Vehicle pedestrian communication method and device based on driving scene, equipment and storage medium

Abstract

The application provides a vehicle-pedestrian communication method and device based on a driving scene, an equipment and a storage medium. The driving scene parameter of a vehicle is acquired. A first variable and a second variable are generated based on the driving scene parameter. The first variable is used to determine whether the vehicle can communicate with a pedestrian. The second variable is used to describe the details of the driving scene. The first variable is compared with a preset value range. When the first variable meets the value range, a target scene description is constructed according to the first variable and the second variable. A target communication sentence and a target communication form are selected based on the target scene description. The target communication sentence is sent to the pedestrian in the target communication form, so that the vehicle communicates with the pedestrian. The application uses the driving scene parameter of the vehicle to determine whether the vehicle can communicate with the pedestrian in the current state. In the case that the vehicle can communicate, the corresponding communication sentence and communication form are selected, so that the vehicle automatically and effectively communicates with the pedestrian.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle information processing, in particular to a vehicle-pedestrian communication method and device based on a driving scene, equipment and a storage medium. BACKGROUND

[0002] The emergence of autonomous vehicles brings potential risks to other road users, especially pedestrians. In the traditional vehicle-pedestrian interaction process, pedestrians can judge whether they are noticed by the vehicle and whether they should pass by observing the driver. After the emergence of autonomous vehicles, the driving task is transferred to the system, and pedestrians can no longer obtain reliable interaction clues through the driver. At the same time, the driving behavior of the system is not completely consistent with that of the driver, and pedestrians may form false expectations based on past experiences and interactions with autonomous vehicles, leading to traffic accidents.

[0003] However, in the prior art, there are still devices for prompting pedestrians, such as the patent CN107054211A, which records that "when the driver needs to avoid pedestrians, the switch can be pressed to place the device in front of the window glass to prompt the pedestrians to 'please go first, I am avoiding'. Through the device, the purpose of communication with road pedestrians is achieved". However, the driver still needs to manually control it, and the communication with pedestrians cannot be completed through the autonomous driving system. In addition, in the prior art, there is currently no model framework based on vehicle scenes and pedestrians, resulting in a narrow coverage of existing communication methods and an inability to cover all driving scenes. Moreover, the communication process is too simple and cannot select communication sentences and communication methods. SUMMARY

[0004] In view of the above-mentioned shortcomings of the prior art, the present application provides a vehicle-pedestrian communication method and device based on a driving scene, equipment and a storage medium to solve the above-mentioned technical problems.

[0005] The present application provides a vehicle-pedestrian communication method based on a driving scene, which comprises:

[0006] obtaining driving scene parameters of a vehicle;

[0007] generating a first variable based on driving scene parameters that affect vehicle-pedestrian communication, and taking the first variable as a basis variable, superimposing driving scene parameters that do not affect vehicle-pedestrian communication on the vehicle driving scene to generate a second variable;

[0008] comparing the first variable with a preset value range;

[0009] when the first variable meets the preset value range, constructing a target scene description according to the first variable and the second variable, and selecting a target communication sentence and a target communication form based on the target scene description;

[0010] sending the target communication sentence to the pedestrian according to the target communication form, so that the vehicle communicates with the pedestrian.

[0011] In an embodiment of the present application, the target scene description is constructed according to the first variable and the second variable, and the target communication sentence is selected based on the target scene description, including:

[0012] The target scene description is constructed according to the first variable and the second variable.

[0013] The pre-established communication sentence library is queried according to the target scene description, and the corresponding target communication sentence is matched; wherein the pre-established communication sentence library includes a mapping relationship between the target scene description and the target communication sentence.

[0014] In an embodiment of the present application, when the number of the first variables is multiple, the target scene description is constructed according to the first variable and the second variable, including:

[0015] The multiple first variables are combined to obtain a basic scene description.

[0016] The basic scene description is sequentially adjusted according to a semantic rule to obtain an intermediate scene description.

[0017] The second variable is superimposed to the intermediate scene description to obtain the target scene description.

[0018] In an embodiment of the present application, the driving scene parameter of the vehicle is obtained, including:

[0019] The driving variable of the vehicle during driving is obtained; wherein the driving variable includes at least one of the following: driving mode information, system fault information, recognition state information, current speed, acceleration information, deceleration information, steering information, and reverse information.

[0020] The pedestrian and the road environment during driving of the vehicle are recognized to obtain pedestrian variable and road environment variable, respectively.

[0021] The driving scene parameter is constructed by the driving variable, the pedestrian variable, and the road environment variable.

[0022] In an embodiment of the present application, after the target communication sentence is obtained, it further includes:

[0023] A virtual reality scene is constructed according to the target scene description.

[0024] The target communication sentence is simulated and output in the virtual reality scene.

[0025] In an embodiment of the present application, when the number of target communication sentences is more than one, the target communication sentences are sent to the pedestrian in the target communication form, so that the vehicle communicates with the pedestrian, comprising:

[0026] The target communication sentence with the highest priority is obtained from the target communication sentences;

[0027] The target communication sentence with the highest priority is sent to the pedestrian in the target communication form, so that the vehicle communicates with the pedestrian.

[0028] In an embodiment of the present application, when the first variable includes pedestrian attention, the second variable includes the number of pedestrians and the age of pedestrians, the target communication form is selected according to the pedestrian attention, the number of pedestrians and the age of pedestrians, comprising:

[0029] The first content adjustment form and the first communication channel are obtained when the pedestrian attention is a first preset value, the second content adjustment form and the second communication channel are obtained when the number of pedestrians is a second preset value, and the third content adjustment form and the third communication channel are obtained when the age of pedestrians is a third preset value;

[0030] The communication form with the highest priority is selected as the target communication channel from the first communication channel, the second communication channel and the third communication channel;

[0031] The current communication form is constructed by the first content adjustment form, the second content adjustment form, the third content adjustment form and the target communication channel, and the current communication form is selected as the target communication form.

[0032] In an embodiment of the present application, when the first variable includes the driving task of the vehicle, the running state of the vehicle, the pedestrian recognition state of the vehicle, the purpose of the pedestrian, the relative position of the pedestrian and the vehicle, the moving direction of the pedestrian, the moving speed of the pedestrian, the attention of the pedestrian, the type of road and the right of way, the first variable is compared with a preset value range to obtain a comparison result, comprising:

[0033] When the driving task of the vehicle, the running state of the vehicle, the pedestrian recognition state of the vehicle, the purpose of the pedestrian, the relative position of the pedestrian and the vehicle, the moving direction of the pedestrian, the moving speed of the pedestrian, the attention of the pedestrian, the type of road and the right of way satisfy a target condition at the same time, it is determined that the first variable meets the value range, otherwise it is determined that the first variable does not meet the value range; the target condition comprises:

[0034] The driving task of the vehicle is one of starting, parking, straight driving, left turning and right turning;

[0035] The running state of the vehicle is one of static waiting, deceleration giving way, and maintaining the original state.

[0036] The pedestrian recognition state of the vehicle is one of recognizing a pedestrian and not recognizing a pedestrian.

[0037] The pedestrian purpose is one of staying, crossing the road, and passing by.

[0038] The relative position of the pedestrian and the vehicle is one of the front, the left front, the right front, the left side, the right side, the left rear, the right rear, and the rear.

[0039] The pedestrian movement direction is one of perpendicular to the vehicle movement direction and parallel to the vehicle movement direction.

[0040] The pedestrian movement speed is one of static, walking, and running.

[0041] The pedestrian attention is one of paying attention to the vehicle and not paying attention to the vehicle.

[0042] The road type is one of a parking area, an internal road, an entrance and exit, a straight road section, and an intersection.

[0043] The right of way is one of in the vehicle, in the pedestrian, and unclear.

[0044] The application also provides a vehicle pedestrian communication device based on a driving scene, the device comprising:

[0045] A collection module is configured to acquire driving scene parameters of a vehicle.

[0046] A variable generation module is configured to generate a first variable based on driving scene parameters that affect vehicle-pedestrian communication, and to generate a second variable by superimposing driving scene parameters that do not affect vehicle-pedestrian communication on the vehicle driving scene, with the first variable as the base variable; the second variable has the first variable as the base variable and superimposes vehicle driving scene details.

[0047] A comparison module is configured to compare the first variable with a preset value range.

[0048] A selection module is configured to construct a target scene description according to the first variable and the second variable when the first variable meets the preset value range, and to select a target communication sentence and a target communication form based on the target scene description.

[0049] A communication module is configured to send the target communication sentence to a pedestrian in the target communication form, so that the vehicle and the pedestrian communicate.

[0050] In an embodiment of the present application, when the number of target communication sentences is more than one, the target communication sentences are sent to the pedestrian in the target communication form, so that the vehicle communicates with the pedestrian, comprising:

[0051] The target communication sentence with the highest priority is obtained from the target communication sentences;

[0052] The target communication sentence with the highest priority is sent to the pedestrian in the target communication form, so that the vehicle communicates with the pedestrian.

[0053] In an embodiment of the present application, when the first variable includes pedestrian attention, the second variable includes the number of pedestrians and the age of pedestrians, the target communication form is selected according to the pedestrian attention, the number of pedestrians and the age of pedestrians, comprising:

[0054] The first content adjustment form and the first communication channel are obtained when the pedestrian attention is a first preset value, the second content adjustment form and the second communication channel are obtained when the number of pedestrians is a second preset value, and the third content adjustment form and the third communication channel are obtained when the age of pedestrians is a third preset value;

[0055] The communication form with the highest priority is selected as the target communication channel from the first communication channel, the second communication channel and the third communication channel;

[0056] The current communication form is constructed by the first content adjustment form, the second content adjustment form, the third content adjustment form and the target communication channel, and the current communication form is selected as the target communication form.

[0057] In an embodiment of the present application, when the first variable includes the driving task of the vehicle, the running state of the vehicle, the pedestrian recognition state of the vehicle, the purpose of the pedestrian, the relative position of the pedestrian and the vehicle, the moving direction of the pedestrian, the moving speed of the pedestrian, the attention of the pedestrian, the type of road and the right of way, the first variable is compared with a preset value range to obtain a comparison result, comprising:

[0058] When the driving task of the vehicle, the running state of the vehicle, the pedestrian recognition state of the vehicle, the purpose of the pedestrian, the relative position of the pedestrian and the vehicle, the moving direction of the pedestrian, the moving speed of the pedestrian, the attention of the pedestrian, the type of road and the right of way satisfy a target condition at the same time, it is determined that the first variable meets the value range, otherwise it is determined that the first variable does not meet the value range; the target condition comprises:

[0059] The driving task of the vehicle is one of starting, parking, straight driving, left turning and right turning;

[0060] The running state of the vehicle is one of static waiting, deceleration giving way, and maintaining the original state.

[0061] The pedestrian recognition state of the vehicle is one of recognizing a pedestrian and not recognizing a pedestrian.

[0062] The pedestrian purpose is one of staying, crossing the road, and passing by.

[0063] The relative position of the pedestrian and the vehicle is one of the front, the left front, the right front, the left side, the right side, the left rear, the right rear, and the rear.

[0064] The pedestrian moving direction is one of perpendicular to the vehicle moving direction and parallel to the vehicle moving direction.

[0065] The pedestrian moving speed is one of static, walking, and running.

[0066] The pedestrian attention is one of paying attention to the vehicle and not paying attention to the vehicle.

[0067] The road type is one of a parking area, an internal road, an entrance and exit, a straight road section, and an intersection.

[0068] The right of way is one of in the vehicle, in the pedestrian, and unclear.

[0069] The application also provides a vehicle pedestrian communication device, which comprises:

[0070] One or more processors;

[0071] A storage device for storing one or more programs, which, when executed by the one or more processors, cause the vehicle pedestrian communication device to implement the vehicle pedestrian communication method based on the driving scene as described above.

[0072] The application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor of a computer, causes the computer to perform the vehicle pedestrian communication method based on the driving scene as described above.

[0073] The beneficial effects of the present application: the vehicle pedestrian communication method, device, equipment and storage medium based on driving scene in the present application, by acquiring the driving scene parameters of the vehicle; the first variable is generated based on the driving scene parameters affecting the communication between the vehicle and the pedestrian, and the driving scene parameters which do not affect the communication between the vehicle and the pedestrian are superimposed on the vehicle driving scene to generate the second variable; the second variable takes the first variable as the basis variable, and superimposes the vehicle driving scene details; compare the first variable with the preset value range; when the first variable meets the preset value range, construct the target scene description according to the first variable and the second variable, and select the target communication sentence and the target communication form based on the target scene description; the target communication sentence is sent to the pedestrian according to the target communication form, so that the vehicle communicates with the pedestrian. The present application uses the driving scene parameters of the vehicle to determine whether the current state can communicate with the pedestrian, and in the case of being able to communicate with the pedestrian, the communication sentence and the communication form are selected according to the driving scene parameters, so as to facilitate the vehicle to automatically and effectively communicate with the pedestrian. In addition, the present application takes the first variable as the basis scene variable, and then superimposes the driving scene details on the basis of the first variable, which can generate a test scene from top to bottom, so as to comprehensively cover all scenes when the vehicle communicates with the pedestrian; and after the basis scene variable is determined, the corresponding communication target and communication content are also determined, so as to facilitate the design of the interactive interface and the evaluation of the communication effect, and the driving scene details are superimposed on the basis scene variable, which is more flexible to increase and decrease. At the same time, the present application can generate multiple vehicle pedestrian communication model frameworks by randomly combining the first variable and the second variable, which can cover all scenes when the vehicle communicates with the pedestrian, and each scene can select the communication way and the communication sentence, avoiding the oversimplification and singleness of the communication process.

[0074] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0075] The drawings incorporated into the specification and forming part of the specification, show the embodiments consistent with the present application, and together with the specification, serve to explain the principles of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. In the drawings:

[0076] Figure 1 is an application scene diagram of the vehicle pedestrian communication method based on driving scene shown by an exemplary embodiment of the present application;

[0077] Figure 2is a schematic diagram of a communication framework shown in an example embodiment of the present application;

[0078] Figure 3 is a flowchart of a vehicle pedestrian communication method based on a driving scenario shown in an example embodiment of the present application;

[0079] Figure 4 is a schematic diagram of a vehicle driving scenario shown in an example embodiment of the present application;

[0080] Figure 5 is a simplified schematic diagram of a vehicle driving scenario shown in an example embodiment of the present application;

[0081] Figure 6 is a schematic diagram of a virtual reality scenario shown in an example embodiment of the present application;

[0082] Figure 7 is a structural diagram of a vehicle pedestrian communication device based on a driving scenario shown in an example embodiment of the present application;

[0083] Figure 8 A structural schematic diagram of a computer system of a vehicle pedestrian communication device suitable for implementing embodiments of the present application is shown. DETAILED DESCRIPTION

[0084] Other advantages and effects of the present application can be easily understood by those skilled in the art from the description of the embodiments of the present application disclosed herein. The present application can also be implemented or applied in other different specific embodiments, and the details in the description can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, and are not intended to limit the protection scope of the present application.

[0085] It should be noted that the diagrams provided in the following embodiments only schematically illustrate the basic concept of the present application, and only the components related to the present application are shown in the diagrams, rather than the number, shape and size of the components when actually implemented. The actual implementation of each component can be a random change in shape, number and proportion, and the layout pattern of the components can also be more complex.

[0086] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application, however, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details, and in other embodiments, the known structures and devices are shown in the form of block diagrams rather than in the form of details, to avoid making the embodiments of the present application difficult to understand.

[0087] Figure 1is an application scenario diagram of a vehicle-pedestrian communication method based on a driving scenario according to an example embodiment of the present application, as shown in Figure 1 As shown, the autonomous vehicle communicates with the pedestrian through an external interaction device, which includes but is not limited to an LED headlamp, a light language system, a vehicle horn, and an external loudspeaker. The external interaction device is essentially a kind of signal device that presents certain content in a certain form to convey information such as vehicle movement and intention to the pedestrian, helping the pedestrian to form a more reliable understanding of the current situation and make a more safe and efficient decision.

[0088] Scenario research is an essential part of developing and evaluating vehicle external interaction interfaces. Vehicle, pedestrian, environment, and task information are all included in the scenario. Through analysis and organization of this information, the interaction target, interaction content, and the most appropriate interaction form of the vehicle and the pedestrian in the current scenario can be derived, forming the necessary knowledge reserve for the development and evaluation of vehicle-pedestrian external interaction interfaces. From the perspective of development, the development of external interaction interfaces cannot be done in a vacuum and cannot be separated from scenarios. The interaction target, interaction content, and form of different scenarios are different, and the demand for external interaction interfaces is also different. From the perspective of evaluation, scenarios are also test environments that include several challenges that need to be overcome. The developed external interaction interfaces need to be tested in some scenarios to evaluate various indicators including safety and effectiveness.

[0089] Scenario research needs to serve the development and evaluation of vehicle external interaction interfaces and should focus on vehicle-pedestrian interaction communication and distinguish variables in the scenario that have different effects on interaction.

[0090] Figure 2 is a schematic diagram of a communication framework according to an example embodiment of the present application, as shown in Figure 2 The vehicle-pedestrian interaction communication is divided into three parts: 1) communication target; 2) communication content; and 3) communication form.

[0091] 1) Communication target: from the perspective of achieving functions, the communication target mainly has three levels, namely, perception level, understanding level, and behavior level, which are logically progressive.

[0092] The communication target at the perception level is for the pedestrian to notice the vehicle, which is the basis for achieving higher-level communication targets. The communication target at the understanding level is for the pedestrian to understand the information presented by the vehicle, that is, to understand what the vehicle is expressing. After the pedestrian perceives the vehicle and understands the information presented by the vehicle, some changes should be made at the behavior (or behavioral intention) level, which is the ultimate goal of vehicle-pedestrian interaction.

[0093] The communication target of the understanding level and the behavior level are usually closely related, mainly depending on the vehicle driving task, the current behavior and motion state mentioned in the scene analysis part, and the pedestrian purpose. For example, in the case of a vehicle straight ahead encountering a pedestrian preparing to cross the road, if the vehicle slows down to let the pedestrian pass, the communication target of the understanding level is to let the pedestrian understand that the vehicle is "decelerating" in the physical motion state, and the "let the pedestrian pass" intention behind it, while the communication target of the behavior level is "the pedestrian crossing the road". This example also shows that the communication target and the communication content are closely related.

[0094] 2) Communication content, including: system state information, physical motion information, dialogue information.

[0095] System state information is information about the internal state of the vehicle. System state information includes:

[0096] a. Driving mode information: manual, automatic, and hybrid driving. In addition, there is a special transition case, that is, the state of switching from one mode to another mode, which needs to present additional process information to the pedestrian, meaning "switching to" a certain mode.

[0097] b. System failure information: whether the automatic driving system is functioning properly, which is for the case where the vehicle is already in automatic driving mode.

[0098] c. Recognition state information: reflects the internal state of the vehicle in an explicit way. When automatic driving, the driver may perform some tasks unrelated to driving, and it is necessary to compensate for this information.

[0099] Vehicle physical motion information is an important type of communication content. The essence of vehicle physical motion is translation and rotation, with parameters such as direction, angle, speed, and speed change rate, which can objectively and rigorously describe the vehicle physical motion. The physical motion information is sorted by frequency of use:

[0100] a. Current speed: This is information that is always present on the car dashboard, but the speed information presented by the dashboard has been conveyed to the driver in the past. The vehicle exterior interface can convey this information to pedestrians;

[0101] b. Acceleration and deceleration: corresponding to the operation of the accelerator and brake, which frequently occurs during driving. In traditional interaction, pedestrians can only judge the vehicle acceleration and deceleration through implicit means, and the vehicle exterior interface can explicitly inform pedestrians of this information;

[0102] c. Steering: corresponding to the operation of the steering wheel, the turn signal in traditional interaction conveys this information to pedestrians and other road users, and the vehicle exterior interface can provide more expression methods;

[0103] d. Backward: usually appears in parking situations, although physically the forward and backward of the vehicle are symmetrical, in real life the vehicle basically always drives forward, so the vehicle forward information is generally defined by default without the need to express, only the vehicle backward information needs to be expressed.

[0104] The dialogue information refers to the vehicle directly expressing its appeal and reasons to the pedestrian, including:

[0105] a. Suggestion / request information: mainly including attracting attention, reminding, urging and leaving. Attracting attention refers to asking the pedestrian to pay attention to the vehicle, which is applicable to various situations where the pedestrian does not notice the vehicle, and the communication goal expected to be achieved is the perception level; reminding refers to reminding the pedestrian to cross the road or not, urging refers to asking the pedestrian to cross the road as soon as possible, which is applicable to common situations such as the pedestrian crossing the road, and the communication goal expected to be achieved is the understanding and behavior level; leaving refers to asking the pedestrian to give way to the vehicle, which is mainly applicable to small and micro conflict scenes such as starting and parking, and the communication goal expected to be achieved is the understanding and behavior level.

[0106] b. Explanation information: supplementary description of the suggestion / request information. It is very abrupt to directly suggest or request the pedestrian, and it will be more reasonable and natural after adding the explanation, for example, the pedestrian leaves because the vehicle is about to drive away, the pedestrian is urged because the vehicle owner has an urgent matter, etc. However, for the situation of reminding the pedestrian to cross the road, the pedestrian can usually determine that the vehicle is giving way to them based on the motion state of the vehicle, and no additional explanation information is needed.

[0107] 3) Communication form

[0108] The communication content can be divided into verbal and non-verbal, verbal is the language in daily life, and non-verbal is the symbol system other than daily language. Further combined with the sensory channel, mainly considering the visual channel and the auditory channel. Verbal plus visual channel becomes text; verbal plus auditory channel becomes voice; non-verbal plus visual channel becomes graphics, light strips, etc.; non-verbal plus auditory channel becomes sound.

[0109] Figure 3 is a flowchart of a vehicle-pedestrian communication method based on a driving scene according to an exemplary embodiment of the present application, as shown in Figure 3 As shown in FIG. 3, in an exemplary embodiment, the vehicle-pedestrian communication method based on the driving scene at least includes steps S310 to S350, which are described in detail as follows:

[0110] S310, obtaining the driving scene parameters of the vehicle;

[0111] In this embodiment, the driving scene parameters are the self parameters of the vehicle when driving and the perception parameters of the surrounding environment, including pedestrian perception parameters and road perception parameters. These parameters are obtained through various sensors of the vehicle;

[0112] The specific acquisition process includes steps S311 to S313, which are described in detail as follows:

[0113] S311, acquiring a driving variable of the vehicle during driving;

[0114] The driving variable can include driving mode information, system fault information, identification state information, current speed, acceleration and deceleration, steering, reversing, and the like, and the above information is used as a variable to reflect the driving state of the vehicle, such as the current speed variable, which can be one of high speed, medium speed, and low speed; the driving model information variable is the motion mode; and the system fault information is no fault, and the like.

[0115] S312, identifying pedestrians and road environments during driving of the vehicle to obtain pedestrian variables and road environment variables, respectively;

[0116] The vehicle cannot directly acquire information of pedestrians and roads, and therefore needs to rely on existing identification technology to identify pedestrians and roads to obtain pedestrian variables and road environment variables. The pedestrian variables include but are not limited to the number of people, age, attention level (whether the vehicle is noticed), and the like; and the road environment variables include but are not limited to road type, road facilities, road right, weather, lighting, and the like.

[0117] S313, constructing a driving scene parameter based on the driving variable, the pedestrian variable, and the road environment variable.

[0118] In this embodiment, the above three types of variables are collected to constitute the required driving scene parameter.

[0119] S320, generating a first variable based on the driving scene parameter affecting communication between the vehicle and the pedestrian, and superimposing the driving scene parameter not affecting the communication between the vehicle and the pedestrian on the vehicle driving scene to generate a second variable based on the first variable as a basic variable;

[0120] The specific generation process of the first variable and the second variable can include steps S321 to S322, which are described in detail as follows:

[0121] S321, screening the driving scene parameter according to whether it affects the communication effectiveness;

[0122] S322, generating a first variable based on the driving scene parameter affecting communication between the vehicle and the pedestrian, and superimposing the driving scene parameter not affecting the communication between the vehicle and the pedestrian on the vehicle driving scene to generate a second variable based on the first variable as a basic variable.

[0123] The embodiment further establishes a method of generating standardized test scenarios based on the communication framework. Taking vehicle-pedestrian interaction communication as the center, the variables in the scenario that have different influences on the interaction are distinguished. The variables in the scenario are divided into two categories, one is G (General) variable (i.e. the first variable), and the other is S (Special) variable (i.e. the second variable). The G variable is used to generate the basic scenario, and the S variable is added to the basic scenario as details. The basic scenario is generated by the G variable, and the S variable is added to the basic scenario. Finally, the standardized test scenario is generated by G+S. In this embodiment, according to the complexity of the scenario, detailed division or brief division of G variables and S variables can be selected, and the division results are shown in Tables 1 and 2:

[0124] Table 1. Detailed division table of G variables and S variables

[0125]

[0126]

[0127] Table 2. Brief division table of G variables and S variables

[0128]

[0129] The G variable is a scenario variable that affects both the communication target and the communication content, and will be used as a parameter to generate a basic scenario. Taking the driving task as an example, in different scenarios, the vehicle has different driving tasks, which will affect both the communication target and the communication content. For example, in the starting task, if the pedestrian blocks the way, the communication target is for the pedestrian to understand that the vehicle wants to start and give way to the vehicle, and the communication content is to express the request to leave and explain the intention of the vehicle to start. For example, in the straight task, the pedestrian wants to cross the road, and the vehicle gives way, the communication target changes to the pedestrian's understanding of the vehicle's deceleration state and the intention behind it, and the behavior level changes to the pedestrian crossing the road, and the communication content changes to the vehicle's physical movement information and the pedestrian's reminder that he can cross the road.

[0130] The S-class scene variable mainly affects the communication content or the communication form, usually does not affect the communication target, and even has no effect on the interaction, and will be used as details in the basic scene. Taking the vehicle speed as an example, the vehicle speed is a variable in the scene and also the communication content in the interaction process, but it does not affect the communication target, such as the vehicle straightening for the pedestrian preparing to cross the road to give way, regardless of the vehicle speed, the communication target is still that the pedestrian understands that the vehicle is decelerating and the intention behind the deceleration and crosses the road, but the physical movement information presented changes according to the actual vehicle speed. Taking the age of the pedestrian as another example, such as the pedestrian blocking the way of the vehicle, the vehicle hopes to please the pedestrian to leave, regardless of whether the pedestrian is a child, an adult or an old person, the established communication target will not change, and the meaning of the communication content will not change, but some details of the communication content and the communication form may be adjusted, for example, although the meaning of the communication content is to please the pedestrian to leave, some polite language can be added for the old person, and a graphical and simplified form can be considered for the child.

[0131] S330, comparing the first variable with a preset value range;

[0132] In this embodiment, when the first variable (G variable) meets the preset value range, it indicates that the current scene can communicate with the pedestrian, and various conditions can support the vehicle to express the meaning to the pedestrian.

[0133] Specifically, the value range of the first variable (G variable) is shown in Table 3 and Table 4.

[0134] Table 3. Detailed value range data table of G-class variables

[0135]

[0136]

[0137] Table 4. Brief value range data table of G-class variables

[0138]

[0139] Taking Table 3 as an example, when the driving task of the vehicle, the running state of the vehicle, the pedestrian recognition state of the vehicle, the pedestrian, the relative position between the pedestrian and the vehicle, the moving direction of the pedestrian, the moving speed of the pedestrian, the attention of the pedestrian, the road type, and the road right meet the target condition at the same time, it is determined that the first variable meets the value range, otherwise it is determined that the first variable does not meet the value range; the target condition includes:

[0140] (1) the driving task of the vehicle is one of starting, parking, straightening, left turning and right turning;

[0141] (2) the running state of the vehicle is one of static waiting, deceleration giving way and maintaining the original state;

[0142] (3) the pedestrian recognition state of the vehicle is one of recognizing a pedestrian and not recognizing a pedestrian;

[0143] (4) the pedestrian purpose is one of standing, crossing a road, and passing by;

[0144] (5) the relative position of the pedestrian and the vehicle is one of a front, a left front, a right front, a left side, a right side, a left rear, a right rear, and a rear;

[0145] (6) the pedestrian moving direction is one of perpendicular to a moving direction of the vehicle and parallel to the moving direction of the vehicle;

[0146] (7) the pedestrian moving speed is one of standing still, walking, and running;

[0147] (8) the pedestrian attention is one of paying attention to the vehicle and not paying attention to the vehicle;

[0148] (9) the road type is one of a parking area, an internal road, an entrance and exit, a straight road section, and an intersection;

[0149] (10) the right of way is one of being in the vehicle, being in the pedestrian, and being unclear.

[0150] In addition, if the current communication scenario is not very complex, the value range of Table 4 can also be used to judge the communication effectiveness, and when the G variable meets the value range in Table 4, it is considered that the vehicle performs meaning expression to the pedestrian in the current scenario.

[0151] S340 when the first variable meets the preset value range, constructing a target scenario description according to the first variable and the second variable, and selecting a target communication sentence and a target communication form based on the target scenario description;

[0152] In this embodiment, when the comparison result is that the first variable meets the value range, it indicates that communication can be performed in the current scenario, so after determining that communication can be performed, it is necessary to determine how to communicate; how to communicate includes communication content and communication form.

[0153] (A) Communication content: the communication content can be used to build a basic scenario according to the first variable (G variable), and then the second variable (S variable) is added in the current scenario to obtain a completed scenario; specifically including steps S3411 to S3412, which are described in detail as follows:

[0154] S341, constructing a target scenario description according to the first variable and the second variable;

[0155] S3411, combining a plurality of first variables to obtain a basic scenario description;

[0156] S3412, sequentially adjust the basic scene description according to the semantic rules to obtain an intermediate scene description;

[0157] S3413, superimpose the second variable to the intermediate scene description to obtain a target scene description.

[0158] In this embodiment, a plurality of basic scenes can be generated by different combinations of G-type variable values. In order to make the description of the basic scene more natural, some adjustments need to be made to the order of the variables to conform to the habits of Chinese language context daily language. It is suggested to describe in the following order: road type - vehicle driving task - pedestrian relative vehicle direction - pedestrian moving direction - pedestrian moving speed - pedestrian purpose - road right - vehicle recognition state - current behavior and motion state - pedestrian attention level. The following are several examples of generating basic scenes:

[0159] 1. Straight section, vehicle straight, pedestrian in front of vehicle right side, perpendicular to vehicle moving direction (left), static, (waiting for the opportunity to cross the road) stay, road right in vehicle, vehicle recognizes pedestrian, maintain the status quo, pedestrian notices vehicle.

[0160] 2. Parking area, vehicle starts, pedestrian in front of vehicle, perpendicular to vehicle moving direction (right), walk, pass, road right is not clear, vehicle recognizes pedestrian, static waiting, pedestrian notices vehicle.

[0161] 3. Internal road, vehicle straight, pedestrian in front of vehicle left side, parallel to vehicle moving direction (forward), walk, pass, road right is not clear, vehicle recognizes pedestrian, slow down and let go, pedestrian does not notice vehicle.

[0162] 4. Entrance and exit, vehicle right turn, pedestrian on the right side of the vehicle, perpendicular to the vehicle moving direction (left), walk, pass, road right is not clear, vehicle recognizes pedestrian, maintain the status quo, pedestrian notices vehicle.

[0163] 5. Intersection, vehicle left turn, pedestrian in front of vehicle, perpendicular to vehicle moving direction (right), run, cross the road, road right in pedestrian, vehicle recognizes pedestrian, slow down and let go, pedestrian notices vehicle.

[0164] In the basic scene, superimpose S-type variables to generate the final target scene description:

[0165] S-type variables usually do not affect the communication target, mainly affect the communication content or communication form, as details superimposed on the basic scene. Table 5 and Table 6 specify the detailed value range and brief value range of S-type variables, which can be selected according to the complexity of the scene.

[0166] Table 5. Detailed value range data table of S-type variables

[0167]

[0168] Table 6. Brief value range data table of S-class variables

[0169]

[0170]

[0171] The road facilities in the S-class variables are more special, as mentioned above. In short, the signal light and zebra crossing will affect the G-class variable road right, and the street lamp will affect the lighting, which is also an S-class variable, but only in the case of night. In order to facilitate the development of the scene, further sorting is made in Table 7 and Table 8, as shown in Table 7 and Table 8:

[0172] Table 7. Value range and supplementary detailed description table of road facilities

[0173]

[0174] Table 8. Value range and supplementary brief description table of road facilities

[0175] Road facility Value range Supplementary note Number of lanes 1、2、4、6、8 / Type of lane One-way, two-way / Zebra crossing Yes, no Need and G-class variable "right-of-way" are considered together

[0176] S342, according to the target scene description, querying the pre-established communication sentence library to match the corresponding target communication sentence; wherein the pre-established communication sentence library includes the mapping relationship between the target scene description and the target communication sentence.

[0177] In this embodiment, due to time limit, scene limit or external interaction device limit of the vehicle, it is not possible to effectively communicate with the pedestrian through a long speech, in order to ensure the efficiency of communication, some refined sentences are usually used for expression. In this embodiment, the refined communication sentence is stored in the communication sentence library, and is one-to-one corresponding (or mapping relationship) with a plurality of target scene descriptions, and the vehicle can obtain the corresponding communication sentence by querying after constructing the target scene description.

[0178] In addition, if the vehicle generates a plurality of target scene descriptions according to the driving scene parameters in a short time, thereby obtaining a plurality of communication sentences, it is necessary to selectively output according to the priority of the scene, therefore, it is necessary to define the priority of the plurality of communication sentences in advance, therefore, the corresponding relationship of the basic scene, the target scene description and the communication sentence (simplified command) is shown in Table 9 and Table 10:

[0179] Table 9. Detailed corresponding relationship table of basic scene, target scene description and simplified command

[0180]

[0181]

[0182] Table 10. Brief correspondence table of base scene, target scene description, and simplified command

[0183]

[0184] (B) The specific process of selecting the communication form includes steps S343 to S345, which are described in detail as follows:

[0185] S343, obtaining the first content adjustment form, the first communication channel when the pedestrian attention is the first preset value, obtaining the second content adjustment form, the second communication channel when the pedestrian quantity is the second preset value, and obtaining the third content adjustment form, the third communication channel when the pedestrian age is the third preset value;

[0186] In this embodiment, the correspondence between the pedestrian attention, the pedestrian quantity, the pedestrian age, and the communication form is established in advance, wherein the communication form includes the adjustment form of the communication content and the communication channel.

[0187] S344, when the pedestrian attention is the first preset value, the pedestrian quantity is the second preset value, and the pedestrian age is the third preset value, selecting the communication form with the highest priority from the first communication channel, the second communication channel, and the third communication channel as the target communication channel;

[0188] S345, constructing the current communication form with the first content adjustment form, the second content adjustment form, the third content adjustment form, and the target communication channel, and selecting the current communication form as the target communication form.

[0189] In this embodiment, the content adjustment form adopts the cumulative adjustment mode, and the communication channel adopts the selection mode. The specific correspondence between the variables and the communication form is shown in Tables 11 and 12:

[0190] Table 11. Detailed correspondence table of variables and communication forms

[0191]

[0192] Table 12. Brief correspondence table of variables and communication forms

[0193]

[0194] Taking Table 11 as an example, the specific conditions include:

[0195] (1) In the case of a single pedestrian, a child (less than the preset age range), and a pedestrian paying attention to the vehicle, a simplified, easy-to-understand, and colloquial adjustment method is used to adjust the text, and a visual graphical communication channel is used for communication.

[0196] (2) In the case of multiple pedestrians, children (less than the preset age range), and pedestrians paying attention to the vehicle, a disambiguation, generalization, direction, simplification, easy-to-understand, and colloquial adjustment method is used to adjust the text, and a visual graphical communication channel is used for communication.

[0197] (3) In the case of a single pedestrian, an adult (within the preset age range), and a pedestrian paying attention to the vehicle, a default content adjustment form (i.e., no adjustment) is used, and a default communication channel (visual text form) is used for communication.

[0198] (4) In the case of multiple pedestrians, adults (within the preset age range), and pedestrians paying attention to the vehicle, a disambiguation, generalization, and direction adjustment method is used to adjust the text, and a default communication channel (visual text form) is used for communication.

[0199] (5) In the case of a single pedestrian, an elderly person (greater than the preset age range), and a pedestrian paying attention to the vehicle, a simplified, polite, and colloquial adjustment method is used to adjust the text, and a default communication channel (visual text form) is used for communication.

[0200] (6) In the case of multiple pedestrians, elderly people (greater than the preset age range), and pedestrians paying attention to the vehicle, a disambiguation, generalization, direction, simplification, politeness, and colloquial adjustment method is used to adjust the text, and a default communication channel (visual text form) is used for communication.

[0201] (7) In the case of a single pedestrian, a child (less than the preset age range), and a pedestrian not paying attention to the vehicle (visual limitation), a simplified, easy-to-understand, and colloquial adjustment method is used to adjust the text, and a visual graphical communication channel is used for communication.

[0202] In (7), the communication channel corresponding to the child is visual graphics, but the communication channel corresponding to the pedestrian not paying attention to the vehicle (visual limitation) is auditory form, which is contradictory, so it needs to be selected according to the priority ranking. The priority ranking is as follows: visual prominence > visual graphics > auditory > default, so visual graphics is selected according to the priority, thereby preventing the child from running away in surprise;

[0203] (8) When the number of pedestrians is multiple, the age of the pedestrians is children (less than the preset age range), and the attention level of the pedestrians is not paying attention to the vehicle (visual limitation), the adjustment mode of disambiguation, generalization, pointing, simplification, easy-to-understand, and oralization is adopted to adjust the text, and the visual graphical communication channel is used for communication;

[0204] (9) When the number of pedestrians is single, the age of the pedestrians is adult (within the preset age range), and the attention level of the pedestrians is not paying attention to the vehicle (visual limitation), the default content adjustment form is adopted, and the auditory form is used for communication;

[0205] (10) When the number of pedestrians is multiple, the age of the pedestrians is adult (within the preset age range), and the attention level of the pedestrians is not paying attention to the vehicle (visual limitation), the adjustment mode of disambiguation, generalization, and pointing is adopted to adjust the text, and the auditory form is used for communication;

[0206] (11) When the number of pedestrians is single, the age of the pedestrians is elderly (greater than the preset age range), and the attention level of the pedestrians is not paying attention to the vehicle (visual limitation), the adjustment mode of simplification, politeness, and oralization is adopted to adjust the text, and the auditory form is used for communication;

[0207] (12) When the number of pedestrians is multiple, the age of the pedestrians is elderly (greater than the preset age range), and the attention level of the pedestrians is not paying attention to the vehicle (visual limitation), the adjustment mode of disambiguation, generalization, pointing, simplification, politeness, and oralization is adopted to adjust the text, and the auditory form is used for communication;

[0208] (13) When the number of pedestrians is single, the age of the pedestrians is children (less than the preset age range), and the attention level of the pedestrians is not paying attention to the vehicle (auditory limitation), the adjustment mode of simplification, easy-to-understand, and oralization is adopted to adjust the text, and the visual prominent form of communication channel is used for communication;

[0209] (14) When the number of pedestrians is multiple, the age of the pedestrians is children (less than the preset age range), and the attention level of the pedestrians is not paying attention to the vehicle (auditory limitation), the adjustment mode of disambiguation, generalization, pointing, simplification, easy-to-understand, and oralization is adopted to adjust the text, and the visual prominent form of communication channel is used for communication;

[0210] (15) When the number of pedestrians is single, the age of the pedestrians is adult (within the preset age range), and the attention level of the pedestrians is not paying attention to the vehicle (auditory limitation), the default content adjustment form is adopted, and the visual prominent form is used for communication;

[0211] (16) When the number of pedestrians is multiple, the age of the pedestrians is adult (within the preset age range), and the attention level of the pedestrians is not paying attention to the vehicle (hearing limited), the adjustment mode of disambiguation, generalization, and direction is used to adjust the text, and the text is communicated in a visually prominent form;

[0212] (17) When the number of pedestrians is single, the age of the pedestrians is old (greater than the preset age range), and the attention level of the pedestrians is not paying attention to the vehicle (hearing limited), the adjustment mode of simplification, politeness, and colloquialization is used to adjust the text, and the text is communicated in a visually prominent form;

[0213] (18) When the number of pedestrians is multiple, the age of the pedestrians is old (greater than the preset age range), and the attention level of the pedestrians is not paying attention to the vehicle (hearing limited), the adjustment mode of disambiguation, generalization, direction, simplification, politeness, and colloquialization is used to adjust the text, and the text is communicated in a visually prominent form.

[0214] After (A) content selection and (B) communication form selection are completed, sending can be performed.

[0215] S350, the target communication sentence is sent to the pedestrian in the target communication form, so that the vehicle communicates with the pedestrian.

[0216] The sending process includes steps S351 to S352, which are described in detail as follows:

[0217] S351, the target communication sentence with the highest priority is obtained from the multiple target communication sentences;

[0218] S352, the target communication sentence with the highest priority is sent to the pedestrian in the target communication form, so that the vehicle communicates with the pedestrian.

[0219] In another embodiment of the application, the process after obtaining the target communication sentence can further include steps S360 to S370, which are described in detail as follows:

[0220] S360, a virtual reality scene is constructed according to the target scene description;

[0221] S370, the target communication sentence is simulated and output in the virtual reality scene.

[0222] In another embodiment of the application, to make the interactive scene more intuitive and visual, and facilitate subsequent development work, a small amount of story elements can be added to the above scene and organized to form a journey linking multiple scenes, as shown in Figure 4 Then, the scene description in Figure 4 is simplified to obtain the scene shown in Figure 5 .

[0223] Build in the form of VR Figure 5 The scene of G+S scene definition, can be built in the form of VR, build as follows:

[0224] Build driving scene:

[0225] Morning, near the side parking space of the community express cabinet, pedestrians take the express to stand in front of the main car to check, notice that the main car started. As shown in Figure 6 The lowermost car in the figure is the main car.

[0226] Basic scene: parking area, vehicle start, pedestrian in front of the vehicle, parallel to the vehicle moving direction (back), static, (because of something) stay, unclear right of way, vehicle identification to pedestrian, static waiting, pedestrian notice the vehicle.

[0227] Confirm S (variable configuration), see table 13:

[0228] Table 13. S variable configuration table

[0229] Vehicle speed 0-10 km / h (0 km / h) Relative distance to pedestrian Close, 0-10 meters (2 meters) Number of people Single person Age Adult Number of lanes One lane Type of lane One-way Lighting Daytime

[0230] Communication target in straight scene, see table 14:

[0231] Table 14. Communication target confirmation table

[0232] Level of awareness Noticed by the pedestrian (achieved) Level of understanding Pedestrian understands that the vehicle is about to start and move away, and blocks the way of the vehicle Level of behavior Pedestrian gives way to the vehicle

[0233] Communication content in straight scene, see table 15:

[0234] Table 15. Communication content confirmation table

[0235] Driving mode information Automatic driving System failure information Normal Identification status information Identified pedestrian Physical motion information Stationary Suggestion / request information Please leave (please the pedestrian give way to the vehicle) Explanation information The vehicle is about to start

[0236] Other scenes are built in this way, which will not be described here.

[0237] The vehicle-pedestrian communication method based on a driving scene in the application, by acquiring driving scene parameters of a vehicle; generating a first variable and a second variable based on the driving scene parameters, the first variable is used to determine whether the vehicle can communicate with the pedestrian, and the second variable is based on the first variable and superimposes vehicle driving scene details; comparing the first variable with a preset value range; when the first variable meets the preset value range, constructing a target scene description according to the first variable and the second variable, and selecting a target communication sentence and a target communication form based on the target scene description; sending the target communication sentence to the pedestrian according to the target communication form, so that the vehicle communicates with the pedestrian. The application uses the driving scene parameters of the vehicle to determine whether the current state can communicate with the pedestrian, and in the case of being able to communicate with the pedestrian, the communication sentence and the communication form are selected according to the driving scene parameters, so as to facilitate the vehicle to automatically and effectively communicate with the pedestrian. In addition, the method takes the first variable as the basic scene variable, and then superimposes the driving scene details on the basis of the first variable, which can generate a test scene from top to bottom, so as to comprehensively cover all scenes when the vehicle communicates with the pedestrian; and after the basic scene variable is determined, the corresponding communication target and communication content are also determined, so as to facilitate the design of the interactive interface and the evaluation of the communication effect, and the driving scene details are superimposed on the basic scene variable, which is more flexible to increase or decrease. At the same time, the method can generate multiple vehicle-pedestrian communication model frameworks by randomly combining the first variable and the second variable, which can cover all scenes when the vehicle communicates with the pedestrian, and each scene can select a communication way and a communication sentence, avoiding the oversimplification and singleness of the communication process.

[0238] As Figure 7 shown, the application also provides a vehicle-pedestrian communication device based on a driving scene, which comprises:

[0239] The acquisition module is used to acquire driving scene parameters of a vehicle;

[0240] The variable generation module is used to generate a first variable and a second variable based on the driving scene parameters, the first variable is used to determine whether the vehicle can communicate with the pedestrian, and the second variable is based on the first variable and superimposes vehicle driving scene details;

[0241] The comparison module is used to compare the first variable with a preset value range;

[0242] The selection module is used to construct a target scene description according to the first variable and the second variable when the first variable meets the preset value range, and select a target communication sentence and a target communication form based on the target scene description;

[0243] The communication module is used to send the target communication sentence to the pedestrian according to the target communication form, so that the vehicle communicates with the pedestrian.

[0244] The vehicle-pedestrian communication device based on a driving scene in the present application judges whether the vehicle can communicate with the pedestrian by obtaining the driving scene parameter of the vehicle, generates a first variable and a second variable based on the driving scene parameter, the first variable is used to judge whether the vehicle can communicate with the pedestrian, the second variable takes the first variable as a basis variable and superimposes the driving scene details of the vehicle, compares the first variable with a preset value range, constructs a target scene description according to the first variable and the second variable when the first variable meets the preset value range, selects a target communication sentence and a target communication form based on the target scene description, and sends the target communication sentence to the pedestrian according to the target communication form, so that the vehicle communicates with the pedestrian. The present application uses the driving scene parameter of the vehicle to judge whether the current state can communicate with the pedestrian, and selects the communication sentence and the communication form according to the driving scene parameter when the vehicle can communicate with the pedestrian, so as to facilitate the vehicle to automatically and effectively communicate with the pedestrian. In addition, the present system takes the first variable as a basis scene variable, and then superimposes the driving scene details on the basis of the first variable, can generate a test scene from top to bottom, and thus comprehensively covers all scenes when the vehicle communicates with the pedestrian. After the basis scene variable is determined, the corresponding communication target and communication content are also determined, so as to facilitate the design of the interactive interface and the evaluation of the communication effect, and the driving scene details are superimposed on the basis scene variable, and the increase and decrease are more flexible. At the same time, the present system can generate multiple vehicle-pedestrian communication model frameworks by randomly combining the first variable and the second variable, can cover all scenes when the vehicle communicates with the pedestrian, and each scene can select the communication mode and the communication sentence, avoiding the oversimplification and singleness of the communication process.

[0245] It should be noted that the vehicle-pedestrian communication device based on a driving scene provided in the above embodiments and the vehicle-pedestrian communication method based on a driving scene provided in the above embodiments belong to the same concept, wherein the specific manner in which each module and unit performs operations has been described in detail in the method embodiments, which will not be described here. The vehicle-pedestrian communication device based on a driving scene provided in the above embodiments can be completed by different functional modules according to the needs in actual application, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above, and this is not limited herein.

[0246] Embodiments of the present application also provide a vehicle-pedestrian communication device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the vehicle-pedestrian communication device implements the vehicle-pedestrian communication method based on a driving scene provided in each of the above embodiments.

[0247] Figure 8A schematic diagram of a computer system suitable for implementing the vehicle-pedestrian communication device of the embodiments of this application is shown. It should be noted that... Figure 8 The computer system 800 of the vehicle-pedestrian communication device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0248] like Figure 8 As shown, the computer system 800 includes a Central Processing Unit (CPU) 801, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on a program stored in Read-Only Memory (ROM) 802 or a program loaded from storage portion 808 into Random Access Memory (RAM) 803. The RAM 803 also stores various programs and data required for system operation. The CPU 801, ROM 802, and RAM 803 are interconnected via a bus 804. An Input / Output (I / O) interface 805 is also connected to the bus 804.

[0249] The following components are connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 810 as needed so that computer programs read from it can be installed into storage section 808 as needed.

[0250] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by central processing unit (CPU) 801, it performs various functions defined in the system of this application.

[0251] Note that the computer readable medium shown in the embodiments of the present application can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium may, for example, be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, the computer readable signal medium can include a data signal embodied in or transmitted by a carrier wave or a program medium, in which the computer readable program can be included. Such a program medium can take many forms, including but not limited to, a magnetic storage medium, an optical storage medium, or any suitable combination thereof. The computer readable program medium can also be any computer readable medium other than a storage medium that can transmit, propagate or transport the program for use by or in connection with an instruction execution system, apparatus or device. The computer readable program medium includes the computer readable program that can be transmitted or transported by a computer readable signal medium. The computer readable program medium can be transmitted or transported by any medium including, but not limited to, wireless, wire line, optical fiber cable, RF, etc., or any suitable combination thereof.

[0252] The flowcharts and block diagrams in the drawings illustrate the possible architectures, functionality, and operations of systems, methods, and computer program products according to various embodiments of the present application. Each block in the flowcharts or block diagrams can represent a module, a program segment, or a portion of code that comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks noted in succession can in fact be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowcharts, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0253] The units described in the embodiments of the present application can be implemented in the form of software, or can be implemented in the form of hardware, and the described units can also be arranged in a processor. In some cases, the names of the units do not constitute a limitation on the units themselves.

[0254] Another aspect of the present application also provides a computer readable storage medium, which stores a computer program. When the computer program is executed by a processor of a computer, the computer executes the vehicle-pedestrian communication method based on a driving scenario as described above. The computer readable storage medium can be included in the vehicle-pedestrian communication device described in the above embodiments, or can exist separately and not be assembled into the vehicle-pedestrian communication device.

[0255] Another aspect of the present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the vehicle-pedestrian communication method based on a driving scenario provided in each of the above embodiments.

[0256] The above embodiments only exemplarily illustrate the principles and effects of the present application, and are not used to limit the present application. Any person skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes completed by those skilled in the art without departing from the spirit and technical thought of the present application should be covered by the claims of the present application.

Claims

1. A vehicle-pedestrian communication method based on driving scenarios, characterized in that, The method includes: Obtain vehicle driving scenario parameters; The first variable is generated based on the driving scenario parameters that affect vehicle-pedestrian communication. Then, the second variable is generated by superimposing the driving scenario parameters that do not affect vehicle-pedestrian communication with the vehicle driving scenario. Compare the first variable with the preset value range; When the first variable meets the preset value range, a target scenario description is constructed based on the first variable and the second variable, and a target communication statement and target communication form are selected based on the target scenario description; The target communication statement is sent to the pedestrian according to the target communication format, so that the vehicle can communicate with the pedestrian; When the first variable includes pedestrian attention and the second variable includes pedestrian number and pedestrian age, the process of selecting a target communication format based on pedestrian attention, pedestrian number, and pedestrian age includes: The system acquires a first content adjustment format and a first communication channel when the pedestrian's attention is at a first preset value; acquires a second content adjustment format and a second communication channel when the number of pedestrians is at a second preset value; and acquires a third content adjustment format and a third communication channel when the pedestrian's age is at a third preset value. Select the communication method with the highest priority from the first communication channel, the second communication channel, and the third communication channel as the target communication channel; The current communication form is constructed using the first content adjustment form, the second content adjustment form, the third content adjustment form, and the target communication channel, and the current communication form is selected as the target communication form.

2. The vehicle-pedestrian communication method based on driving scenarios according to claim 1, characterized in that, Constructing a target scenario description based on the first variable and the second variable, and selecting a target communication statement based on the target scenario description, including: Construct a target scene description based on the first variable and the second variable; The pre-established communication statement library is queried according to the target scenario description to match the corresponding target communication statement; wherein, the pre-established communication statement library includes the mapping relationship between the target scenario description and the target communication statement.

3. The vehicle-pedestrian communication method based on driving scenarios according to claim 2, characterized in that, When there are multiple first variables, a target scene description is constructed based on the first variables and the second variables, including: By combining multiple of the first variables, a basic scenario description is obtained; The order of the basic scene descriptions is adjusted according to semantic rules to obtain intermediate scene descriptions; The second variable is superimposed on the intermediate scene description to obtain the target scene description.

4. The vehicle-pedestrian communication method based on driving scenarios according to claim 1, characterized in that, Obtain vehicle driving scenario parameters, including: Acquire driving variables while the vehicle is in motion; wherein, the driving variables include at least one of the following: driving mode information, system fault information, identification status information, current speed, acceleration information, deceleration information, steering information, and reversing information; Pedestrians and the road environment are identified when vehicles are in motion, and pedestrian variables and road environment variables are obtained respectively. Driving scenario parameters are constructed using the driving variables, pedestrian variables, and road environment variables.

5. The vehicle-pedestrian communication method based on driving scenarios according to claim 2, characterized in that, After obtaining the target communication statement, it also includes: Construct a virtual reality scene based on the target scene description; The target communication statement is simulated and output in the virtual reality scene.

6. The vehicle-pedestrian communication method based on driving scenarios according to claim 2, characterized in that, When there are multiple target communication statements, the target communication statements are sent to the pedestrians according to the target communication format to enable communication between the vehicle and the pedestrians, including: Obtain the highest priority target communication statement from among the multiple target communication statements; The highest priority target communication statement is sent to the pedestrian in the target communication format so that the vehicle can communicate with the pedestrian.

7. The vehicle-pedestrian communication method based on driving scenarios according to claim 1, characterized in that, When the first variable includes the vehicle's driving task, vehicle's operating status, vehicle's pedestrian recognition status, pedestrian's purpose, relative position between pedestrian and vehicle, pedestrian's direction of movement, pedestrian's speed of movement, pedestrian's attention, road type, and right-of-way, the process of comparing the first variable with a preset value range includes: When the vehicle's driving task, the vehicle's operating status, the vehicle's pedestrian recognition status, the pedestrian's gaze, the relative position of the pedestrian and the vehicle, the pedestrian's direction of movement, the pedestrian's speed of movement, the pedestrian's attention, the road type, and the right-of-way simultaneously meet the target conditions, the first variable is determined to be within the specified value range; otherwise, the first variable is determined to be outside the specified value range. The target conditions include: The driving task of the vehicle is one of the following: starting, parking, going straight, turning left, or turning right; The vehicle's operating state is one of the following: stationary waiting, slowing down to yield, or maintaining its original state; The vehicle's pedestrian recognition status is either pedestrian detected or pedestrian not detected. The pedestrian's purpose is one of stopping, crossing the road, or passing by; The relative position of the pedestrian and the vehicle is one of the following: directly in front, left front, right front, left, right, left rear, right rear, or directly behind. The pedestrian's movement direction is either perpendicular to the vehicle's movement direction or parallel to the vehicle's movement direction; The pedestrian's movement speed is one of three: stationary, walking, or running. The pedestrian's attention is defined as either not noticing the vehicle or not noticing the vehicle. The road type is one of the following: parking area, internal road, entrance / exit, straight road section, or intersection; The right-of-way is defined as being for vehicles, pedestrians, or something else entirely.

8. A vehicle-pedestrian communication device based on driving scenarios, characterized in that, The device includes: The data acquisition module is used to obtain vehicle driving scenario parameters; The variable generation module is used to generate a first variable based on driving scenario parameters that affect vehicle-pedestrian communication, and to generate a second variable by superimposing driving scenario parameters that do not affect vehicle-pedestrian communication with the vehicle driving scenario based on the first variable. The comparison module is used to compare the first variable with a preset value range; The selection module is used to construct a target scenario description based on the first variable and the second variable when the first variable meets the preset value range, and to select a target communication statement and a target communication form based on the target scenario description. The communication module is used to send the target communication statement to the pedestrian according to the target communication format, so that the vehicle can communicate with the pedestrian; When the first variable includes pedestrian attention and the second variable includes pedestrian quantity and pedestrian age, the process by which the selection module selects a target communication form based on the pedestrian attention, the pedestrian quantity, and the pedestrian age includes: obtaining a first content adjustment form and a first communication channel when the pedestrian attention is a first preset value; obtaining a second content adjustment form and a second communication channel when the pedestrian quantity is a second preset value; and obtaining a third content adjustment form and a third communication channel when the pedestrian age is a third preset value; selecting the communication form with the highest priority from the first communication channel, the second communication channel, and the third communication channel as the target communication channel; constructing a current communication form using the first content adjustment form, the second content adjustment form, the third content adjustment form, and the target communication channel; and selecting the current communication form as the target communication form.

9. The vehicle-pedestrian communication device based on driving scenarios according to claim 8, characterized in that, When the first variable includes the vehicle's driving task, vehicle's operating status, vehicle's pedestrian recognition status, pedestrian's purpose, relative position between pedestrian and vehicle, pedestrian's direction of movement, pedestrian's speed of movement, pedestrian's attention, road type, and right-of-way, the comparison module compares the first variable with a preset value range to obtain the comparison result. The process includes: When the vehicle's driving task, the vehicle's operating status, the vehicle's pedestrian recognition status, the pedestrian's gaze, the relative position of the pedestrian and the vehicle, the pedestrian's direction of movement, the pedestrian's speed of movement, the pedestrian's attention, the road type, and the right-of-way simultaneously meet the target conditions, the first variable is determined to be within the specified value range; otherwise, the first variable is determined to be outside the specified value range. The target conditions include: The driving task of the vehicle is one of the following: starting, parking, going straight, turning left, or turning right; The vehicle's operating state is one of the following: stationary waiting, slowing down to yield, or maintaining its original state; The vehicle's pedestrian recognition status is either pedestrian detected or pedestrian not detected. The pedestrian's purpose is one of stopping, crossing the road, or passing by; The relative position of the pedestrian and the vehicle is one of the following: directly in front, left front, right front, left, right, left rear, right rear, or directly behind. The pedestrian's movement direction is either perpendicular to the vehicle's movement direction or parallel to the vehicle's movement direction; The pedestrian's movement speed is one of three: stationary, walking, or running. The pedestrian's attention is defined as either not noticing the vehicle or not noticing the vehicle. The road type is one of the following: parking area, internal road, entrance / exit, straight road section, or intersection; The right-of-way is defined as being for vehicles, pedestrians, or something else entirely.

10. A vehicle-pedestrian communication device, characterized in that, The device includes: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the vehicle-pedestrian communication device to implement the vehicle-pedestrian communication method based on a driving scenario as described in any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the vehicle-pedestrian communication method based on any one of claims 1 to 7.

Images