Intelligent driving interaction method and system based on AI glasses

Abstract

The invention provides an intelligent driving interaction method and system based on AI glasses, and the method comprises the steps: collecting the current surrounding environment perception information of a vehicle in real time through a vehicle sensor; through AI glasses worn on the head of the driver, environment images in the current visual field range of the driver are collected in real time, and the head posture of the driver is tracked; fusing the surrounding environment perception information and the environment image, and based on at least one target object identified in the surrounding environment perception information, positioning an image area of the target object in the environment image; generating augmented reality prompt information in semantic association with the target object according to the spatial relationship between the head posture and the image region; and through the AI glasses, the augmented reality prompt information is superimposed and projected in the current visual field of the driver in a visual mode, and the display position of the augmented reality prompt information corresponds to the spatial position of the target object in the current visual field. Through the method, the transmission intuition of the driving prompt information and the driving safety are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to an intelligent driving interaction method and system based on AI glasses. Background Technology

[0002] With the development of intelligent driving technology, vehicles are increasingly able to acquire environmental information. How to efficiently, intuitively and safely transmit massive amounts of environmental information to the driver has become an important issue in the field of human-computer interaction.

[0003] Currently, common methods of providing driving information include the instrument panel, the central control screen, and the head-up display (HUD). HUDs, by projecting key information such as vehicle speed and navigation onto the windshield, reduce the frequency with which drivers need to look down at the instrument panel. However, existing HUD technologies have inherent limitations: their display area and projection position are usually fixed, failing to match the driver's dynamically changing natural gaze. This means that drivers still need to actively shift their gaze to the fixed HUD display area to obtain information, a process that itself causes a shift and interruption of visual attention. Furthermore, the fixed display position prevents the information from being directly associated spatially with the specific external objects the driver is focused on (such as pedestrians, vehicles, and traffic signs). The information presentation is not intuitive enough, requiring drivers to pay extra attention to match abstract symbols with real-world entities, potentially increasing cognitive load and reaction delays in complex or emergency scenarios. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide an intelligent driving interaction method and system based on AI glasses, so as to deeply integrate driving information with the driver's visual focus and the real driving environment, fundamentally reduce the driver's visual distraction, and improve the intuitiveness of driving prompt information transmission and driving safety.

[0005] In a first aspect, embodiments of this application provide an intelligent driving interaction method based on AI glasses, the method comprising: During the vehicle's operation, the vehicle's sensors collect real-time information about the vehicle's surrounding environment. The system uses AI glasses worn by the driver to collect real-time images of the environment within the driver's current field of vision and tracks the driver's head posture. By fusing the surrounding environment perception information and the environment image, and based on at least one target object identified in the surrounding environment perception information, the image region of the target object is located in the environment image; Based on the spatial relationship between the head pose and the image region, augmented reality prompt information semantically associated with the target object is generated; The augmented reality prompts are projected onto the driver's current field of vision using the AI ​​glasses, and the display position of the augmented reality prompts corresponds to the spatial position of the target object in the current field of vision.

[0006] In conjunction with the first aspect, this application provides a first possible implementation of the first aspect, wherein the vehicle sensor includes at least one of: lidar, millimeter-wave radar, ultrasonic radar, and vehicle-mounted camera.

[0007] In conjunction with the first aspect, this application provides a second possible implementation of the first aspect, wherein the AI ​​glasses include a binocular camera, a gyroscope, and an accelerometer; the step of acquiring environmental images within the driver's current field of vision in real time through the AI ​​glasses worn on the driver's head, and tracking the driver's head posture, includes: The binocular camera captures real-time environmental images within the driver's current field of vision, and the gyroscope and accelerometer track the driver's head posture.

[0008] In conjunction with the first aspect, this application provides a third possible implementation of the first aspect, wherein the method further includes: When the AI ​​glasses detect that the driver's gaze duration on the target object or the augmented reality prompt information of the target object reaches a preset duration, detailed extended information of the target object is generated. The AI ​​glasses project the detailed extended information into the driver's current field of vision.

[0009] In conjunction with the first aspect, this application provides a fourth possible implementation of the first aspect, wherein the method further includes: The AI ​​glasses recognize the driver's gesture commands and, in response to the gesture commands, control the operating mode of the AI ​​glasses.

[0010] In conjunction with the first aspect, this application provides a fifth possible implementation of the first aspect, wherein the method further includes: The AI ​​glasses respond to the driver's selection of the interaction prompt mode and adjust the interaction prompt mode of the augmented reality prompt information; the interaction prompt mode includes a simplified prompt mode and a full information prompt mode.

[0011] In conjunction with the first aspect, this application provides a sixth possible implementation of the first aspect, wherein generating augmented reality prompt information semantically associated with the target object based on the spatial relationship between the head pose and the image region includes: Based on the current driving scenario of the vehicle, key prompt objects are dynamically selected from at least one of the target objects; Based on the spatial relationship between the head pose and the image region of the key prompt object, augmented reality prompt information semantically associated with the key prompt object is generated.

[0012] In conjunction with the sixth possible implementation of the first aspect, this application provides a seventh possible implementation of the first aspect, wherein dynamically selecting key prompt objects from at least one of the target objects based on the current driving scenario of the vehicle includes: If the current driving scenario of the vehicle is an urban road scenario, then pedestrians and non-motorized vehicles will be selected as key prompting targets; If the current driving scenario of the vehicle is a highway scenario, then the driver status monitoring event is identified as a key notification target; wherein, the driver status monitoring event includes at least one of hands-off driving event or fatigue driving event.

[0013] In conjunction with the sixth possible implementation of the first aspect, this application provides an eighth possible implementation of the first aspect, wherein the method further includes: The AI ​​glasses generate and broadcast voice prompts associated with the target object or the augmented reality prompts based on the type of the target object, the current driving scenario, or the selected interaction prompt mode.

[0014] Secondly, embodiments of this application also provide an intelligent driving interaction system based on AI glasses, the system comprising: vehicle sensors on the vehicle, AI glasses worn by the driver, and a processing unit; The vehicle sensor is used to collect real-time information about the vehicle's surrounding environment while the vehicle is in motion. The AI ​​glasses are used to collect environmental images within the driver's current field of vision in real time and track the driver's head posture. The processing unit is configured to fuse the surrounding environment perception information and the environment image, locate the image region of the target object in the environment image based on at least one target object identified in the surrounding environment perception information, and generate augmented reality prompt information semantically associated with the target object according to the spatial relationship between the head pose and the image region. The AI ​​glasses are also used to visually overlay and project the augmented reality prompt information onto the driver's current field of vision, and the display position of the augmented reality prompt information corresponds to the spatial position of the target object in the current field of vision.

[0015] This application provides an intelligent driving interaction method and system based on AI glasses. The method fuses ambient perception information from vehicle sensors with environmental images captured by the AI ​​glasses to accurately locate target objects (such as vehicles, pedestrians, obstacles, traffic signs, etc.) within the driver's field of vision (environmental image). Then, the generated augmented reality (AR) prompts are directly overlaid onto the corresponding spatial location of the target object in the driver's current field of vision. This allows the AR prompts to be displayed on top of the real target object, achieving seamless visual integration between the virtual AR prompts and the real target object, greatly improving the intuitiveness of the driving prompts (i.e., AR prompts).

[0016] Furthermore, because augmented reality cues are presented directly near the target object that the driver is focused on or should focus on, the driver does not need to shift their gaze from the road environment to a fixed display area (such as the dashboard or traditional HUD area) to obtain driving cues. This significantly reduces attentional distractions and potential safety risks caused by frequent gaze shifts, and lowers the cognitive effort required for the driver to associate abstract cues with specific environmental entities.

[0017] Furthermore, by tracking the driver's head posture in real time through AI glasses and combining this with the image region of the located target object, the augmented reality prompts are dynamically calculated and maintained in the correct projection position within the driver's current field of vision. Regardless of how the driver's head turns, the augmented reality prompts consistently and stably point to the corresponding real-world target object, thus ensuring the real-time nature and accuracy of the interaction and providing the driver with stable and reliable visual assistance.

[0018] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart of an intelligent driving interaction method based on AI glasses, provided in an embodiment of this application, is shown. Figure 2 This illustration shows a structural diagram of an AI-based intelligent driving interaction system provided in an embodiment of this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] Currently, common methods of providing driving information include the instrument panel, the central control screen, and the head-up display (HUD). HUDs, by projecting key information such as vehicle speed and navigation onto the windshield, reduce the frequency with which drivers need to look down at the instrument panel. However, existing HUD technologies have inherent limitations: their display area and projection position are usually fixed, failing to match the driver's dynamically changing natural gaze. This means that drivers still need to actively shift their gaze to the fixed HUD display area to obtain information, a process that itself causes a shift and interruption of visual attention. Furthermore, the fixed display position prevents the information from being directly associated spatially with the specific external objects the driver is focused on (such as pedestrians, vehicles, and traffic signs). The information presentation is not intuitive enough, requiring drivers to pay extra attention to match abstract symbols with real-world entities, potentially increasing cognitive load and reaction delays in complex or emergency scenarios.

[0023] Based on this, this application provides an intelligent driving interaction method and system based on AI glasses, which will be described below through embodiments.

[0024] To facilitate understanding of this embodiment, a detailed description of an AI-based intelligent driving interaction method disclosed in this application embodiment will be provided first. For example... Figure 1 As shown, the process includes the following steps S101-S105: S101: During the driving process, the vehicle collects real-time information about the vehicle's surrounding environment through the vehicle's sensors. S102: Through AI glasses worn by the driver, the system collects environmental images within the driver's current field of vision in real time and tracks the driver's head posture. S103: Fuse surrounding environment perception information and environmental image, and locate the image region of the target object in the environmental image based on at least one target object identified in the surrounding environment perception information; S104: Generate augmented reality prompts that are semantically related to the target object based on the spatial relationship between the head pose and the image region; S105: Through AI glasses, augmented reality prompts are visually overlaid and projected onto the driver's current field of vision, and the display position of the augmented reality prompts corresponds to the spatial position of the target object in the current field of vision.

[0025] In this embodiment, the AI ​​glasses-based intelligent driving interaction method is applied to an AI glasses-based intelligent driving interaction system, which includes vehicle sensors configured on the vehicle, AI glasses for wearing on the driver's head, and a processing unit.

[0026] In step S101, the vehicle sensors include at least one of the following: LiDAR (point cloud modeling), millimeter-wave radar (speed detection), ultrasonic radar (near-range obstacle detection), and onboard camera (image detection). The vehicle sensors have 360° all-around perception capability, enabling them to perceive environmental information (i.e., surrounding environment perception information) around the vehicle in 360 degrees.

[0027] In step S102, the AI ​​glasses include a binocular camera, a gyroscope, and an accelerometer. The binocular camera (main camera + wide-angle) can achieve a 120° FOV (field of view), meaning the binocular camera's field of view is no less than 120 degrees. The gyroscope and accelerometer are used to track the driver's head posture with an error ≤0.5°.

[0028] In this embodiment, the environmental image captured by the AI ​​glasses changes as the driver's current field of vision changes. The driver's head posture includes the direction of the driver's head and the position of the head.

[0029] In one possible implementation, step S102 can be performed according to the following steps: The system uses binocular cameras to capture real-time images of the environment within the driver's field of vision, and gyroscopes and accelerometers to track the driver's head posture.

[0030] In step S103, the target object includes at least one of dynamic traffic participants, static traffic facilities, or road geometry elements. Dynamic traffic participants include at least one of pedestrians, non-motorized vehicles, and other motor vehicles. Static traffic facilities include at least one of traffic lights, traffic signs, and road barriers. Road geometry includes at least one of lane-level elements (such as lane lines, road boundaries, curbs / shoulders) and road contour elements (such as drivable area boundaries, medians / green belts).

[0031] In step S104, the content of the augmented reality prompt (such as shape, color, and text) is generated based on the type, state, or meaning of the target object itself. For example, if the target object is a pedestrian, the augmented reality prompt might be a red highlighted box; if the target object is a speed limit sign, the augmented reality prompt might be a flashing number "60"; if the target object is a navigation intersection, the augmented reality prompt might be a floating arrow.

[0032] In one possible implementation, when performing step S104, the following steps S1041-S1042 can be specifically performed: S1041: Based on the current driving scenario of the vehicle, dynamically select key prompt objects from at least one target object; S1041: Generate augmented reality prompt information that is semantically related to the key prompt object based on the spatial relationship between the head pose and the image region of the key prompt object.

[0033] In this embodiment, if the current driving scenario of the vehicle is an urban road scenario, pedestrians and non-motorized vehicles are selected as key prompt objects; If the current driving scenario of the vehicle is a highway scenario, then the driver status monitoring event will be identified as the key notification target; among them, the driver status monitoring event includes at least one of the following: hands-free driving event or fatigue driving event.

[0034] In step S105, the AI ​​glasses visually overlay and project (i.e., AR projection) augmented reality prompts onto the driver's current field of vision, and the display position of the augmented reality prompts corresponds to the spatial position of the target object in the current field of vision. For example, when the target object is a bicycle, the AI ​​glasses highlight the pixel position of the bicycle (i.e., the real-world position) through AR projection, directly guiding the driver's line of sight.

[0035] In one possible implementation, the method may also be performed according to the following steps S201-S202: S201: When the AI ​​glasses detect that the driver's gaze on the target object or the augmented reality prompt information of the target object has reached the preset duration, detailed extended information of the target object is generated. S202: Detailed extended information is projected into the driver's current field of vision through AI glasses.

[0036] In this embodiment, if the driver continues to stare at a target object (such as a complex road sign) for more than a preset time, it will be assumed that the driver wants to know more detailed information about the target object. At this time, detailed extended information of the target object (i.e., augmented reality detailed extended information) is automatically generated and visually superimposed and projected onto the driver's current field of vision. The display position of the detailed extended information corresponds to the spatial position of the target object in the current field of vision. For example, the detailed extended information is expanded next to the target object (such as enlarging the road sign text or translating the content).

[0037] In one possible implementation, the method may also be performed according to the following steps: The AI ​​glasses recognize the driver's gesture commands and respond to the gesture commands to control the operation mode of the AI ​​glasses.

[0038] In this embodiment, the driver can use specific gestures (such as pressing or sliding their fingers on the temple of the glasses) to select whether to turn off the AI ​​glasses mode or access other operation pages. The operation modes of the AI ​​glasses include turning off the AI ​​glasses mode and turning on the AI ​​glasses mode.

[0039] In one possible implementation, the method may also be performed according to the following steps: The AI ​​glasses respond to the driver's selection of the interaction prompt mode and adjust the interaction prompt mode of the augmented reality prompt information; the interaction prompt modes include a simplified prompt mode and a full information prompt mode.

[0040] In this embodiment, the driver can select the interactive prompt mode based on their own driving characteristics. To avoid excessive interference while driving, a simplified prompt mode can be selected. If a more comprehensive understanding of the target object's information is desired, a full-information prompt mode can be selected. Generally, the augmented reality prompts in the full-information prompt mode contain more information than those in the simplified prompt mode.

[0041] In one possible implementation, the method may also be performed according to the following steps: AI glasses generate and broadcast voice prompts associated with the target object or augmented reality prompts, based on the type of the target object, the current driving scenario, or the selected interaction prompt mode.

[0042] In this embodiment, voice prompts can improve driver safety when visibility is obstructed or when an emergency warning is needed.

[0043] Based on the same technical concept, embodiments of this application also provide an intelligent driving interaction system based on AI glasses, such as... Figure 2 As shown, the system includes: vehicle sensors on the vehicle, AI glasses worn by the driver, and a processing unit; The vehicle sensor is used to collect real-time information about the vehicle's surrounding environment while the vehicle is in motion. The AI ​​glasses are used to collect environmental images within the driver's current field of vision in real time and track the driver's head posture. The processing unit is configured to fuse the surrounding environment perception information and the environment image, locate the image region of the target object in the environment image based on at least one target object identified in the surrounding environment perception information, and generate augmented reality prompt information semantically associated with the target object according to the spatial relationship between the head pose and the image region. The AI ​​glasses are also used to visually overlay and project the augmented reality prompt information onto the driver's current field of vision, and the display position of the augmented reality prompt information corresponds to the spatial position of the target object in the current field of vision.

[0044] Optionally, the vehicle sensor includes at least one of: lidar, millimeter-wave radar, ultrasonic radar, and vehicle-mounted camera.

[0045] Optionally, the AI ​​glasses include a binocular camera, a gyroscope, and an accelerometer; when used to acquire environmental images within the driver's current field of vision in real time and track the driver's head posture, the AI ​​glasses are specifically used for: The binocular camera captures real-time environmental images within the driver's current field of vision, and the gyroscope and accelerometer track the driver's head posture.

[0046] Optionally, the processing unit is further configured to generate detailed extended information about the target object when the AI ​​glasses detect that the driver's gaze duration on the target object or the augmented reality prompt information of the target object reaches a preset duration; The AI ​​glasses are also used to project the detailed extended information into the driver's current field of vision.

[0047] Optionally, the AI ​​glasses are also used to recognize the driver's gesture commands and, in response to the gesture commands, control the operating mode of the AI ​​glasses.

[0048] Optionally, the AI ​​glasses are also configured to adjust the interactive prompt mode of the augmented reality prompt information in response to the driver's selection of the interactive prompt mode; the interactive prompt mode includes a simplified prompt mode and a full information prompt mode.

[0049] Optionally, when the processing unit generates augmented reality prompt information semantically associated with the target object based on the spatial relationship between the head pose and the image region, it is specifically used for: Based on the current driving scenario of the vehicle, key prompt objects are dynamically selected from at least one of the target objects; Based on the spatial relationship between the head pose and the image region of the key prompt object, augmented reality prompt information semantically associated with the key prompt object is generated.

[0050] Optionally, when the processing unit dynamically filters out key prompt objects from at least one of the target objects based on the current driving scenario of the vehicle, it is specifically used for: If the current driving scenario of the vehicle is an urban road scenario, then pedestrians and non-motorized vehicles will be selected as key prompting targets; If the current driving scenario of the vehicle is a highway scenario, then the driver status monitoring event is identified as a key notification target; wherein, the driver status monitoring event includes at least one of hands-off driving event or fatigue driving event.

[0051] Optionally, the AI ​​glasses are also used to generate and broadcast voice prompts associated with the target object or the augmented reality prompts, based on the type of the target object, the current driving scenario, or the selected interaction prompt mode.

[0052] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0053] In the several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. The system embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some communication interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0054] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0055] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0056] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0057] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims.

Claims

1. A smart driving interaction method based on AI glasses, characterized in that, The method includes: During the vehicle's operation, the vehicle's sensors collect real-time information about the vehicle's surrounding environment. The system uses AI glasses worn by the driver to collect real-time images of the environment within the driver's current field of vision and tracks the driver's head posture. By fusing the surrounding environment perception information and the environment image, and based on at least one target object identified in the surrounding environment perception information, the image region of the target object is located in the environment image; Based on the spatial relationship between the head pose and the image region, augmented reality prompt information semantically associated with the target object is generated; The augmented reality prompts are projected onto the driver's current field of vision using the AI ​​glasses, and the display position of the augmented reality prompts corresponds to the spatial position of the target object in the current field of vision.

2. The method according to claim 1, characterized in that, The vehicle sensors include at least one of the following: lidar, millimeter-wave radar, ultrasonic radar, and vehicle-mounted camera.

3. The method according to claim 1, characterized in that, The AI ​​glasses include a binocular camera, a gyroscope, and an accelerometer; the AI ​​glasses, worn by the driver, acquire real-time environmental images within the driver's current field of vision and track the driver's head posture, including: The binocular camera captures real-time environmental images within the driver's current field of vision, and the gyroscope and accelerometer track the driver's head posture.

4. The method according to claim 1, characterized in that, The method further includes: When the AI ​​glasses detect that the driver's gaze duration on the target object or the augmented reality prompt information of the target object reaches a preset duration, detailed extended information of the target object is generated. The AI ​​glasses project the detailed extended information into the driver's current field of vision.

5. The method according to claim 1, characterized in that, The method further includes: The AI ​​glasses recognize the driver's gesture commands and, in response to the gesture commands, control the operating mode of the AI ​​glasses.

6. The method according to claim 1, characterized in that, The method further includes: The AI ​​glasses respond to the driver's selection of the interaction prompt mode and adjust the interaction prompt mode of the augmented reality prompt information; the interaction prompt mode includes a simplified prompt mode and a full information prompt mode.

7. The method according to claim 1, characterized in that, The step of generating augmented reality prompt information semantically associated with the target object based on the spatial relationship between the head pose and the image region includes: Based on the current driving scenario of the vehicle, key prompt objects are dynamically selected from at least one of the target objects; Based on the spatial relationship between the head pose and the image region of the key prompt object, augmented reality prompt information semantically associated with the key prompt object is generated.

8. The method according to claim 7, characterized in that, The step of dynamically selecting key prompt objects from at least one of the target objects based on the current driving scenario of the vehicle includes: If the current driving scenario of the vehicle is an urban road scenario, then pedestrians and non-motorized vehicles will be selected as key prompting targets; If the current driving scenario of the vehicle is a highway scenario, then the driver status monitoring event is identified as a key notification target; wherein, the driver status monitoring event includes at least one of hands-off driving event or fatigue driving event.

9. The method according to claim 7, characterized in that, The method further includes: The AI ​​glasses generate and broadcast voice prompts associated with the target object or the augmented reality prompts based on the type of the target object, the current driving scenario, or the selected interaction prompt mode.

10. An intelligent driving interaction system based on AI glasses, characterized in that, The system includes: vehicle sensors on the vehicle, AI glasses worn by the driver, and a processing unit; The vehicle sensor is used to collect real-time information about the vehicle's surrounding environment while the vehicle is in motion. The AI ​​glasses are used to collect environmental images within the driver's current field of vision in real time and track the driver's head posture. The processing unit is configured to fuse the surrounding environment perception information and the environment image, locate the image region of the target object in the environment image based on at least one target object identified in the surrounding environment perception information, and generate augmented reality prompt information semantically associated with the target object according to the spatial relationship between the head pose and the image region. The AI ​​glasses are also used to visually overlay and project the augmented reality prompt information onto the driver's current field of vision, and the display position of the augmented reality prompt information corresponds to the spatial position of the target object in the current field of vision.

Images