Control method for vehicle, control device for vehicle, and vehicle

Abstract

The application provides a control method of a vehicle, a control device of the vehicle and the vehicle, and relates to the field of human-computer interaction. The method comprises the following steps: when detecting an eye movement control instruction of a user, acquiring measurement data of at least two positioning base stations outside the vehicle, wherein the measurement data comprises signal propagation time, and the signal propagation time is used to represent the propagation time of the transmission of the positioning base stations to an eye movement tracking device outside the vehicle; determining the spatial coordinates of the eye movement tracking device based on the measurement data of the at least two positioning base stations; and determining the coordinate information of a target fixation point of the user based on the spatial coordinates, and the coordinate information of the target fixation point is used to control the vehicle to perform an operation corresponding to the target fixation point. The method can improve the accuracy of detecting the fixation point of the user.

Description

Technical Field

[0001] This application relates to the field of human-computer interaction, and more specifically, to a vehicle control method, a vehicle control device, and a vehicle in the field of human-computer interaction. Background Technology

[0002] As vehicle intelligence continues to improve, eye-tracking-based human-computer interaction technology has become an important means to enhance user experience. However, existing eye-tracking vehicle control technologies are affected by factors such as lighting, weather, and user posture, resulting in low accuracy in recognizing the user's gaze point. This limits the application of eye-tracking vehicle control technology outside the vehicle and degrades the user experience.

[0003] Therefore, improving the accuracy of detecting users' gaze points is an urgent problem to be solved. Summary of the Invention

[0004] This application provides a vehicle control method, a vehicle control device, and a vehicle, which can improve the accuracy of detecting the user's gaze point.

[0005] Firstly, a vehicle control method is provided, the control method comprising: When a user's eye-tracking control command is detected, measurement data from at least two positioning base stations outside the vehicle is acquired. The measurement data includes signal propagation time, which represents the propagation time from the positioning base stations to the eye-tracking device outside the vehicle. The spatial coordinates of the eye-tracking device are determined based on measurement data from at least two positioning base stations. Based on spatial coordinates, the coordinate information of the user's target gaze point is determined, and the coordinate information of the target gaze point is used to control the vehicle to perform operations corresponding to the target gaze point.

[0006] In the embodiments of this application, upon detecting a user's eye-tracking control command, measurement data from at least two positioning base stations outside the vehicle are acquired. This measurement data includes the signal propagation time between the positioning base stations and the eye-tracking device outside the vehicle. Based on the measurement data from at least two positioning base stations, the spatial coordinates of the eye-tracking device are determined. Then, based on these spatial coordinates, the user's target gaze point is determined. Compared to existing technologies, eye-tracking positioning schemes are limited to the vehicle cabin, and in complex external environments, factors such as changes in lighting and obstacle obstruction can lead to decreased positioning accuracy or even positioning gaps. This solution acquires measurement data from at least two positioning base stations outside the vehicle. Therefore, the spatial coordinates of the eye-tracking device determined by this solution based on the measurement data from each positioning base station are more accurate than those measured by a single positioning base station. This reduces the impact of signal loss when a single base station is obstructed, thereby achieving accurate determination of the target gaze point in external scenarios, improving the accuracy of the gaze point in eye-tracking control. Furthermore, since the coordinate information of the gaze point is used to further generate a target control strategy for the vehicle, this solution improves the accuracy and real-time performance of vehicle control.

[0007] In conjunction with the first aspect, among some possible implementations, the control method also includes: Obtain the locations of at least two positioning base stations; Based on measurement data from at least two positioning base stations, the spatial coordinates of the eye-tracking device are determined, including: Based on the signal propagation time corresponding to at least two positioning base stations, a time difference is determined, which includes the difference in signal propagation time between any two positioning base stations among the at least two positioning base stations; The spatial coordinates of the eye-tracking device are determined based on the position and time difference of at least two positioning base stations.

[0008] In the embodiments of this application, the positions of at least two positioning base stations outside the vehicle are obtained. The time difference between any two positioning base stations is determined based on the signal propagation time corresponding to the at least two positioning base stations. The spatial coordinates of the eye-tracking device are then determined by combining the positions of the at least two positioning base stations with the time difference. Compared to the prior art, which uses a single base station to send and receive round-trip signals for distance measurement, this method avoids the problem of coordinate calculation when the base station is obstructed by obstacles, as this leads to the failure of the corresponding ranging path. This solution obtains the positions of multiple positioning base stations and uses the time difference between different base stations receiving the same signal to calculate the position. Since the calculation process relies on the relative time difference between base stations rather than the absolute distance value of a single base station, even if some base stations experience increased signal delay or loss due to obstruction, the spatial coordinates of the eye-tracking device can still be determined using the time difference between the remaining base stations and their corresponding positions. This reduces the risk of positioning interruption due to partial obstruction and improves the accuracy and reliability of determining the spatial coordinates of the eye-tracking device.

[0009] Combining the first aspect and the above implementation methods, in some possible implementations, the spatial coordinates include the coordinates of the first component and the second component in the eye-tracking device. Based on the spatial coordinates, the coordinate information of the user's target gaze point is determined, including: The user's facial orientation is determined based on the coordinates of the first component and the second component; Based on facial orientation and spatial coordinates, the coordinate information of the target gaze point is determined.

[0010] In the embodiments of this application, the user's facial orientation is determined based on the coordinates of the first and second components in the eye-tracking device. Then, the coordinates of the target gaze point are determined by combining the facial orientation with the spatial coordinates. Compared to existing technologies where spatial coordinates and facial orientation are acquired separately by the positioning module and the posture sensor, respectively, this approach avoids data synchronization delays and errors in posture changes such as when the user turns to the side or bends over. This solution simultaneously calculates the spatial coordinates of the first and second components from the positioning signal and determines the user's facial orientation based on the difference vector between the two coordinates. This allows position and orientation calculations to be completed synchronously in the same coordinate system, eliminating the need for an additional posture sensor, reducing hardware costs, avoiding data synchronization delays, improving the accuracy of facial orientation judgment under different body postures, and enhancing the reliability of target gaze point determination.

[0011] Combining the first aspect and the above implementation methods, in some possible implementations, a third component is configured outside the vehicle. The power consumption of the third component is lower than that of the positioning base station. The control method also includes: Obtain the first distance between the third component and the eye-tracking device; Based on measurement data from at least two positioning base stations, the spatial coordinates of the eye-tracking device are determined, including: Based on the first distance, the measurement data of at least two positioning base stations are calibrated. Based on the calibrated measurement data, the spatial coordinates of the eye-tracking device are determined.

[0012] In the embodiments of this application, a third component with lower power consumption than the positioning base station is configured outside the vehicle. Before determining the spatial coordinates based on the measurement data of the positioning base station, a first distance between the third component and the eye-tracking device is first obtained, and the measurement data of the positioning base station is calibrated based on the first distance. Then, the spatial coordinates are determined based on the calibrated measurement data. This solution introduces a low-power third component to pre-acquire distance information, and uses this distance information to calibrate the measurement data of the positioning base station before performing coordinate calculation. This can reduce the interference of environmental factors on the measurement data, thereby improving the accuracy of subsequent spatial coordinate calculation.

[0013] The third component represents a ranging assembly mounted on the vehicle body, used for short-range communication with the eye-tracking device to acquire distance information between them. The third component consumes less power than the positioning power of the positioning base station and the first / second components, and can replace the positioning base station for distance detection or assist in calibrating the measurement data of the positioning base station in close-range scenarios.

[0014] Combining the first aspect and the above implementation methods, in some possible implementations, a camera is installed outside the vehicle, and the control method also includes: Acquire the target image captured by the camera; Based on the target image, determine the reference position of the eye-tracking device; Based on the first distance, the measurement data from at least two positioning base stations are calibrated, including: Based on the first distance and the reference position, the measurement data of at least two positioning base stations are calibrated.

[0015] In the embodiments of this application, a camera is installed outside the vehicle to acquire target images and determine the reference position of the eye-tracking device based on the target images. Then, the measurement data of the positioning base station is calibrated by combining the first distance obtained by the third component with the image reference position. Compared to calibration relying solely on distance information from the third component, where changes in lighting or signal reflection in complex external environments may lead to deviations from a single calibration source, this solution introduces a camera. The reference position of the eye-tracking device is obtained through the target images acquired by the camera, combining distance-based calibration with image-based visual positioning. This collaborative calibration of the positioning base station's measurement data from different dimensions improves the reliability of the calibration process and thus enhances the accuracy of the measurement data.

[0016] In one implementation, after determining the reference position of the eye-tracking device based on the target image, the control method further includes: Calculate the positional deviation between the spatial coordinates and the reference position; When the detected position deviation is greater than the preset deviation threshold, the spatial coordinates are replaced based on the image reference position, or the spatial coordinates and the reference position are weighted and fused.

[0017] In combination with the first aspect and the above implementation methods, in some possible implementation methods, based on the first distance, the measurement data of at least two positioning base stations are calibrated, including: When the first distance is detected to be less than a preset distance threshold, the measurement data of at least two positioning base stations are calibrated.

[0018] In the embodiments of this application, after obtaining the first distance between the third component and the eye-tracking device, when the first distance is detected to be less than a preset distance threshold, the measurement data of at least two positioning base stations are calibrated. This scheme sets a preset distance threshold. When the first distance is less than the preset distance threshold, i.e., in a close-range scenario, the ranging results of the third component are used to calibrate the measurement data of the positioning base stations. This fully leverages the high ranging accuracy of the third component within the close-range range, avoiding interference from low-precision ranging data at long distances, thereby improving the rationality of the calibration process.

[0019] In combination with the first aspect and the above implementation methods, in some possible implementation methods, the control method also includes: Obtain the weights of at least two positioning base stations and the third component; Based on measurement data from at least two positioning base stations, the spatial coordinates of the eye-tracking device are determined, including: The spatial coordinates of the eye-tracking device are determined based on the weights of at least two positioning base stations, the weight of the third component, the first distance, and the measurement data from at least two positioning base stations.

[0020] In the embodiments of this application, the weights of at least two positioning base stations and a third component are obtained. Based on the weights of the at least two positioning base stations, the weight of the third component, a first distance, and measurement data from the at least two positioning base stations, the spatial coordinates of the eye-tracking device are jointly determined. This solution assigns weights to different positioning sources and performs weighted fusion of multi-source positioning data. It can adjust the weights of different positioning sources in the calculation process according to their confidence levels, reduce the impact of anomalies in a single data source on the overall positioning result, and improve the accuracy of determining the spatial coordinates of the eye-tracking device.

[0021] In combination with the first aspect and the above implementation methods, in some possible implementation methods, the control method also includes: Obtain vehicle environmental information; When environmental information is detected to indicate that the vehicle is in an abnormal environment, the weights of at least two positioning base stations and the weight of the third component are adjusted to obtain the adjusted weights of at least two positioning base stations and the adjusted weights of the third component. Among them, the weights of at least two positioning base stations after adjustment are less than the weights of at least two positioning base stations, and the weights of the third component after adjustment are greater than the weights of the third component.

[0022] In the embodiments of this application, environmental information of the vehicle is acquired. When the environmental information indicates that the vehicle is in an abnormal environment, the weights of at least two positioning base stations are reduced and the weight of the third component is increased. The adjusted weights are then used for subsequent coordinate calculation. Compared to multi-source positioning data fusion using a fixed weight allocation method, this approach does not consider the performance differences of positioning sources under different environmental conditions. For example, in scenarios with abnormal lighting or severe weather, the signal of the positioning base station may attenuate, while the short-range ranging of the third component is less affected by the environment. This solution identifies the abnormal environment in which the vehicle is located and adjusts the weight allocation of different positioning sources. In abnormal environments, the weight of data sources that are susceptible to environmental influences is reduced, while the weight of data sources with greater stability is increased. This improves the positioning stability of the eye-tracking device's spatial coordinates under different environmental conditions.

[0023] Secondly, a vehicle control device is provided, the control device comprising: The acquisition module is used to acquire measurement data from at least two positioning base stations outside the vehicle when a user's eye-tracking control command is detected. The measurement data includes signal propagation time, which represents the propagation time from the positioning base station to the eye-tracking device outside the vehicle. The processing module is used to determine the spatial coordinates of the eye-tracking device based on measurement data from at least two positioning base stations; and based on the spatial coordinates, to determine the coordinate information of the user's target gaze point, wherein the coordinate information of the target gaze point is used to control the vehicle to perform an operation corresponding to the target gaze point.

[0024] In conjunction with the second aspect, in some implementations of the second aspect, the processing module is further specifically used to: acquire the positions of at least two positioning base stations; determine the spatial coordinates of the eye-tracking device based on the measurement data of at least two positioning base stations, including: determining a time difference based on the signal propagation time corresponding to at least two positioning base stations, the time difference including the difference in signal propagation time between any two of the at least two positioning base stations; and determining the spatial coordinates of the eye-tracking device based on the position and time difference of at least two positioning base stations.

[0025] Combining the second aspect and the above implementation methods, in some possible implementation methods, the processing module is specifically used to: determine the user's facial orientation based on the coordinates of the first component and the coordinates of the second component; and determine the coordinate information of the target gaze point based on the facial orientation and spatial coordinates.

[0026] In conjunction with the second aspect and the above implementation methods, in some possible implementation methods, the processing module is further used to: obtain a first distance between the third component and the eye-tracking device; determine the spatial coordinates of the eye-tracking device based on the measurement data of at least two positioning base stations, including: calibrating the measurement data of at least two positioning base stations based on the first distance; and determining the spatial coordinates of the eye-tracking device based on the calibrated measurement data.

[0027] In conjunction with the second aspect and the above implementation methods, in some possible implementation methods, the processing module is further used to: acquire the target image captured by the camera; determine the reference position of the eye-tracking device based on the target image; and perform calibration processing on the measurement data of at least two positioning base stations based on the first distance, including: performing calibration processing on the measurement data of at least two positioning base stations based on the first distance and the reference position.

[0028] In combination with the second aspect and the above implementation methods, in some possible implementation methods, the processing module is specifically used to: when the first distance is detected to be less than a preset distance threshold, to perform calibration processing on the measurement data of at least two positioning base stations.

[0029] In conjunction with the second aspect and the above implementation methods, in some possible implementation methods, the processing module is further used to: obtain the weights of at least two positioning base stations and the third component; determine the spatial coordinates of the eye-tracking device based on the measurement data of at least two positioning base stations, including: determining the spatial coordinates of the eye-tracking device based on the weights of at least two positioning base stations, the weight of the third component, the first distance and the measurement data of at least two positioning base stations.

[0030] In conjunction with the second aspect and the above implementation methods, in some possible implementation methods, the processing module is further configured to: acquire environmental information of the vehicle; when environmental information is detected to indicate that the vehicle is in an abnormal environment, adjust the weights of at least two positioning base stations and the weight of the third component to obtain the adjusted weights of at least two positioning base stations and the adjusted weight of the third component; wherein the adjusted weights of at least two positioning base stations are less than the weights of at least two positioning base stations, and the adjusted weight of the third component is greater than the weight of the third component.

[0031] Thirdly, a vehicle is provided, 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, causing the vehicle to perform the vehicle control method of the first aspect or any possible implementation thereof.

[0032] Fourthly, a computer program product is provided, comprising: computer program code, which, when run on a computer, causes the computer to execute the vehicle control method of the first aspect or any possible implementation thereof.

[0033] Fifthly, a computer-readable storage medium is provided that stores computer program code, which, when executed on a computer, causes the computer to perform the vehicle control method of the first aspect or any possible implementation thereof. Attached Figure Description

[0034] Figure 1 This is a schematic diagram of a vehicle control method provided in an embodiment of this application; Figure 2 This is a schematic flowchart of a vehicle control method provided in an embodiment of this application; Figure 3 This is a schematic flowchart of another vehicle control method provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Detailed Implementation

[0035] 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.

[0036] 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.

[0037] Before introducing the methods of the embodiments of this application, the technical terms that may be involved in the embodiments of this application will be explained first.

[0038] Eye-tracking devices, also known as eye trackers, wearable gaze tracking devices, or smart glasses-style interactive terminals, refer to wearable devices worn on the head that can collect real-time data on the user's three-dimensional spatial coordinates and gaze direction, and interact with positioning base stations wirelessly or via wired means. For example, an eye-tracking device can support UWB and Bluetooth dual-mode transmission, collect its own three-dimensional coordinates, real-time orientation angle (horizontal / vertical dual dimensions), and the wearer's gaze direction in real time, with a sampling frequency that meets the requirements for real-time interaction, and can be linked with vehicle systems to transmit data via Controller Area Network (CAN) or Local Interconnect Network (LIN).

[0039] Ultra-wideband (UWB) technology, also known as ultra-wideband positioning technology, ultra-wideband ranging technology, or pulse radio positioning technology, 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. Time-of-Flight (TOF) ranging, also known as time-of-flight ranging, signal propagation time ranging, or pulse-reflection ranging, is used to calculate the distance between a transmitter and a target by measuring the propagation time of a signal from the transmitter to the target and back, combined with the signal propagation speed. TOF ranging offers high accuracy and fast response, making it suitable for short-range, high-precision positioning scenarios.

[0040] The Time Difference of Arrival (TDOA) algorithm, also known as the time difference positioning algorithm or signal arrival time difference solution algorithm, is used to calculate the spatial location of a signal transmitter by the time difference between multiple reception times of the same signal. For example, the TDOA algorithm may include obtaining the time information of at least two positioning base stations receiving signals transmitted by an eye-tracking device, calculating the time difference between each base station, and constructing a hyperboloid equation system based on the preset positions of each base station to solve for the spatial coordinates of the eye-tracking device in the vehicle coordinate system; or, it may include obtaining the time information of the time the eye-tracking device receives signals transmitted by at least two positioning base stations, calculating the time difference between each base station, and constructing a hyperboloid equation system based on the preset positions of each base station to solve for the spatial coordinates of the eye-tracking device in the vehicle coordinate system.

[0041] As vehicles become increasingly intelligent, eye-tracking-based human-computer interaction technology has become an important means of enhancing user experience. Eye-tracking-based human-computer interaction technology, also known as eye-controlled vehicle technology, typically refers to the technology that enables interactive control of vehicle functions by tracking the user's gaze.

[0042] In existing technologies, eye-tracking vehicle control typically uses eye-tracking devices as data acquisition carriers. These devices are located via a single Bluetooth or infrared sensor, and combined with a posture sensor to obtain the user's head orientation. The user's gaze point is then calculated and mapped to interactive controls within the cabin (such as the central control screen, air conditioning panel, and window switches) to execute corresponding control operations. This technology can reduce manual operation by the driver, improve driving safety, and enhance the convenience of vehicle cabin interaction.

[0043] However, in existing technologies, eye-tracking vehicle control is mostly limited to the vehicle's cabin, resulting in the following drawbacks: First, coordinate calculation and orientation calculation are separate; the spatial position of the eye-tracking device needs to be obtained by the positioning module, while facial orientation needs to be obtained by the posture sensor. The synchronization of these two data points is delayed, leading to high hardware integration costs and low accuracy in judging user posture. Second, single-sensor positioning is susceptible to signal attenuation and decreased accuracy due to user movement and surrounding obstacles. Third, continuous use of UWB positioning results in high power consumption; when the vehicle lacks charging facilities, the battery life of eye-tracking positioning cannot support extended use.

[0044] In view of this, this application provides a vehicle control method, a vehicle control device, and a vehicle. Upon detecting a user's eye-tracking control command, the method acquires measurement data from at least two positioning base stations outside the vehicle. The measurement data includes the signal propagation time between the positioning base stations and the eye-tracking device outside the vehicle. Based on the measurement data from the at least two positioning base stations, the method determines the spatial coordinates of the eye-tracking device. Then, based on the spatial coordinates, the method determines the user's target gaze point. Compared to existing technologies, eye-tracking positioning schemes are limited to the vehicle cabin, and in complex external environments, factors such as changes in lighting and obstacle occlusion can lead to decreased positioning accuracy or even positioning interruptions. This solution acquires measurement data from at least two positioning base stations outside the vehicle. Therefore, the spatial coordinates of the eye-tracking device determined by this solution based on the measurement data from each positioning base station are more accurate than those measured by a single positioning base station. This reduces the impact of signal loss when a single base station is obstructed, thereby achieving accurate determination of the target gaze point in external scenarios, improving the accuracy of the gaze point in eye-tracking control. Furthermore, since the coordinate information of the gaze point is used to further generate a target control strategy for controlling the vehicle, this solution improves the accuracy and real-time performance of vehicle control.

[0045] For example, Figure 1This is a schematic diagram of a vehicle control method provided in an embodiment of this application, such as... Figure 1 As shown, scenario 100 includes 10, 11, 20, 21, and 22. In scenario 100, 10 and 11 represent positioning base stations configured outside the vehicle, used to send / receive signals from the eye-tracking device. These signals are used to determine the time difference between signals received by different positioning base stations, assisting in calculating the spatial coordinates of the eye-tracking device. In scenario 100, 20 represents the eye-tracking device worn by the user. In scenario 100, 21 and 22 represent positioning elements configured on the eye-tracking device, used to receive / transmit positioning signals for the positioning base stations outside the vehicle to locate the eye-tracking device. The coordinate data from 21 and 22 can further determine the user's facial orientation and gaze direction, providing data support for subsequent gaze point calculation.

[0046] In scenario 100, the positioning base stations 10 and 11 configured outside the vehicle work together with the positioning elements 21 and 22 on the eye-tracking device. This can avoid positioning deviations caused by obstacles or changes in lighting in complex environments outside the vehicle, where a single base station or positioning element is susceptible to such deviations. Even when the user moves around the vehicle, changes their standing posture, or adjusts their facial orientation, the spatial coordinates of the eye-tracking device can still be stably obtained, providing a reliable data foundation for determining the target gaze point and thus improving the accuracy of gaze point determination in external eye-tracking control.

[0047] The following is combined with Figure 2 A vehicle control method provided in the embodiments of this application will be described in detail.

[0048] Figure 2 This is a schematic flowchart illustrating a vehicle control method provided in an embodiment of this application. Figure 2 As shown, method 200 includes S201 to S203, which are described in detail below.

[0049] For example, Figure 2 The method 200 shown can be executed by a vehicle; or by a processor in the vehicle; or by a chip in the processor of the vehicle; or by a software platform integrated in an electronic device.

[0050] S201, when a user's eye-tracking control command is detected, acquire measurement data from at least two positioning base stations outside the vehicle.

[0051] The eye-tracking control commands can represent control signals issued by the user through eye movements or in conjunction with other modalities (voice, buttons) to trigger eye-tracking interaction. For example, eye-tracking control commands could be a user's gaze duration exceeding a preset threshold, continuous blinking reaching a preset number of times, or issuing a specific voice command. The positioning base station represents a wireless signal transceiver device. For example, the positioning base station could be a UWB base station, a Bluetooth positioning base station, or an infrared positioning base station, capable of transmitting signals and / or receiving reflected signals. Measurement data represents the raw parameters obtained from signal interaction between the positioning base station and the eye-tracking device, including but not limited to signal propagation time, signal strength (signal quality), and angle of arrival.

[0052] It should be understood that signal propagation time is used to represent the one-way signal transmission time from the positioning base station to the eye-tracking device, that is, the time it takes for the signal to be transmitted from the positioning base station to the eye-tracking device.

[0053] Optionally, in one implementation, when a user's eye-tracking control command is detected, the eye-tracking device is controlled to send signals to multiple positioning base stations, and the signal propagation time is used to represent the time it takes for the signal to be sent from the eye-tracking device to the positioning base stations.

[0054] Alternatively, in another implementation, when a user's eye-tracking control command is detected, multiple positioning base stations are controlled to send signals to the eye-tracking device, and the signal propagation time is used to represent the time it takes for the signal to be sent from the positioning base station to the eye-tracking device.

[0055] In the embodiments of this application, when a user's eye-tracking control command is detected, measurement data from at least two positioning base stations pre-deployed at different locations within the vehicle's cabin are acquired. This measurement data includes at least the signal propagation time between each base station and the eye-tracking device worn by the user, serving as input for subsequent calculation of the spatial coordinates of the eye-tracking device. By acquiring measurement data from at least two base stations, the robustness and anti-interference capability of positioning can be improved by utilizing measurement data collected from multiple base stations.

[0056] For example, after detecting that the user issues the voice command "I want to measure tire pressure", the system recognizes the voice command as an eye-tracking control command and triggers three UWB base stations located outside the vehicle to simultaneously transmit signals to the eye tracker worn by the user, obtaining three sets of signal propagation time data (e.g., the time from base station 1 to the eye tracker is 1.2 nanoseconds, the time from base station 2 to the eye tracker is 1.5 nanoseconds, and the time from base station 3 to the eye tracker is 1.8 nanoseconds), which serve as the basis for subsequent spatial coordinate calculation.

[0057] For example, when a user is detected staring at the left rear wheel for more than 0.5 seconds, the staring command is detected, and three UWB base stations located outside the vehicle are triggered to simultaneously transmit UWB signals to the eye tracker worn by the user. Each base station measures the signal propagation time and obtains three sets of measurement data. For example, the time from base station 1 to the eye tracker is 1.2 nanoseconds, the time from base station 2 to the eye tracker is 1.5 nanoseconds, and the time from base station 3 to the eye tracker is 1.8 nanoseconds.

[0058] In one implementation, when a user's eye-tracking control command is detected, it is determined whether the user is outside the vehicle. If the user is detected outside the vehicle, the eye-tracking device is controlled to send signals to multiple positioning base stations outside the vehicle, or multiple positioning base stations outside the vehicle are controlled to send signals to the eye-tracking device. If the user is detected inside the vehicle (in the vehicle cabin), measurement data from at least two positioning base stations pre-deployed at different locations in the vehicle cabin are acquired. This measurement data includes at least the signal propagation time between each base station and the eye-tracking device worn by the user, as input for subsequent calculation of the spatial coordinates of the eye-tracking device.

[0059] In another implementation, the measurement data is not the result of a single signal reception, but rather obtained by acquiring multiple sets of measurement data and filtering them. This filtering process can be median filtering, mean filtering, or Kalman filtering. By smoothing multiple sets of measurement data, noise interference in a single measurement can be reduced, improving the stability of the measurement data.

[0060] Optionally, the action of acquiring measurement data from at least two positioning base stations in the vehicle can be performed periodically, for example, continuously acquiring measurement data from each positioning base station at a preset period (20ms) until it is detected that the user removes the eye-tracking device, the eye-tracking device is turned off, or the user exits the eye-tracking control mode.

[0061] In another implementation, when acquiring measurement data from the positioning base station periodically (e.g., with a period of 20ms), the transmission period can be dynamically adjusted based on the distance between the eye-tracking device and the vehicle (or positioning base station). When the eye-tracking device is far from the vehicle (or positioning base station) (e.g., greater than 1.2 meters), the transmission frequency is reduced (e.g., the period is adjusted to 30ms) to save power consumption of the eye-tracking device; when the eye-tracking device is close to the vehicle (e.g., less than or equal to 1.2 meters), the transmission frequency is increased (e.g., the period is adjusted to 15ms) to obtain more frequent measurement data updates, thereby improving the real-time performance of coordinate calculation in close-range interaction scenarios.

[0062] It should be noted that eye-tracking control mode refers to a working mode in which the vehicle responds to eye-tracking control commands and realizes cockpit function interaction based on eye-tracking data. In this mode, the vehicle continuously collects and processes eye-related data to provide users with eye-tracking controlled cockpit interaction services. This mode can be manually activated by the user (e.g., by pressing the eye-tracking activation button on the steering wheel) or automatically triggered (e.g., when the user is detected wearing an eye-tracking device and the vehicle is parked or moving). In eye-tracking control mode, the system continuously monitors the user's eye movements and gaze information, and executes corresponding vehicle function controls according to preset interaction strategies. Conditions for exiting eye-tracking control mode may include: the user actively turning off the mode, detecting that the user has removed the eye-tracking device, the vehicle being powered off, or detecting that the user has not engaged in eye-tracking interaction for an extended period of time.

[0063] In one embodiment, S201 is performed with the eye-tracking control mode enabled.

[0064] S202, Based on measurement data from at least two positioning base stations, determine the spatial coordinates of the eye-tracking device.

[0065] In the embodiments of this application, based on the known location information of each positioning base station and the signal propagation time contained in the measurement data, combined with the signal propagation speed, the time measurement information is converted into the spatial coordinates of the eye-tracking device in the vehicle body coordinate system using a multi-base station geometric solution method, thereby realizing the spatial positioning of the eye-tracking device worn by the user in the external vehicle scene.

[0066] In one implementation, the process of acquiring the locations of at least two positioning base stations and determining the spatial coordinates of the eye-tracking device based on the measurement data from the at least two positioning base stations may include: Based on the signal propagation time corresponding to at least two positioning base stations, a time difference is determined, which includes the difference in signal propagation time between any two positioning base stations among the at least two positioning base stations; The spatial coordinates of the eye-tracking device are determined based on the position and time difference of at least two positioning base stations.

[0067] Among them, the positions of at least two positioning base stations are used to represent the pre-calibrated coordinates of each positioning base station in the vehicle's body coordinate system (also known as the cockpit coordinate system), serving as reference positions when calculating the spatial coordinates of the eye-tracking device.

[0068] In the embodiments of this application, based on the measurement data of at least two positioning base stations, the time information of each positioning base station receiving the positioning signal transmitted by the eye-tracking device is determined, the time difference between different positioning base stations is calculated, and combined with the pre-calibrated position of each positioning base station in the vehicle coordinate system, a system of equations is constructed using the TDOA algorithm to solve for the spatial coordinates of the eye-tracking device in the vehicle coordinate system.

[0069] It should be understood that the system of equations can be a hyperboloid system of equations with the base station location as the focus.

[0070] For example, assume three positioning base stations are deployed on the outside of the vehicle body, with their positions in the vehicle coordinate system as follows: base station 1 (1.2, 0, 0.5), base station 2 (0, 0.8, 0.9), and base station 3 (-1.1, 0, 0.5); the propagation time of the signal between the eye-tracking device and the first base station is T1, the propagation time between the eye-tracking device and the second base station is T2, and the propagation time between the eye-tracking device and the third base station is T3; calculate the time difference ΔT12 = T2 - T1 between the first and second base stations, and the time difference ΔT13 = T3 - T1 between the first and third base stations. T1; The distance difference between the first base station and the second base station is obtained by multiplying the time difference ΔT12 and the signal propagation speed. The distance difference between the first base station and the third base station is obtained by multiplying the time difference ΔT13 and the signal propagation speed. The first hyperboloid equation is constructed with the positions of the first base station and the second base station as the focus and the first distance difference as a constant. The second hyperboloid equation is constructed with the positions of the first base station and the third base station as the focus and the second distance difference as a constant. The third hyperboloid equation is constructed by combining the time difference ΔT23 between the second base station and the third base station. The three hyperboloid equations are solved simultaneously to determine the spatial coordinates (0.3, 1.5, 1.2) of the eye-tracking device.

[0071] In one embodiment, when a positioning base station is detected to have received a signal quality lower than a preset quality threshold due to obstruction by an obstacle, the measurement data of that base station is removed from the current calculation. The remaining base stations with signal quality higher than or equal to the preset quality threshold are then used to construct and solve the equations. Since the number of positioning base stations outside the vehicle exceeds the minimum number required for the minimum calculation, even after removing some abnormal base stations, the remaining base stations can continue to be used to maintain redundant calculation of spatial coordinates, thus avoiding positioning interruption.

[0072] In another embodiment, the positioning base station acts as the signal receiver, and the eye-tracking device acts as the signal transmitter. After obtaining the spatial coordinates, the theoretical reception time of each positioning base station is calculated using the spatial coordinates. The theoretical reception time is compared with the actual reception time, and the difference is used to obtain the residual value. If the residual value of a certain base station exceeds a preset residual threshold, it is determined that the measurement data of that base station has an error. The measurement data of that base station is then discarded, and the remaining base stations are used to recalculate the coordinates to improve the accuracy of the coordinates.

[0073] Optionally, the two embodiments described above can be combined. Base station measurement data can be eliminated based on signal quality, and the remaining base station measurement data can be re-verified based on residual analysis. When either condition triggers an anomaly determination, the measurement data of that base station can be eliminated. This approach comprehensively eliminates abnormal measurement values, thereby improving the accuracy of fixation point determination.

[0074] In the above implementation, the positions of at least two positioning base stations outside the vehicle are obtained. The time difference between any two positioning base stations is determined based on the signal propagation time corresponding to these two base stations. The spatial coordinates of the eye-tracking device are then determined by combining the positions and time differences of the at least two positioning base stations. Compared to existing technologies that use a single base station to send and receive round-trip signals for distance measurement, where the ranging path fails and coordinates cannot be calculated when the base station is obstructed by an obstacle, this solution obtains the positions of multiple positioning base stations and uses the time difference between the signals received by different base stations to calculate the position. Since the calculation process relies on the relative time difference between base stations rather than the absolute distance value of a single base station, even if some base stations experience increased signal delay or loss due to obstruction, the spatial coordinates of the eye-tracking device can still be determined using the time difference between the remaining base stations and their corresponding positions. This reduces the risk of positioning interruption due to local obstruction and improves the accuracy and reliability of determining the spatial coordinates of the eye-tracking device.

[0075] In one implementation, a third component is configured outside the vehicle. The specific process of the third component having lower power consumption than the positioning base station may include: Based on the first distance, the measurement data of at least two positioning base stations are calibrated. Based on the calibrated measurement data, the spatial coordinates of the eye-tracking device are determined.

[0076] The third component represents a ranging component mounted on the vehicle body, used for short-range communication with the eye-tracking device to acquire distance information between them. The positioning power consumption of the third component is lower than that of the positioning base station and the first / second component. In near-field scenarios, it can replace the positioning base station for distance detection or assist in calibrating the measurement data of the positioning base station. For example, the third component can represent a Bluetooth positioning module (e.g., deployed on the left and right rearview mirrors or door handles of the vehicle), and the eye-tracking device can be equipped with a Bluetooth tag. When a user wearing the eye-tracking device approaches the vehicle within a preset range, the Bluetooth positioning module establishes a communication connection with the Bluetooth tag, determining a first distance by receiving signal strength or by a phase-based ranging method. In near-field scenarios (e.g., when the distance between the eye-tracking device and the Bluetooth module is within a preset range), the Bluetooth positioning module continuously acquires the first distance to maintain position monitoring of the eye-tracking device, while the long-range positioning module in the eye-tracking device enters a sleep state to reduce power consumption. When higher-precision positioning is required, the first distance acquired by the Bluetooth positioning module is used as a reference value to correct deviations in the measurement data of the positioning base station, thereby improving the accuracy of spatial coordinate calculation.

[0077] In the embodiments of this application, a first distance between the vehicle and the eye-tracking device is obtained through a third component configured outside the vehicle. This first distance is used as a calibration reference value to calibrate the measurement data of at least two positioning base stations, and the spatial coordinates of the eye-tracking device are determined based on the calibrated measurement data.

[0078] For example, a low-power Bluetooth module (i.e., the third component) is configured at the rearview mirror of the vehicle, and a corresponding Bluetooth tag is configured on the eye-tracking device; when the distance between the user wearing the eye-tracking device and the vehicle is within the Bluetooth positioning range, the Bluetooth module establishes a connection with the Bluetooth tag, and obtains the first distance as one meter through the Bluetooth signal strength; at the same time, the distance between the eye-tracking device and a certain base station is measured by the positioning base station as 1.8 meters; using the one meter obtained by Bluetooth as a reference benchmark, the measurement data of the positioning base station is corrected for deviation, and the corrected measurement data is used for subsequent spatial coordinate calculation to obtain the corrected spatial coordinates of the eye-tracking device.

[0079] In one embodiment, the calibration process can employ a correction coefficient method. Based on historical deviation data between the first distance and the distance measured by the positioning base station, correction coefficient curves corresponding to different distance intervals are established. During calibration, the corresponding correction coefficient is selected according to the interval in which the current first distance is located, compensating the measurement data of the positioning base station to improve the accuracy of the calibration.

[0080] In another embodiment, the reliability of each positioning base station is determined based on the calibration results. If the deviation between the measured distance of the positioning base station and the first distance is within a preset deviation range, the measurement data of that base station is retained; if the deviation exceeds the preset deviation range, it is determined that the base station may be faulty or subject to continuous interference, and the weight of the base station's measurement data in subsequent calculations is reduced or it is removed.

[0081] In the above implementation, a third component with lower power consumption than the positioning base station is installed outside the vehicle. Before determining the spatial coordinates based on the measurement data from the positioning base station, a first distance between the third component and the eye-tracking device is obtained. The measurement data from the positioning base station is then calibrated based on this first distance, and the spatial coordinates are determined based on the calibrated measurement data. This solution introduces a low-power third component to pre-acquire distance information and uses this distance information to calibrate the measurement data from the positioning base station before coordinate calculation. This reduces the interference of environmental factors on the measurement data, thereby improving the accuracy of subsequent spatial coordinate calculation.

[0082] In one implementation, a camera is installed on the exterior of the vehicle, and the control method further includes: Acquire the target image captured by the camera; Based on the target image, determine the reference position of the eye-tracking device; The specific process of calibrating measurement data from at least two positioning base stations based on a first distance may include: Based on the first distance and the reference position, the measurement data of at least two positioning base stations are calibrated.

[0083] The term "camera" refers to an image acquisition device deployed on the vehicle body, used to collect environmental image data of the vehicle. This camera includes, but is not limited to, surround-view cameras, fisheye cameras, and infrared cameras. The target image refers to single or multiple frames of image data acquired by the camera, and should contain all or part of the features of the eye-tracking device. The reference position refers to the position information of the eye-tracking device in the image coordinate system extracted from the target image using an image recognition algorithm, and its spatial position in the vehicle body coordinate system after coordinate transformation.

[0084] In the embodiments of this application, For example, during the calibration process of measurement data from at least two positioning base stations based on a first distance, a target image is acquired by a camera configured outside the vehicle. The characteristics of the eye-tracking device are identified through the target image to determine the reference position of the eye-tracking device in the vehicle coordinate system. This reference position is then combined with the first distance acquired by a third component to jointly calibrate the measurement data of the positioning base stations, thereby improving the reliability and accuracy of the measurement data correction.

[0085] For example, assuming the third component measures a first distance of 1.5 meters, the target image captured by the surround-view camera is used to identify the outline of the eye-tracking device and calculate its reference position in the vehicle coordinate system as (0.32, 1.48, 1.18). The first distance of 1.5 meters and the reference position (0.32, 1.48, 1.18) are used as references and compared with the distance and position calculated from the original measurement data of the positioning base station. If the distance calculated from the measurement data of the positioning base station is 1.7 meters, it is corrected based on the first distance and the reference position.

[0086] It should be understood that the camera can adaptively adjust the exposure parameters according to the ambient lighting conditions. When the ambient light exceeds the preset intensity threshold, the camera reduces the exposure time or decreases the gain to prevent the image from being overexposed; when the ambient light is less than the preset intensity threshold, the camera extends the exposure time or increases the gain to enhance the image brightness.

[0087] Optionally, in one implementation, confidence weights are set for the first distance and the reference position. When the image quality of the target image is detected to be higher than a preset image quality and / or the contour recognition confidence is higher than a preset confidence, the weight of the reference position participating in the calibration is increased; when the image quality is detected to be poor due to lighting or occlusion, the weight of the reference position participating in the calibration is decreased.

[0088] In the above implementation, a camera is installed outside the vehicle to acquire target images. Based on these images, the reference position of the eye-tracking device is determined. Then, the measurement data of the positioning base station is calibrated by combining the first distance obtained by the third component with the image reference position. Compared to calibration relying solely on distance information from the third component, where changes in lighting or signal reflection in complex external environments can lead to deviations from a single calibration source, this solution introduces a camera. The reference position of the eye-tracking device is obtained from the target images captured by the camera. This combines distance-based calibration with image-based visual positioning, enabling collaborative calibration of the positioning base station's measurement data from different dimensions. This improves the reliability of the calibration process and thus enhances the accuracy of the measurement data.

[0089] In one implementation, after determining the reference position of the eye-tracking device based on the target image, the control method further includes: Calculate the positional deviation between the spatial coordinates and the reference position; When the detected position deviation is greater than the preset deviation threshold, the spatial coordinates are replaced based on the image reference position, or the spatial coordinates and the reference position are weighted and fused.

[0090] For example, the spatial coordinates of the eye-tracking device are calculated as (0.3, 1.5, 1.2) based on the measurement data from three positioning base stations, and the reference position is calculated as (0.28, 1.47, 1.21) based on the target image collected by the surround-view camera. The distance between the two is calculated as the position deviation, and the deviation value is approximately 0.04 meters. Assuming that the preset deviation threshold is 0.05 meters, the current deviation is 0.04 meters, which is less than the preset deviation threshold. At this time, it is determined that the deviation between the positioning base station calculation result and the visual recognition result is within an acceptable range, and the spatial coordinates are used as the calculation result.

[0091] For example, suppose the spatial coordinates calculated based on the measurement data of the positioning base station are (0.4, 1.6, 1.1), while the reference position is (0.29, 1.48, 1.19). The deviation between the two reaches 0.18 meters, which exceeds the preset deviation threshold of 0.05 meters. Then, a weighted fusion method is adopted, for example, the reference position is fused with a weight of 0.7 and the spatial coordinates with a weight of 0.3, to obtain the corrected spatial coordinates (0.323, 1.516, 1.163).

[0092] In one implementation, the specific process of calibrating the measurement data of at least two positioning base stations based on a first distance may include: When the first distance is detected to be less than a preset distance threshold, the measurement data of at least two positioning base stations are calibrated.

[0093] In the embodiments of this application, after obtaining the first distance between the third component and the eye-tracking device, the first distance is compared with a preset distance threshold. When the first distance is detected to be less than the preset distance threshold, it indicates that the eye-tracking device has entered the effective ranging range of the third component. At this time, the ranging result of the third component has high accuracy, and the measurement data of the positioning base station is calibrated using the first distance. When the first distance is detected to be greater than or equal to the preset distance threshold, it indicates that the eye-tracking device is outside the effective ranging range of the third component, and the ranging accuracy of the third component may decrease. At this time, the calibration process is not triggered, and the spatial coordinates are calculated using the original measurement data of the positioning base station.

[0094] For example, assuming the preset distance threshold is 1.5 meters, when a user wearing an eye-tracking device walks towards a vehicle, the third component first obtains a first distance of 2.0 meters, which is greater than the preset distance threshold of 1.5 meters. At this time, positioning is performed solely based on the measurement data from the positioning base station. When the user continues to approach to a first distance of 1.2 meters, it detects that 1.2 meters is less than the preset distance threshold of 1.5 meters, triggering a calibration process. The 1.2 meters obtained by the third component is used as a reference benchmark to correct the distance information calculated from the measurement data of the positioning base station. The calibrated measurement data is used for the subsequent accurate calculation of spatial coordinates.

[0095] Optionally, in one implementation, when the eye-tracking device enters a preset distance threshold range, it indicates that the user has approached the vehicle. At this time, the positioning accuracy can be improved through calibration while the transmission power of the positioning base station is turned off or reduced to save power consumption. When the user is far away from the vehicle, the positioning base station operates at normal power to maintain long-distance positioning capability, thus achieving a balance between accuracy and power consumption.

[0096] Optionally, in one implementation, the result of the calibration process is stored. If a consistent deviation trend is detected in the measurement data of a certain positioning base station during multiple calibration processes (for example, the measurement data of base station A is detected to be 0.5cm to the left in five consecutive measurements), the deviation trend is taken as a system error and superimposed as an error compensation amount in subsequent calculations to reduce subsequent calibration processes.

[0097] Optionally, in one implementation, the decision to perform calibration can be based on the motion state of the eye-tracking device. If the eye-tracking device is detected to be stationary (e.g., the movement amplitude in the past 2 seconds is less than a preset movement amplitude), even if the first distance is less than a preset distance threshold, the frequency of calibration is reduced or calibration is not performed, thereby saving computational resources; if the eye-tracking device is detected to be moving (e.g., the movement amplitude in the past 1 second is greater than or equal to a preset movement amplitude), the frequency of calibration is increased to ensure timely correction.

[0098] It should be understood that the above implementation methods can be combined. For example, while turning off or reducing the transmission power of the positioning base station to save power consumption, the frequency of calibration processing can be dynamically adjusted based on the motion state of the eye-tracking device; while determining the compensation amount of system error based on historical deviation trends, the motion state of the eye-tracking device can be used to determine whether to reduce the calibration frequency.

[0099] In the above implementation, after obtaining the first distance between the third component and the eye-tracking device, when the first distance is detected to be less than a preset distance threshold, the measurement data of at least two positioning base stations are calibrated. This solution sets a preset distance threshold. When the first distance is less than the preset distance threshold, i.e., in a close-range scenario, the ranging results of the third component are used to calibrate the measurement data of the positioning base stations. This fully leverages the high ranging accuracy of the third component within a close-range range, avoiding interference from low-precision ranging data at long distances, thereby improving the rationality of the calibration process.

[0100] In one implementation, the control method further includes: Obtain the weights of at least two positioning base stations and the third component; The specific process of determining the spatial coordinates of an eye-tracking device based on measurement data from at least two positioning base stations may include: The spatial coordinates of the eye-tracking device are determined based on the weights of at least two positioning base stations, the weight of the third component, the first distance, and the measurement data from at least two positioning base stations.

[0101] In the embodiments of this application, the weights corresponding to at least two positioning base stations and the weight corresponding to the third component are obtained. The first distance obtained by the third component and the measurement data of the positioning base stations are used as inputs and weighted and fused according to their respective weights to determine the spatial coordinates of the eye-tracking device in the vehicle coordinate system.

[0102] For example, assume that the weight of the positioning base station is 0.7 and the weight of the third component is 0.3 in the current measurement cycle; the positioning base station calculates the preliminary spatial coordinates of the eye-tracking device based on the measurement data as (0.3, 1.5, 1.2), and the first distance obtained by the third component is 1.48 meters; a spatial spherical constraint with the third component as the center and the first distance as the radius can be determined according to the deployment position of the third component and the first distance; the two positioning constraints are solved by weighted least squares with the weight of the positioning base station of 0.7 and the weight of the third component of 0.3, and the spatial coordinates (0.31, 1.49, 1.19) are obtained.

[0103] Optionally, the weights can be based on the determination of signal quality parameters. For example, for a positioning base station, its reliability can be determined based on at least one of the parameters such as the received signal strength and signal-to-noise ratio difference of the positioning signal received by each base station; the higher the reliability, the higher the weight. For the third component, its reliability can be determined based on at least one of the following: the communication connection quality between the third component and the eye-tracking device, the historical fluctuation range of the first distance, and whether the current distance is within its optimal ranging range; the higher the reliability, the higher the weight.

[0104] In one embodiment, when the credibility of a source is detected to be lower than a preset credibility level, or when the weight of a source is set to zero or less than a preset weight value, it indicates that the source is untrustworthy at the current moment, and a positioning mode based on another source is adopted. For example, when the positioning base station is severely obstructed, resulting in poor signal quality, its weight value is lower than a preset weight value (e.g., 0.1), and the system switches to a positioning mode based on ranging by a third component.

[0105] In the above implementation, the weights of at least two positioning base stations and the third component are obtained. Based on the weights of the at least two positioning base stations, the weight of the third component, the first distance, and the measurement data of the at least two positioning base stations, the spatial coordinates of the eye-tracking device are jointly determined. This scheme assigns weights to different positioning sources and performs weighted fusion of multi-source positioning data. It can adjust the weights of different positioning sources in the solution process according to their confidence levels, reduce the impact of anomalies in a single data source on the overall positioning results, and improve the accuracy of determining the spatial coordinates of the eye-tracking device.

[0106] In one implementation, the control method further includes: Obtain vehicle environmental information; When environmental information is detected to indicate that the vehicle is in an abnormal environment, the weights of at least two positioning base stations and the weight of the third component are adjusted to obtain the adjusted weights of at least two positioning base stations and the adjusted weights of the third component. In this context, the adjusted weights of at least two positioning base stations are less than the weights of at least two positioning base stations, while the adjusted weight of the third component is greater than the weight of the third component. Environmental information is used to represent data indicating the current external scene state of the vehicle; environmental information may include, but is not limited to, light intensity information, meteorological information, ambient humidity information, or ambient temperature information, used to determine the impact of the current environment on the measurement accuracy of each positioning source. Abnormal environment is used to represent external environmental states that may negatively affect the measurement accuracy of at least one positioning source; this abnormal environment may be a strong light environment, a weak light environment, a rain / snow precipitation environment, or a low visibility environment, etc.

[0107] In the embodiments of this application, environmental information of the vehicle's environment is obtained, and the vehicle is determined to be in an abnormal environment based on the environmental information. When the environmental information indicates that the vehicle is in an abnormal environment, the weights of at least two positioning base stations are reduced and the weight of the third component is increased. The measurement data of the positioning base stations and the first distance of the third component are weighted and fused with the adjusted weights to determine the spatial coordinates of the eye-tracking device.

[0108] For example, if a vehicle detects that the ambient light intensity exceeds a preset strong light threshold using a light sensor, it determines that the vehicle is in an abnormal environment with strong light. This environment may cause the positioning base station signal to become less accurate due to increased thermal noise. In this case, the weights of at least two positioning base stations are reduced from 0.7 to 0.4, and the weight of the third component is increased from 0.3 to 0.6. The adjusted weights are then used to perform a weighted fusion of the preliminary spatial coordinates calculated by the positioning base stations and the first distance obtained by the third component to obtain the spatial coordinates.

[0109] It should be noted that the determination of abnormal environments can be based on a comparison of a single environmental parameter with a threshold, or on a combination of multiple environmental parameters. For example, a light intensity greater than a preset strong light threshold is determined to be an abnormal strong light environment, or a rain sensor detecting precipitation is determined to be an abnormal rain / snow environment. A combination of multiple parameters, such as simultaneously detecting light intensity below a preset weak light threshold and ambient humidity above a preset humidity threshold, is determined to be an abnormal weak light and rain / fog environment. In this case, the impact on the location source is greater, and the weight adjustment can be correspondingly increased.

[0110] Optionally, the magnitude of the weight adjustment can be tiered according to the severity of the abnormal environment. In slightly abnormal environments, the weight adjustment magnitude is smaller; in severely abnormal environments, the weight adjustment magnitude is larger. For example, when the light intensity exceeds the first strong light threshold, the weight of the positioning base station decreases from 0.7 to 0.6; when the light intensity exceeds the second strong light threshold (the second strong light threshold is greater than the first strong light threshold), the weight of the positioning base station decreases from 0.7 to 0.3.

[0111] In the above implementation, environmental information of the vehicle is acquired. When environmental information indicates that the vehicle is in an abnormal environment, the weights of at least two positioning base stations are reduced and the weight of the third component is increased. The adjusted weights are then used for subsequent coordinate calculations. Compared to multi-source positioning data fusion using a fixed weight allocation method, this approach does not consider the performance differences of positioning sources under different environmental conditions. For example, in scenarios with abnormal lighting or severe weather, the signal of the positioning base station may attenuate, while the short-range ranging of the third component is less affected by the environment. This solution identifies the abnormal environment in which the vehicle is located and adjusts the weight allocation of different positioning sources. In abnormal environments, the weight of data sources that are susceptible to environmental influences is reduced, while the weight of data sources with greater stability is increased. This improves the positioning stability of the eye-tracking device's spatial coordinates under different environmental conditions.

[0112] S203, based on spatial coordinates, determines the coordinate information of the user's target gaze point.

[0113] The coordinates of the target gaze point are used to control the vehicle to perform operations corresponding to that gaze point. The target gaze point represents the location where the user's gaze falls within the vehicle's cabin. This gaze point can be located on interactive components such as the central control screen, air conditioning vents, window switches, seats, and rearview mirrors. The coordinate information represents the specific numerical description of the target gaze point in the cabin coordinate system, such as (x, y, z), or, when the gaze point falls on a display screen, it can be converted to screen pixel coordinates (u, v). The target gaze point represents the final determined gaze point, used for subsequent vehicle control to perform corresponding operations; it represents the target of the user's gaze with control intent.

[0114] It should be noted that the target gaze point is used to generate the target control strategy for controlling the vehicle. The target control strategy is a strategy used to enable the target object to take over the intelligent driving system. The target control strategy may include, but is not limited to, adjusting the seat, turning the air conditioning on / off, opening / closing the windows, adjusting the rearview mirrors, preparing to park, adjusting the vehicle speed, and preparing to turn. In some embodiments, the target object's driving intention can be identified first through the target gaze point. Only when the driving intention indicates a need to take over the intelligent driving system will the target control strategy be determined based on the target gaze point. The target object's driving intention is used to indicate whether the target object needs to take over the intelligent driving system. When controlling the vehicle based on the target control strategy, the target control strategy can be converted into target control commands that the vehicle can use, and then 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, the engine, motor, steering wheel, windows, and seats.

[0115] After executing S204, the coordinate information of the target gaze point is matched with the spatial coordinate range of multiple components pre-stored in the vehicle. These components include, but are not limited to, virtual buttons on the central control screen, air conditioning vents, sunroof, window switches, seats, and rearview mirrors. When the coordinate information of the target gaze point falls within the coordinate range corresponding to a component, a corresponding control command is generated, and the operation is executed according to the control command; or, when the coordinate information of the target gaze point falls within the coordinate range corresponding to a component, the component is controlled to perform a preset function.

[0116] For example, if the coordinates of the target gaze point are detected to be within the coordinate range of the sunroof in the vehicle, a control command is sent to the motor that controls the sunroof; after receiving the control command, the motor controls the sunroof to open.

[0117] In one implementation, the spatial coordinates include the coordinates of a first component and a second component in the eye-tracking device. The specific process of determining the coordinate information of the user's target gaze point based on these spatial coordinates may include: The user's facial orientation is determined based on the coordinates of the first component and the second component; Based on facial orientation and spatial coordinates, the coordinate information of the target gaze point is determined.

[0118] In the embodiments of this application, the user's facial orientation is obtained by calculating the coordinates between the first component and the second component. Since the facial orientation is used to represent the user's posture information and the spatial coordinates are used to represent the position of the user's eyes, the coordinate information of the user's target gaze point can be obtained by combining the facial orientation and the spatial coordinates.

[0119] For example, let the coordinates of the first component be... Second component coordinates Preset fixed spacing The difference vector is Horizontal orientation angle Vertical orientation angle That is, the user's face is horizontally 45° to the right and front; the midpoint between the first and second components (i.e., the spatial coordinates of the eye-tracking device). Assuming the eye is located If the eye is 0.03m in front and 0.01m below, then the eye coordinates are: Assuming the eye-tracking module of the eye-tracking device measures that the eyeball deflects 5° to the right and 3° downward, the direction of gaze is horizontally to the right at 50° and vertically at -3°. Starting from the eye coordinates, a ray is emitted along the direction of gaze, and the intersection point formed with the component inside the vehicle is determined as the target gaze point.

[0120] Specifically, in the embodiments of this application, the eye-tracking device is configured with two components, and the line connecting the two components is parallel to the horizontal direction of the wearer's face. Therefore, the difference vector between the first and second components is parallel to the horizontal direction of the wearer's face. Based on the components of this difference vector on each axis of the cockpit coordinate system, the angle parameters of the facial orientation can be calculated: the horizontal orientation angle is the angle between the projection of the difference vector onto the horizontal plane (i.e., the XY plane) and the X-axis (vehicle longitudinal axis) of the cockpit coordinate system, which can be obtained by calculating the ratio of the Y-axis component to the X-axis component of the difference vector using an inverse trigonometric function (such as the arctan function); the vertical orientation angle is the angle between the difference vector and the horizontal plane, which can be obtained by calculating the ratio of the Z-axis component of the difference vector to a preset fixed distance using an inverse trigonometric function (such as the arcsin function). Thus, this solution does not require a posture sensor and can synchronously calculate the user's facial orientation information using the spatial coordinates of the two components themselves.

[0121] Alternatively, in one implementation, the user's facial orientation can be determined based on target images captured by cameras located outside the vehicle.

[0122] Specifically, the camera can be used to capture target images that include eye-tracking devices and the user's facial area; by performing portrait detection and facial key point extraction on the target image, the pose information of the user's face in the image coordinate system is obtained, and the pose information is transformed into the vehicle coordinate system to obtain the user's facial orientation.

[0123] For example, when a user wearing an eye-tracking device stands on the left side of a vehicle, a camera deployed at the left rearview mirror captures the user's facial image, extracts multiple key points of the user's facial features from the image, and obtains the user's facial posture angles (such as horizontal and vertical angles). These posture angles are used as auxiliary information to determine the target gaze point.

[0124] In one embodiment, when one of the dual positioning components loses signal due to occlusion and cannot calculate the face orientation through the difference vector, the system can switch to a camera-based face orientation determination method.

[0125] In another embodiment, the facial orientation determined based on the coordinate difference between two components can be compared and verified with the facial orientation determined based on the camera image. If the deviation of the orientation angle obtained by the two methods is within a preset range, the accuracy of the facial orientation is confirmed. If the deviation exceeds the preset range, the confidence level can be evaluated based on signal quality parameters and / or image clarity, and the more reliable method can be selected to determine the facial orientation.

[0126] In the above implementation, the user's facial orientation is determined based on the coordinates of the first and second components in the eye-tracking device. Then, the coordinates of the target gaze point are determined by combining the facial orientation with the spatial coordinates. Compared to existing technologies where spatial coordinates and facial orientation are acquired separately by the positioning module and the posture sensor, respectively, this approach avoids data synchronization delays and errors in posture changes such as when the user turns to the side or bends over. Instead, this solution simultaneously calculates the spatial coordinates of the first and second components from the positioning signal and determines the user's facial orientation based on the difference vector between the two coordinates. This allows position and orientation calculations to be completed synchronously in the same coordinate system, eliminating the need for an additional posture sensor, reducing hardware costs, avoiding data synchronization delays, improving the accuracy of facial orientation judgment under different body postures, and enhancing the reliability of target gaze point determination.

[0127] In the above embodiments, upon detecting a user's eye-tracking control command, measurement data from at least two positioning base stations outside the vehicle are acquired. This measurement data includes the signal propagation time between the positioning base stations and the eye-tracking device outside the vehicle. Based on the measurement data from at least two positioning base stations, the spatial coordinates of the eye-tracking device are determined. Then, based on these spatial coordinates, the user's target gaze point is determined. Compared to existing technologies, eye-tracking positioning schemes are limited to the vehicle cabin, and in complex external environments, factors such as changes in lighting and obstacle obstruction can lead to decreased positioning accuracy or even positioning gaps. This solution acquires measurement data from at least two positioning base stations outside the vehicle. Therefore, the spatial coordinates of the eye-tracking device determined by this solution based on the measurement data from each positioning base station are more accurate than those measured by a single positioning base station. This reduces the impact of signal loss when a single base station is obstructed, thereby achieving accurate determination of the target gaze point in external scenarios, improving the accuracy of the gaze point in eye-tracking control. Furthermore, since the coordinate information of the gaze point is used to further generate a target control strategy for the vehicle, this solution improves the accuracy and real-time performance of vehicle control.

[0128] The following is combined with Figure 3 Another vehicle control method provided in the embodiments of this application will be described in detail.

[0129] Figure 3 This is a schematic flowchart illustrating another vehicle control method provided in an embodiment of this application. Figure 3 As shown, method 300 includes S301 to S312, which are described in detail below.

[0130] For example, Figure 3 The method 300 shown can be executed by a vehicle; or by a processor in the vehicle; or by a chip in the processor of the vehicle; or by a software platform integrated in an electronic device.

[0131] S301, in response to the user's eye-tracking control command, determines the distance between the eye-tracking device and the vehicle.

[0132] For example, after detecting that the user issues the voice command "I want to measure tire pressure with eye tracking", the system recognizes the voice command as an eye tracking command, starts the low-power Bluetooth module to scan, and controls the eye tracking device to establish a connection with the vehicle's Bluetooth module to complete the initial distance detection.

[0133] S302 controls multiple base stations to simultaneously send signals to the eye-tracking device and calculates the time difference.

[0134] For example, multiple positioning base stations at the front of the vehicle, the left rearview mirror, and the rear of the vehicle simultaneously send positioning signals to the first and second components of the eye-tracking device, record the time when each base station receives the signal, and calculate the time difference. For example, the time difference between the front base station and the left rearview mirror base station receiving the signal from the first component is 0.8 nanoseconds.

[0135] S303, determine the coordinates of the first component and the second component based on the time difference.

[0136] For example, based on the time difference of 0.8 nanoseconds between the vehicle front base station and the left rearview mirror base station and the preset position coordinates of the two base stations, the coordinates of the first component are calculated as (0.5, 1.8, 1.2) and the coordinates of the second component are (0.55, 1.8, 1.2) by the time difference of arrival algorithm.

[0137] S304, determine whether the distance is less than the preset distance threshold; if yes, execute S304; if no, execute S306 and S308.

[0138] For example, assuming the preset distance threshold is 1.0 meter, if the measured distance is 0.5 meters, which is less than the preset distance threshold, the UWB module is calibrated because the positioning of the Bluetooth / vehicle camera is relatively accurate, and S304 is executed; if it is greater than or equal to the preset distance threshold, the positioning of the Bluetooth / vehicle camera is inaccurate, and S306 and S308 are executed.

[0139] S305 calibrates the UWB module based on data collected by the Bluetooth / vehicle camera.

[0140] For example, if the distance is 0.5 meters (less than a preset distance threshold), the coordinates calculated by the positioning base station are calibrated using the distance measured by the Bluetooth / vehicle camera.

[0141] Alternatively, while performing calibration via Bluetooth, images captured by a vehicle body camera (e.g., a surround-view image acquisition device) can be accessed to identify the contour position of the eye-tracking device for secondary calibration.

[0142] S306, the midpoint of the spatial coordinates of the first component and the second component is determined as the spatial coordinates of the eye-tracking device.

[0143] For example, the midpoint between the coordinates of the first component (0.5, 1.8, 1.2) and the coordinates of the second component (0.55, 1.8, 1.2) is calculated to obtain the spatial coordinates of the eye-tracking device as (0.525, 1.8, 1.2).

[0144] S307, acquire the eye deflection angle obtained from the eye-tracking device.

[0145] For example, the eye-tracking device detected that the user's eyes were horizontally deflected 4° to the left and vertically deflected 1° downward relative to the face.

[0146] S308, the difference vector is obtained based on the spatial coordinates of the first component and the second component.

[0147] For example, subtracting the coordinates of the first component from the coordinates of the second component yields the difference vector (0.55-0.5, 1.8-1.8, 1.2-1.2) = (0.05, 0, 0).

[0148] S309, determine the facial orientation based on the difference vector.

[0149] For example, based on the component of the difference vector in the positive X-axis direction in the vehicle coordinate system, and combined with the coordinate axis direction calculation, the horizontal orientation angle is 0° (towards the front of the vehicle) and the vertical orientation angle is 0°, thus determining that the user's face is facing the front of the vehicle.

[0150] S310 determines the gaze vector based on the face orientation and eye deflection angle.

[0151] For example, by combining facial orientation (0° horizontally, 0° vertically) with eye deflection (-4° horizontally, -1° vertically), the gaze direction is obtained as 4° horizontally to the left and 1° vertically downward, and this is determined as the gaze vector.

[0152] S311 determines the gaze point based on the spatial coordinates of the eye-tracking device and the gaze vector.

[0153] For example, based on the eye-tracking device coordinates (0.055, 0.025, 0.12) and eye offset, a ray is emitted along the line of sight to determine the parametric equation of the line of sight. The intersection of this parametric equation with the plane outside the vehicle is the point where the line of sight lands.

[0154] Optionally, when determining the gaze point based on the spatial coordinates of the eye-tracking device and the gaze vector, the user's eye offset is taken into account. For example, if the eye offset is (0.03, -0.01), the spatial coordinates of the eye-tracking device are first adjusted to account for the eye offset. If the spatial coordinates of the eye-tracking device are (0.055, 0.025, 0.12), after adjusting the eye offset, the eye coordinates are obtained as (0.085, 0.025, 0.11).

[0155] S312, determine the target gaze point based on the coordinate range of the gaze point and multiple components inside the vehicle.

[0156] For example, suppose the parametric equation of the ray in the direction of the gaze intersects the position of the left rear tire (assuming plane X=0.6) at the point (0.6, 0.639, 0.068), and intersects the left rear tire at the point (0.6, 0.02, 0.38), which is the gaze point. Comparing the gaze point (0.6, 0.02, 0.38) with the pre-stored rear tire coordinate range (X∈[0.58, 0.62], Y∈[-0.05, 0.05], Z∈[0.35, 0.42]), we determine that the gaze point is within this range, and therefore this point is determined as the target gaze point.

[0157] In the above embodiments, upon detecting a user's eye-tracking control command, measurement data from at least two positioning base stations outside the vehicle are acquired. This measurement data includes the signal propagation time between the positioning base stations and the eye-tracking device outside the vehicle. Based on the measurement data from at least two positioning base stations, the spatial coordinates of the eye-tracking device are determined. Then, based on these spatial coordinates, the user's target gaze point is determined. Compared to existing technologies, eye-tracking positioning schemes are limited to the vehicle cabin, and in complex external environments, factors such as changes in lighting and obstacle obstruction can lead to decreased positioning accuracy or even positioning gaps. This solution acquires measurement data from at least two positioning base stations outside the vehicle. Therefore, the spatial coordinates of the eye-tracking device determined by this solution based on the measurement data from each positioning base station are more accurate than those measured by a single positioning base station. This reduces the impact of signal loss when a single base station is obstructed, thereby achieving accurate determination of the target gaze point in external scenarios, improving the accuracy of the gaze point in eye-tracking control. Furthermore, since the coordinate information of the gaze point is used to further generate a target control strategy for the vehicle, this solution improves the accuracy and real-time performance of vehicle control.

[0158] The above text combined Figures 1 to 3 This application provides a detailed description of a vehicle control method based on its embodiments; the following will be combined with... Figure 4 and Figure 5 The apparatus embodiments of this application are described in detail below. It should be understood that the apparatus in the embodiments of this application can perform the various methods described in the foregoing embodiments of this application, that is, the specific working processes of the various products described below can be referred to the corresponding processes in the foregoing method embodiments.

[0159] Figure 4 This is a schematic diagram of a vehicle control device provided in an embodiment of this application. The vehicle control device 400 includes an acquisition module 410 and a processing module 420.

[0160] The acquisition module 410 is used to acquire measurement data from at least two positioning base stations outside the vehicle when a user's eye-tracking control command is detected. The measurement data includes signal propagation time, which represents the propagation time from the positioning base station to the eye-tracking device outside the vehicle. The processing module 420 is used to determine the spatial coordinates of the eye-tracking device based on measurement data from at least two positioning base stations; and to determine the coordinate information of the user's target gaze point based on the spatial coordinates.

[0161] Optionally, as an embodiment, the processing module 420 is further configured to: acquire the positions of at least two positioning base stations; determine the spatial coordinates of the eye-tracking device based on the measurement data of the at least two positioning base stations, including: determining a time difference based on the signal propagation time corresponding to the at least two positioning base stations, wherein the time difference includes the difference in signal propagation time between any two of the at least two positioning base stations; and determine the spatial coordinates of the eye-tracking device based on the position and time difference of the at least two positioning base stations.

[0162] Optionally, as an embodiment, the processing module 420 is specifically used to: determine the user's facial orientation based on the coordinates of the first component and the coordinates of the second component; and determine the coordinate information of the target gaze point based on the facial orientation and spatial coordinates.

[0163] Optionally, as an embodiment, the processing module 420 is further configured to: obtain a first distance between the third component and the eye-tracking device; determine the spatial coordinates of the eye-tracking device based on measurement data from at least two positioning base stations, including: calibrating the measurement data from at least two positioning base stations based on the first distance; and determining the spatial coordinates of the eye-tracking device based on the calibrated measurement data.

[0164] Optionally, as an embodiment, the processing module 420 is further configured to: acquire a target image captured by a camera; determine a reference position of the eye-tracking device based on the target image; and perform calibration processing on the measurement data of at least two positioning base stations based on a first distance, including: performing calibration processing on the measurement data of at least two positioning base stations based on the first distance and the reference position.

[0165] Optionally, as an embodiment, the processing module 420 is specifically used to: when a first distance is detected to be less than a preset distance threshold, to perform calibration processing on the measurement data of at least two positioning base stations.

[0166] Optionally, as an embodiment, the processing module 420 is further configured to: obtain the weights of at least two positioning base stations and a third component; and determine the spatial coordinates of the eye-tracking device based on the measurement data of at least two positioning base stations, including: determining the spatial coordinates of the eye-tracking device based on the weights of at least two positioning base stations, the weight of the third component, a first distance, and the measurement data of at least two positioning base stations.

[0167] Optionally, as an embodiment, the processing module 420 is further configured to: acquire environmental information of the vehicle; when the environmental information is detected to indicate that the vehicle is in an abnormal environment, adjust the weights of at least two positioning base stations and the weight of the third component to obtain the adjusted weights of at least two positioning base stations and the adjusted weight of the third component; wherein the adjusted weights of at least two positioning base stations are less than the weights of at least two positioning base stations, and the adjusted weight of the third component is greater than the weight of the third component.

[0168] It should be noted that the control device 400 of the aforementioned vehicle is embodied in the form of a functional unit. The term "module" here can be implemented in software and / or hardware, without specific limitations.

[0169] For example, a "module" can be a software program, hardware circuit, or a combination of both that implements the above functions. Hardware circuits may include application-specific integrated circuits (ASICs), electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memory for executing one or more software or firmware programs, combined logic circuits, and / or other suitable components that support the described functions.

[0170] Therefore, the units of the various examples described in the embodiments of this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0171] Figure 5 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0172] For example, vehicle 500 includes processor 510, memory 520 and executable program code 530.

[0173] For example, vehicle 500 includes one or more processors 510 that can support the vehicle control method in the method embodiment. The processor 510 can be a general-purpose processor or a special-purpose processor. For example, processor 510 can be a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0174] For example, processor 510 can be used to control vehicle 500, execute software programs, and process data from the software programs. Vehicle 500 may also include a communication unit for receiving and transmitting signals.

[0175] For example, the vehicle 500 may include one or more memories 520 storing executable program code 530. The executable program code 530 can be run by the processor 510 to generate instructions, causing the processor 510 to execute the vehicle control method described in the above method embodiments according to the instructions. For example, the processor 510 executes the following according to the instructions: when a user's eye-tracking control command is detected, it acquires measurement data from at least two positioning base stations outside the vehicle. The measurement data includes signal propagation time, which represents the propagation time from the positioning base stations to the eye-tracking device outside the vehicle; based on the measurement data from at least two positioning base stations, it determines the spatial coordinates of the eye-tracking device; based on the spatial coordinates, it determines the coordinate information of the user's target gaze point, which is used to control the vehicle to perform an operation corresponding to the target gaze point.

[0176] Optionally, the memory 520 may also store data. Optionally, the processor 510 may also read data stored in the memory 520, which may be stored at the same memory address as the executable program code 530, or the data may be stored at a different memory address than the executable program code 530.

[0177] For example, the processor 510 and memory 520 can be configured separately or integrated together, for example, integrated on the system-on-chip (SOC) of the terminal device.

[0178] For example, the memory 520 can be used to store the relevant program of the vehicle control method provided in the embodiments of this application, and the processor 510 can be used to call the executable program code 530 stored in the memory 520 when controlling the vehicle to execute the vehicle control method of the embodiments of this application. This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle control method of any of the foregoing embodiments.

[0179] The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, Digital Video Discs (DVDs), Compact Disc Read-Only Memory (CD-ROMs), microdrives, and magneto-optical disks, read-only memory (ROMs), random access memory (RAMs), erasable programmable read-only memory (EPROMs), electrically erasable programmable read-only memory (EEPROMs), dynamic random access memory (DRAMs), video random access memory (VRAMs), flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0180] This application also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement the vehicle control method in the above embodiments.

[0181] In addition, the electronic device provided in the embodiments of this application may specifically be a chip, component or module. The electronic device may include a connected processor and a memory. The memory is used to store instructions. When the electronic device is running, the processor may call and execute the instructions to make the chip execute the vehicle control method in the above embodiments.

[0182] The vehicle, computer-readable storage medium, computer program product or chip provided in this application are all used to execute the corresponding vehicle control method provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding vehicle control method provided above, and will not be repeated here.

[0183] 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.

[0184] 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 device, 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 devices or units may be electrical, mechanical, or other forms.

[0185] 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 control method of a vehicle, characterized by, The control method includes: When a user's eye-tracking control command is detected, measurement data from at least two positioning base stations outside the vehicle is acquired. The measurement data includes signal propagation time, which represents the propagation time from the positioning base stations to the eye-tracking device outside the vehicle. Based on the measurement data from the at least two positioning base stations, the spatial coordinates of the eye-tracking device are determined; Based on the spatial coordinates, the coordinate information of the user's target gaze point is determined, and the coordinate information of the target gaze point is used to control the vehicle to perform the operation corresponding to the target gaze point.

2. The control method according to claim 1, characterized by, The control method further includes: Obtain the locations of the at least two positioning base stations; Determining the spatial coordinates of the eye-tracking device based on measurement data from the at least two positioning base stations includes: Based on the signal propagation time corresponding to the at least two positioning base stations, a time difference is determined, wherein the time difference includes the difference in signal propagation time between any two of the at least two positioning base stations; The spatial coordinates of the eye-tracking device are determined based on the location of the at least two positioning base stations and the time difference.

3. The control method according to claim 1, characterized by, The spatial coordinates include the coordinates of the first component and the second component in the eye-tracking device. Determining the coordinate information of the user's target gaze point based on the spatial coordinates includes: The user's facial orientation is determined based on the coordinates of the first component and the coordinates of the second component; Based on the facial orientation and the spatial coordinates, the coordinate information of the target gaze point is determined.

4. The control method according to claim 1, characterized by, The vehicle is equipped with a third component, the power consumption of which is lower than that of the positioning base station. The control method further includes: Obtain the first distance between the third component and the eye-tracking device; Determining the spatial coordinates of the eye-tracking device based on measurement data from the at least two positioning base stations includes: Based on the first distance, the measurement data of the at least two positioning base stations are calibrated. Based on the calibrated measurement data, the spatial coordinates of the eye-tracking device are determined.

5. The control method according to claim 4, characterized by The vehicle is equipped with a camera, and the control method further includes: Acquire the target image captured by the camera; Based on the target image, determine the reference position of the eye-tracking device; The calibration process for the measurement data of the at least two positioning base stations based on the first distance includes: The calibration process is performed on the measurement data of the at least two positioning base stations based on the first distance and the reference position.

6. The control method according to claim 4, characterized by The calibration process for the measurement data of the at least two positioning base stations based on the first distance includes: When the first distance is detected to be less than a preset distance threshold, the calibration process is performed on the measurement data of the at least two positioning base stations.

7. The control method according to any one of claims 4 to 6, characterized by, The control method further includes: Obtain the weights of the at least two positioning base stations and the third component; Determining the spatial coordinates of the eye-tracking device based on measurement data from the at least two positioning base stations includes: The spatial coordinates of the eye-tracking device are determined based on the weights of the at least two positioning base stations, the weight of the third component, the first distance, and the measurement data of the at least two positioning base stations.

8. The control method according to claim 7, characterized by, The control method further includes: Obtain the environmental information of the vehicle; When the environmental information is detected to indicate that the vehicle is in an abnormal environment, the weights of the at least two positioning base stations and the weight of the third component are adjusted to obtain the adjusted weights of the at least two positioning base stations and the adjusted weights of the third component. Wherein, the weight of the adjusted at least two positioning base stations is less than the weight of the at least two positioning base stations, and the weight of the adjusted third component is greater than the weight of the third component.

9. A control device of a vehicle characterized by comprising: The control device includes: The acquisition module is used to acquire measurement data from at least two positioning base stations outside the vehicle when a user's eye-tracking control command is detected. The measurement data includes signal propagation time, which represents the propagation time from the positioning base station to the eye-tracking device outside the vehicle. The processing module is used to determine the spatial coordinates of the eye-tracking device based on the measurement data from the at least two positioning base stations; and to determine the coordinate information of the user's target gaze point based on the spatial coordinates, wherein the coordinate information of the target gaze point is used to control the vehicle to perform an operation corresponding to the target gaze point.

10. A vehicle characterized by comprising: The vehicles include: Memory, used to store executable program code; A processor is configured to call and run the executable program code from the memory, causing the vehicle to perform the control method as described in any one of claims 1 to 8.

Images