CN115027503A - Control method, device and autonomous vehicle for autonomous vehicle - Google Patents

Abstract

An automatic driving vehicle control method, device and automatic driving vehicle, the method includes: during the driving process of the automatic driving vehicle, predicting the behavior of surrounding obstacles in real time, wherein the obstacles include a first obstacle and a first obstacle Two obstacles, each first obstacle corresponds to a unique behavior prediction result, and each second obstacle corresponds to at least two behavior prediction results; determine the decision result for each behavior prediction result; determine the first behavior based on the unique decision result Solution space; determine multiple second solution spaces based on multiple non-unique decision results; select the optimal second solution space from the multiple second solution spaces; obtain the first solution space according to the optimal second solution space and the first solution space. The third solution space is used to determine the driving strategy of the autonomous vehicle based on the third solution space. The invention can make the automatic driving vehicle avoid obstacles in time when driving in a scene with many obstacles, and ensure the safety of the driving process.

Description

Control method, device and autonomous vehicle for autonomous vehicle

technical field

The present invention relates to the field of automatic driving vehicles, and more particularly, to a control method and device for automatic driving vehicles and automatic driving vehicles.

Background technique

For autonomous vehicles, the interaction strategy is equivalent to the human driver's brain, which is used to guide the actions that the autonomous vehicle should take when facing other traffic participants, such as braking, accelerating, and detouring. With the gradual maturity of autonomous driving technology, its application scenarios have begun to be subdivided. For different application scenarios, autonomous vehicles should have different interaction strategies with social vehicles. At present, most interaction strategies focus on high-speed scenarios and urban road scenarios, and there is no effective solution for non-motorized vehicle lane scenarios at low speeds. How to ensure the efficiency and safety of self-driving vehicles in non-motorized vehicle lanes with many pedestrians has become an urgent problem for self-driving vehicles.

SUMMARY OF THE INVENTION

A series of concepts in simplified form have been introduced in the Summary section, which are described in further detail in the Detailed Description section. The Summary of the Invention section of the present invention is not intended to attempt to limit the key features and essential technical features of the claimed technical solution, nor is it intended to attempt to determine the protection scope of the claimed technical solution.

In view of the deficiencies of the prior art, the first aspect of the embodiments of the present invention provides a control method for an automatic driving vehicle, the method comprising:

During the driving process of the autonomous driving vehicle, the behavior of obstacles around the autonomous driving vehicle is predicted in real time, wherein the obstacles include a first obstacle and a second obstacle, and each of the first obstacles corresponds to Unique behavior prediction results, each of the second obstacles corresponds to at least two behavior prediction results;

determining a decision result for each of the behavior prediction results, wherein each of the first obstacles corresponds to a unique decision result, and each of the second obstacles corresponds to at least two non-unique decision results;

Determining the first solution space by synthesizing the unique decision result;

Determining a plurality of second solution spaces by synthesizing the non-unique decision results;

selecting an optimal second solution space from the plurality of second solution spaces;

A third solution space is obtained according to the optimal second solution space and the first solution space, and a driving strategy of the autonomous vehicle is determined based on the third solution space.

In some embodiments, the method is used while the autonomous vehicle is traveling in a non-motorized lane.

In some embodiments, the real-time prediction of the behavior of obstacles around the self-driving vehicle during the driving of the self-driving vehicle includes:

During the driving process of the self-driving vehicle, obtain the position information of obstacles around the self-driving vehicle in real time;

The behavior of the obstacle is predicted based on the change of the position information over time.

In some embodiments, the determining a plurality of second solution spaces based on a plurality of the non-unique decision results includes:

Arrange and combine any one of the non-unique decision results corresponding to each second obstacle, and determine the second solution space according to the combination of the non-unique decision results corresponding to different second obstacles .

In some embodiments, the selecting an optimal second solution space from the plurality of second solution spaces includes:

Each second solution space is scored based on a scoring model, and the second solution space with the highest score is used as the optimal second solution space.

In some embodiments, the scoring model scores the second solution space according to at least one of the following factors: a somatosensory factor, a safety factor.

In some embodiments, the behavior prediction results include at least one of the following: cutting vehicles, driving side by side, driving backwards, and following vehicles.

In some embodiments, the decision result includes at least one of the following: yield, overtake, ignore, be vigilant, and detour.

A second aspect of the embodiments of the present invention provides a control device for an automatic driving vehicle, the control device includes a memory and a processor, the memory stores a computer program executed by the processor, and the computer program is run by the processor. When the processor is running, the control method of the automatic driving vehicle as described above is executed.

A third aspect of the embodiments of the present invention provides an automatic driving vehicle, the automatic driving vehicle includes a body, a driving device for driving the body to run, and a sensor provided on the body; the automatic driving vehicle further includes A control device for connecting the driving device and the sensor, the control device for executing the control method of the autonomous driving vehicle as described above.

An embodiment of the present invention further provides a storage medium, where a computer program is stored on the storage medium, and the computer program executes the above-mentioned control method for an automatic driving vehicle when running.

The control method for an automatic driving vehicle and the automatic driving vehicle according to the embodiments of the present invention can enable the automatic driving vehicle to avoid obstacles in time when driving in a scene with many obstacles, and ensure the safety of the driving process.

Description of drawings

The above and other objects, features and advantages of the present invention will become more apparent from the more detailed description of the embodiments of the present invention in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification, and together with the embodiments of the present invention, they are used to explain the present invention, and do not limit the present invention. In the drawings, the same reference numbers generally refer to the same components or steps.

FIG. 1 is a schematic flowchart of a control method for an automatic driving vehicle according to an embodiment of the present invention;

FIG. 2 is a schematic block diagram of a control device for an automatic driving vehicle according to an embodiment of the present invention;

FIG. 3 is a schematic block diagram of an autonomous driving vehicle according to an embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present application more apparent, the exemplary embodiments according to the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein. Based on the embodiments of the present application described in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced without one or more of these details. In other instances, some technical features known in the art have not been described in order to avoid confusion with the present application.

It should be understood that the application may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of this application to those skilled in the art.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a," "an," and "the/the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the terms "compose" and/or "include", when used in this specification, identify the presence of stated features, integers, steps, operations, elements and/or components, but do not exclude one or more other The presence or addition of features, integers, steps, operations, elements, parts and/or groups. As used herein, the term "and/or" includes any and all combinations of the associated listed items.

For a thorough understanding of the present application, detailed structures will be presented in the following description in order to explain the technical solutions proposed by the present application. Alternative embodiments of the present application are described in detail below, however, the present application may have other embodiments in addition to these detailed descriptions.

In the field of autonomous driving, the interaction strategy focuses more on the interaction with motor vehicles and a small number of non-motor vehicles. Commonly used interaction strategies include: 1. Giving/rushing strategies based on game theory; 2. Rule-based interaction strategies based on decision trees and Markov decision models; 3. Based on road static characteristics and dynamic characteristics of traffic participants. machine learning model.

The above technical solutions have achieved certain practical results in high-speed scenarios and urban road scenarios. However, in low-speed environments such as non-motorized lanes, pedestrians and non-motorized vehicles account for most of them as traffic participants. Compared with urban roads, non-motorized vehicles will interact more frequently with pedestrians and autonomous vehicles. Vehicles with autonomous driving systems will have more obstacles during driving, and the passage space will be narrower. How to effectively ensure the safe driving of vehicles? Safety and efficiency, there is no clear and effective solution at present.

For example, if the game-theory-based yield/rush strategy is adopted, the game balance point is more difficult to achieve than the regulated motor vehicle road environment, and the consequences of game failure are more serious, and it is easy to cause harm to pedestrians. If a rule-based interaction strategy such as decision tree and Markov decision model is adopted, the overall decision link is too long, which may lead to high time consumption, and the system delay is too high, resulting in slow execution and difficulty in handling emergencies. More of these scenarios. For the machine model method, since the behavior of participants in non-motorized lanes is more discrete, the long-tail problem is more difficult to converge, and many problems remain that cannot be solved.

In view of the above problems, the embodiment of the present invention proposes a control method for an automatic driving vehicle. In an environment with strong uncertainty such as a non-motorized vehicle lane, various possible behaviors of obstacles are taken into account, and a complex unmanned vehicle is considered. The deterministic problem is divided into multiple simple sub-problems, and then the optimal results are obtained from the multiple sub-problems, and then the optimal driving strategy that conforms to the expected behavior is obtained, so that the self-driving vehicle can be used in non-motorized vehicle lanes such as non-motorized vehicles and pedestrians. When driving in many scenarios, it can avoid obstacles in time and effectively ensure the safety of the driving process. The following describes the method for controlling an automatic driving vehicle and the automatic driving vehicle provided by the embodiments of the present invention with reference to the accompanying drawings.

Referring first to FIG. 1 , FIG. 1 shows a schematic flowchart of a control method 100 for an automatic driving vehicle for an automatic driving vehicle according to an embodiment of the present invention. The control method 100 for an automatic driving vehicle according to the embodiment of the present invention is used for an automatic driving vehicle. The automatic driving vehicle may also be called an unmanned vehicle. vehicle. As shown in FIG. 1 , a control method 100 for an autonomous driving vehicle according to an embodiment of the present invention includes the following steps:

In step S110, during the driving process of the autonomous driving vehicle, the behavior of obstacles around the autonomous driving vehicle is predicted in real time, wherein the obstacles include a first obstacle and a second obstacle, each of which is a first obstacle and a second obstacle. One obstacle corresponds to a unique behavior prediction result, and each of the second obstacles corresponds to at least two behavior prediction results;

In step S120, a decision result for each of the behavior prediction results is determined, wherein each of the first obstacles corresponds to a unique decision result, and each of the second obstacles corresponds to at least two non-unique decision results ;

In step S130, a first solution space is determined based on at least one of the unique decision results;

In step S140, a plurality of second solution spaces are determined based on a plurality of the non-unique decision results;

In step S150, the optimal second solution space is selected from the plurality of second solution spaces;

In step S160, a third solution space is obtained according to the optimal second solution space and the first solution space, and a driving strategy of the automatic driving vehicle is determined based on the third solution space.

The control method 100 for an autonomous vehicle according to the embodiment of the present invention first determines a first solution space according to a decision result corresponding to a definite behavior prediction result, then determines a second solution space according to a decision result corresponding to an unclear behavior prediction result, and finally determines the second solution space according to the decision result corresponding to the unclear behavior prediction result. In the second solution space, the optimal second solution space is selected and fused with the first solution space, so as to take into account the possible various behaviors of obstacles in the environment with strong uncertainty, and finally obtain the optimal driving that meets the expected behavior. Strategy.

Exemplarily, the method 100 for controlling an automatic driving vehicle according to the embodiment of the present invention is implemented when the automatic driving vehicle is driving on a non-motorized vehicle lane. Compared with urban roads, the interactions between autonomous vehicles, non-motor vehicles and pedestrians will be more frequent in the non-motor vehicle lane environment, there will be more obstacles during the driving process, and the passage space will be narrower. The interaction strategy between autonomous vehicles and social vehicles can ensure the driving safety and trafficability of autonomous vehicles in environments with many pedestrians and non-motor vehicles such as non-motorized vehicle lanes. Exemplarily, when it is determined that the automatic driving vehicle is driving on a non-motor vehicle lane, the control method 100 for an automatic driving vehicle according to the embodiment of the present invention can be enabled; when the automatic driving vehicle is driving on a motor vehicle lane, other interaction strategies can be enabled. The embodiment does not limit this. In addition to the non-motorized vehicle lane, the interaction strategy of the embodiment of the present invention can also be implemented in other similar scenarios.

Specifically, in step S110, during the driving process of the autonomous driving vehicle, the behavior of obstacles around the autonomous driving vehicle is predicted in real time. The obstacles around the autonomous vehicle may refer to obstacles within a preset range around the autonomous vehicle, including but not limited to vehicles and pedestrians around the autonomous vehicle. Predict the behavior of obstacles around the autonomous vehicle, that is, according to the behavior of obstacles in the past period of time, predict their behavior in the future period of time, so as to respond to their behavior in a timely and effective manner.

Exemplarily, the method for predicting the behavior of the obstacle includes: acquiring the position information of the obstacle around the autonomous driving vehicle, and predicting the behavior of the obstacle according to the change of the position information with time. As an implementation manner, the position information of obstacles around the autonomous driving vehicle may be acquired based on the radar, and the position information may be the relative position relationship between the obstacles and the autonomous driving vehicle. Specifically, the point cloud data of the surrounding environment is collected by a radar set on the autonomous vehicle. The radar can be a lidar, and the lidar can be either a regular repetitive scanning lidar, or a non-repetitive scanning feature. The scanning trajectory of a complex lidar. Radar can sense external environmental information, such as distance information, azimuth information, reflection intensity information, speed information, etc. of environmental targets. Next, point cloud clusters of obstacles are extracted from the point cloud data. For example, the point cloud data can be clustered to identify point cloud clusters that belong to different obstacles. When applied to the scene of non-motorized vehicle lanes, the obstacles mainly include non-motorized vehicles and pedestrians. According to the distance information and orientation information contained in the point cloud cluster, the relative position of the obstacle and the autonomous vehicle can be determined, and the position information of the obstacle can also be determined over time according to the position of the same obstacle in the continuously collected point cloud data. The change.

It should be noted that the method for obtaining the position information of obstacles in this embodiment of the present invention is not limited to obtaining the position information of obstacles through radar, and it is also possible to obtain position information of obstacles through other sensors. Other sensors include but are not limited to visual sensors, infrared sensors, ultrasonic sensors, etc. .

After that, the behavior of the obstacle is identified according to the change of the position information of the obstacle over time. For example, the behavior of an obstacle can be marked as car cutting, side-by-side driving, reverse driving, following, etc. Specific methods for identifying the behavior of obstacles include, but are not limited to, machine learning methods, that is, inputting the location information of the obstacles into a pre-trained machine learning label, and the machine learning model outputs the recognition result of its behavior. When training the machine learning model, the position information of the obstacles is used as input, and the model parameters are optimized to make the predicted results of the obstacle behavior output by the machine learning model close to the real behavior of the manually labeled obstacles. The trained machine learning model can be used to predict the behavior of obstacles. It should be noted that the method of recognizing the behavior of the obstacle is not limited to the machine learning method.

Obstacles around autonomous vehicles may have multiple behaviors, some of which are relatively clear and unique behavior prediction results can be obtained. For example, when an obstacle stops in front of the autonomous vehicle's direction of travel, it can be unequivocally determined that its behavior is hindering travel. Other behaviors are ambiguous, and there may be multiple behavior prediction results. For example, for a vehicle approaching an autonomous vehicle, it is impossible to predict whether its behavior is to cut the car or drive side by side, so at least two non-unique behavior predictions will be obtained. result. For the convenience of description, the obstacle that can obtain a unique prediction result is defined as the first obstacle, and the obstacle that cannot obtain a unique prediction result is defined as the second obstacle; the first obstacle and the second obstacle do not constitute a pair of obstacles. type restrictions, and over time, the first obstacle and the second obstacle can also be converted to each other.

Then, in step S120, for each behavior prediction result of each obstacle, a decision result for the behavior prediction result is determined. Decision results include but are not limited to yield, overtake, ignore, caution, nudge, etc. It can be understood that since each first obstacle corresponds to a unique behavior prediction result, each first obstacle corresponds to a unique decision result; since each second obstacle corresponds to at least two non-unique prediction results, therefore Each second obstacle corresponds to at least two non-unique decision outcomes.

Next, in step S130, a first solution space is determined based on the unique decision result. The solution space is the drivable space at each time point of the time series, and it is safe to exercise within the range defined by the solution space. Specifically, a first solution space is divided by synthesizing the unique decision results of all the first obstacles, and the first solution space is a solution space obtained by only considering the decision results of explicit behaviors. The unique decision result of each first obstacle constitutes a restriction on the solution space. After synthesizing the unique decision results of multiple first obstacles, a solution space in which the optimal solution can be easily obtained based on methods such as optimization is obtained.

Afterwards, in step S140, a plurality of second solution spaces are determined by synthesizing the non-unique decision results. Multiple second solution spaces consider multiple decision outcomes for multiple possible behaviors. Specifically, any decision result may be selected from the non-unique decision results corresponding to each second obstacle for arrangement and combination, and the decision result may be determined according to the combination of the non-unique decision results corresponding to different second obstacles. The second solution space. For example, assuming that N second obstacles are identified around the autonomous vehicle, each second obstacle may have M kinds of behavior prediction results, and each behavior prediction result has a corresponding decision result, so a total of N × M are obtained. The second solution space. Of course, the above is just an example, and the number of behavior prediction results for different obstacles may be different.

After that, in step S150, the optimal second solution space is selected from the plurality of second solution spaces. For example, each second solution space is scored based on the scoring model, and the second solution space with the highest score is selected as the optimal second solution space. When scoring the second solution space, the scoring model considers factors including but not limited to safety factors, somatosensory factors, and the like.

Finally, in step S160, a third solution space is obtained according to the optimal second solution space and the first solution space, and a driving strategy of the autonomous vehicle is determined based on the third solution space. Specifically, the intersection of the first solution space and the optimal second solution space can be obtained, and the final solution space can be obtained as the output result of the solution space

To sum up, the control method 100 for an automatic driving vehicle according to the embodiment of the present invention can enable the automatic driving vehicle to avoid obstacles in time when driving in a scene with many obstacles, so as to ensure the safety of the driving process.

An embodiment of the present invention further provides a control device for an automatic driving vehicle. Referring to FIG. 2 , the control device 200 for an automatic driving vehicle includes a memory 210 and a processor 220. The memory 210 stores a computer program run by the processor 220. The computer program The control method 100 of an autonomous vehicle is performed when executed by the processor 220 .

Illustratively, memory 210 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and/or cache memory, or the like. The non-volatile memory may include, for example, read only memory (ROM), hard disk, flash memory, and the like.

The processor 220 may execute the program instructions stored in the memory 210 to implement the functions (implemented by the processor) in the embodiments of the invention described herein and/or other desired functions. Various application programs and various data, such as various data used and/or generated by the application program, etc. may also be stored in the computer-readable storage medium. Processor 220 may be a central processing unit (CPU), application specific integrated circuit (ASIC), field programmable gate array (FPGA), or other form of processing unit having data processing capabilities and/or instruction execution capabilities.

The embodiment of the present invention further provides an automatic driving vehicle, and the automatic driving vehicle can be used to realize the control method 100 of the automatic driving vehicle described above. The self-driving vehicle is an intelligent vehicle that does not require the driver to perform driving operations and can automatically complete the vehicle driving task instead of the driver; the self-driving vehicle may also have a manual driving function. Referring to FIG. 3, FIG. 3 shows a schematic block diagram of an autonomous driving vehicle according to an embodiment of the present invention.

As shown in FIG. 3 , the autonomous driving vehicle includes a body 300 , a driving device 310 , a sensor 320 and a control device 330 . The control device 330 is connected to the driving device 310 and the sensor 320 , and the control device 330 can execute the control method for the autonomous driving vehicle as described above. 100, to control the driving device 310 to drive the vehicle body to run. The sensor 320 includes a radar, an image sensor, an infrared sensor, and the like. It should be noted that the autonomous driving vehicle further includes other components, which are not limited in the embodiment of the present invention. For the control method 100 of the automatic driving vehicle executed by the control device 330, reference may be made to the above, and details are not described here.

The automatic driving vehicle of the embodiment of the present invention can avoid obstacles in time when driving in a scene with many obstacles, so as to ensure the safety of the driving process.

In addition, according to an embodiment of the present invention, a computer storage medium is also provided, where program instructions are stored on the computer storage medium, and when the program instructions are run by a computer or a processor, the program instructions are used to execute automatic functions of the embodiments of the present invention. For the corresponding steps of the control method 100 for driving a vehicle, the specific details can be referred to above. The computer storage medium may include, for example, memory cards for smartphones, storage components for tablet computers, hard disks for personal computers, read only memory (ROM), erasable programmable read only memory (EPROM), portable compact disk read only Memory (CD-ROM), USB memory, or any combination of the above storage media. The computer-readable storage medium can be any combination of one or more computer-readable storage media.

Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above-described example embodiments are exemplary only and are not intended to limit the scope of the application thereto. Various changes and modifications may be made therein by those of ordinary skill in the art without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of this application as claimed in the appended claims.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or May be integrated into another device, or some features may be omitted, or not implemented.

In the description provided herein, numerous specific details are set forth. It will be understood, however, that the embodiments of the present application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it is to be understood that in the description of the exemplary embodiments of the present application, various features of the present application are sometimes grouped together into a single embodiment, FIG. , or in its description. However, this method of application should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as the corresponding claims reflect, the invention lies in the fact that the corresponding technical problem may be solved with less than all features of a single disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this application.

It will be understood by those skilled in the art that all features disclosed in this specification (including the accompanying claims, abstract and drawings) and any method or apparatus so disclosed may be used in any combination, except that the features are mutually exclusive. Processes or units are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that although some of the embodiments described herein include certain features, but not others, included in other embodiments, that combinations of features of different embodiments are intended to be within the scope of the present application within and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

Various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some modules according to the embodiments of the present application. The present application can also be implemented as a program of apparatus (eg, computer programs and computer program products) for performing part or all of the methods described herein. Such a program implementing the present application may be stored on a computer-readable medium, or may be in the form of one or more signals. Such signals may be downloaded from Internet sites, or provided on carrier signals, or in any other form.

It should be noted that the above-described embodiments illustrate rather than limit the application, and alternative embodiments may be devised by those skilled in the art without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. do not denote any order. These words can be interpreted as names.

The above are only specific embodiments of the present application or descriptions of the specific embodiments, and the protection scope of the present application is not limited thereto. The changes or substitutions that come to mind should all fall within the protection scope of the present application. The protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. A control method for an automatic driving vehicle, wherein the method comprises: During the driving process of the autonomous driving vehicle, the behavior of obstacles around the autonomous driving vehicle is predicted in real time, wherein the obstacles include a first obstacle and a second obstacle, and each of the first obstacles corresponds to Unique behavior prediction results, each of the second obstacles corresponds to at least two behavior prediction results; determining a decision result for each of the behavior prediction results, wherein each of the first obstacles corresponds to a unique decision result, and each of the second obstacles corresponds to at least two non-unique decision results; Determining the first solution space by synthesizing the unique decision result; Determining a plurality of second solution spaces by synthesizing the non-unique decision results; selecting an optimal second solution space from the plurality of second solution spaces; A third solution space is obtained according to the optimal second solution space and the first solution space, and a driving strategy of the autonomous vehicle is determined based on the third solution space. 2 . The control method for an automatic driving vehicle according to claim 1 , wherein the method is used when the automatic driving vehicle is driving on a non-motorized vehicle lane. 3 . 3. The control method of the self-driving vehicle according to claim 1, wherein, in the process of driving the self-driving vehicle, predicting the behavior of obstacles around the self-driving vehicle in real time comprises: During the driving process of the self-driving vehicle, obtain the position information of obstacles around the self-driving vehicle in real time; The behavior of the obstacle is predicted based on the change of the position information over time. 4. The control method for an autonomous driving vehicle according to claim 1, wherein the determining a plurality of second solution spaces based on a plurality of the non-unique decision results, comprising: Arrange and combine any one of the non-unique decision results corresponding to each second obstacle, and determine the second solution space according to the combination of the non-unique decision results corresponding to different second obstacles . 5. The control method for an autonomous driving vehicle according to claim 1, wherein the selecting an optimal second solution space from the plurality of second solution spaces comprises: Each second solution space is scored based on a scoring model, and the second solution space with the highest score is used as the optimal second solution space. 6 . The control method for an autonomous vehicle according to claim 5 , wherein the scoring model scores the second solution space according to at least one of the following factors: a somatosensory factor and a safety factor. 7 . 7 . The method for controlling an autonomous driving vehicle according to claim 1 , wherein the behavior prediction result comprises at least one of the following: cutting vehicles, side-by-side driving, reverse driving, and following vehicles. 8 . 8 . The control method for an autonomous vehicle according to claim 1 , wherein the decision result comprises at least one of the following: yield, overtake, ignore, be vigilant, and detour. 9 . 9. A control device for an autonomous vehicle, characterized in that the control device comprises a memory and a processor, the memory stores a computer program run by the processor, and the computer program is processed by the processor The control method for an autonomous driving vehicle according to any one of claims 1 to 8 is executed when the machine is running. 10. An autonomous driving vehicle, characterized in that the autonomous driving vehicle comprises a body, a driving device for driving the body to run, and a sensor provided on the body; The autonomous driving vehicle further includes a control device connected to the driving device and the sensor, and the control device is configured to execute the control method of the autonomous driving vehicle according to any one of claims 1-8.

Images