Control method of vehicle, electronic device, and vehicle

Abstract

This application provides a vehicle control method, electronic device, and vehicle, belonging to the field of human-computer interaction. Using the technical solution provided in this application, the driving intention of a target object wearing an eye tracker is identified by determining the target gaze point and driving-related data of the vehicle. Then, when the driving intention indicates a need to take over the intelligent driving system, a target control strategy is determined using the target gaze point to control the vehicle. This allows driving intentions related to the target gaze point to be applied to intelligent driving scenarios, enabling the driver to control the vehicle without cumbersome additional operations, significantly reducing the risk of driver distraction. The interaction method is natural and intuitive, improving the human-computer collaboration experience. Furthermore, the target control strategy is only determined when the target object needs to take over the intelligent driving system, improving the accuracy and flexibility of vehicle control.

Description

Technical Field

[0001] This application relates to the field of human-computer interaction, and more specifically, to vehicle control methods, electronic devices, and vehicles in the field of human-computer interaction. Background Technology

[0002] In autonomous driving scenarios, when drivers need to adjust intelligent driving strategies, they typically do so manually or by issuing voice commands. However, manual operation can distract the driver and poses safety risks. Voice commands require precise expression from the driver, are easily affected by in-vehicle noise, have insufficient recognition accuracy, and cannot quickly convey the driver's immediate intentions, resulting in a less intuitive interaction. These issues include control delays and high safety risks.

[0003] Therefore, how to intuitively and quickly adjust intelligent driving strategies is a hot research topic. Summary of the Invention

[0004] This application provides a vehicle control method, electronic device, and vehicle. The method can intuitively and quickly adjust the intelligent driving strategy. The technical solution is as follows: Firstly, a method for controlling a vehicle is provided, the method comprising: Determine the target fixation point corresponding to the target object, wherein the target object is the object wearing the eye tracker; Based on the target gaze point and the vehicle's driving-related data, the driving intention of the target object is identified; In cases where the driving intention representation requires takeover of the intelligent driving system, a target control strategy is determined based on the target gaze point; The vehicle is controlled based on the target control strategy.

[0005] In this implementation, the driving intention of the target subject wearing an eye tracker is identified by determining the target gaze point and the vehicle's driving-related data. Then, when the driving intention indicates that the subject needs to take over the intelligent driving system, a target control strategy is determined using the target gaze point. This allows the driver to control the vehicle without cumbersome additional operations, significantly reducing the risk of driver distraction. The interaction is natural and intuitive, improving the human-machine collaboration experience. Furthermore, the target control strategy is only determined when the target subject needs to take over the intelligent driving system, improving the accuracy and flexibility of vehicle control.

[0006] In conjunction with the first aspect, in some possible implementations, determining the target control strategy based on the target gaze point includes: generating at least one candidate strategy and a weight value corresponding to each candidate strategy based on the target object corresponding to the target gaze point and a preset mapping rule; and determining the candidate strategy with the highest weight value as the target control strategy.

[0007] In this implementation, candidate strategies and weight values ​​for each candidate strategy are generated by the target object corresponding to the target gaze point and the preset mapping rules. The candidate strategy with the highest weight value is then determined as the target control strategy. Compared with the mapping of a single strategy, multiple related candidate strategies can be established for a target object, thereby selecting the target control strategy most suitable for the current scene and improving the accuracy of the target control strategy.

[0008] In combination with the first aspect and the above implementation methods, in some possible implementation methods, controlling the vehicle based on the target control strategy includes: generating target interaction content based on the target control strategy; outputting the target interaction content to the target object, and receiving target response content from the target object to the target interaction content; and controlling the vehicle based on the target response content.

[0009] In this implementation, a target control strategy is used to generate and output target interaction content to the target object. Then, the vehicle is controlled by the target object's target response to the target interaction content. The accuracy of the current target control strategy can be quickly confirmed through the target interaction content, which further improves the accuracy of vehicle control.

[0010] In combination with the first aspect and the above implementation methods, in some possible implementation methods, controlling the vehicle based on the target response content includes: if the target response content indicates that the target object has confirmed the target control strategy, controlling the vehicle based on the target control strategy; if the target response content indicates that the target object has not confirmed the target control strategy, re-determining the candidate strategy whose weight value is after the target control strategy as the target control strategy, and executing the steps of generating target interaction content and subsequent steps based on the target control strategy again.

[0011] In this implementation, if the target response indicates that the target object has confirmed the target control strategy, the vehicle is controlled by the target control strategy. If the target response indicates that the target object has not confirmed the target control strategy, the candidate strategy with a weight value after the target control strategy is re-determined as the target control strategy and the target control strategy is confirmed again. The vehicle can be controlled by selecting an appropriate method according to the target response. If the current target control strategy is not confirmed, the target control strategy will be further modified, thus realizing a closed loop of vehicle control.

[0012] In combination with the first aspect and the above implementation methods, in some possible implementation methods, controlling the vehicle based on the target control strategy includes: acquiring target road condition information of the vehicle; and controlling the vehicle based on the target control strategy when the target road condition information satisfies a first execution condition of the target control strategy.

[0013] In this implementation, the vehicle will only be controlled based on the target control strategy if the acquired target road condition information meets the first execution condition of the target control strategy. This allows for a comprehensive assessment of the feasibility of the road conditions before executing the target control strategy, thus avoiding safety hazards caused by intelligent driving adjustments from the source and improving vehicle safety.

[0014] In combination with the first aspect and the above implementation methods, in some possible implementation methods, the method further includes: continuously acquiring the target road condition information during the execution of the target control strategy; pausing the execution of the target control strategy when the target road condition information does not meet the first execution condition; and outputting prompt information to the target object.

[0015] In this implementation, target road condition information is continuously acquired during the execution of the target control strategy. If the target road condition information does not meet the first execution condition, the execution of the target control strategy is suspended and a prompt message is output to the target object. This allows for real-time and continuous monitoring of the feasibility of the target control strategy, ensuring driving safety. At the same time, when the execution of the target control strategy is suspended, a prompt message is output to the target object, enabling the target object to quickly know the vehicle's status.

[0016] In combination with the first aspect and the above implementation methods, in some possible implementation methods, determining the target gaze point corresponding to the target object includes: when the target object gazes toward the outside of the vehicle, determining the target gaze point based on the target object's target gaze vector, the first three-dimensional coordinates of the eye tracker, and the initial image captured by the target camera.

[0017] In this implementation, when the target object gazes at the outside of the vehicle, the target gaze point is determined by the target object's gaze vector, the first three-dimensional coordinates of the eye tracker, and the initial image captured by the target camera. Compared with related technologies that do not identify the gaze point outside the vehicle, this method can accurately identify the target gaze point without fixed parts being calibrated outside the vehicle, thereby forming a closed-loop control of the vehicle.

[0018] In conjunction with the first aspect and the above implementation methods, in some possible implementation methods, identifying the driving intention of the target object based on the target gaze point and the vehicle's driving-related data includes: acquiring the driving-related data when the duration of the target object corresponding to the target gaze point is greater than or equal to a time threshold, wherein the driving-related data includes at least one of the vehicle's driving mode, navigation information, and target road condition information; determining that the driving intention representation needs to take over the intelligent driving system when the driving-related data meets a second execution condition; and determining that the driving intention representation does not need to take over the intelligent driving system when the driving-related data does not meet the second execution condition.

[0019] In this implementation, when the duration of the target object corresponding to the target gaze point is greater than or equal to a time threshold, the system determines whether the driving intention representation needs to take over the intelligent driving system by checking whether the acquired driving-related data meets the second execution condition. The driving intention is identified through two dimensions: the duration of the target gaze point and the driving-related data. Compared with using a single dimension, this improves the accuracy and stability of the driving intention.

[0020] Secondly, a vehicle control device is provided, the device comprising: The determination module is used to determine the target gaze point corresponding to the target object, wherein the target object is an object wearing an eye tracker; The recognition module is used to recognize the driving intention of the target object based on the target gaze point and the vehicle's driving-related data; The determining module is used to determine a target control strategy based on the target gaze point when the driving intention representation requires takeover of the intelligent driving system. A control module is used to control the vehicle based on the target control strategy.

[0021] In conjunction with the second aspect, in some possible implementations, the device further includes a generation module, configured to generate at least one candidate strategy and a weight value corresponding to each candidate strategy based on the target object corresponding to the target gaze point and a preset mapping rule; the determination module is configured to determine the candidate strategy with the highest weight value as the target control strategy.

[0022] In combination with the second aspect and the above implementation methods, in some possible implementation methods, the generation module is used to generate target interaction content based on the target control strategy; output the target interaction content to the target object, and receive target response content from the target object to the target interaction content; the control module is used to control the vehicle based on the target response content.

[0023] In combination with the second aspect and the above implementation methods, in some possible implementation methods, the control module is used to control the vehicle based on the target control strategy when the target response content indicates that the target object has confirmed the target control strategy; the generation module is used to re-determine the candidate strategy whose weight value is after the target control strategy as the target control strategy when the target response content indicates that the target object has not confirmed the target control strategy, and to execute the steps of generating target interaction content based on the target control strategy and subsequent steps again.

[0024] In conjunction with the second aspect and the above implementation methods, in some possible implementation methods, the device further includes an acquisition module for acquiring target road condition information of the vehicle; and a control module for controlling the vehicle based on the target control strategy when the target road condition information satisfies the first execution condition of the target control strategy.

[0025] In combination with the second aspect and the above implementation methods, in some possible implementation methods, the acquisition module is used to continuously acquire the target road condition information during the execution of the target control strategy; the control module is used to suspend the execution of the target control strategy and output prompt information to the target object when the target road condition information does not meet the first execution condition.

[0026] In combination with the second aspect and the above implementation methods, in some possible implementation methods, the determining module is used to determine the target gaze point based on the target object's target gaze vector, the first three-dimensional coordinates of the eye tracker, and the initial image captured by the target camera when the target object gazes toward the outside of the vehicle.

[0027] In conjunction with the second aspect and the above implementation methods, in some possible implementation methods, the acquisition module is used to acquire the driving-related data when the duration of the target object corresponding to the target gaze point is greater than or equal to a time threshold. The driving-related data includes at least one of the vehicle's driving mode, navigation information, and target road condition information. The identification module is used to determine that the driving intention representation needs to take over the intelligent driving system when the driving-related data meets the second execution condition, and to determine that the driving intention representation does not need to take over the intelligent driving system when the driving-related data does not meet the second execution condition.

[0028] Thirdly, a vehicle is provided, the vehicle including one or more processors and one or more memories, the one or more memories storing at least one piece of program code, the program code being loaded and executed by the one or more processors to implement the operations performed by the control method of the vehicle.

[0029] Fourthly, a computer-readable storage medium is provided, wherein at least one piece of program code is stored therein, the program code being loaded and executed by a processor to implement the operations performed by the vehicle control method.

[0030] Fifthly, an electronic device is provided, including a memory and a processor, wherein the memory is used to store executable program code; and the processor is used to call and run the executable program code from the memory, causing the electronic device to perform the vehicle control method of the first aspect or any possible implementation thereof.

[0031] By employing the technical solution provided in this application, the driving intention of a target object wearing an eye tracker is identified by determining the target gaze point and the vehicle's driving-related data. Then, when the driving intention indicates a need to take over the intelligent driving system, a target control strategy is determined using the target gaze point. This allows the vehicle to be controlled through the target control strategy, enabling the application of driving intentions related to the target gaze point to intelligent driving scenarios. This allows the driver to control the vehicle without cumbersome additional operations, significantly reducing the risk of driver distraction. The interaction method is natural and intuitive, improving the human-machine collaboration experience. Furthermore, the target control strategy is only determined when the target object needs to take over the intelligent driving system, improving the accuracy and flexibility of vehicle control. Attached Figure Description

[0032] Figure 1 This is a flowchart of a vehicle control method provided in an embodiment of this application; Figure 2 This is a flowchart of another vehicle control method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Detailed Implementation

[0033] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0034] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0035] In order to illustrate the technical solutions provided in the embodiments of this application, some terms involved in the embodiments of this application will be explained below.

[0036] Eye trackers, also known as eye-tracking glasses, wearable eye-tracking acquisition devices, or driver / passenger eye-tracking interaction terminals, are worn by drivers and passengers to collect real-time data on the wearer's spatial three-dimensional coordinates, head orientation angle, and gaze direction. For example, a glasses-type eye tracker may include low-power passive marker elements, transmitting the collected data to an onboard processing unit via wired / wireless communication.

[0037] In autonomous driving scenarios, drivers can adjust intelligent driving strategies. However, related technologies suffer from the following problems in adjusting intelligent driving strategies: First, adjustments are typically made manually or via voice commands. Manual operation distracts the driver and poses safety risks, while voice commands require precise driver input, are susceptible to in-vehicle noise, have insufficient recognition accuracy, and cannot quickly convey the driver's immediate intentions, resulting in a less intuitive interaction. Second, human-machine collaboration is poor. The intelligent driving system cannot perceive the driver's gaze and can only adjust according to preset routes or manual commands. The driver must actively initiate commands, making natural interaction based on gaze-based adjustments impossible. Third, scenario adaptability is weak. It only supports certain intelligent driving scenarios, and strategy adjustments are disconnected from eye-tracking interaction technology, failing to leverage existing eye-tracking positioning and point-of-attack judgment capabilities for collaborative optimization.

[0038] Therefore, how to intuitively and quickly adjust intelligent driving strategies is a hot research topic.

[0039] The application scenarios of the technical solutions provided in the embodiments of this application are described below. The technical solutions provided in the embodiments of this application can be applied to different types of vehicles, such as hybrid vehicles, electric vehicles, and pure fuel vehicles. Of course, with the development of science and technology, other types of vehicles may also emerge, and the technical solutions provided in the embodiments of this application are also applicable to other types of vehicles.

[0040] After introducing the application scenarios of the embodiments of this application, the technical solutions provided by the embodiments of this application will be described below. (See also...) Figure 1 The method includes the following steps.

[0041] 101. Determine the target fixation point corresponding to the target object, which is the object wearing an eye tracker.

[0042] In this context, the target object is the person wearing an eye tracker. An eye tracker is a device used to track and record eye movements and the location of the gaze point. In some embodiments, the target object is the driver in a vehicle wearing an eye tracker. The target gaze point is the gaze point generated when the target object gazes at a target object. In some embodiments, the target gaze point is located outside the vehicle and is a three-dimensional coordinate in the vehicle's coordinate system. The target object is an object identified from objects located outside the vehicle that the target object is gazing at. The identified object can be any suitable type, such as a pedestrian, parking space, lane, etc.

[0043] 102. Identify the driving intention of the target object based on the target gaze point and vehicle driving-related data.

[0044] Driving-related data refers to data relevant to the vehicle's autonomous driving process. In some embodiments, driving-related data may include, but is not limited to, at least one of the following: vehicle driving mode, navigation information, and target road condition information. The vehicle's driving mode is the mode currently used by the vehicle for intelligent driving. The vehicle's driving mode may include, but is not limited to, Level 1-2 assisted driving, Level 3 conditional automated driving, Level 4 highly automated driving, and Level 5 fully automated driving. Navigation information is used to provide real-time location, route planning, and navigation guidance for the target object. Navigation information can be obtained from the vehicle's navigation system. The vehicle's navigation system utilizes the Global Positioning System (GPS) and map data to help the driver select the best route in complex road environments through voice prompts and a visual interface. Target road condition information characterizes the overall condition of the road the vehicle is currently traveling on. Target road condition information may include, but is not limited to, road surface conditions, road width, vehicle speed, road curvature, and traffic flow. Road surface conditions refer to the condition assessment value of the road surface the vehicle is currently traveling on. Road width refers to the width of the road ahead of the vehicle. Road curvature refers to the curvature of the road ahead of the vehicle. Traffic flow characterizes the number and speed of other vehicles around the vehicle. Vehicle speed refers to the vehicle's speed at the current moment. The target's driving intention indicates whether the target needs to take over the intelligent driving system.

[0045] 103. When the driving intention representation requires taking over the intelligent driving system, determine the target control strategy based on the target gaze point.

[0046] The target driver's driving intention is used to characterize whether the target driver needs to take over the intelligent driving system. If the driving intention indicates no need to take over, the vehicle can continue to be controlled according to the current intelligent driving control strategy. If the driving intention indicates a need to take over, a target control strategy needs to be determined based on the target driver's gaze point. The target control strategy is the strategy used to enable the target driver to take over the intelligent driving system. Target control strategies may include, but are not limited to, preparing to stop, adjusting speed, and preparing to turn.

[0047] 104. Controlling vehicles based on target control strategies.

[0048] In cases where the driver's intent requires takeover of the intelligent driving system, a target control strategy is first determined. This strategy is then converted into target control commands usable by the vehicle. These commands are then sent to the appropriate execution modules to achieve vehicle control. Execution modules may include, but are not limited to, the engine, electric motor, and steering wheel.

[0049] By employing the technical solution provided in this application, the driving intention of a target object wearing an eye tracker is identified by determining the target gaze point and the vehicle's driving-related data. Then, when the driving intention indicates a need to take over the intelligent driving system, a target control strategy is determined using the target gaze point. This allows the vehicle to be controlled through the target control strategy, enabling the application of driving intentions related to the target gaze point to intelligent driving scenarios. This allows the driver to control the vehicle without cumbersome additional operations, significantly reducing the risk of driver distraction. The interaction method is natural and intuitive, improving the human-machine collaboration experience. Furthermore, the target control strategy is only determined when the target object needs to take over the intelligent driving system, improving the accuracy and flexibility of vehicle control.

[0050] It should be noted that steps 101-104 above are a simplified description of the vehicle control method provided in the embodiments of this application. The vehicle control method provided in the embodiments of this application will be described in more detail below with some examples. See [link to relevant documentation]. Figure 2 The method includes the following steps.

[0051] 201. Determine the target fixation point corresponding to the target object, which is the object wearing an eye tracker.

[0052] In this context, the target object is the person wearing an eye tracker. An eye tracker is a device used to track and record eye movements and the location of the gaze point. In some embodiments, the target object is the driver in a vehicle wearing an eye tracker. The target gaze point is the gaze point generated when the target object gazes at a target object. In some embodiments, the target gaze point is located outside the vehicle and is a three-dimensional coordinate in the vehicle's coordinate system. The target object is an object identified from objects located outside the vehicle that the target object is gazing at. The identified object can be any suitable type, such as a pedestrian, parking space, lane, etc.

[0053] In one possible implementation, when the target object is gazing toward the outside of the vehicle, the target gaze point is determined based on the target object's gaze vector, the first three-dimensional coordinates of the eye tracker, and the initial image captured by the target camera.

[0054] In this application, when a target object wearing an eye tracker gazes at the exterior of a vehicle, the gaze point is located outside the vehicle. Therefore, the detection of the gaze point outside the vehicle is required according to the technical solution of this application. The target gaze vector is the gaze vector generated when the target object gazes at the exterior of the vehicle. The gaze vector is a three-dimensional vector representing the direction of observation and is widely used in computer vision, eye tracking, and virtual reality. The first three-dimensional coordinates are the three-dimensional coordinate positions of the eye tracker when the target object gazes at the exterior of the vehicle. In some embodiments, the first three-dimensional coordinates are three-dimensional coordinates in the vehicle body coordinate system. The target camera is the camera currently used to acquire the initial image of the exterior of the vehicle. In some embodiments, the target camera can be any suitable type, such as a surround-view camera, a forward-view camera, etc. The initial image is the raw image acquired by the target camera.

[0055] In some embodiments, the target camera can be determined from at least one camera located outside the vehicle by using the orientation angle of the eye tracker. Then, the target camera is invoked to acquire an initial image. Further, based on the target gaze vector and a first three-dimensional coordinate, a target recognition region is determined from the initial image to identify the target gaze point within that region. The orientation angle of the eye tracker refers to the deflection angle of the eye tracker in the horizontal and vertical directions, which can be used to characterize the pose information of the target object. The target recognition region includes at least one recognized object located outside the vehicle. The recognized object can be any suitable type, such as a pedestrian, parking space, lane, etc.

[0056] In some embodiments, the angular coverage area of ​​the eye tracker can be obtained based on the horizontal and vertical orientation angles of the eye tracker's orientation angles. Then, cameras located within the coverage area are selected from at least one camera located outside the vehicle. The camera closest to the eye tracker among the cameras in the coverage area is selected as the target camera, and the target camera is then invoked to acquire the initial image.

[0057] In some embodiments, the target gaze vector can be calculated using the Pupil-Center Corneal Reflection (PCCR) algorithm. The PCCR algorithm is a high-precision method widely used in eye-tracking technology. Its core principle is to use an infrared light source to illuminate the surface of the eyeball and calculate the gaze direction by capturing the relative positional relationship between the corneal reflection point and the pupil center. Specifically: First, the built-in infrared light source of the eye tracker captures the positional deviation between the pupil center and the corneal reflection point. The horizontal / vertical rotation angle of the eyeball is calculated based on the positional deviation. Combined with the current first three-dimensional coordinates and orientation angle of the eye tracker, and substituted into the spatial coordinate transformation formula, a gaze unit vector in the vehicle coordinate system is generated. Simultaneously, the target gaze vector needs to be updated in real time, with the update frequency consistent with the eye tracker's sampling frequency, to ensure the real-time performance and accuracy of gaze capture.

[0058] In some embodiments, when determining whether a target object is gazing at the outside of the vehicle, a target ray can be generated along the direction of the target gaze vector, starting from the current first three-dimensional coordinates of the eye tracker. If the target ray extends through the vehicle window glass to the outside of the vehicle, it can be determined that the target object is gazing at the outside of the vehicle. If the target ray eventually points to a calibrated object inside the vehicle, it can be determined that the target object is gazing at the inside of the vehicle.

[0059] In some embodiments, the vehicle includes at least two positioning base stations that can interact with an eye tracker to determine the gaze point of a target object within the vehicle. When determining whether the target object is gazing towards the outside of the vehicle, interaction between the positioning base stations and the eye tracker can be detected. If interaction exists, it indicates that the gaze point of the target object within the vehicle is being determined, thus confirming that the target object is gazing towards the interior of the vehicle. Conversely, if no interaction exists, it indicates that the target object is gazing towards an object outside the vehicle, thus confirming that the target object is gazing towards the outside of the vehicle.

[0060] In some embodiments, the eye tracker can support dual-mode transmission of Ultra-Wide Band (UWB) and Bluetooth, enabling real-time acquisition of the eye tracker's first three-dimensional coordinates, orientation angle, and target gaze vector of the target object. The sampling frequency meets real-time interaction requirements, and the wearable device transmits data in conjunction with the vehicle system via Controller Area Network (CAN) or Local Interconnect Network (LIN). UWB technology, also known as ultra-wideband positioning, ultra-wideband ranging, or pulse radio positioning, is used to measure the time of flight of a target object using pulse signals. UWB technology offers high ranging accuracy, communication range covering the entire cockpit area, and strong anti-interference capabilities.

[0061] In this implementation, when the target object gazes at the outside of the vehicle, the target gaze point is determined by the target object's gaze vector, the first three-dimensional coordinates of the eye tracker, and the initial image captured by the target camera. Compared with related technologies that do not identify the gaze point outside the vehicle, this method can accurately identify the target gaze point without fixed parts being calibrated outside the vehicle, thereby forming a closed-loop control of the vehicle.

[0062] 202. Identify the driving intention of the target object based on the target gaze point and vehicle driving-related data.

[0063] Driving-related data refers to data relevant to the vehicle's autonomous driving process. In some embodiments, driving-related data may include, but is not limited to, at least one of the following: vehicle driving mode, navigation information, and target road condition information. The vehicle's driving mode is the mode currently used by the vehicle's intelligent driving system. The vehicle's driving mode may include, but is not limited to, Level 1-2 assisted driving, Level 3 conditional automated driving, Level 4 highly automated driving, and Level 5 fully automated driving. Navigation information is used to provide real-time location, route planning, and navigation guidance for the target object. Navigation information can be obtained from the vehicle's navigation system. The vehicle's navigation system utilizes GPS and map data to help the driver choose the best route in complex road environments through voice prompts and a visual interface.

[0064] Target road condition information may include, but is not limited to, road surface conditions, road width, vehicle speed, road curvature, and traffic flow. Road surface conditions refer to the assessment of the current road surface conditions, which may include conditions affecting illumination reflection and friction coefficient, such as dryness / wetness, water accumulation, snow accumulation, and icing. Road width refers to the width of the road in front of the vehicle. Road curvature refers to the curvature of the road in front of the vehicle. In some embodiments, the road curvature can be obtained by analyzing images of the road ahead acquired by a visual sensor. Traffic flow is used to characterize the number and speed of other vehicles around the vehicle. Vehicle speed refers to the vehicle's current speed value, which can be any suitable value, such as 50 km / h, 63 km / h, etc. Vehicle speed can be obtained from a vehicle speed sensor or inertial navigation unit via a CAN bus. The CAN bus is a serial communication protocol bus used for real-time applications; it can use twisted-pair cables to transmit signals and is one of the most widely used fieldbuses in the world. In some embodiments, target road condition information can be acquired by at least one radar or at least one camera in the vehicle.

[0065] In one possible implementation, if the duration of the target object corresponding to the target gaze point is greater than or equal to a time threshold, driving-related data is acquired. This driving-related data includes at least one of the vehicle's driving mode, navigation information, and target road condition information. If the driving-related data satisfies a second execution condition, it is determined that the driving intention representation requires takeover of the intelligent driving system. If the driving-related data does not satisfy the second execution condition, it is determined that the driving intention representation does not require takeover of the intelligent driving system.

[0066] The duration refers to the length of time the target object corresponding to the target gaze point remains unchanged, used to characterize whether the target object is continuously gazing at a target object. The duration can be any suitable size, such as 0.2s, 0.58s, etc. The time threshold can be any suitable size, such as 1.5s, 2s, etc. When the duration of the target object corresponding to the target gaze point is greater than or equal to the time threshold, it indicates that the target object needs to transfer the vehicle's control target to the target object. Therefore, further driving-related data is needed to determine the driving intention.

[0067] Driving-related data refers to data relevant to the autonomous driving process of a vehicle. In some embodiments, driving-related data may include, but is not limited to, at least one of the following: vehicle driving mode, navigation information, and target road condition information. The second execution condition is a condition used to determine the driving intention corresponding to the current driving-related data. In some embodiments, different data in the driving-related data can be fused to obtain target fused data, and then it can be further determined whether the target fused data can satisfy the second execution condition.

[0068] In some embodiments, different second execution conditions are set for different data in the driving-related data. If at least one driving-related data satisfies the second execution condition, it can be confirmed that the driving intention representation needs to take over the intelligent driving system. For example, for the vehicle's driving mode, the second execution condition may be that the current driving mode is at a level between L3 and L5. For navigation information, the second execution condition may be that the current navigation information cannot meet the control requirements of the target object. For target road condition information, the second execution condition may be that the current target road condition information can meet the control requirements of the target object. If none of the driving-related data satisfies the second execution condition, it is determined that the driving intention representation does not need to take over the intelligent driving system.

[0069] In this implementation, when the duration of the target object corresponding to the target gaze point is greater than or equal to a time threshold, the system determines whether the driving intention representation needs to take over the intelligent driving system by checking whether the acquired driving-related data meets the second execution condition. The driving intention is identified through two dimensions: the duration of the target gaze point and the driving-related data. Compared with using a single dimension, this improves the accuracy and stability of the driving intention.

[0070] 203. When the driving intention representation requires taking over the intelligent driving system, determine the target control strategy based on the target gaze point.

[0071] The target driver's driving intention is used to characterize whether the target driver needs to take over the intelligent driving system. If the driving intention indicates no need to take over, the vehicle can continue to be controlled according to the current intelligent driving control strategy. If the driving intention indicates a need to take over, a target control strategy needs to be determined based on the target driver's gaze point. The target control strategy is the strategy used to enable the target driver to take over the intelligent driving system. Target control strategies may include, but are not limited to, preparing to stop, adjusting speed, and preparing to turn.

[0072] In one possible implementation, based on the target object corresponding to the target gaze point and a preset mapping rule, at least one candidate strategy and a weight value corresponding to each candidate strategy are generated. The candidate strategy with the highest weight value is determined as the target control strategy.

[0073] The target object can be of any suitable type, such as a ramp, parking space, adjacent lane, road sign, etc. Preset mapping rules are used to characterize the candidate strategies corresponding to different target objects. In some embodiments, one target object corresponds to at least one candidate strategy; that is, in the preset mapping rules, different mapping rules are used to characterize at least one candidate strategy corresponding to one target object.

[0074] In some embodiments, the preset mapping rules can be understood as a data table. At least one candidate strategy can be obtained by querying the preset mapping rules using the target object in a table lookup manner.

[0075] The preset mapping rule stores multiple target objects and at least one candidate strategy for each target object. By querying the preset mapping rule for a target object, at least one candidate strategy corresponding to the target object can be obtained. The preset mapping rule is calibrated by technicians according to actual conditions. At the same time, it supports personalized fine-tuning by users and can optimize the correspondence according to driving habits to improve interaction adaptability. This application embodiment does not limit this aspect.

[0076] For example, the preset mapping rules can be as follows: The target object is a ramp, and candidate strategies may include: leaving the highway, accelerating, decelerating, activating manual mode, and canceling adaptive cruise control in advance.

[0077] The target object is a parking space, and candidate strategies may include: preparing to park, shifting into reverse, folding in the rearview mirrors, applying the brakes, and turning on the hazard lights.

[0078] The target object is the adjacent lane, and the candidate strategies can include: lane change, honking, acceleration, active deceleration, etc.

[0079] The target object is a speed limit sign, and candidate strategies may include: adjusting vehicle speed, switching to sport mode, downshifting, etc.

[0080] The target object is a road sign, and candidate strategies can include: changing the destination, turning on the headlights, accelerating, and decelerating.

[0081] In some embodiments, within the preset mapping rules, the weight values ​​corresponding to candidate strategies for the same target object are all set to the same default value. When generating at least one candidate strategy and its corresponding weight value based on the target object and the preset mapping rules, the actual scenario in which the vehicle is currently located can be identified by combining current driving-related data, thereby setting different weight values ​​for different candidate strategies. After generating at least one candidate strategy and its corresponding weight value, the candidate strategy with the highest weight value is determined as the target control strategy.

[0082] In this implementation, candidate strategies and weight values ​​for each candidate strategy are generated by the target object corresponding to the target gaze point and the preset mapping rules. The candidate strategy with the highest weight value is then determined as the target control strategy. Compared with the mapping of a single strategy, multiple related candidate strategies can be established for a target object, thereby selecting the target control strategy most suitable for the current scene and improving the accuracy of the target control strategy.

[0083] 204. Controlling vehicles based on target control strategies.

[0084] In cases where the driver's intent requires takeover of the intelligent driving system, a target control strategy is first determined. This strategy is then converted into target control commands usable by the vehicle. These commands are then sent to the appropriate execution modules to achieve vehicle control. Execution modules may include, but are not limited to, the engine, electric motor, and steering wheel.

[0085] In one possible implementation, target interaction content is generated based on a target control strategy. The target interaction content is output to the target object, and the target object's response content to the target interaction content is received. The vehicle is then controlled based on the target response content.

[0086] The target interaction content refers to the interactive information related to the target control strategy, used to determine whether the target control strategy needs to be executed. In some embodiments, the target interaction content can be in any suitable form, such as voice, text, or images. The target interaction content can be output in any suitable component of the vehicle, such as speakers, displays, or head-up displays (HUDs). The target interaction content can be displayed on the vehicle's displays or HUD through a graphical user interface (GUI). A GUI is a human-computer interaction interface format.

[0087] The target response content is the feedback information from the target object in response to the target interaction content. In some embodiments, the target response content can be in any suitable form, such as voice, text, etc. The target response content can be received by the vehicle's sensors. Sensors may include, but are not limited to, cameras, microphones, displays, etc. Sensor monitoring events can be set, and the system can then monitor in real time whether the target response content is received. Furthermore, the microphone can be equipped with a noise reduction algorithm to effectively resist interference from ambient noise inside the vehicle, ensuring the accuracy of target response content recognition.

[0088] In some embodiments, a first time threshold can be set. When target interaction content is output to the target object, the waiting time for acquiring the target response content begins. If the waiting time exceeds the first time threshold, the steps for determining the target gaze point corresponding to the target object and subsequent steps are re-executed, and the target control strategy is regenerated. If the waiting time is less than or equal to the first time threshold, the vehicle is further controlled based on the target response content. The first time threshold can be any suitable size, such as 10 seconds, 5 seconds, etc.

[0089] In this implementation, a target control strategy is used to generate and output target interaction content to the target object. Then, the vehicle is controlled by the target object's target response to the target interaction content. The accuracy of the current target control strategy can be quickly confirmed through the target interaction content, which further improves the accuracy of vehicle control.

[0090] In one possible implementation, if the target response content indicates that the target object has confirmed the target control strategy, the vehicle is controlled based on the target control strategy. If the target response content indicates that the target object has not confirmed the target control strategy, the candidate strategy with a weight value following the target control strategy is re-determined as the target control strategy, and the steps of generating target interaction content and subsequent steps based on the target control strategy are executed again.

[0091] The target response content can be in any suitable form, such as voice or text. In some embodiments, after receiving the target object's response content to the target interaction content, the target response content can be parsed to obtain the semantic information represented by the target response content. Furthermore, based on the semantic information represented by the target response content, it can be determined whether the target object has confirmed the target control strategy.

[0092] In some embodiments, if the target response indicates that the target object has confirmed the target control strategy, it means the target control strategy meets the target object's control requirements; therefore, the vehicle can be controlled based on the target control strategy. If the target response indicates that the target object has not confirmed the target control strategy, it means the target control strategy does not meet the target object's control requirements. Therefore, it is necessary to re-determine the candidate strategies whose weight values ​​are after the target control strategy as the target control strategy, and then re-execute the steps of generating target interaction content and subsequent steps based on the target control strategy. This is to facilitate outputting and querying the target object about the feasibility of the target control strategy again.

[0093] In some embodiments, a second time threshold can be set. When generating candidate strategies, the generation duration of the candidate strategies is acquired. If the target response content indicates that the target object has not confirmed the target control strategy, the relationship between the generation duration and the second time threshold is determined. If the generation duration is greater than the second time threshold, the steps of determining the target gaze point corresponding to the target object and subsequent steps are re-executed, and the target control strategy is generated again. If the generation duration is less than or equal to the second time threshold, the candidate strategies whose weight values ​​are after the target control strategy are further re-determined as the target control strategy, and the steps of generating target interaction content based on the target control strategy and subsequent steps are executed again. The second time threshold can be any suitable size, such as 10s, 20s, etc.

[0094] For example, the target interaction content is voice-based, specifically: "Do you need to exit the highway at the next ramp?" One second later, the target object's response is received, also voice-based, specifically: "Yes." It is evident that the semantic information of the target response content can indicate that the target object has confirmed the target control strategy, thereby enabling further vehicle control based on the current target control strategy.

[0095] In this implementation, if the target response indicates that the target object has confirmed the target control strategy, the vehicle is controlled by the target control strategy. If the target response indicates that the target object has not confirmed the target control strategy, the candidate strategy with a weight value after the target control strategy is re-determined as the target control strategy and the target control strategy is confirmed again. The vehicle can be controlled by selecting an appropriate method according to the target response. If the current target control strategy is not confirmed, the target control strategy will be further modified, thus realizing a closed loop of vehicle control.

[0096] In one possible implementation, target road condition information for the vehicle is acquired. If the target road condition information satisfies a first execution condition of the target control strategy, the vehicle is controlled based on the target control strategy.

[0097] The target road condition information may include, but is not limited to, road surface conditions, road width, vehicle speed, road curvature, and traffic flow. Road surface conditions refer to the assessment of the current road surface conditions, which may include conditions affecting illumination reflection and friction coefficient, such as dryness / wetness, water accumulation, snow accumulation, and icing. Road width refers to the width of the road in front of the vehicle. Road curvature refers to the curvature of the road in front of the vehicle. In some embodiments, the road curvature can be obtained by analyzing images of the road ahead acquired by a visual sensor. Traffic flow is used to characterize the number and speed of other vehicles around the vehicle. Vehicle speed refers to the vehicle's current speed value, which can be any suitable value, such as 50 km / h, 63 km / h, etc. Vehicle speed can be obtained from a vehicle speed sensor or inertial navigation unit via the CAN bus.

[0098] The first execution condition is used to determine whether the current target control strategy can be executed. In some embodiments, the first execution condition is different for different target control strategies. For example, when the target control strategy is lane changing, the first execution condition may be confirming that there are no oncoming vehicles in the adjacent lane and that the vehicle speed is appropriate. When the target control strategy is ramp driving, the first execution condition may be confirming that there are no obstacles and that the ramp curvature is suitable. When the target control strategy is speed adjustment, the first execution condition may be confirming that the distance between the vehicle and the vehicle in front is safe.

[0099] In some embodiments, if the target road condition information does not meet the first execution condition of the target control strategy, the vehicle can continue to be controlled based on the original control strategy to ensure the continuity of vehicle control. If the target road condition information meets the first execution condition of the target control strategy, it indicates that the target control strategy can be executed. Therefore, the target control strategy can be converted into target control commands that the vehicle can use, and these commands can be sent to the corresponding execution modules to achieve the purpose of controlling the vehicle. Execution modules may include, but are not limited to, engines, motors, steering wheels, etc.

[0100] In this implementation, the vehicle will only be controlled based on the target control strategy if the acquired target road condition information meets the first execution condition of the target control strategy. This allows for a comprehensive assessment of the feasibility of the road conditions before executing the target control strategy, thus avoiding safety hazards caused by intelligent driving adjustments from the source and improving vehicle safety.

[0101] 205. During the execution of the target control strategy, continuously acquire target road condition information.

[0102] The target road condition information may include, but is not limited to, road surface conditions, road width, vehicle speed, road curvature, and traffic flow. During the execution of the target control strategy, target road condition information can be continuously acquired through various sensors of the vehicle at a fixed sampling frequency.

[0103] 206. If the target road condition information does not meet the first execution condition, suspend the execution of the target control strategy and output a prompt message to the target object.

[0104] The first execution condition is used to determine whether the current target control strategy can be executed. In some embodiments, the first execution condition varies depending on the target control strategy. For example, when the target control strategy is lane changing, the first execution condition may be confirming that there are no oncoming vehicles in the adjacent lane and that the vehicle speed is appropriate. When the target control strategy is ramp driving, the first execution condition may be confirming that there are no obstacles and that the ramp curvature is suitable. When the target control strategy is speed adjustment, the first execution condition may be confirming that the distance between the vehicle and the vehicle in front is safe.

[0105] In some embodiments, during the execution of the target control strategy, it is also necessary to continuously determine whether the target road condition information meets the first execution condition. If the target road condition information meets the first execution condition, the target control strategy continues to be executed. If the target road condition information does not meet the first execution condition, continuing to execute the target control strategy would pose a safety hazard to the vehicle. Therefore, it is necessary to pause the execution of the target control strategy and output a warning message to the target object. Simultaneously, based on the target road condition information, emergency braking or a regeneration of the target control strategy can be selected to improve the continuity of vehicle control while ensuring vehicle safety.

[0106] The prompt message is used to indicate to the target object that the target control strategy has been suspended. In some embodiments, the prompt message can be in any suitable form, such as voice, text, or images. The target interaction content can be output through any suitable component of the vehicle, such as speakers, displays, or HUDs. The target interaction content can be displayed on the vehicle's display screen or HUD via a GUI. After outputting the prompt message to the target object, a target question can be further output to inquire about the target object's driving intentions, thereby enabling vehicle control based on the target object's driving intentions.

[0107] In this implementation, target road condition information is continuously acquired during the execution of the target control strategy. If the target road condition information does not meet the first execution condition, the execution of the target control strategy is suspended and a prompt message is output to the target object. This allows for real-time and continuous monitoring of the feasibility of the target control strategy, ensuring driving safety. At the same time, when the execution of the target control strategy is suspended, a prompt message is output to the target object, enabling the target object to quickly know the vehicle's status.

[0108] Figure 3 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application. See also... Figure 3 The vehicle control device 300 includes: The determination module 301 is used to determine the target gaze point corresponding to the target object, where the target object is the object wearing the eye tracker. The recognition module 302 is used to recognize the driving intention of the target object based on the target gaze point and driving-related data of the vehicle; The determination module 301 is used to determine the target control strategy based on the target gaze point when the driving intention representation requires the takeover of the intelligent driving system. Control module 303 is used to control the vehicle based on a target control strategy.

[0109] In one possible implementation, the device further includes a generation module for generating at least one candidate strategy and a weight value corresponding to each candidate strategy based on the target object corresponding to the target gaze point and a preset mapping rule; and a determination module 301 for determining the candidate strategy with the highest weight value as the target control strategy.

[0110] In one possible implementation, the generation module is used to generate target interaction content based on the target control strategy; output the target interaction content to the target object; and receive the target object's target response content to the target interaction content; the control module 303 is used to control the vehicle based on the target response content.

[0111] In one possible implementation, the control module 303 is used to control the vehicle based on the target control strategy when the target response content indicates that the target object has confirmed the target control strategy; the generation module is used to re-determine the candidate strategy whose weight value is after the target control strategy as the target control strategy when the target response content indicates that the target object has not confirmed the target control strategy, and then execute the steps of generating target interaction content and subsequent steps based on the target control strategy again.

[0112] In one possible implementation, the device further includes an acquisition module for acquiring target road condition information of the vehicle; and a control module 303 for controlling the vehicle based on the target control strategy when the target road condition information meets the first execution condition of the target control strategy.

[0113] In one possible implementation, the acquisition module is used to continuously acquire target road condition information during the execution of the target control strategy; the control module 303 is used to suspend the execution of the target control strategy and output prompt information to the target object when the target road condition information does not meet the first execution condition.

[0114] In one possible implementation, the determining module 301 is used to determine the target gaze point based on the target object's gaze vector, the first three-dimensional coordinates of the eye tracker, and the initial image captured by the target camera when the target object is gazing toward the outside of the vehicle.

[0115] In one possible implementation, the acquisition module is configured to acquire driving-related data when the duration of the target object corresponding to the target gaze point is greater than or equal to a time threshold. The driving-related data includes at least one of the vehicle's driving mode, navigation information, and target road condition information. The identification module 302 is configured to determine that the driving intention representation needs to take over the intelligent driving system when the driving-related data meets a second execution condition, and to determine that the driving intention representation does not need to take over the intelligent driving system when the driving-related data does not meet the second execution condition.

[0116] It should be noted that the vehicle control device provided in the above embodiments is only illustrated by the division of the above functional modules when controlling the vehicle. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, the vehicle control device and the vehicle control method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0117] By employing the technical solution provided in this application, the driving intention of a target object wearing an eye tracker is identified by determining the target gaze point and the vehicle's driving-related data. Then, when the driving intention indicates a need to take over the intelligent driving system, a target control strategy is determined using the target gaze point. This allows the vehicle to be controlled through the target control strategy, enabling the application of driving intentions related to the target gaze point to intelligent driving scenarios. This allows the driver to control the vehicle without cumbersome additional operations, significantly reducing the risk of driver distraction. The interaction method is natural and intuitive, improving the human-machine collaboration experience. Furthermore, the target control strategy is only determined when the target object needs to take over the intelligent driving system, improving the accuracy and flexibility of vehicle control.

[0118] This application also provides a vehicle. Figure 4 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0119] Typically, vehicle 400 includes one or more processors 401 and one or more memories 402.

[0120] Processor 401 may include one or more processing cores, such as a quad-core processor, a penta-core processor, etc. Processor 401 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 401 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 401 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 401 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0121] The memory 402 may include one or more computer-readable storage media, which may be non-transitory. The memory 402 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 402 are used to store at least one computer program, which is executed by the processor 401 to implement the vehicle control method provided in the method embodiments of this application.

[0122] Those skilled in the art will understand that Figure 4 The structure shown does not constitute a limitation on vehicle 400 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0123] In addition, the device provided in the embodiments of this application may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute a vehicle control method provided in the above embodiments.

[0124] This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the above-described method steps to implement a vehicle control method provided in the above embodiment.

[0125] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement a vehicle control method provided in the above embodiment.

[0126] This embodiment also provides an electronic device, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the electronic device performs the above-described method for controlling the vehicle.

[0127] In this embodiment, the device, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0128] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0129] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0130] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for controlling a vehicle, characterized in that, The method includes: Determine the target fixation point corresponding to the target object, wherein the target object is the object wearing the eye tracker; Based on the target gaze point and the vehicle's driving-related data, the driving intention of the target object is identified; In cases where the driving intention representation requires takeover of the intelligent driving system, a target control strategy is determined based on the target gaze point; The vehicle is controlled based on the target control strategy.

2. The method according to claim 1, characterized in that, The step of determining the target control strategy based on the target gaze point includes: Based on the target object corresponding to the target gaze point and the preset mapping rule, at least one candidate strategy and a weight value corresponding to each candidate strategy are generated. The candidate strategy with the highest weight value is determined as the target control strategy.

3. The method according to claim 2, characterized in that, Controlling the vehicle based on the target control strategy includes: Based on the target control strategy, target interactive content is generated; Output the target interaction content to the target object, and receive the target object's target response content to the target interaction content; The vehicle is controlled based on the target response content.

4. The method according to claim 3, characterized in that, Controlling the vehicle based on the target response content includes: If the target response content indicates that the target object has confirmed the target control strategy, the vehicle is controlled based on the target control strategy. If the target response content indicates that the target object has not confirmed the target control strategy, the candidate strategy whose weight value is after the target control strategy is re-determined as the target control strategy, and the steps of generating target interaction content based on the target control strategy and subsequent steps are executed again.

5. The method according to claim 1, characterized in that, Controlling the vehicle based on the target control strategy includes: Obtain the target road condition information of the vehicle; If the target road condition information satisfies the first execution condition of the target control strategy, the vehicle is controlled based on the target control strategy.

6. The method according to claim 5, characterized in that, The method further includes: During the execution of the target control strategy, the target road condition information is continuously acquired; If the target road condition information does not meet the first execution condition, the execution of the target control strategy is suspended, and a prompt message is output to the target object.

7. The method according to claim 1, characterized in that, Determining the target gaze point corresponding to the target object includes: When the target object gazes toward the outside of the vehicle, the target gaze point is determined based on the target object's gaze vector, the first three-dimensional coordinates of the eye tracker, and the initial image captured by the target camera.

8. The method according to claim 1, characterized in that, The step of identifying the driving intention of the target object based on the target gaze point and the vehicle's driving-related data includes: If the duration of the target object corresponding to the target gaze point is greater than or equal to a time threshold, the driving-related data is acquired. The driving-related data includes at least one of the vehicle's driving mode, navigation information, and target road condition information. If the driving-related data meets the second execution condition, it is determined that the driving intention representation needs to take over the intelligent driving system; If the driving-related data does not meet the second execution condition, it is determined that the driving intention representation does not require takeover of the intelligent driving system.

9. An electronic device, characterized in that, The vehicles include: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method as described in any one of claims 1 to 8.

10. A vehicle, characterized in that, The vehicles include: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method as described in any one of claims 1 to 8.

Images