted terminal judges whether the current vehicle will collide according to the relative motion information of the sensing target, the second driving information and the current driving route information of the vehicle; if a collision occurs, the third sensing target information and The second driving information generates the first route planning information; if there is no collision, the driving continues according to the current driving route information.

An autonomous valet parking perception decision-making system, comprising: a first vehicle-mounted terminal and at least one second vehicle-mounted terminal; after the first vehicle-mounted terminal is connected with the at least one second vehicle-mounted terminal, it receives a second vehicle-mounted terminal sent by the second vehicle-mounted terminal. Perceiving target information, acquiring first perceiving target information, generating first route planning information according to the first perceiving target information and second perceiving target information, and generating first direction control instruction information according to the first routing information to control the vehicle Driving; after the second vehicle-mounted terminal establishes a connection with the first vehicle-mounted terminal, it sends the second sensing target information to the first vehicle-mounted terminal.

An in-vehicle terminal includes: a sensing unit, a processing unit, a control unit and an interaction unit; the sensing unit is used to collect sensing target information around the vehicle body and send the sensing target information to the processing unit; the processing unit is used to receive the self-vehicle The sensing target information, as well as the sensing target information and decision-making information sent by other vehicle-mounted terminals, generate decision-making information and send it to the control unit; the control unit is used to send execution instructions to the vehicle-mounted equipment according to the decision-making information; the interaction unit is used to communicate with other vehicle-mounted terminals. Establish connections, and receive or send perception target information and decision-making information.

The technical effect achieved by the present invention by adopting the above technical solutions is: on the basis of the perception of the self-vehicle, by exchanging perception target information with the vehicles within the communication range, the perception area of the self-vehicle is spatially expanded, and the target in the blind area of the self-vehicle perception is realized. At the same time, the secondary verification and confirmation of the jointly detected target increases the confidence of target perception and improves the robustness and reliability of the perception system; and by continuously collecting dynamic targets shared by other vehicles within the communication range It can realize continuous tracking and motion situation prediction of dynamic targets in the super-perceptual range, judge the relative motion relationship between the target and the target based on the trajectory and route of the vehicle, and then respond to risky dynamic targets in advance, so as to achieve an earlier and faster response. Precise planning control.

The above description is only an overview of the technical solutions of the present invention, in order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand , the preferred embodiments are given below and described in detail in conjunction with the accompanying drawings.

Description of drawings

1 is a flowchart of a first embodiment of an autonomous valet parking perception decision-making method of the present invention;

2 is a flowchart of a second embodiment of an autonomous valet parking perception decision-making method of the present invention;

3 is a schematic structural diagram of an autonomous valet parking perception decision-making system according to a third embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a vehicle-mounted terminal according to a fourth embodiment of the present invention.

Detailed ways

In order to further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose of the invention, the embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same throughout or similar elements or elements having the same or similar functions. The embodiments described below are only some of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the embodiments of the present invention. Through the description of the specific embodiments, the technical means and effects adopted by the present invention to achieve the predetermined purpose can be more deeply and specifically understood, and the accompanying drawings are only for reference and description, not for the present invention. limit.

The method provided by the invention is suitable for several AVP vehicles within a specified communication range, and the vehicle-mounted terminal performs dynamic ad hoc network based on the C-V2X protocol. Each AVP vehicle can establish a connection with other vehicles within the specified range, obtain relevant perception control information, and also share the self-vehicle perception control information with other vehicles.

Please refer to FIG. 1 , which is a flowchart of a first embodiment of an autonomous valet parking perception decision-making method of the present invention.

As shown in FIG. 1 , the first embodiment of the autonomous valet parking perception decision-making method of the present invention includes the following steps:

Step S11: establishing a communication connection between the first vehicle-mounted terminal and at least one second vehicle-mounted terminal;

The step of establishing a communication connection between the first vehicle-mounted terminal and the at least one second vehicle-mounted terminal includes: acquiring position information of the first vehicle-mounted terminal; acquiring information of the second vehicle-mounted terminal within a preset range of the first vehicle-mounted terminal, establishing the first vehicle-mounted terminal and the The communication connection of the second vehicle terminal.

Step S12: the first vehicle-mounted terminal receives the second sensing target information sent by the second vehicle-mounted terminal;

Specifically, perceptual target information, including target position, target speed, timestamp, confidence and other information.

Step S13: the first vehicle-mounted terminal acquires the first sensing target information;

Specifically, step S13: the first vehicle-mounted terminal acquires the first sensing target information, including: the first vehicle-mounted terminal collects the first sensing target information through the vehicle-mounted sensor, and the vehicle-mounted sensor at least includes a camera, an ultrasonic radar, a millimeter-wave radar, and a laser radar. A sort of.

Step S14: The first vehicle-mounted terminal generates first route planning information according to the first sensing target information and the second sensing target information, and generates first direction control instruction information according to the first route planning information to control the driving of the vehicle.

Specifically, in one embodiment, the first vehicle-mounted terminal will analyze and judge after receiving the above-mentioned decision control information, and the target position of each sensing target can be used to assist the first vehicle-mounted terminal in determining how to use the sensing target from other vehicles. information and update the path plan of the vehicle.

Specifically, step S14: the first vehicle-mounted terminal generates first route planning information according to the first sensing target information and the second sensing target information, and generates first direction control instruction information according to the first route planning information, so as to control the driving of the vehicle, including : The first vehicle-mounted terminal acquires the third sensing target information in the area where the first vehicle-mounted terminal is located according to the first sensing target information and the second sensing target information.

Specifically, step S14: the first vehicle-mounted terminal generates first route planning information according to the first sensing target information and the second sensing target information, and generates first direction control instruction information according to the first route planning information, so as to control the driving of the vehicle, including : The first vehicle-mounted terminal judges whether a collision will occur according to the first sensing target information, the second sensing target information and the current driving route information of the vehicle, and the first sensing target information and the second sensing target information include relative motion information of the sensing target; When the first vehicle-mounted terminal collides with any target in the first sensing target information or the second sensing target information, the first route planning information is generated according to the second sensing target information and the first sensing target information.

Specifically, step S14: the first vehicle-mounted terminal generates first route planning information according to the first sensing target information and the second sensing target information, and generates first direction control instruction information according to the first route planning information to control the driving of the vehicle, and then The method includes: the first vehicle-mounted terminal sends the first sensing target information, the first route planning information and the first direction control instruction information to the second vehicle-mounted terminal.

Please refer to FIG. 2 . FIG. 2 is a flowchart of an autonomous valet parking perception decision-making method according to a second embodiment of the present invention.

As shown in FIG. 2 , the second embodiment of the present invention's autonomous valet parking perception decision-making method includes the following steps:

Step S21: establishing a communication connection between the first vehicle-mounted terminal and at least one second vehicle-mounted terminal;

Step S22: the first vehicle-mounted terminal receives the second sensing target information and the second driving information sent by the second vehicle-mounted terminal, and the second driving information includes the second route planning information and the second direction control instruction information;

Specifically, perceptual target information, including target position, target speed, timestamp, confidence and other information. The second driving information includes position information of surrounding vehicles, in particular of front and rear vehicles, global and/or local path planning, and lateral and longitudinal control commands.

Step S23: the first vehicle-mounted terminal acquires the first sensing target information;

Step S24: The first vehicle-mounted terminal generates first route planning information according to the first sensing target information, the second sensing target information, and the second driving information, and generates first direction control instruction information according to the first route planning information, so as to control the driving of the vehicle .

Specifically, in one embodiment, the first vehicle-mounted terminal analyzes and judges according to the above-mentioned decision control information, and the local path and global path information (second route planning information) can be used to judge the travel plan and target position of other vehicles , which can be used to assist the ego vehicle in judging how to use the perceptual target information from other cars and update the ego car’s path planning; the received lateral and longitudinal control commands of other cars can be used as the lowest-level decision-making control reference to assist the ego car’s path. Planning and horizontal and vertical control to achieve pre-control and pre-response

Specifically, the first vehicle-mounted terminal generates first route planning information according to the first sensing target information, the second sensing target information, and the second driving information, and generates first direction control instruction information according to the first route planning information, so as to control the driving of the vehicle The steps include: the first vehicle-mounted terminal obtains third perception target information in the area where the first vehicle-mounted terminal is located according to the first perception target information and the second perception target information, and the third perception target information includes relative motion information of the perception target; The in-vehicle terminal determines whether the current vehicle will collide according to the relative motion information of the sensing target, the second driving information and the current driving route information of the vehicle; if a collision occurs, the first route is generated according to the third sensing target information and the second driving information planning information; if there is no collision, continue to drive according to the current driving route information.

The autonomous valet parking perception decision-making method provided by the present invention, the V2V-based autonomous valet parking perception decision-making system, on the basis of self-vehicle perception, exchanges perception target information with vehicles within the communication range through the V2V module, thereby expanding spatially. The self-vehicle perception area is realized, the detection of the target in the blind area of the self-vehicle perception is realized, and the jointly detected target is checked and confirmed twice, which increases the confidence of the target perception and improves the reliability; The basic information of dynamic targets shared by other vehicles can realize continuous tracking and motion situation prediction of dynamic targets in the super-perceptual range, judge the relative motion relationship with the target based on the trajectory and route of the self-vehicle, and then respond to risky dynamic targets in advance. , to achieve earlier and more accurate planning control; and this method can realize formation driving and horizontal and vertical pre-control in specific scenarios by directly sharing the planning decision-making information of surrounding vehicles, reducing the probability of emergency braking and steering, reducing the Collision risk and reduced vehicle energy consumption. Through collaborative perception and system control, efficiency and reliability are improved, and it is less dependent on infrastructure such as field terminals, and is easy to promote and mass-produce.

Please refer to FIG. 3 , which is a schematic structural diagram of an autonomous valet parking perception decision-making system according to a third embodiment of the present invention.

As shown in FIG. 3 , the autonomous valet parking perception decision-making system according to the third embodiment of the present invention includes: a first on-board terminal and at least one second on-board terminal; a communication connection between the first on-board terminal and at least one second on-board terminal Then, receive the second sensing target information sent by the second vehicle-mounted terminal, obtain the first sensing target information, and then generate the first route planning information according to the first sensing target information and the second sensing target information, and according to the first route planning information The first direction control instruction information is generated to control the driving of the vehicle; after the second vehicle-mounted terminal establishes a connection with the first vehicle-mounted terminal, the second sensing target information is sent to the first vehicle-mounted terminal.

Specifically, in another embodiment, the system workflow further includes the following steps: S1, establish a connection, the first vehicle-mounted terminal sends broadcast handshake information through the interaction unit, and communicates with the vehicle (the second vehicle-mounted terminal) within the communication range according to specific rules. ) handshake to confirm the establishment of the connection; S2, the first on-board terminal broadcasts and sends perception target information, decision-making planning information, and control information within the networking range; S3, the first on-board terminal receives the information of other vehicles (the second on-board terminal) within the networking range. Perceiving target information, decision planning information, and control information; S4, the processing unit of the first vehicle-mounted terminal analyzes and processes the perception target information, decision-making planning information, and control information from other vehicles (second vehicle-mounted terminal) according to the set rules; S5, The processing unit of the first vehicle-mounted terminal synthesizes the sensing target information of the own vehicle, and the sensing target information, decision-making planning information and control information from other vehicles (second vehicle-mounted terminal) comprehensively generates the own-vehicle decision-making planning information and control instructions, and sends them to the control unit; S6 , the control unit of the first vehicle-mounted terminal feeds back the horizontal and vertical control instructions actually executed by the vehicle to the processing unit, so as to assist the processing unit to make the next decision-making plan.

Please refer to FIG. 4 , which is a schematic structural diagram of a vehicle-mounted terminal according to a fourth embodiment of the present invention.

As shown in FIG. 4 , the vehicle-mounted terminal according to the fourth embodiment of the present invention includes: a sensing unit, a processing unit, a control unit and an interaction unit; the sensing unit is used to collect sensing target information around the vehicle body and send the sensing target information to processing unit; the processing unit is used to receive the perception target information of the own vehicle, as well as the perception target information and decision planning information sent by other vehicle terminals, generate decision planning information and send it to the control unit; the control unit is used to send the information to the vehicle according to the decision planning information. The device sends execution instructions; the interaction unit is used to establish connections with other vehicle-mounted terminals, and to receive or send perception target information and decision-making planning information.

Specifically, in one embodiment, the perception unit includes various types of sensors for AVP functions, such as cameras, ultrasonic radars, millimeter-wave radars, and lidars, etc., which are responsible for the perception of the vehicle's own environment, and send the perception data generated by the sensors to into the processing unit for processing. The processing unit is responsible for performing arithmetic processing based on the perception target information and decision-making control data of other vehicles, combined with the relevant information of the own vehicle, to generate control data and transmit it to the control unit. The control unit is responsible for converting the decision control data sent by the processing unit into vehicle control commands and assigning them to different actuators to respond to the relevant commands. The interaction unit is responsible for directly establishing a connection with the AVP vehicle within the communication range, transmitting the relevant sensing and control information agreed in the protocol, and transmitting the information to the processing unit on the own vehicle for analysis and processing. It should be pointed out that the interaction unit is the information transmission window of the vehicle-mounted terminal. From the establishment of the connection between the vehicle-mounted terminal of the current vehicle and other vehicle-mounted terminals, to the transmission of own vehicle information, and the reception of other vehicle information, all are carried out through this unit.

Specifically, in one embodiment, the other vehicle information received by the processing unit from the interaction unit includes perception target information and decision control information. Perceived target information includes encapsulation according to the specified protocol, including target position, target speed, timestamp, confidence and other information; after the processing unit receives this information, it will analyze and process the information according to a certain algorithm to assist the self-vehicle to carry out decision making. In addition to perceiving target information, the interaction unit can also receive decision-making control information of other vehicles within the communication range, including local path planning and global path planning of other vehicles, as well as horizontal and vertical control instructions of other vehicles. These decision control information will be analyzed and judged after entering the processing unit of the own vehicle. The local path and global path information can be used to judge the travel plan and target position of other vehicles, and can be used to assist the own vehicle to determine how to use the perceived target information from other vehicles. And update the path planning of the own vehicle; the received horizontal and vertical control commands of other vehicles can be used as the lowest-level decision-making control reference to assist and influence the own vehicle to carry out path planning and horizontal and vertical control, so as to achieve pre-control and pre-response.

Specifically, in another embodiment, the perception unit is responsible for collecting the perception data of the vehicle itself, including visual perception information, radar perception information, and the like. The processing unit not only processes the sensing target information from the own vehicle, but also receives the sensing target information, decision planning information and control information from other vehicles within the communication range. , decision planning information and control information are processed and shared with other vehicles within the communication range to assist other vehicles in enhancing perception decision-making.

It should be understood that although the steps in the flowcharts of FIG. 1 and FIG. 2 are displayed in sequence according to the arrows, these steps are not necessarily executed in the sequence indicated by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order and may be performed in other orders. Moreover, at least a part of the steps in FIG. 1 and FIG. 2 may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution sequence is also It does not have to be performed sequentially, but may be performed alternately or alternately with other steps or at least a portion of sub-steps or stages of other steps.

The preferred embodiments of the present invention have been described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the specific details of the above-mentioned embodiments. The above-mentioned embodiments and accompanying drawings are exemplary, and the modules or processes in the accompanying drawings are not necessarily It is necessary to implement the embodiments of the present invention and should not be construed as a limitation of the present invention. Within the scope of the technical concept of the present invention, a variety of simple modifications and combinations can be made to the technical solutions of the present invention, and these simple modifications and combinations belong to the present invention. protected range.

Claims (10)

1. An autonomous valet parking perception decision-making method, wherein the autonomous valet parking perception decision-making method comprises: establishing a communication connection between the first vehicle-mounted terminal and at least one second vehicle-mounted terminal; receiving, by the first vehicle-mounted terminal, second sensing target information sent by the second vehicle-mounted terminal; obtaining, by the first vehicle-mounted terminal, first sensing target information; The first vehicle-mounted terminal generates first route planning information according to the first sensing target information and the second sensing target information, and generates first direction control instruction information according to the first route planning information, so as to control the driving of the vehicle . 2. The autonomous valet parking perception decision-making method according to claim 1, wherein the step of establishing a communication connection between the first vehicle-mounted terminal and at least one second vehicle-mounted terminal comprises: obtaining location information of the first vehicle-mounted terminal; Acquire information of a second vehicle-mounted terminal within a preset range of the first vehicle-mounted terminal, and establish a communication connection between the first vehicle-mounted terminal and the second vehicle-mounted terminal. 3. The autonomous valet parking perception decision-making method according to claim 1, wherein the step of acquiring the first perception target information by the first vehicle-mounted terminal comprises: The first vehicle-mounted terminal collects the first sensing target information through vehicle-mounted sensors, and the vehicle-mounted sensors include at least one of a camera, an ultrasonic radar, a millimeter-wave radar, and a laser radar. 4. The autonomous valet parking perception decision-making method according to claim 1, wherein the first vehicle-mounted terminal generates first route planning information according to the first perception target information and the second perception target information , and the steps of generating first direction control instruction information according to the first route planning information to control the driving of the vehicle include: The first vehicle-mounted terminal acquires, according to the first sensing target information and the second sensing target information, third sensing target information in an area where the first vehicle-mounted terminal is located. 5 . The autonomous valet parking perception decision-making method according to claim 1 , wherein the first vehicle-mounted terminal generates first route planning information according to the first perception target information and the second perception target information. 6 . , and the steps of generating first direction control instruction information according to the first route planning information to control the driving of the vehicle include: The first vehicle terminal determines whether a collision will occur according to the first sensing target information, the second sensing target information and the current driving route information of the vehicle, and the first sensing target information and the second sensing target information include the sensing target. relative motion information; When the first vehicle-mounted terminal will collide with any target in the first sensing target information or the second sensing target information, generate the data according to the second sensing target information and the first sensing target information First route planning information. 6. The autonomous valet parking perception decision-making method according to claim 1, wherein the first vehicle-mounted terminal generates first route planning information according to the first perception target information and the second perception target information, and The step of generating first direction control instruction information according to the first route planning information to control the driving of the vehicle includes: The first vehicle-mounted terminal sends the first sensing target information, the first route planning information and the first direction control instruction information to the second vehicle-mounted terminal. 7. An autonomous valet parking perception decision-making method, wherein the autonomous valet parking perception decision-making method comprises: establishing a communication connection between the first vehicle-mounted terminal and at least one second vehicle-mounted terminal; receiving, by the first vehicle-mounted terminal, second sensing target information and second driving information sent by the second vehicle-mounted terminal, where the second driving information includes second route planning information and second direction control instruction information; obtaining, by the first vehicle-mounted terminal, first sensing target information; The first vehicle terminal generates first route planning information according to the first sensing target information, the second sensing target information and the second driving information, and generates first direction control instruction information according to the first route planning information , to control the driving of the vehicle. 8 . The autonomous valet parking perception decision-making method according to claim 7 , wherein the first vehicle-mounted terminal generates the information according to the first perception target information, the second perception target information and the second driving information. 9 . The first route planning information, and generating the first direction control instruction information according to the first route planning information, so as to control the driving of the vehicle, the steps include: The first vehicle-mounted terminal acquires third perception target information in the area where the first vehicle-mounted terminal is located according to the first perception target information and the second perception target information, where the third perception target information includes the relative motion of the perception target information; The first vehicle-mounted terminal determines whether the current vehicle will collide according to the relative motion information of the sensing target, the second driving information and the current driving route information of the vehicle; If a collision occurs, generating first route planning information according to the third sensing target information and the second driving information; If there is no collision, continue to drive according to the current driving route information. 9. An autonomous valet parking perception decision-making system, wherein the autonomous valet parking perception decision-making system comprises: a first vehicle-mounted terminal and at least one second vehicle-mounted terminal; After the first vehicle-mounted terminal is connected to at least one second vehicle-mounted terminal for communication, it receives the second sensing target information sent by the second vehicle-mounted terminal, obtains the first sensing target information, and then according to the first sensing target information generating first route planning information with the second perceptual target information, and generating first direction control instruction information according to the first route planning information, so as to control the driving of the vehicle; After the second vehicle-mounted terminal establishes a connection with the first vehicle-mounted terminal, the second vehicle-mounted terminal sends second sensing target information to the first vehicle-mounted terminal. 10. A vehicle-mounted terminal, characterized in that the vehicle-mounted terminal comprises: a sensing unit, a processing unit, a control unit and an interaction unit; the sensing unit, configured to collect sensing target information around the vehicle body, and send the sensing target information to the processing unit; The processing unit is configured to receive the sensing target information of the own vehicle, as well as the sensing target information and decision-making information sent by other vehicle-mounted terminals, generate decision-making information and send it to the control unit; The control unit is configured to send an execution instruction to the vehicle-mounted device according to the decision information The interaction unit is used for establishing connection with other vehicle-mounted terminals, and receiving or sending sensing target information and decision-making information.

Images