CN111290386A - Path planning method and device and carrying tool - Google Patents

Abstract

The invention discloses a path planning method and device and a delivery vehicle. Wherein, the method comprises the following steps: acquiring a first image of a target object in front of a first vehicle, wherein the first image is a radar image; extracting feature information of a target object from the first image; identifying the type of the target object according to the characteristic information, wherein the type comprises the following steps: obstacles and liquids located on the ground in front; it is determined whether to alter the planned route of the first vehicle depending on the type. The invention solves the technical problem that whether the liquid on the ground is an obstacle or not cannot be distinguished in the related technology, and the path planning is influenced.

Description

Path planning method and device, and vehicle

technical field

The present invention relates to the field of unmanned driving, and in particular, to a path planning method and device, and a vehicle.

Background technique

In the related art, during the driving process of the unmanned vehicle, for the sake of safety, it is necessary to identify whether the object in front of the vehicle is an obstacle or a non-obstruction. When identifying obstacles, the radar signal installed on the unmanned vehicle can be used for identification. However, since the radar image obtained based on the radar signal is determined based on the radar echo signal, it is difficult to recognize that the object ahead is distributed in the The water on the ground is also an obstacle, which is easy to cause errors in judgment. For the above problems, no effective solution has been proposed yet.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a path planning method, device, and vehicle, so as to at least solve the technical problem in the related art that it is impossible to distinguish whether the liquid on the ground is an obstacle, which affects path planning.

According to an aspect of the embodiments of the present invention, a path planning method is provided, including: collecting a first image of a target object located in front of a first vehicle, where the first image is a radar image; extracting a target object's image from the first image characteristic information; identifying the type of the target object according to the characteristic information, wherein the types include: obstacles and liquids on the ground ahead; determining whether to change the planned route of the first vehicle according to the type.

Optionally, collecting the first image of the target object located in front of the first vehicle includes: scanning the target object through a radar device installed in the first vehicle to obtain the first image; extracting feature information of the target object from the first image, Including: extracting the shape of the target object from the first image.

Optionally, identifying the type of the target object according to the feature information includes: determining the type of the target object based on the shape of the target object in the first image.

Optionally, determining the type of the target object based on the shape of the target object in the first image includes: when the shape of the target object is a regular shape, determining that the target object is an obstacle; when the shape of the target object is an irregular shape, determining The target object is liquid.

Optionally, determining that the target object is an obstacle includes: judging whether the target object is from a second vehicle in front of the first vehicle; when the judgment result indicates that the target object is not from the second vehicle and the shape of the target object is a regular shape, determining the target The object is an obstacle.

Optionally, judging whether the target object is from a second vehicle in front of the first vehicle includes: acquiring a second image of the second vehicle, where the second image is an RGB image; inputting the second image into a machine learning model for analysis to obtain the first image. 2. The operation status of the vehicle and, wherein, the operation status includes: spraying operation and no spraying operation; the machine learning model is obtained by training multiple sets of data, and each set of data in the multiple sets of data includes: the second vehicle The image and the image used to mark the second vehicle are labels of the working state; when the working state is a spraying operation, the type of the spraying object corresponding to the spraying operation is determined; when the type is consistent with the type of the target object, the target object is determined from the second vehicle.

Optionally, before determining whether to change the planned route of the first vehicle according to the type, the method further includes: acquiring attitude information of the second vehicle and information of the road where the second vehicle is located; predicting the driving direction of the second vehicle based on the attitude information; When the driving direction of the second vehicle changes and there is a road adjacent to the road where the second vehicle is located in the changed driving direction, the first vehicle is controlled to continue to travel according to the planned route.

Optionally, when the driving direction of the second vehicle does not change, the first vehicle is controlled to change the planned route to avoid obstacles.

Optionally, before controlling the first vehicle to change the planned route, the method further includes: acquiring the relative speed of the first vehicle and the second vehicle; when the relative speed is greater than 0, controlling the first vehicle to change the planned route; when the relative speed is less than 0 or When it is equal to 0, the first vehicle is controlled to continue to travel according to the planned route.

Optionally, the attitude information includes: the head direction of the second vehicle.

Optionally, the method further includes: determining that the driving direction of the second vehicle is changed after the head direction of the second vehicle is changed and after the head direction is changed and travels for a preset period of time according to the changed head direction.

Optionally, determining whether to change the driving route of the first vehicle according to the type includes: when the type is an obstacle, then modifying the planned route of the first vehicle, wherein the target object is avoided in the revised planned route; When the liquid is present, the vehicle is controlled to continue driving according to the current planned route.

According to another aspect of the embodiments of the present application, a path planning device is provided, comprising: a collection module for collecting a first image of a target object located in front of a first vehicle, where the first image is a radar image; an extraction module, The feature information of the target object is extracted from the first image; the identification module is used to identify the type of the target object according to the feature information, wherein the types include: obstacles and liquids on the ground ahead; Determines whether to change the planned route of the first vehicle.

Optionally, the acquisition module is used for scanning the target object through the radar device installed in the first vehicle to obtain the first image; the extraction module is used for extracting the shape of the target object from the first image.

Optionally, an identification module, configured to determine the type of the target object based on the shape of the target object in the first image.

Optionally, the identification module is configured to determine that the target object is an obstacle when the shape of the target object is a regular shape; and determine that the target object is a liquid when the shape of the target object is an irregular shape.

According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, the storage medium includes a stored program, wherein when the program runs, the device where the storage medium is located is controlled to execute the above path planning method.

According to another aspect of the embodiments of the present application, a vehicle is provided, comprising: an electronic device, the electronic device comprising: a memory for storing program instructions; a processor for retrieving the program instructions stored in the memory, Perform the following functions: collect a first image of the target object located in front of the first vehicle, the first image is a radar image; extract feature information of the target object from the first image; identify the type of the target object according to the feature information, wherein the type Including: obstacles and liquids on the ground ahead; depending on the type, whether to change the planned route of the first vehicle.

In the embodiment of the present invention, the method of identifying the type of the target object in front based on the radar image is adopted, so that the identification of obstacles or liquids can be realized according to the final identification result, so as to avoid misjudgment, and further solve the problem of inability to distinguish between the ground and the ground in the related art. Whether the liquid is an obstacle affects the technical problem of path planning.

Description of drawings

The accompanying drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the attached image:

1 is a schematic flowchart of a path planning method according to an embodiment of the present application;

2 is a schematic structural diagram of a path planning apparatus according to an embodiment of the present application;

FIG. 3 is a schematic structural diagram of a vehicle according to an embodiment of the present application.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only Embodiments are part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

It should be noted that the terms "first", "second" and the like in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

According to an embodiment of the present invention, a method embodiment of a path planning method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings may be executed in a computer system such as a set of computer-executable instructions, and, Although a logical order is shown in the flowcharts, in some cases steps shown or described may be performed in an order different from that herein.

FIG. 1 is a path planning method according to an embodiment of the present invention. As shown in FIG. 1 , the method includes the following steps:

Step S102, collecting a first image of the target object located in front of the first vehicle, where the first image is a radar image;

In some embodiments of the present application, collecting the first image of the target object located in front of the first vehicle includes: scanning the target object through a radar device installed in the first vehicle to obtain the first image of the target object, in order to ensure the accuracy of the detection results Accuracy, the radar equipment that collects images can be multiple equipment installed in different positions of the vehicle, for example, a radar equipment is placed on the left and right ends of the top position of the vehicle, or multiple types of radar equipment can be used in combination, for example, the millimeter Wave radar and ultrasonic radar are used in combination; it should be noted that the target object can be vehicles, branches on both sides of the road, pedestrians and other objects; the feature information of the target object is extracted from the first image above, and the feature information can be the shape of the target object , state of motion, size, etc.

Step S104, extracting feature information of the target object from the first image;

It should be noted that the feature information includes, but is not limited to, the shape, motion state, and volume of the target object.

Step S106, identifying the type of the target object according to the feature information, and determining the type of the target object based on the shape of the target object in the first image, there are two cases, when the shape of the target object is a regular shape, it is determined that the target object is an obstacle. ; When the shape of the target object is irregular, it is determined that the target object is liquid. It should be noted that a regular shape is a shape with a smooth boundary, and an irregular shape is a shape with an uneven boundary. When the target object is an irregular shape, the points reflected by the radar are irregular, and when the target object is a regular shape When , the target object is determined to be an obstacle; when the shape of the target object is an irregular shape, it is determined that the target object is a liquid.

In another optional embodiment, identifying the type of the target object according to the feature information includes: determining the type of the target object based on the shape of the target object in the first image, for example, when the target object is a car parked on the side of the road On a car, when the radar device scans the car, it can be determined based on the deep learning visual algorithm that it is a car; similarly, when the target object is a bicycle parked on the side of the road, it can be determined based on the deep learning visual algorithm. a bicycle.

In an embodiment of the present application, when the points reflected by the radar are not arranged regularly, it is considered that the liquid on the ground is water. Secondly, the liquid can be determined to be other compounds in combination with the driving environment in front of the first vehicle. For example, when the lidar is combined with other signal acquisition devices to identify that the vehicle in front of the first vehicle is a tanker, it is determined that the type of liquid is gasoline or diesel.

Step S108, determining whether to change the planned route of the first vehicle according to the type.

In an optional embodiment of the present application, when determining whether the target object is an obstacle: it may be first determined whether the target object is from a second vehicle in front of the first vehicle; when the determination result indicates that the target object is not from the second vehicle, and When the shape of the target object is a regular shape, it is determined that the target object is an obstacle, that is, all objects that do not belong to the second vehicle and are identified as regular shapes are regarded as obstacles.

In an optional embodiment of the present application, in order to determine whether the target object is from the second vehicle and the accuracy of the result, when judging whether the target object is from the second vehicle in front of the first vehicle, the first Two images, the second image is an RGB image; then the second image is input into the machine learning model for analysis to obtain the working state of the second vehicle and based on the machine learning model to determine the working state of the second vehicle to further determine whether the target object comes from The second vehicle, wherein, the operation status includes but is not limited to the following situations: the first operation status is in the spraying operation; the second operation status is not performing the spraying operation; the machine learning model is obtained through multiple sets of data training, wherein multiple sets of Each set of data in the data includes, but is not limited to: an image of the second vehicle and a label used to mark the image of the second vehicle as a working state; when the working state is a spraying operation, determine the size of the spraying object corresponding to the spraying operation. Type; when the type is consistent with the type of the target object, it is determined that the target object is from the second vehicle.

In an optional embodiment of the present application, before determining whether to change the planned route of the first vehicle according to the type, the method further includes: acquiring attitude information of the second vehicle and information of the road where the second vehicle is located; predicting the first vehicle based on the attitude information 2. The driving direction of the vehicle; when the driving direction of the second vehicle changes and there is a road adjacent to the road where the second vehicle is located in the changed driving direction, the first vehicle is controlled to continue to travel according to the planned route.

In an optional embodiment of the present application, when the driving direction of the second vehicle does not change, the first vehicle is controlled to change the planned route to avoid obstacles.

In an optional embodiment of the present application, before controlling the first vehicle to change the planned route, the method further includes: acquiring the relative speed of the first vehicle and the second vehicle; when the relative speed is greater than 0, controlling the first vehicle to change the planned route ; when the relative speed is less than 0 or equal to 0, the first vehicle is controlled to continue to travel according to the planned route. Among them, the relative speed is the difference between the speed of the first vehicle and the second vehicle; when the speed of the first vehicle is greater than the speed of the second vehicle, the two vehicles may collide at this time, so the previous planned route must be changed. ; When the speed of the first vehicle is lower than the speed of the second vehicle, at this time, because the relative distance between the second vehicle and the first vehicle is increasing, no collision will occur, and the vehicle can continue to travel according to the previously planned route.

It should be noted that the attitude information includes but is not limited to: the head direction of the second vehicle.

In an optional embodiment of the present application, the method further includes: after the head direction of the second vehicle is changed and the head direction of the second vehicle is changed and the vehicle head is driven for a preset period of time according to the changed head direction, determining that the travel direction of the second vehicle occurs. Change.

In another optional embodiment of the present application, whether to change the driving route of the first vehicle is determined according to the type of the target object, and the types include obstacles and liquids. When it is determined that the type of the target object is an obstacle, the Planning a route, in which the revised planning route is used to avoid the target object; when the type of the target object is determined to be liquid, the vehicle is controlled to continue driving according to the current planned route, that is, the liquid is not considered to be an obstacle. When the water sprayed by the sprinkler is sprayed onto the first vehicle, it is not considered to have an impact on the safe driving of the first vehicle, and the first vehicle can drive according to the pre-planned route as required, and there is no need to change the driving route.

In the embodiment of the present application, the method of identifying the type of the target object in front based on the radar image is adopted, so that the identification of obstacles or liquids can be realized according to the final identification result, so as to avoid misjudgment, thereby solving the problem of inability to distinguish between the objects on the ground in the related art Whether the liquid is an obstacle affects the technical problem of path planning.

The embodiment of the present application further provides a path planning device. As shown in FIG. 2 , the device includes: a collection module 20 for collecting a first image of a target object located in front of a first vehicle, where the first image is a radar image The extraction module 22 is used to extract the feature information of the target object from the first image; the identification module 24 is used to identify the type of the target object according to the feature information, wherein the type includes: obstacles and the liquid on the ground ahead; The module 26 is used to determine whether to change the planned route of the first vehicle according to the type; in the embodiment of the present invention, the method of identifying the type of the target object ahead based on the radar image is adopted, so that the obstacle or liquid can be detected according to the final identification result. identification, avoid misjudgment, and then solve the technical problem of inability to distinguish whether the liquid on the ground is an obstacle and affect the path planning in the related technology

In some embodiments of the present application, the acquisition module 20 is used for scanning the target object through the radar device installed in the first vehicle to obtain the first image; the extraction module 22 is used for extracting the shape of the target object from the first image.

Specifically, in order to ensure the accuracy of the detection results, in an optional embodiment of the present application, the radar devices that collect images may be multiple devices installed in different positions of the vehicle, for example, placed at the left and right ends of the vehicle top respectively. One radar device, and in another optional embodiment of the present application, multiple types of radar devices can be used in combination, for example, a millimeter-wave radar and an ultrasonic radar can be used in combination.

In an optional embodiment of the present application, the identification module 24 is configured to determine the type of the target object based on the shape of the target object in the first image. Optionally, the identification module is configured to determine that the target object is an obstacle when the shape of the target object is a regular shape; and determine that the target object is a liquid when the shape of the target object is an irregular shape.

Specifically, when the type of the target object is determined based on the shape of the target object in the first image, there are two cases. When the shape of the target object is a regular shape, the target object is determined to be an obstacle; when the shape of the target object is irregular When forming a shape, determine that the target object is a liquid. It should be noted that a regular shape is a shape with a smooth boundary, and an irregular shape is a shape with an uneven boundary. When the target object is an irregular shape, the points reflected by the radar are irregular, and when the target object is a regular shape When , the target object is determined to be an obstacle; when the shape of the target object is an irregular shape, it is determined that the target object is a liquid. It should be noted that a regular shape is a shape with a smooth boundary, and an irregular shape is a shape with an uneven boundary. When the target object has an irregular shape, the points reflected by the radar are irregular. In an embodiment of the present application Among them, when the points reflected by the radar are not arranged regularly, it is considered that the liquid on the ground is water. Secondly, it can also be combined with the driving environment in front of the first vehicle to determine that the liquid is other compounds. For example, when the lidar is combined with other compounds The signal acquisition device recognizes that the vehicle in front of the first vehicle is an oil tanker, and determines that the type of the liquid is gasoline or diesel.

In some embodiments of the present application, the determination module 26 is configured to determine whether to change the planned route of the first vehicle according to the type.

Specifically, in an optional embodiment of the present application, when determining whether the target object is an obstacle: it can be first judged whether the target object is from a second vehicle in front of the first vehicle; when the judgment result indicates that the target object is not from the first vehicle When the second vehicle and the shape of the target object is a regular shape, the target object is determined to be an obstacle, that is, all target objects that do not belong to the second vehicle and are identified as a regular shape are identified as obstacles.

In an optional embodiment of the present application, in order to determine whether the target object is from the second vehicle and the accuracy of the result, when judging whether the target object is from the second vehicle in front of the first vehicle, the first Two images, wherein the second image includes but is not limited to RGB images; then the second image is input into the machine learning model for analysis, to obtain the working state of the second vehicle and judging the working state of the second vehicle based on the machine learning model to further determine the target Whether the object is from the second vehicle, it should be noted that the operation state includes but is not limited to the following situations: the first operation state is performing spraying operation; the second operation state is not performing spraying operation. The machine learning model is obtained by training multiple sets of data, wherein each set of data in the multiple sets of data includes but is not limited to: an image of the second vehicle and a label used to mark the image of the second vehicle as a working state; When the spraying operation is being performed, it is determined whether the type of the spraying object corresponding to the spraying operation is from the second vehicle; when the type is the same as the type of the target object, it is determined that the target object is from the second vehicle.

In an optional embodiment of the present application, before determining whether to change the planned route of the first vehicle according to the type, the method further includes: acquiring attitude information of the second vehicle and information of the road where the second vehicle is located; predicting the first vehicle based on the attitude information The driving direction of the second vehicle; when the driving direction of the second vehicle changes, the first vehicle is controlled to continue to travel according to the planned route. The attitude information includes, but is not limited to, the head orientation, that is, when the second vehicle and the first vehicle do not belong to the same route, it is considered that the second vehicle does not belong to an obstacle, and the first vehicle may travel according to the planned route.

In an optional embodiment of the present application, when the driving direction of the second vehicle does not change, the first vehicle is controlled to change the planned route to avoid obstacles, that is, when the second vehicle and the When the routes of one vehicle overlap, it is considered that the second vehicle is an obstacle, and at this time, the driving route of the first vehicle needs to be re-planned.

In another optional embodiment of the present application, whether to change the driving route of the first vehicle is determined according to the type of the target object, and the types include obstacles and liquids. When it is determined that the type of the target object is an obstacle, the Planning a route, in which the revised planning route is used to avoid the target object; when the type of the target object is determined to be liquid, the vehicle is controlled to continue driving according to the current planned route, that is, the liquid is not considered to be an obstacle. When the water sprayed by the sprinkler is sprayed onto the first vehicle, it is not considered to have an impact on the safe driving of the first vehicle, and the first vehicle can drive according to the pre-planned route as required, and there is no need to change the driving route.

In the embodiment of the present application, the method of identifying the type of the target object in front based on the radar image is adopted, so that the identification of obstacles or liquids can be realized according to the final identification result, so as to avoid misjudgment, thereby solving the problem of inability to distinguish between the objects on the ground in the related art Whether the liquid is an obstacle, which affects the technical problem of path planning

According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, the storage medium includes a stored program, wherein, when the program runs, the device where the storage medium is located is controlled to execute the above path planning method. For example, the following may be performed Program instructions: collect a first image of a target object located in front of the first vehicle, where the first image is a radar image; extract feature information of the target object from the first image; identify the type of the target object according to the feature information, wherein the type includes : Obstacles and liquids on the ground ahead; determine whether to change the planned route of the first vehicle depending on the type.

According to another aspect of the embodiments of the present application, a vehicle is provided. As shown in FIG. 3 , the vehicle includes: an electronic device 3 , and the electronic device includes: a memory 30 for storing program instructions; a processor 32 , It is used for retrieving the program instructions stored in the memory to perform the following functions: collecting a first image of the target object located in front of the first vehicle, where the first image is a radar image; extracting feature information of the target object from the first image; The type of the target object is identified according to the characteristic information, wherein the type includes: obstacles and liquids on the ground ahead; whether to change the planned route of the first vehicle is determined according to the type.

Optionally, the memory is further used to store a program for performing the following functions: scanning the target object by the radar device installed in the first vehicle to obtain a first image; and extracting the shape of the target object from the first image.

Optionally, the memory is further configured to store a program for performing the following function: determining the type of the target object based on the shape of the target object in the first image. When the shape of the target object is a regular shape, the target object is determined to be an obstacle; when the shape of the target object is an irregular shape, it is determined that the target object is a liquid.

In the embodiment of the present invention, the method of identifying the type of the target object in front based on the radar image is adopted, so that the identification of obstacles or liquids can be realized according to the final identification result, so as to avoid misjudgment, and further solve the problem of inability to distinguish between the ground and the ground in the related art. Whether the liquid is an obstacle affects the technical problem of path planning.

The above-mentioned serial numbers of the embodiments of the present invention are only for description, and do not represent the advantages or disadvantages of the embodiments.

In the above-mentioned embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are only illustrative, for example, the division of the units may be a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components may be combined or Integration into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of units or modules, and may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes .

The above are only the preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, without departing from the principles of the present invention, several improvements and modifications can be made. It should be regarded as the protection scope of the present invention.

Claims (18)

1. a path planning method, is characterized in that, comprises: collecting a first image of the target object located in front of the first vehicle, where the first image is a radar image; extracting feature information of the target object from the first image; Identifying the type of the target object according to the feature information, wherein the type includes: obstacles and liquids on the ground ahead; Whether to change the planned route of the first vehicle is determined according to the type. 2. The method according to claim 1, wherein Collecting a first image of a target object located in front of a first vehicle includes: scanning the target object through a radar device installed in the first vehicle to obtain the first image; Extracting the feature information of the target object from the first image includes: extracting the shape of the target object from the first image. 3. The method according to claim 2, wherein identifying the type of the target object according to the feature information comprises: The type of the target object is determined based on the shape of the target object in the first image. 4. The method according to claim 3, wherein determining the type of the target object based on the shape of the target object in the first image comprises: When the shape of the target object is a regular shape, determine that the target object is an obstacle; When the shape of the target object is an irregular shape, it is determined that the target object is liquid. 5. The method according to claim 4, wherein determining the target object as an obstacle comprises: determining whether the target object is from a second vehicle in front of the first vehicle; When the judgment result indicates that the target object is not from the second vehicle and the shape of the target object is a regular shape, it is determined that the target object is an obstacle. 6. The method according to claim 5, wherein determining whether the target object is from a second vehicle in front of the first vehicle comprises: acquiring a second image of the second vehicle, where the second image is an RGB image; The second image is input into the machine learning model for analysis, and the operation status of the second vehicle is obtained, wherein the operation status includes: spraying operation is being performed and spraying operation is not being performed; the machine learning model is obtained by Obtained by training on multiple sets of data, each of the multiple sets of data includes: an image of the second vehicle and a label for marking the image of the second vehicle as a working state; When the operation status is the ongoing spraying operation, the type of the spraying object corresponding to the spraying operation is determined; when the type is the same as the type of the target object, it is determined that the target object is from the first Two vehicles. 7. The method according to claim 5, wherein before determining whether to change the planned route of the first vehicle according to the type, the method further comprises: acquiring the attitude information of the second vehicle and the road where the second vehicle is located; predicting the driving direction of the second vehicle based on the attitude information; When the driving direction of the second vehicle changes and there is a road adjacent to the road where the second vehicle is located in the changed driving direction, the first vehicle is controlled to continue to travel according to the planned route. 8 . The method according to claim 7 , wherein when the driving direction of the second vehicle does not change, the first vehicle is controlled to change the planned route to avoid obstacles. 9 . 9. The method according to claim 8, wherein before controlling the first vehicle to change the planned route, the method further comprises: obtaining the relative speed of the first vehicle and the second vehicle; When the relative speed is greater than 0, the first vehicle is controlled to change the planned route; when the relative speed is less than 0 or equal to 0, the first vehicle is controlled to continue to travel according to the planned route. 10 . The method according to claim 9 , wherein the attitude information comprises: the head direction of the second vehicle. 11 . 11. The method of claim 10, wherein the method further comprises: It is determined that the driving direction of the second vehicle is changed after the head direction of the second vehicle is changed and the head direction of the second vehicle is changed and the vehicle travels in accordance with the changed head direction for a preset period of time. 12. The method according to claim 1, wherein determining whether to change the driving route of the first vehicle according to the type comprises: When the type is an obstacle, modifying the planned route of the first vehicle, wherein the target object is avoided in the revised planned route; When the type is liquid, the vehicle is controlled to continue driving according to the current planned route. 13. A path planning device, comprising: a collection module, configured to collect a first image of the target object located in front of the first vehicle, where the first image is a radar image; an extraction module for extracting feature information of the target object from the first image; an identification module, configured to identify the type of the target object according to the feature information, wherein the type includes: obstacles and liquids on the ground ahead; A determination module, configured to determine whether to change the planned route of the first vehicle according to the type. 14. The apparatus of claim 13, wherein The acquisition module is configured to scan the target object through the radar device installed in the first vehicle to obtain the first image; The extraction module is used for extracting the shape of the target object from the first image. 15. The apparatus according to claim 14, wherein the identification module is configured to determine the type of the target object based on the shape of the target object in the first image. 16. The device according to claim 15, wherein the identification module is configured to determine that the target object is an obstacle when the shape of the target object is a regular shape; When the shape is irregular, it is determined that the target object is liquid. 17. A non-volatile storage medium, characterized in that the storage medium comprises a stored program, wherein when the program is run, a device where the storage medium is located is controlled to execute any one of claims 1 to 12. The path planning method described above. 18. A vehicle, comprising: electronic equipment, the electronic equipment comprising: memory for storing program instructions; A processor, configured to call program instructions stored in the memory, and implement the following functions when running the program instructions: collecting a first image of the target object located in front of the first vehicle, where the first image is a radar image; extracting feature information of the target object from the first image; Identifying the type of the target object according to the feature information, wherein the type includes: obstacles and liquids on the ground ahead; Whether to change the planned route of the first vehicle is determined according to the type.

Images