Vehicle rearview mirror control method and device, vehicle and medium

Abstract

The invention discloses a vehicle rearview mirror control method and device, a vehicle and a medium, and relates to the technical field of automobiles. The method comprises the steps that multiple pieces of sensor information of a vehicle are acquired, first scores corresponding to the sensor information are fused, and a second score of the vehicle is obtained; turning down a rearview mirror of the vehicle from a driving angle to a parking angle in response to the condition that the second score meets a score threshold value, and continuously monitoring the current running state of the vehicle; and when the current running state is in the parking state, the rearview mirror is kept at the parking angle until the current running state is changed into the parking completion state, and the rearview mirror is restored to the driving angle from the parking angle. According to the method, the rearview mirror is controlled to turn downwards when the vehicle operation meets the preset conditions until the vehicle is parked, and then the rearview mirror is restored to the driving angle, so that it is guaranteed that the rearview mirror only conducts one-time effective turning in the whole parking process of the vehicle, motor abrasion caused by multiple times of turning can be effectively avoided, and the service life of a motor is prolonged.

Description

Technical Field

[0001] This disclosure relates to the field of automotive technology, and in particular to a method, device, vehicle, and medium for controlling a vehicle rearview mirror. Background Technology

[0002] Most cars nowadays are equipped with the function of automatically tilting down the exterior rearview mirrors when reverse gear is engaged. This function can expand the driver's downward field of vision when reversing, so as to assist the driver in parking safely. However, in actual use scenarios, drivers often cannot accurately park the vehicle in a parking space with just one gear shift. Instead, they need to shift gears multiple times or even quickly to park the vehicle in a parking space. At this time, the rearview mirror motor will rotate rapidly during the rapid gear shifting process, causing the motor to overheat and suffer damage, which will seriously affect the lifespan of the rearview mirror motor. Summary of the Invention

[0003] In view of the above problems, this disclosure provides a method, device, vehicle, and medium for controlling a vehicle rearview mirror to overcome or at least partially solve the above problems. The technical solution is as follows: A method for controlling a vehicle rearview mirror includes: acquiring multiple sensor information of the vehicle and fusing a first score corresponding to each sensor information to obtain a second score of the vehicle; responding to the second score satisfying a scoring threshold, tilting the rearview mirror of the vehicle from a driving angle to a parking angle and continuously monitoring the current operating state of the vehicle; when the current operating state is in a parking state, keeping the rearview mirror at the parking angle until the current operating state changes to parking completed, and then restoring the rearview mirror from the parking angle to the driving angle.

[0004] This disclosure provides a method for controlling a vehicle rearview mirror. Through the fusion and scoring mechanism of multiple sensor information, the vehicle's behavior is quantified to obtain a second score. Based on the score, the vehicle's parking behavior is accurately identified, providing reliable data support for reducing the number of rearview mirror flips. Subsequently, when the second score meets a threshold, a rearview mirror flip command is immediately triggered to control the mirror to flip from a driving angle to a parking angle. This eliminates response lag and improves the safety of reversing. Simultaneously, the current operating status of the vehicle is continuously monitored, providing data support for controlling the mirror flip state based on the vehicle's operating status. Later, when the vehicle is detected to be in a parking state, the rearview mirror is controlled to maintain the parking angle, preventing repeated flips. This ensures that the mirror flips only once while the vehicle is parked until parking is complete, effectively avoiding motor overheating and wear caused by frequent motor start-stop cycles, thus extending the motor's lifespan. Furthermore, when the vehicle is parked, the mirror is controlled to return to the driving angle, ensuring timely reset and not affecting normal driving, thereby guaranteeing vehicle safety.

[0005] Optionally, the first scores corresponding to each of the sensor information are fused to obtain the second score of the vehicle, including: for each of the sensor information, the following processing is performed: comparing the sensor information with the preset judgment conditions corresponding to the sensor information to obtain a comparison result; if the comparison result indicates that the sensor information meets the preset judgment conditions, a first preset value is used as the first score corresponding to the sensor information; if the comparison result indicates that the sensor information does not meet the preset judgment conditions, a second preset value is used as the first score corresponding to the sensor information, wherein the first preset value is greater than the second preset value; and the first scores corresponding to each of the sensor information are added together to obtain the second score of the vehicle.

[0006] In this embodiment, by setting exclusive preset judgment conditions for each sensor information and comparing each sensor information with these conditions, sensor information that meets the conditions can be selected to provide reliable data support for subsequent scoring. Different scores are assigned based on different comparison results, transforming sensor information into standardized scores, which improves the objectivity of vehicle scoring. Subsequently, by accumulating the scores corresponding to each sensor information, collaborative decision-making based on multi-sensor information can be achieved, avoiding decision-making errors based on single sensor information and thus improving the accuracy of decision-making. Furthermore, the system can accurately identify the timing of the vehicle's rearview mirror tilting down through the scoring mechanism, avoiding the risk of response lag and improving driving safety.

[0007] Optionally, the method further includes: changing the current operating state from parking to normal driving, and restoring the rearview mirror from the parking angle to the driving angle.

[0008] In this embodiment, when the vehicle's current operating state changes from parking to normal driving, the rearview mirror is automatically restored to the driving angle to ensure a safe field of vision when the vehicle is driving normally. This reduces the risk of the vehicle moving forward and ensures that when the user briefly switches gears to adjust the vehicle and then drives normally, the rearview mirror is restored to the driving angle rather than the parking angle, thus adapting to more vehicle scenarios and improving the stability of system control.

[0009] Optionally, the method further includes: parsing the seat information and image information of the vehicle to obtain the driver's height, and acquiring obstacle information around the vehicle; determining the driver's blind spot based on the obstacle information around the vehicle and the current flip angle of the rearview mirror; and determining the parking angle of the rearview mirror based on the driver's height and the driver's blind spot.

[0010] In this embodiment, the driver's height is obtained by parsing seat information and image information, and information on obstacles around the vehicle is acquired. This provides reliable data support for subsequent vehicle field of vision calculations. Subsequently, the driver's blind spot is calculated by analyzing obstacle information and the tilt angle of the rearview mirror. This effectively identifies the driver's blind spot within the current tilt angle of the rearview mirror, allowing for subsequent adjustment of the rearview mirror angle based on the blind spot, rather than blindly tilting it. This reduces field of vision distortion caused by excessive adjustment of the rearview mirror. Then, based on the driver's height and the blind spot, the additional angle that the rearview mirror needs to be adjusted to cover the blind spot is dynamically calculated. This ensures that the current tilt angle of the rearview mirror can effectively adapt to different drivers, avoiding the limitations of traditional fixed tilt angles. This eliminates the need for drivers to manually and repeatedly adjust the rearview mirror, reducing driving burden and ensuring the safety and comfort of reversing, thereby effectively improving the driver's driving experience.

[0011] Optionally, determining the driver's blind spot based on obstacle information around the vehicle and the current tilt angle of the rearview mirror includes: predicting the field of view of the rearview mirror based on the current tilt angle of the rearview mirror to obtain the theoretical field of view of the rearview mirror; and performing superposition analysis on the theoretical field of view of the rearview mirror and obstacle information around the vehicle to obtain the driver's blind spot.

[0012] In this embodiment, the theoretical field of view of the rearview mirror is simulated and calculated based on its current flip angle. This transforms the abstract flip angle into a calculable field of view, providing a reference for determining blind spots. Furthermore, by examining the obstacle information around the vehicle based on the theoretical field of view, the range of obstacle information identification is expanded, reducing the system's computational load. Simultaneously, by superimposing the theoretical field of view with obstacle information, blind spots during reversing are effectively identified, avoiding risks such as collisions caused by blind spots. The blind spots guide the precise flipping of the rearview mirror, ensuring that the vehicle's field of view covers the most critical and safest areas during reversing, avoiding distortion caused by excessive adjustment.

[0013] Optionally, determining the parking angle of the rearview mirror based on the driver's height and the driver's blind spot includes: mapping the driver's height to obtain the driver's line of sight height, and analyzing the driver's field of vision based on the driver's line of sight height to obtain the driver's basic field of vision range; and predicting the flip angle of the rearview mirror based on the driver's basic field of vision range and the driver's blind spot to obtain the parking angle of the rearview mirror.

[0014] In this embodiment, by mapping the driver's height, the driver's actual height can be determined to ensure that each driver's basic field of vision is adapted to that driver, avoiding the limitations of traditional fixed field of vision, and better adapting to different driver identities. Then, based on the driver's basic field of vision and blind spot, the angle adjustment amount required to cover the blind spot is calculated, and the basic field of vision and blind spot compensation amount are fused to obtain the parking angle of the rearview mirror. This ensures that the flip angle of the rearview mirror retains the driver's habitual basic field of vision and specifically compensates for the blind spot, avoiding vision distortion caused by excessive adjustment, thereby improving the driver's driving experience.

[0015] Optionally, parking includes shifting gears and completing parking preparation; continuously monitoring the current operating status of the vehicle, including: continuously acquiring sensor information of the vehicle; determining the current operating status of the vehicle as "driving" in response to the sensor information indicating that the vehicle speed is greater than or equal to a speed threshold; determining the current operating status of the vehicle as "decelerating" in response to the sensor information indicating that the vehicle speed is less than the speed threshold and the duration reaches a first duration threshold; determining the current operating status of the vehicle as "stopped" in response to the sensor information indicating that the vehicle speed is a third preset value and the range of wheel speed change is less than a preset range; The vehicle's current operating state is determined to be shifting gears when the sensor information indicates that the vehicle's gear has been switched to parking gear; the vehicle's current operating state is determined to be parking preparation completed when the sensor information indicates that the vehicle's handbrake has been released or the vehicle's seat belt has been unfastened; the vehicle's current operating state is determined to be driver preparing to leave the vehicle when the sensor information indicates that the vehicle's door handle has been activated or the vehicle's steering wheel torque is less than a torque threshold; and the vehicle's current operating state is determined to be parking completed when the sensor information indicates that the vehicle remains stationary within the parking area for a duration reaching a second duration threshold.

[0016] In this embodiment, state judgment is achieved through multi-sensor information, which avoids single sensor failure or false triggering, thereby improving the accuracy of vehicle operating status recognition. It can effectively solve problems such as "rearview mirrors accidentally resetting due to brief gear shifts" and "resetting the rearview mirrors prematurely before parking." By combining multi-sensor information to accurately identify the vehicle's operating status, the vehicle's parking status can be dynamically tracked. Based on different parking statuses, the rearview mirrors' flipping behavior can be accurately controlled, providing a reference for ensuring that the rearview mirrors only flip once during the entire parking phase. This reduces the number of motor start-stop cycles, thereby greatly extending the motor's lifespan. At the same time, it ensures that the rearview mirrors respond without delay, improving the safety and convenience of reversing the vehicle and reducing the driver's operational burden.

[0017] Optionally, continuously monitoring the current operating status of the vehicle includes: continuously acquiring sensor information of the vehicle; extracting features from the sensor information of the vehicle to obtain a first feature of the vehicle; and predicting the state of the vehicle based on the first feature to obtain the current operating status of the vehicle.

[0018] In this embodiment, by continuously collecting data from multiple vehicle system sensors, the system can ensure full-cycle perception of the driving scenario, avoiding control logic failures caused by single signals. It can promptly capture changes in the vehicle's dynamic scene and extract features from the collected sensor data to obtain key features related to the vehicle's operating state. This filters out invalid data and noise, reducing the computational load and interference for subsequent state prediction and providing reliable data input for subsequent state prediction. Subsequently, based on the extracted features, the vehicle's current operating state is predicted, providing a basis for judgment on the subsequent rearview mirror's action execution logic. This improves the safety and convenience of reversing the vehicle and reduces the driver's operational burden.

[0019] A control device for a vehicle rearview mirror, comprising: an acquisition module for acquiring multiple sensor information of the vehicle and determining a second score of the vehicle based on a first score corresponding to each sensor information; a first control module for, in response to the second score satisfying a scoring threshold, tilting the rearview mirror of the vehicle from a driving angle to a parking angle and continuously monitoring the current operating state of the vehicle; and a second control module for, when the current operating state is in a parking state, keeping the rearview mirror at the parking angle until the current operating state changes to parking completion, and then restoring the rearview mirror from the parking angle to the driving angle.

[0020] A vehicle includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform: acquiring multiple sensor information of the vehicle, and determining a second score of the vehicle based on a first score corresponding to each of the sensor information; in response to the second score satisfying a score threshold, tilting the rearview mirror of the vehicle from a driving angle to a parking angle, and continuously monitoring the current operating state of the vehicle; when the current operating state is in a parking state, maintaining the rearview mirror at the parking angle until the current operating state changes to parking completed, and restoring the rearview mirror from the parking angle to the driving angle.

[0021] A computer-readable storage medium storing computer-executable instructions, the computer-executable instructions being configured to: acquire multiple sensor information of a vehicle, and determine a second score of the vehicle based on a first score corresponding to each of the sensor information; in response to the second score satisfying a scoring threshold, tilt the rearview mirror of the vehicle from a driving angle to a parking angle, and continuously monitor the current operating state of the vehicle; when the current operating state is in a parking state, keep the rearview mirror at the parking angle until the current operating state changes to parking completed, and restore the rearview mirror from the parking angle to the driving angle. Attached Figure Description

[0022] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are used to explain the disclosure, but do not constitute an undue limitation of the disclosure. In the drawings: Figure 1 This is a schematic flowchart of a vehicle rearview mirror control method provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this disclosure. Detailed Implementation

[0023] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0024] It is understood that in the embodiments of this disclosure, data related to user information (such as driver height) is involved. When the embodiments of this disclosure are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with relevant laws, regulations and standards.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The terminology used herein is for the purpose of describing embodiments of this disclosure only and is not intended to be limiting of this disclosure.

[0026] In the following description, the terms “first, second, ...” are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that “first, second, ...” may be interchanged in a specific order or sequence where permitted, so that the embodiments of this disclosure described herein can be implemented in an order other than that illustrated or described herein.

[0027] Most cars nowadays are equipped with the function of automatically tilting down the exterior rearview mirrors when reverse gear is engaged. This function can expand the driver's downward field of vision when reversing, so as to assist the driver in parking safely. However, in actual use scenarios, drivers often cannot accurately park the vehicle in a parking space with just one gear shift. Instead, they need to shift gears multiple times or even quickly to park the vehicle in a parking space. At this time, the rearview mirror motor will rotate rapidly during the rapid gear shifting process, causing the motor to overheat and suffer damage, which will seriously affect the lifespan of the rearview mirror motor.

[0028] In existing technologies, the above problems are usually solved by delay triggering and state holding mechanisms. However, although the delay triggering mechanism can avoid accidental triggering of the rearview mirror to tilt down, in scenarios of rapid and frequent gear shifting, it may cause the rearview mirror tilting command to not be executed in time, thereby increasing driving risks. Although the state holding mechanism can reduce the number of motor start-stop cycles to a certain extent, if the driver manually adjusts the rearview mirror during reversing, the timer reset or interruption may cause confusion, or even cause the motor to stall.

[0029] Therefore, this disclosure provides a method for controlling a vehicle rearview mirror. Figure 1 This is a flowchart illustrating a vehicle rearview mirror control method provided in an embodiment of this disclosure. The method can be applied to different types of vehicles, and the process can be executed by a computing device in the corresponding field (e.g., a controller installed in the vehicle, a vehicle-mounted system, or a server located in the cloud). Certain input parameters or intermediate results in the process can be manually adjusted to help improve accuracy.

[0030] This disclosure provides a method for controlling a vehicle rearview mirror. It should be noted that the executing entity in these embodiments can be a server or any terminal device with data processing capabilities. For example, the server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The terminal device can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, in-vehicle terminal, etc., but is not limited to these.

[0031] like Figure 1 As shown, this disclosure provides a method for controlling a vehicle rearview mirror, including: Step 101: Obtain information from multiple vehicle sensors.

[0032] It should be noted that multiple sensor information can come from multiple sensors of the same type, such as wheel speed sensors from different wheels; or from multiple sensors of different types, such as wheel speed sensors, handbrake sensors, dynamic stability sensors, engine sensors, seat pressure sensors, seat belt sensors, etc., without specific limitations.

[0033] As an example, suppose the sensors include a handbrake sensor, accelerator sensor, seat pressure sensor, seat belt sensor, and engine sensor. By collecting data from each of the vehicle's sensors, multiple sensor information can be obtained. For example, the handbrake sensor transmits information that the handbrake has been released, the accelerator sensor transmits information that the accelerator has been pressed, the seat pressure sensor transmits information that the seat is occupied, the seat belt sensor transmits information that the seat belt is fastened, and the engine sensor transmits information that the engine speed is 1000 rpm.

[0034] Step 102: Fuse the first scores corresponding to each of the sensor information to obtain the second score of the vehicle.

[0035] It should be noted that the first score is used to characterize the contribution of each sensor's information to the vehicle's reversing intention. For example, the first score corresponding to the gear position sensor information "R gear" can be 5, the first score corresponding to the gear position sensor information "D gear" can be 0, the first score corresponding to the handbrake sensor information "handbrake released" can be 5, and the first score corresponding to the handbrake sensor information "handbrake lifted" can be 0. The second score characterizes the comprehensive score of whether the vehicle's current behavior is a true reversing action, and can be used to determine whether the rearview mirror tilting down is triggered. The method of determining the second score based on the first score can be implemented by simple accumulation calculation, weighted summation, or deep learning network, without specific limitations here.

[0036] In some embodiments, step 102 described above can be implemented as follows: for each piece of sensor information, the following processing is performed: the sensor information is compared with a preset judgment condition corresponding to the sensor information to obtain a comparison result; if the comparison result indicates that the sensor information meets the preset judgment condition, a first preset value is used as a first score corresponding to the sensor information; if the comparison result indicates that the sensor information does not meet the preset judgment condition, a second preset value is used as a first score corresponding to the sensor information, wherein the first preset value is greater than the second preset value; the first scores corresponding to each piece of sensor information are added together to obtain a second score for the vehicle.

[0037] Thus, by setting specific preset judgment conditions for each sensor information and comparing each sensor information with these conditions, sensor information that meets the preset judgment conditions can be selected to provide reliable data support for subsequent scoring. Different scores are assigned based on different comparison results, transforming sensor information into standardized scores, which can improve the objectivity of vehicle scoring. Subsequently, by accumulating the scores corresponding to each sensor information, collaborative decision-making based on multi-sensor information can be achieved, avoiding decision-making errors based on single sensor information, thereby improving the accuracy of decision-making. Furthermore, the system can accurately identify the timing of the vehicle's rearview mirror tilting down through the scoring mechanism, avoiding the risk of response lag and improving driving safety.

[0038] It should be noted that the first preset value and the second preset value can refer to a certain preset value, for example, the first preset value is 5 and the second preset value is 0.

[0039] As an example, suppose the sensors include wheel speed sensors, handbrake sensors, dynamic stability sensors, engine sensors, and seat pressure sensors. The first preset value is 5, and the second preset value is 0. The wheel speed sensor transmits the sensor information "vehicle speed is 3 km / h," with the corresponding preset judgment condition being "vehicle speed less than 5 km / h." The handbrake sensor transmits the sensor information "handbrake released," with the corresponding preset judgment condition being "handbrake released." The dynamic stability sensor transmits the sensor information "pitch angle change 0.3°," with the corresponding preset judgment condition being "pitch angle / roll angle change > 0.5°." The engine sensor transmits the sensor information "engine speed is 400 rpm," with the corresponding preset judgment condition being "engine speed greater than 800 rpm." The seat pressure sensor transmits the sensor information "seat pressure is..." The preset judgment condition for "occupancy" is "seat is occupied". By comparing the information of each sensor with the preset judgment condition corresponding to the sensor, the comparison result of each sensor information can be obtained as follows: "Wheel speed sensor: meets preset judgment condition, handbrake sensor: meets preset judgment condition, dynamic stability sensor: does not meet preset judgment condition, engine sensor: does not meet preset judgment condition, seat pressure sensor: meets preset judgment condition". According to the comparison result, the first score corresponding to the wheel speed sensor information is 5, the first score corresponding to the handbrake sensor information is 5, the first score corresponding to the dynamic stability sensor is 0, the first score corresponding to the engine sensor is 0, and the first score corresponding to the seat pressure sensor is 5. Finally, the first scores corresponding to each sensor information are added together to obtain the second score of the vehicle as 15.

[0040] Step 103: In response to the second score meeting the scoring threshold, the rearview mirror of the vehicle is tilted down from the driving angle to the parking angle.

[0041] It should be noted that the driving angle refers to the tilt angle of the rearview mirror when the vehicle is driving normally, and the parking angle refers to the tilt angle of the rearview mirror when the vehicle is parked. The driving angle and parking angle can be fixed angle values ​​or dynamically determined according to the current operating scenario of the vehicle. No specific limitation is made here.

[0042] Continuing with the example above, the vehicle's second score is calculated to be 15. Assuming the score threshold is 10, meaning the second score meets the score threshold, a control command is sent to the vehicle's rearview mirror to control the mirror to flip down from the driving angle to the parking angle, so that the rearview mirror can better assist the vehicle in parking.

[0043] In some embodiments, before performing step 103, the following processes may also be performed: parsing the seat information and image information of the vehicle to obtain the driver's height and acquiring obstacle information around the vehicle; determining the driver's blind spot based on the obstacle information around the vehicle and the current flip angle of the rearview mirror; and determining the parking angle of the rearview mirror based on the driver's height and the driver's blind spot.

[0044] In this way, by analyzing seat information and image information to obtain the driver's height and acquiring information about obstacles around the vehicle, reliable data support can be provided for subsequent vehicle field of vision calculations. Subsequently, by analyzing obstacle information and the tilt angle of the rearview mirror, the driver's blind spot can be calculated. This can effectively determine the driver's blind spot within the current tilt angle of the rearview mirror, allowing for subsequent adjustment of the rearview mirror angle based on the blind spot, rather than blindly tilting it. This reduces the field of vision distortion caused by excessive adjustment of the rearview mirror. Then, based on the driver's height and the blind spot, the additional angle that the rearview mirror needs to be adjusted to cover the blind spot is dynamically calculated. This ensures that the current tilt angle of the rearview mirror can effectively adapt to different drivers, avoiding the limitations of traditional fixed tilt angles. This eliminates the need for drivers to manually and repeatedly adjust the rearview mirror, reducing driving burden and ensuring the safety and comfort of reversing, thereby effectively improving the driver's driving experience.

[0045] As an example, assuming the vehicle's seat information shows the seat rail is in its forward position, the corresponding driver height range is 1.5m-1.7m. The image information is the driver's head information captured by the camera. Based on the driver's head information and seat height, the driver's eye level is estimated to be 65cm above the seat surface. By combining the seat information and eye level information, the driver's height can be approximated as 1.6m. Subsequently, obstacle information is obtained through surround-view cameras and ultrasonic radar. For example, the surround-view camera identifies a 30cm obstacle 1 meter to the left rear. The stone block (coordinates: 1m to the left rear, 30cm above the ground) is confirmed by ultrasonic radar to be 1.1m away, consistent with the camera data. At the same time, based on the current rotation angle of the rearview mirror (e.g., 0° horizontal, 0° vertical), the current field of view can be obtained through an optical model. By superimposing the obstacle coordinates with the current field of view, the driver's blind spot can be obtained. For example, the stone block located 1m to the left rear and 30cm above the ground is in the driver's blind spot. Then, based on the driver's height and the driver's blind spot, the rotation angle required for the rearview mirror to cover the blind spot is calculated, which gives the parking angle of the rearview mirror.

[0046] In some embodiments, the above-mentioned determination of the driver's blind spot based on obstacle information around the vehicle and the current flip angle of the rearview mirror can be achieved by: predicting the field of view of the rearview mirror based on the current flip angle of the rearview mirror to obtain the theoretical field of view of the rearview mirror; and performing superimposed analysis on the theoretical field of view of the rearview mirror and obstacle information around the vehicle to obtain the driver's blind spot.

[0047] In this way, by simulating and calculating the theoretical field of view of the rearview mirror based on its current flip angle, the abstract flip angle is transformed into a calculable field of view. This provides a reference for determining blind spots and allows for the identification of obstacles around the vehicle based on the theoretical field of view. This reduces the computational load on the system. Furthermore, by superimposing the theoretical field of view with obstacle information, blind spots during reversing can be effectively identified to avoid collisions caused by blind spots. The blind spots then guide the precise flipping of the rearview mirror to ensure that the vehicle's field of view covers the most critical and safest areas while reversing, avoiding distortion of the field of view caused by over-adjustment.

[0048] As an example, assuming the current driving angle of the rearview mirror (e.g., 0° horizontally, 0° vertically), combined with an optical model (e.g., mirror curvature, installation position), the theoretical field of view that the driver can observe through the rearview mirror is predicted to be: "Horizontal field of view: extending 30° to the left and right from the vehicle's centerline (i.e., horizontal -30° to +30°, covering the rear fan-shaped area); Vertical field of view: extending 10° downwards and 5° upwards from the vehicle's horizontal line (i.e., vertical -10° to +5°, covering low curbs and higher obstacles)." Simultaneously, based on obstacle information obtained from the surround-view camera and ultrasonic radar, "The surround-view camera identifies an SUV 1.5m to the right rear, with coordinates '1.5m to the right rear, height 1.7m'; the ultrasonic radar confirms a distance of 1.6m." Then, superimposing the SUV's coordinates with the theoretical field of view reveals that the SUV's height of 1.7m and distance of 1.5m will obstruct the theoretical field of view from "vertical -5° to 0°, horizontal -20° to +5°." The "-10°" area is used to obtain the driver's blind spot, which is the "vertical -5°~0°, horizontal -20°~-10°" area in the theoretical field of vision.

[0049] In some embodiments, the above-mentioned determination of the parking angle of the rearview mirror based on the driver's height and the driver's blind spot can be achieved in the following way: mapping the driver's height to obtain the driver's line of sight height, and performing a field of vision analysis on the driver based on the driver's line of sight height to obtain the driver's basic field of vision range; and predicting the flip angle of the rearview mirror based on the driver's basic field of vision range and the driver's blind spot to obtain the parking angle of the rearview mirror.

[0050] In this way, by mapping the driver's height, the driver's actual height can be determined to ensure that each driver's basic field of vision is adapted to that driver, avoiding the limitations of traditional fixed field of vision, and better adapting to different driver identities. Then, based on the driver's basic field of vision and blind spot, the angle adjustment required to cover the blind spot is calculated, and the basic field of vision and blind spot compensation are fused to obtain the parking angle of the rearview mirror. This ensures that the rearview mirror's flip angle retains the driver's habitual basic field of vision while specifically compensating for blind spots, avoiding vision distortion caused by excessive adjustment, and thus improving the driver's driving experience.

[0051] As an example, assuming the driver's height is calculated to be 1.9m, and the eye level mapping shows the driver's eye level to be 90cm, then based on this 90cm eye level, using an ergonomic model, the driver's basic field of vision can be calculated as follows: "Horizontal basic field of vision extends 35° to the left and right, and vertical basic field of vision extends 8° downwards from the horizontal line." Then, based on the driver's basic field of vision and blind spots (e.g., a pedestrian 2 meters to the right rear, coordinates: horizontal -18°, vertical -3°), through analysis and comparison, the basic field of vision range (horizontal -35°) is determined to be... The basic field of view (BVR) includes the pedestrian's horizontal position (-18°) within the range of 0° to +35° and vertical position (-8° to 0°). However, the vertical position (-3°) is at the edge of the basic field of view. To ensure that the pedestrian is in the "center of clear vision," the basic field of view needs to be fine-tuned. By analyzing that the basic field of view already covers the pedestrian's horizontal position (-18°), no adjustment is needed. The pedestrian is adjusted from the "edge of the basic field of view" (vertical -3°) to the "center of vision" (vertical -5°), requiring an additional downward compensation of 2°. Finally, the basic field of view and blind spot compensation are fused to obtain the parking angle of the rearview mirror, such as "0° horizontal and 10° vertical."

[0052] Step 104: Continuously monitor the current operating status of the vehicle.

[0053] In some embodiments, parking includes shifting gears and completing parking preparation; step 104 described above can be implemented as follows: continuously acquiring sensor information of the vehicle; in response to the sensor information indicating that the vehicle speed is greater than or equal to a speed threshold, determining that the current operating state of the vehicle is driving; in response to the sensor information indicating that the vehicle speed is less than the speed threshold and the duration reaches a first duration threshold, determining that the current operating state of the vehicle is decelerating; in response to the sensor information indicating that the vehicle speed is a third preset value and the range of wheel speed change of the vehicle is less than a preset range, determining that the current operating state of the vehicle is stopped. In response to the sensor information indicating that the vehicle's gear has been switched to parking gear, the current operating state of the vehicle is determined to be gear shifting; in response to the sensor information indicating that the vehicle's handbrake has been released or the vehicle's seatbelt has been unfastened, the current operating state of the vehicle is determined to be parking preparation completed; in response to the sensor information indicating that the vehicle's door handle is activated or the vehicle's steering wheel torque is less than a torque threshold, the current operating state of the vehicle is determined to be driver preparing to leave the vehicle; in response to the sensor information indicating that the vehicle remains stationary within the parking area for a duration reaching a second duration threshold, the current operating state of the vehicle is determined to be parking completed.

[0054] In this way, by using information from multiple sensors to determine the vehicle's status, it is possible to avoid single sensor failures or false triggers, thereby improving the accuracy of vehicle operating status recognition. This can effectively solve problems such as "rearview mirrors accidentally resetting due to brief gear shifts" and "resetting the rearview mirrors prematurely before parking." By combining information from multiple sensors to accurately identify the vehicle's operating status, the vehicle's parking status can be dynamically tracked. Based on different parking statuses, the rearview mirrors' flipping behavior can be accurately controlled, providing a reference for ensuring that the rearview mirrors only flip once during the entire parking phase. This reduces the number of motor start-stop cycles, thus greatly extending the motor's lifespan. At the same time, it ensures that the rearview mirrors respond without delay, improving the safety and convenience of reversing the vehicle and reducing the driver's workload.

[0055] As an example, suppose that during vehicle operation, when the wheel speed sensor detects a vehicle speed of 20 km / h, which is greater than the speed threshold of 5 km / h, the system determines that the vehicle's current operating state is "driving". When the wheel speed sensor detects a decrease in vehicle speed to 4 km / h, which is less than the speed threshold of 5 km / h (i.e., the speed threshold) and the duration is 1.5 seconds, which is greater than 1 second (the first duration threshold), the system determines that the vehicle's current operating state is "decelerating". The vehicle continues to decelerate, and when the wheel speed sensor detects a speed of 0 (i.e., the third preset value) and the range of wheel speed change is less than 1 km / h (i.e., the preset range), the system determines that the vehicle's current operating state is "stopped". Then, when the system detects that the vehicle's gear has shifted from D to P (i.e., the parking gear), the system determines that the vehicle's current operating state is "gear shifting". Afterwards, when the system detects that the handbrake has been released or the seatbelt has been unfastened, the system determines that the vehicle's current operating state is "parking preparation complete". Finally, when the system detects that the door handle is activated or the driver's hands have left the steering wheel (i.e., the steering wheel torque is less than the torque threshold, for example, a torque threshold of 5 km / h), the system determines that the vehicle's current operating state is "parking preparation complete". The system determines the current operating status of the vehicle as the driver is preparing to leave the vehicle (N·m). Finally, when the vehicle's surround view camera detects that the vehicle has completely entered the parallel parking space (i.e., within the parking area) and the vehicle remains stationary for 10 seconds (i.e., the second duration threshold), the system determines the current operating status of the vehicle as parking completed.

[0056] In some embodiments, step 104 described above can be implemented by: continuously acquiring sensor information of the vehicle; extracting features from the sensor information of the vehicle to obtain a first feature of the vehicle; and predicting the state of the vehicle based on the first feature to obtain the current operating state of the vehicle.

[0057] In this way, by continuously collecting data from multiple vehicle system sensors, the system can ensure full-cycle perception of the driving scenario, avoid control logic failures caused by single signals, and promptly capture changes in the vehicle's dynamic scene. Simultaneously, feature extraction is performed on the collected sensor data to obtain key features related to the vehicle's operating state, filtering out invalid data and noise. This reduces the computational load and interference in subsequent state prediction, providing reliable data input for future predictions. Subsequently, vehicle state prediction is performed based on the extracted features to obtain the vehicle's current operating state, thus providing a basis for the subsequent execution logic of the rearview mirror's actions. This improves the safety and convenience of reversing the vehicle and reduces the driver's operational burden.

[0058] As an example, assuming we continuously acquire sensor information from a vehicle, and perform feature extraction on this sensor information, we can obtain the vehicle's first feature. Then, the first feature The vehicle state prediction model is input into the training model for prediction, and the predicted probabilities of the vehicle corresponding to different operating states can be output. For example, driving: 0.01, decelerating: 0.82, stopped: 0.07, shifting gears: 0.01, preparing to stop: 0.03, driver preparing to leave the vehicle: 0.04, stopping completed: 0.02. By analysis and comparison, it can be determined that the current operating state of the vehicle is decelerating.

[0059] In some embodiments, before performing the feature extraction on the vehicle's sensor information to obtain the vehicle's first feature as described above, the following processing may also be performed: performing feature extraction on the vehicle's historical sensor information to obtain the vehicle's second feature; using an initialized vehicle state prediction model, predicting the vehicle's state based on the second feature to obtain the vehicle's current predicted operating state; determining the model loss based on the difference between the vehicle's current predicted operating state and the reference operating state corresponding to the historical sensor information, and updating the initialized vehicle state prediction model based on the model loss to obtain the trained vehicle state prediction model.

[0060] In this way, by extracting features from historical sensor information, irrelevant data and noise can be filtered out, providing clean training data for model training. Subsequently, through model training, a deep relationship can be established between sensor information and vehicle operating status, thereby reducing the complexity of subsequent judgments on vehicle operating status and accurately identifying vehicle operating status, reducing misjudgments of vehicle operating status.

[0061] It should be noted that the model loss can be calculated using various common loss functions, such as cross-entropy loss function and log loss function, without being specifically limited here.

[0062] As an example, suppose we acquire a large amount of historical sensor information and label each piece of historical sensor information with a tag representing the actual operating state of the vehicle corresponding to that historical sensor information. First, we extract features from the historical sensor information to obtain the vehicle's second feature. Subsequently, based on the second feature By performing state prediction, the predicted operating state of the vehicle can be obtained. For example, the predicted operating state of the vehicle is: Driving: 0.01, Decelerating: 0.82, Stopped: 0.07, Gear Shifting: 0.01, Parking Preparation Completed: 0.03, Driver Preparing to Exit: 0.04, Parking Completed: 0.02; The actual operating state of the vehicle is: Driving: 0, Decelerating: 1, Stopped: 0, Gear Shifting: 0, Parking Preparation Completed: 0, Driver Preparing to Exit: 0, Parking Completed: 0; Then, based on the predicted operating state... Compared with the actual running status The difference between them, calculate the model loss Taking the cross-entropy loss function as an example, the model loss can be calculated using formula (1). Finally, the model parameters are updated by backpropagation based on the model loss, thus obtaining the trained rating prediction model.

[0063] (1) Where N represents the number of vehicle operating states. Let be the predicted probability of the operating state of the i-th vehicle. Let be the true probability of the operating state of the i-th vehicle.

[0064] Here's an explanation of backpropagation: Historical sensor information is input into the input layer of a neural network model (vehicle state prediction model), passes through the hidden layer, and finally reaches the output layer to output the result. This is the forward propagation process of the neural network model. Since there is an error between the output result of the neural network model and the actual result, the error between the calculated result and the actual value is propagated back from the output layer to the hidden layer until it reaches the input layer. During the backpropagation process, the values ​​of the model parameters are adjusted according to the error. This process is iterated until convergence.

[0065] Taking the cross-entropy loss function in this embodiment as an example, the server determines the model loss based on the cross-entropy loss function, backpropagates the model loss from the output layer of the scoring prediction model, and backpropagates the model loss layer by layer. When the model loss reaches each layer, the gradient (that is, the partial derivative of the cross-entropy loss function with respect to the parameters of each layer) is solved in combination with the propagated model loss, and the corresponding gradient value of the parameters of each layer is updated.

[0066] In some embodiments, after step 104, the following process may also be performed: when the current operating state changes from parking to normal driving, the rearview mirror is restored from the parking angle to the driving angle.

[0067] Thus, when the vehicle's current operating state changes from parking to normal driving, the rearview mirrors are automatically restored to the driving angle to ensure a safe field of vision when the vehicle is driving normally. This reduces the risk of the vehicle moving forward and ensures that when the user briefly shifts gears to adjust the vehicle and then drives normally, the rearview mirrors are restored to the driving angle rather than the parking angle, thereby adapting to more vehicle scenarios and improving the stability of system control.

[0068] As an example, suppose that when a vehicle is briefly stopped, the rearview mirror tilts down from the driving angle to the parking angle according to the vehicle's operating status. When the vehicle's operating status is detected to change from parking to normal driving, the rearview mirror is restored from the parking angle to the driving angle.

[0069] Step 105: When the current operating state is in a parking state, keep the rearview mirror at the parking angle until the current operating state changes to parking completed, and then restore the rearview mirror from the parking angle to the driving angle.

[0070] As an example, when the driver engages reverse gear (R), and multiple sensor features (e.g., gear is R, handbrake is released, and wheel speed is greater than or equal to 5 km / h) meet the scoring threshold, the rearview mirror is triggered to tilt from the driving angle (e.g., 0° horizontally, 0° vertically) to the parking angle (e.g., -5° horizontally, 10° vertically). By continuously acquiring sensor information, when the system determines that the current operating state is parking, the rearview mirror maintains the parking angle regardless of how the driver switches gears (e.g., "R→D→R" to adjust the parking position) and does not repeat the tilting action. When the system detects that the current operating state of the vehicle has changed to parking completed, it sends a recovery command to the rearview mirror, controlling the rearview mirror to return from the parking angle (e.g., -5° horizontally, 10° vertically) to the driving angle (e.g., 0° horizontally, 0° vertically).

[0071] The following will describe an exemplary application of the embodiments of this disclosure in a practical application scenario.

[0072] Most cars nowadays are equipped with the function of automatically tilting down the exterior rearview mirrors when reverse gear is engaged. This function can expand the driver's downward field of vision when reversing, so as to assist the driver in parking safely. However, in actual use scenarios, drivers often cannot accurately park the vehicle in a parking space with just one gear shift. Instead, they need to shift gears multiple times or even quickly to park the vehicle in a parking space. At this time, the rearview mirror motor will rotate rapidly during the rapid gear shifting process, causing the motor to overheat and suffer damage, which will seriously affect the lifespan of the rearview mirror motor.

[0073] In existing technologies, the above problems are usually solved by delay triggering and state holding mechanisms. However, although the delay triggering mechanism can avoid accidental triggering of the rearview mirror to tilt down, in scenarios of rapid and frequent gear shifting, it may cause the rearview mirror tilting command to not be executed in time, thereby increasing driving risks. Although the state holding mechanism can reduce the number of motor start-stop cycles to a certain extent, if the driver manually adjusts the rearview mirror during reversing, the timer reset or interruption may cause confusion, or even cause the motor to stall.

[0074] Therefore, this disclosure provides a method for controlling a vehicle rearview mirror. It can use vehicle parameters collected by sensors such as radar, camera, transmission, engine, steering wheel, and seat that are present in the vehicle, and combine them with a parking behavior detection algorithm to accurately identify the complete sequence of user behavior when parking, so as to control the rearview mirror to flip outward only once during the reversing process, thus avoiding motor wear.

[0075] In some embodiments, refer to Table 1, which is a reference table of sensor types, corresponding parameter ranges, and trust levels provided in this disclosure. According to Table 1, by acquiring information from different types of sensors, when the sensor information simultaneously meets the value ranges of parameters A and B, the trust level is increased by 5. Here, the trust level can be appropriately increased or decreased according to the importance of the data provided by the sensor. Table 1 is only for reference. When the calculated cumulative trust level reaches 50 or is greater than 50, it is determined that the current driver has the intention to reverse. At this time, the system sends a tilt command to the vehicle's rearview mirror to control the vehicle's rearview mirror to tilt down to the parking angle.

[0076] Table 1. Reference Table of Sensor Types, Corresponding Parameter Ranges, and Confidence Levels

[0077] In some embodiments, when there is an intention to reverse and the rearview mirror has been tilted down, if it is detected that the handbrake is not engaged, the gear is switched from R to D, all seat belts are closed, the wheel speed is greater than or equal to 10 km / h, the driver's door is open, and the driver's view is restored to the driving view, it is determined that the vehicle has only stopped briefly, and a restoration command is sent to the vehicle's rearview mirror to restore the rearview mirror to the driving angle.

[0078] In some embodiments, the multimodal fusion decision algorithm determines that the user intends to reverse by uploading vehicle status data from vehicle sensors. It then controls the rearview mirrors to tilt down to the parking angle. Throughout the reversing process, whether it's a long reversing session or multiple frequent parking maneuvers, the following states need to be collected in real time: wheel speed changes from ≥5 km / h to 0, gear changes from non-P to P, handbrake is engaged, engine has no idle speed, driver's hands are off the steering wheel and seatbelt is unfastened. After the ultrasonic radar and surround-view camera determine that the vehicle has entered the parking space or completed the parking action using the parking behavior monitoring algorithm, the rearview mirrors are controlled to return to the driving angle. This achieves the effect of the rearview mirrors tilting down only once during the entire parking process, greatly reducing unnecessary wear on the rearview mirror motor and improving product lifespan and user experience.

[0079] Here, if the driver manually adjusts the rearview mirror's tilt angle when it tilts down, the angle adjusted by the driver is used as the parking angle, and after parking, the rearview mirror is controlled to return to the driving angle.

[0080] In some embodiments, raw data is collected from various vehicle sensors, including wheel speed sensors, transmission sensors, cameras, and radar. This data needs to be preprocessed, including data cleaning, outlier filtering, and timestamp alignment, to ensure data real-time performance and prevent the system from making incorrect judgments. When the wheel speed sensor detects a vehicle speed of 20 km / h, which is greater than the vehicle speed threshold of 5 km / h, the system determines that the vehicle's current operating state is driving. When the wheel speed sensor detects a vehicle speed decrease to 4 km / h, which is less than the vehicle speed threshold of 5 km / h (i.e., the vehicle speed threshold) and the duration is greater than 1 second (the first duration threshold) for 1.5 seconds, the system determines that the vehicle's current operating state is deceleration. The system first accelerates the vehicle's speed; then the vehicle continues to decelerate. When the wheel speed sensor detects a speed of 0 (the third preset value) and the wheel speed variation is less than 1 km / h (the preset range), the system determines the vehicle's current operating state as stopped. Next, when the system detects the vehicle shifting from D to P (parking gear), it determines the vehicle's current operating state as shifting gears. Then, when the system detects the handbrake has been released or the seatbelt has been unfastened, it determines the vehicle's current operating state as parking preparation complete. Then, when the system detects the door handles being activated or the driver's hands leaving the steering wheel (i.e., steering wheel torque is less than a torque threshold, for example, 5 N·m), it determines the vehicle's current operating state as the driver preparing to exit. Finally, when the system detects the vehicle's surround-view camera recognizing it as fully entering the parallel parking space (i.e., within the parking area) and remaining stationary for 10 seconds (the second duration threshold), it determines the vehicle's current operating state as parking complete. By fusing the features extracted from each sensor through the above judgment logic, the system accurately identifies the entire parking process, thereby precisely controlling the vehicle's rearview mirror rotation.

[0081] In some embodiments, when the vehicle speed drops from the normal driving speed to below 5 km / h and the wheel speed sensor data continues to decrease, the vehicle's current operating state is determined to change from driving to decelerating, with a reputation score of 20. When the vehicle speed reaches zero and the wheel speed sensor reading is 0 and remains stable, the vehicle's current operating state is determined to change from decelerating to stopping, with a reputation score of 20. When the transmission shifts from driving gear to P gear, the vehicle's current operating state is determined to change from stopping to gear shifting, with a reputation score of 20. When the vehicle's handbrake is engaged or the seatbelt is unfastened, the vehicle's current operating state is determined to change from gear shifting to parking preparation completed, with a reputation score of 10. When the vehicle's door handle is triggered or the steering wheel is fully released, the vehicle's current operating state is determined to change from parking preparation completed to driver preparing to leave the vehicle, with a reputation score of 10. When the vehicle's surround view camera determines that the vehicle is completely stationary and remains stationary for 10 seconds, the vehicle's current operating state is determined to change from driver preparing to leave the vehicle to parking completed, with a reputation score of 20. By accumulating and calculating the vehicle's credit score, when the credit score is greater than 90, it is determined that the driver has completed the task by stopping the vehicle, and at this time the rearview mirror is controlled to return to the driving angle.

[0082] In some embodiments, the parking angle of the vehicle's rearview mirror can be calculated using an intelligent adjustment algorithm. This algorithm estimates the driver's height based on seat position and in-vehicle sensors, and comprehensively detects and analyzes the distribution of obstacles around the vehicle using a sensor system. Subsequently, based on the obstacle distribution, it analyzes the blind spots under the current rearview mirror setting, marking key blind spots. It also assesses and labels the risk levels of different blind spots. Then, based on the driver's height and the blind spot analysis results, it calculates the ideal rearview mirror field of view requirement. This involves calculating the driver's line of sight height and the driver's basic field of view based on that height. By overlaying the blind spot range and the driver's basic field of view, it calculates the compensation angle of the rearview mirror, balancing the basic field of view requirement with the blind spot compensation requirement to determine the optimal rearview mirror angle. Finally, based on the calculated final rearview mirror angle, it controls the rearview mirror to tilt downwards to better adapt to the current driver, effectively improving the driving experience.

[0083] The following description continues to illustrate the exemplary structure of the vehicle rearview mirror control device provided in the embodiments of this disclosure as a software module. In some embodiments, the software module in the vehicle rearview mirror control device may include: an acquisition module, a first control module, and a second control module.

[0084] An acquisition module is used to acquire multiple sensor information of the vehicle and fuse the first score corresponding to each sensor information to obtain a second score of the vehicle; a first control module is used to, in response to the second score meeting the scoring threshold, tilt the rearview mirror of the vehicle from the driving angle to the parking angle and continuously monitor the current operating status of the vehicle; a second control module is used to, when the current operating status is parking, keep the rearview mirror at the parking angle until the current operating status changes to parking completed, and then restore the rearview mirror from the parking angle to the driving angle.

[0085] In some embodiments, the acquisition module is further configured to perform the following processing for each piece of sensor information: compare the sensor information with a preset judgment condition corresponding to the sensor information to obtain a comparison result; if the comparison result indicates that the sensor information meets the preset judgment condition, use a first preset value as a first score corresponding to the sensor information; if the comparison result indicates that the sensor information does not meet the preset judgment condition, use a second preset value as a first score corresponding to the sensor information, wherein the first preset value is greater than the second preset value; and add the first scores corresponding to each piece of sensor information to obtain a second score for the vehicle.

[0086] In some embodiments, the control device for the vehicle rearview mirror further includes a third control module.

[0087] The third control module is used to change the current operating state from parking to normal driving and restore the rearview mirror from the parking angle to the driving angle.

[0088] In some embodiments, the control device for the vehicle rearview mirror further includes a computing module.

[0089] The calculation module is used to analyze the seat information and image information of the vehicle to obtain the driver's height and acquire obstacle information around the vehicle; based on the obstacle information around the vehicle and the current flip angle of the rearview mirror, to determine the driver's blind spot; and based on the driver's height and the driver's blind spot, to determine the parking angle of the rearview mirror.

[0090] In some embodiments, the calculation module is further configured to predict the field of view of the rearview mirror based on the current flip angle of the rearview mirror to obtain the theoretical field of view of the rearview mirror; and to perform superimposed analysis on the theoretical field of view of the rearview mirror and the obstacle information around the vehicle to obtain the driver's blind spot.

[0091] In some embodiments, the calculation module is further configured to map the driver's height to obtain the driver's line-of-sight height, and based on the driver's line-of-sight height, analyze the driver's field of vision to obtain the driver's basic field of vision; based on the driver's basic field of vision and the driver's blind spot, predict the flip angle of the rearview mirror to obtain the parking angle of the rearview mirror.

[0092] In some embodiments, parking includes shifting gears and completing parking preparation; the first control module is further configured to continuously acquire sensor information of the vehicle; in response to the sensor information indicating that the vehicle speed is greater than or equal to a speed threshold, determine that the current operating state of the vehicle is driving; in response to the sensor information indicating that the vehicle speed is less than the speed threshold and the duration reaches a first duration threshold, determine that the current operating state of the vehicle is decelerating; in response to the sensor information indicating that the vehicle speed is a third preset value and the range of wheel speed change of the vehicle is less than a preset range, determine that the current operating state of the vehicle is stopped; in response to the... The sensor information indicates that the vehicle's gear has been switched to parking gear, thus determining the vehicle's current operating state as gear shifting; in response to the sensor information indicating that the vehicle's handbrake has been released or the vehicle's seatbelt has been unfastened, the vehicle's current operating state is determined to be parking preparation complete; in response to the sensor information indicating that the vehicle's door handle has been activated or the vehicle's steering wheel torque is less than a torque threshold, the vehicle's current operating state is determined to be driver preparing to leave the vehicle; in response to the sensor information indicating that the vehicle remains stationary within the parking area for a duration reaching a second duration threshold, the vehicle's current operating state is determined to be parking complete.

[0093] In some embodiments, the first control module is further configured to continuously acquire sensor information of the vehicle; extract features from the sensor information of the vehicle to obtain a first feature of the vehicle; and predict the state of the vehicle based on the first feature to obtain the current operating state of the vehicle.

[0094] Figure 2 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this disclosure.

[0095] For example, such as Figure 2 As shown, the vehicle 200 includes a memory 201 and a processor 202. The memory 201 stores executable program code 2011, and the processor 202 is used to call and execute the executable program code 2011 to perform a control method for the vehicle's rearview mirror.

[0096] This embodiment can divide the vehicle into functional modules according to the above method example. For example, each function can be assigned to a separate module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0097] When each functional module is divided according to its corresponding function, the vehicle may include: Acquire multiple sensor information of the vehicle, and determine a second score of the vehicle based on a first score corresponding to each sensor information; In response to the second score meeting the scoring threshold, the rearview mirror of the vehicle is tilted down from the driving angle to the parking angle, and the current operating status of the vehicle is continuously monitored; When the current operating state is in a parking state, the rearview mirror is kept at the parking angle until the current operating state changes to parking completed, and then the rearview mirror is restored from the parking angle to the driving angle.

[0098] Some embodiments of this disclosure provide corresponding to Figure 1 A computer-readable storage medium storing computer-executable instructions, the computer-executable instructions being configured to: acquire multiple sensor information of a vehicle, and determine a second score of the vehicle based on a first score corresponding to each of the sensor information; in response to the second score satisfying a scoring threshold, tilt the rearview mirror of the vehicle from a driving angle to a parking angle, and continuously monitor the current operating state of the vehicle; when the current operating state is in a parking state, keep the rearview mirror at the parking angle until the current operating state changes to parking completed, and restore the rearview mirror from the parking angle to the driving angle.

[0099] The various embodiments in this disclosure are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for IoT devices and media are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0100] The vehicles and media provided in this disclosure correspond one-to-one with the methods. Therefore, the vehicles and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the vehicles and media will not be repeated here.

[0101] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, vehicles, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (vehicles), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0103] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0104] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0105] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0106] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0107] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0108] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0109] The above description is merely an embodiment of this disclosure and is not intended to limit the scope of this disclosure. Various modifications and variations can be made to this disclosure by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of the claims of this disclosure.

Claims

1. A control method of a vehicle rearview mirror, characterized by, The method comprises: obtaining a plurality of sensor information of a vehicle, and fusing a first score corresponding to each of the sensor information to obtain a second score of the vehicle; in response to the second score satisfying a score threshold, lowering a rearview mirror of the vehicle from a driving angle to a parking angle, and continuously monitoring a current running state of the vehicle; when the current running state is in parking, keeping the rearview mirror at the parking angle until the current running state changes to parking completion, and restoring the rearview mirror from the parking angle to the driving angle.

2. The control method of a vehicle rearview mirror according to claim 1, characterized by, The fusion of the first score corresponding to each of the sensor information to obtain the second score of the vehicle comprises: for each of the sensor information, the following processing is performed respectively: comparing the sensor information with a preset judgment condition corresponding to the sensor information to obtain a comparison result; if the comparison result indicates that the sensor information satisfies the preset judgment condition, a first preset value is taken as the first score corresponding to the sensor information; if the comparison result indicates that the sensor information does not satisfy the preset judgment condition, a second preset value is taken as the first score corresponding to the sensor information, and the first preset value is greater than the second preset value; adding the first score corresponding to each of the sensor information to obtain the second score of the vehicle.

3. The control method of a vehicle rearview mirror according to claim 1, characterized by, The method further comprises: when the current running state changes from the parking to normal driving, restoring the rearview mirror from the parking angle to the driving angle.

4. The control method of a vehicle rearview mirror according to claim 1, characterized by, The method further comprises: analyzing seat information of the vehicle and image information of the vehicle to obtain the height of the driver, and obtaining obstacle information around the vehicle; determining the visual blind area of the driver based on the obstacle information around the vehicle and the current turning angle of the rearview mirror; determining the parking angle of the rearview mirror based on the height of the driver and the visual blind area of the driver.

5. The control method of a vehicle rearview mirror according to claim 4, wherein The determination of the visual blind area of the driver based on the obstacle information around the vehicle and the current turning angle of the rearview mirror comprises: based on the current turning angle of the rearview mirror, predicting the visual range of the rearview mirror to obtain the theoretical visual range of the rearview mirror; superimposing and analyzing the theoretical visual range of the rearview mirror and the obstacle information around the vehicle to obtain the visual blind area of the driver.

6. The control method of a vehicle rearview mirror according to claim 4, wherein The determination of the parking angle of the rearview mirror based on the height of the driver and the visual blind area of the driver comprises: mapping the height of the driver to obtain the line-of-sight height of the driver, and based on the line-of-sight height of the driver, performing visual range analysis on the driver to obtain the basic visual range of the driver; based on the basic visual range of the driver and the visual blind area of the driver, predicting the turning angle of the rearview mirror to obtain the parking angle of the rearview mirror.

7. The control method of a vehicle rearview mirror according to claim 1, characterized by The parking comprises switching gears and completing parking preparation; The continuous monitoring of the current running state of the vehicle comprises: continuously obtaining sensor information of the vehicle; in response to the sensor information representing that the vehicle speed of the vehicle is greater than or equal to a vehicle speed threshold, determining that the current running state of the vehicle is driving; in response to the sensor information representing that the vehicle speed of the vehicle is less than the vehicle speed threshold and the duration reaches a first time threshold, determining that the current running state of the vehicle is decelerating; in response to the sensor information representing that the vehicle speed of the vehicle is a third preset value and the wheel speed variation range of the vehicle is less than a preset range, determining that the current running state of the vehicle is stopping; in response to the sensor information representing that the gear of the vehicle is switched to a parking gear, determining that the current running state of the vehicle is gear switching; in response to the sensor information representing that the handbrake of the vehicle is lifted or the safety belt of the vehicle is released, determining that the current running state of the vehicle is parking preparation completion; in response to the sensor information representing that the door handle of the vehicle is activated or the steering wheel torque of the vehicle is less than a torque threshold, determining that the current running state of the vehicle is driver preparation for leaving the vehicle; in response to the sensor information representing that the vehicle remains stationary in a parking area and the duration reaches a second time threshold, determining that the current running state of the vehicle is parking completion.

8. The control method of a vehicle rearview mirror according to claim 1, wherein The method for continuously monitoring the current running state of the vehicle comprises: continuously obtaining sensor information of the vehicle; performing feature extraction on the sensor information of the vehicle to obtain first features of the vehicle; based on the first features, performing state prediction on the vehicle to obtain the current running state of the vehicle.

9. A vehicle characterized by comprising: The vehicle comprises: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for controlling a vehicle rearview mirror according to any one of claims 1-8.

10. A computer storage medium storing computer-executable instructions, which, when executed by a processor, cause the processor to perform acts comprising: The computer executable instructions, when executed, implement the method for controlling a vehicle rearview mirror according to any one of claims 1-8.

Images