Anti-collision method, device and vehicle

Abstract

The application provides a collision avoidance method and device and a vehicle, which can be applied to the field of intelligent cockpits. The method comprises the following steps: in response to obtaining an instruction, a screen is controlled to be unfolded, the screen being a foldable screen or a curtain in the cockpit; data collected by a plurality of sensors in the cockpit is obtained, and a weight corresponding to each sensor in the plurality of sensors is obtained; a collision risk between the screen and an obstacle is determined according to the data collected by the plurality of sensors and the weight corresponding to each sensor in the plurality of sensors; and in the case that the collision risk meets a preset condition, a collision avoidance operation is performed. The application can be applied to intelligent vehicles or electric vehicles, and helps to avoid the collision risk between the foldable screen and the obstacle, thereby helping to avoid damage to the screen or other devices.

Description

Technical Field

[0001] This application relates to the field of smart cockpits, and more specifically, to a collision avoidance method, device, and vehicle. Background Technology

[0002] With the continuous development of intelligent connected vehicles, more and more car smart cockpits are now equipped with foldable entertainment screens in the rear, including LCD screens and projection screens. Because these rear screens occupy a significant amount of space and move when unfolded, the risk of collisions between the screens and passengers, seats, etc., is greatly increased. Collisions between foldable screens and passengers pose a threat to occupant safety, while collisions between foldable screens and passengers or other cabin components can cause damage to the screens and other equipment. Summary of the Invention

[0003] This application provides a collision avoidance method, device, and vehicle that helps avoid the risk of collision between a foldable screen and an obstacle, thereby helping to avoid damage to the screen or other devices and also helping to avoid safety risks to occupants.

[0004] In a first aspect, this application provides a collision avoidance method, comprising: in response to receiving a first instruction, controlling a first screen to unfold, the first screen being a foldable screen or curtain inside the cockpit; acquiring data collected by multiple sensors inside the cockpit and acquiring the weight corresponding to each of the multiple sensors; determining a first collision risk between the first screen and a first obstacle based on the data collected by the multiple sensors and the weight corresponding to each of the multiple sensors; and performing a collision avoidance operation when the first collision risk meets preset conditions.

[0005] Based on the above technical solution, collision risk is determined by using data collected from multiple sensors and their corresponding weights. This helps improve the accuracy of the determined collision risk, thereby improving the accuracy of the vehicle's collision avoidance operations. Furthermore, when the collision risk meets preset conditions, collision avoidance operations can be performed, helping to avoid collisions between the foldable screen and obstacles, thus preventing damage to the screen or other components and mitigating safety risks to occupants.

[0006] In some possible implementations, the first collision risk between the first screen and the first obstacle is determined based on data collected by multiple sensors and the weight corresponding to each sensor among the multiple sensors. This includes: performing data fusion on the data collected by multiple sensors according to the weight corresponding to each sensor among the multiple sensors to obtain fused data; and determining the first collision risk between the first screen and the first obstacle based on the fused data.

[0007] For example, data fusion is performed on the data collected by multiple sensors according to the weights corresponding to each sensor in the multiple sensors to obtain fused data, including: using a Bayesian inference method to perform data fusion on the data collected by multiple sensors according to the weights corresponding to each sensor in the multiple sensors to obtain fused data.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, the multiple sensors include a vision sensor and a distance sensor, wherein obtaining the weight corresponding to each of the multiple sensors includes: obtaining a first weight corresponding to the vision sensor and a second weight corresponding to the distance sensor based on the lighting conditions in the cockpit; or, obtaining a third weight corresponding to the vision sensor and a fourth weight corresponding to the distance sensor based on the distance between the first obstacle and the first screen.

[0009] Based on the above technical solutions, the weights of the visual sensor and the distance sensor can be obtained based on the lighting conditions inside the cockpit, or the weights can be obtained based on the distance between the obstacle and the screen. This allows for the assignment of different weights to the visual sensor and the distance sensor in different scenarios, helping to improve the accuracy of the determined collision risk.

[0010] In some possible implementations, the first weight and the third weight are different, and the second weight and the fourth weight are different.

[0011] In some possible implementations, the vision sensor includes a two-dimensional (2D) vision sensor or a three-dimensional (3D) vision sensor.

[0012] In some possible implementations, the distance sensor includes at least one of an infrared sensor, an ultrasonic sensor, or a millimeter-wave sensor.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, when the lighting conditions indicate that the light intensity inside the cabin is greater than or equal to a preset light intensity, the first weight is greater than the second weight; or, when the lighting conditions indicate that the light intensity inside the cabin is less than a preset light intensity, the first weight is less than or equal to the second weight.

[0014] Based on the above technical solution, a larger weight can be assigned to the visual sensor under good lighting conditions. This leverages the higher reliability of the visual sensor under good lighting conditions, helping to improve the accuracy of the determined collision risk.

[0015] In conjunction with the first aspect, in some implementations of the first aspect, when the distance between the first obstacle and the first screen is less than or equal to the first preset distance, the third weight is less than the fourth weight; or, when the distance between the first obstacle and the first screen is greater than the first preset distance, the third weight is greater than or equal to the fourth weight.

[0016] Based on the above technical solution, when the distance between the obstacle and the screen is relatively short, a larger weight can be assigned to the distance sensor. This leverages the high accuracy of distance sensors (e.g., ultrasonic sensors) in close-range detection, helping to improve the accuracy of the determined collision risk.

[0017] In conjunction with the first aspect, in some implementations of the first aspect, the multiple sensors include a third sensor, which is used to detect whether the first screen collides with the first obstacle. Before the first obstacle collides with the first screen, the third sensor has a weight of the fifth weight; or, in the case of the first obstacle colliding with the first screen, the third sensor has a weight of the sixth weight; wherein the fifth weight is less than the sixth weight.

[0018] Based on the above technical solution, a higher weight can be assigned to the third sensor after an obstacle collides with the screen. This leverages the high accuracy of the third sensor in detecting collisions, helping to improve the accuracy of the determined collision risk.

[0019] In some possible implementations, the third sensor is a capacitive sensor or a force sensor.

[0020] In conjunction with the first aspect, in certain implementations of the first aspect, when the first collision risk meets preset conditions, an anti-collision operation is performed, including: when it is determined, based on data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle, controlling the first screen to move a distance in the direction opposite to the unfolding direction and controlling the alarm device to indicate that a collision has occurred between the first screen and the first obstacle; in response to receiving a first instruction from the user and determining, based on data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle, ignoring the first instruction, and the first instruction instructing the first screen to unfold.

[0021] Based on the above technical solution, in the event of a collision between the first screen and the first obstacle, the first screen can be controlled to move a certain distance in the opposite direction of its unfolding direction and an alarm can be issued to the user; if the first screen continues to collide with the first obstacle while receiving the user's first instruction, the first instruction can be ignored. This avoids damage to the screen or other devices (e.g., a seat) caused by executing the user's instructions, or it avoids causing harm to the user.

[0022] In some possible implementations, ignoring the first instruction in response to receiving a first instruction from the user and determining, based on data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle includes: ignoring the first instruction when the data collected by the third sensor determines that a collision has occurred between the first screen and the first obstacle upon receiving the first instruction.

[0023] In conjunction with the first aspect, in some implementations of the first aspect, determining the first collision risk between the first screen and the first obstacle includes: determining the distance between the first screen and the first obstacle; wherein, when the first collision risk meets preset conditions, performing an anti-collision operation includes: performing an anti-collision operation when the distance is less than or equal to a second preset distance.

[0024] Based on the above technical solution, when the distance between the first screen and the first obstacle is less than a second preset distance, a collision avoidance operation can be performed. This reduces the risk of collision between the first screen and the first obstacle. For example, if the first obstacle is an occupant, injury to the occupant can be avoided; if the first obstacle is other components within the cabin (e.g., seats), damage to the screen or other components can be avoided.

[0025] In conjunction with the first aspect, in some implementations of the first aspect, determining the first collision risk between the first screen and the first obstacle includes: determining the movement trend of the first obstacle; wherein, when the first collision risk meets preset conditions, performing an anti-collision operation includes: performing an anti-collision operation when the movement trend of the first obstacle indicates that the first obstacle is moving toward the first screen.

[0026] Based on the above technical solution, collision avoidance can be performed when the first obstacle moves towards the first screen. This reduces the risk of collision between the first screen and the first obstacle. For example, if the first obstacle is an occupant, injury to the occupant can be avoided; if the first obstacle is other components within the cabin (e.g., seats), damage to the screen or other components can be avoided.

[0027] In some possible implementations, determining the first collision risk between the first screen and the first obstacle includes: determining the distance between the first screen and the first obstacle and determining the movement trend of the first obstacle; wherein, when the first collision risk meets preset conditions, performing an anti-collision operation includes: performing an anti-collision operation when the distance is less than or equal to a second preset distance and the movement trend of the first obstacle indicates that the first obstacle is moving toward the first screen.

[0028] In conjunction with the first aspect, in some implementations of the first aspect, when the first collision risk meets the preset conditions, an anti-collision operation is performed, including: when the first collision risk meets the preset conditions during the unfolding of the first screen, controlling the unfolding speed of the first screen, or controlling the first screen to move a distance in the opposite direction of the unfolding direction, or controlling the first screen to stop unfolding.

[0029] Based on the above technical solution, the collision avoidance operation performed by the vehicle may include controlling the unfolding speed of the first screen, controlling the first screen to move a distance in the opposite direction of the unfolding direction, or controlling the first screen to stop unfolding.

[0030] In some possible implementations, if the first collision risk meets a preset condition during the unfolding of the first screen, the unfolding speed of the first screen is controlled, including: if the first collision risk meets a preset condition during the unfolding of the first screen and the first obstacle is a seat, the unfolding speed of the first screen is controlled according to the speed at which the seat moves.

[0031] In some possible implementations, if the first collision risk meets a preset condition during the unfolding of the first screen, the first screen is controlled to stop unfolding, including: if the first collision risk meets a preset condition during the unfolding of the first screen and the first screen has already collided with the first obstacle, the first screen is controlled to move a distance in the opposite direction of the unfolding direction.

[0032] In some possible implementations, when the first collision risk meets the preset conditions, an anti-collision operation is performed, including: when the first collision risk meets the preset conditions and the first obstacle is the seat during the unfolding of the first screen, the speed at which the seat moves is controlled according to the unfolding speed of the first screen.

[0033] In conjunction with the first aspect, in some implementations of the first aspect, performing anti-collision operations includes: when the first collision risk meets preset conditions during the unfolding of the first screen, controlling the alarm device to indicate that there is a collision risk between the first screen and the first obstacle; in response to obtaining a second instruction from the user and when there is a collision risk between the first screen and the first obstacle, controlling the first screen to continue unfolding and updating the preset conditions, and the second instruction instructing the first screen to unfold.

[0034] Based on the above technical solution, if the user's second instruction is obtained after the control alarm device alarms the user, and there is still a risk of collision between the first screen and the first obstacle when the second instruction is obtained, then the first screen can be controlled to continue to unfold and the preset condition can be updated.

[0035] In some possible implementations, the preset condition includes that the distance between the first screen and the first obstacle is less than or equal to a second preset distance. When a second instruction from the user is received and the distance between the first screen and the first obstacle is less than or equal to the second preset distance, the first screen can be controlled to unfold at a preset speed, and the preset condition can be updated to that the distance between the first screen and the first obstacle is less than or equal to a third preset distance, where the third preset distance is less than the second preset distance.

[0036] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: during the anti-collision operation, determining a second collision risk between the first screen and the first obstacle based on the weight corresponding to each sensor and the data collected by each sensor; if the second collision risk does not meet the preset conditions, controlling the first screen to continue unfolding at a preset speed.

[0037] Based on the above technical solution, if the collision risk between the first screen and the first obstacle does not meet the preset conditions during the collision avoidance operation, the first screen can be controlled to continue unfolding at a preset speed. In this way, when the collision risk is detected to be eliminated, the first screen can be automatically controlled to continue unfolding without requiring the user to issue another command to unfold the screen, thus improving the user's driving experience.

[0038] In conjunction with the first aspect, in some implementations of the first aspect, determining the first collision risk between the first screen and the first obstacle includes: inputting data collected by at least one of a plurality of sensors into a prediction model to obtain the motion trajectory of the first obstacle over a future period of time; and determining the first collision risk between the first screen and the first obstacle based on the unfolding trajectory of the first screen and the motion trajectory of the first obstacle.

[0039] Based on the above technical solution, by inputting the data collected by at least one of the multiple sensors into the prediction model, the motion trajectory of the first obstacle in the future period can be obtained. Thus, the collision risk can be determined based on the unfolding trajectory of the first screen and the motion trajectory of the first obstacle.

[0040] In some possible implementations, determining the first collision risk between the first screen and the first obstacle includes: inputting data collected by at least one of a plurality of sensors into a prediction model to obtain the first collision risk.

[0041] Secondly, this application provides a collision avoidance device, comprising: a control unit, configured to control the unfolding of a first screen in response to a first instruction acquired by an acquisition unit, wherein the first screen is a foldable screen or curtain inside the cockpit; an acquisition unit, further configured to acquire data collected by multiple sensors inside the cockpit and acquire the weight corresponding to each of the multiple sensors; a determination unit, configured to determine a first collision risk between the first screen and a first obstacle based on the data collected by the multiple sensors and the weight corresponding to each of the multiple sensors; and a collision avoidance operation execution unit, configured to perform a collision avoidance operation when the first collision risk meets preset conditions.

[0042] In conjunction with the second aspect, in some implementations of the second aspect, multiple sensors include a vision sensor and a distance sensor, wherein the acquisition unit is configured to: acquire a first weight corresponding to the vision sensor and a second weight corresponding to the distance sensor based on the lighting conditions inside the cockpit; or, acquire a third weight corresponding to the vision sensor and a fourth weight corresponding to the distance sensor based on the distance between the first obstacle and the first screen.

[0043] In conjunction with the second aspect, in some implementations of the second aspect, when the lighting conditions indicate that the light intensity inside the cabin is greater than or equal to the preset light intensity, the first weight is greater than the second weight; or, when the lighting conditions indicate that the light intensity inside the cabin is less than the preset light intensity, the first weight is less than or equal to the second weight.

[0044] In conjunction with the second aspect, in some implementations of the second aspect, when the distance between the first obstacle and the first screen is less than or equal to the first preset distance, the third weight is less than the fourth weight; or, when the distance between the first obstacle and the first screen is greater than the first preset distance, the third weight is greater than or equal to the fourth weight.

[0045] In conjunction with the second aspect, in some implementations of the second aspect, multiple sensors include a third sensor, which is used to detect whether the first screen collides with the first obstacle. Before the first obstacle collides with the first screen, the third sensor has a weight of the fifth weight; or, in the case of the first obstacle colliding with the first screen, the third sensor has a weight of the sixth weight; wherein the fifth weight is less than the sixth weight.

[0046] In conjunction with the second aspect, in some implementations of the second aspect, the control unit is configured to, when the determining unit determines, based on data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle, control the first screen to move a distance in the direction opposite to the unfolding direction and control the alarm device to indicate that a collision has occurred between the first screen and the first obstacle; the acquisition unit is further configured to, in response to the acquisition unit acquiring a first instruction from the user and the determining unit determining, based on data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle, ignore the first instruction, which instructs the first screen to unfold.

[0047] In conjunction with the second aspect, in some implementations of the second aspect, a determining unit is used to determine the distance between the first screen and the first obstacle; and an anti-collision operation execution unit is used to perform an anti-collision operation when the distance is less than or equal to a second preset distance.

[0048] In conjunction with the second aspect, in some implementations of the second aspect, a determining unit is used to determine the movement trend of the first obstacle; and an anti-collision operation execution unit is used to perform an anti-collision operation when the movement trend of the first obstacle indicates that the first obstacle is moving toward the first screen.

[0049] In conjunction with the second aspect, in some implementations of the second aspect, the anti-collision operation execution unit is used to: control the unfolding speed of the first screen when the first collision risk meets the preset conditions during the unfolding process of the first screen, or control the first screen to move a distance in the opposite direction of the unfolding direction, or control the first screen to stop unfolding.

[0050] In conjunction with the second aspect, in some implementations of the second aspect, the control unit is configured to: control the alarm device to indicate that there is a collision risk between the first screen and the first obstacle when the first collision risk meets the preset conditions during the unfolding of the first screen; and control the first screen to continue unfolding and update the preset conditions in response to the acquisition unit acquiring the user's second instruction, wherein the second instruction instructs the first screen to unfold.

[0051] In conjunction with the second aspect, in some implementations of the second aspect, a determining unit is used to determine the second collision risk between the first screen and the first obstacle based on the weight corresponding to each sensor and the data collected by each sensor during the anti-collision operation execution unit; and a control unit is used to control the first screen to continue unfolding at a preset speed if the second collision risk does not meet the preset conditions.

[0052] In conjunction with the second aspect, in some implementations of the second aspect, a determining unit is used to: input data collected by at least one of a plurality of sensors into a prediction model to obtain the motion trajectory of the first obstacle over a future period of time; and determine the first collision risk between the first screen and the first obstacle based on the unfolding trajectory of the first screen and the motion trajectory of the first obstacle.

[0053] Thirdly, this application provides a collision avoidance device, which includes a processor and a memory, wherein the memory is used to store instructions, and the processor executes the instructions stored in the memory to cause the device to perform any of the possible methods in the first aspect.

[0054] Fourthly, this application provides a collision avoidance system, which includes a sensing system and a computing platform, wherein the computing platform includes any of the possible devices in the second or third aspect.

[0055] Fifthly, this application provides a vehicle that includes any of the possible collision avoidance devices of the second or third aspect, or includes the collision avoidance system described in the fourth aspect.

[0056] In a sixth aspect, this application provides a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform any of the possible anti-collision methods described in the first aspect above.

[0057] It should be noted that the above-mentioned computer program code can be stored in whole or in part on the first storage medium, wherein the first storage medium can be packaged together with the processor or packaged separately from the processor. This application embodiment does not specifically limit this.

[0058] In a seventh aspect, this application provides a computer-readable medium storing program code that, when executed on a computer, causes the computer to perform any of the possible collision avoidance methods described in the first aspect above.

[0059] Eighthly, this application provides a chip system including a processor for calling a computer program or computer instructions stored in a memory to cause the processor to execute any of the possible anti-collision methods described in the first aspect above.

[0060] In conjunction with the eighth aspect, in one possible implementation, the processor is coupled to the memory via an interface.

[0061] In conjunction with the eighth aspect, in one possible implementation, the chip system also includes a memory in which computer programs or computer instructions are stored.

[0062] Ninthly, this application provides a chip system including circuitry for performing any of the possible anti-collision methods described in the first aspect above. Attached Figure Description

[0063] Figure 1 This is a functional block diagram of the vehicle provided in the embodiments of this application.

[0064] Figure 2 This is a schematic diagram of a vehicle cabin scenario provided in an embodiment of this application.

[0065] Figure 3 This is a schematic flowchart of the anti-collision method provided in the embodiments of this application.

[0066] Figure 4 This is a schematic block diagram of the anti-collision system provided in the embodiments of this application.

[0067] Figure 5 This is a schematic block diagram of the anti-collision device provided in the embodiments of this application. Detailed Implementation

[0068] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0069] Figure 1 This is a functional block diagram of a vehicle provided in an embodiment of this application. For example... Figure 1 As shown, the vehicle 100 may include a perception system 110, a display device 130, and a computing platform 150. For example, the perception system 110 includes, but is not limited to, one or more of a 2D vision sensor, 3D vision sensor, infrared sensor, ultrasonic sensor, millimeter-wave sensor, capacitive sensor, and force sensor located within the cabin. For example, the perception system 110 includes, but is not limited to, one or more of a camera, millimeter-wave radar, ultrasonic radar, and lidar located outside the cabin.

[0070] The in-cabin display devices 130 are mainly divided into two categories: the first is the in-vehicle display screen; the second is the projection display screen, such as the head-up display (HUD). An in-vehicle display screen is a physical display screen and an important component of the in-vehicle infotainment system. Multiple displays can be installed in the cabin, such as the digital instrument cluster display, the central control screen, the display screen in front of the front passenger (also known as the front-seat passenger), the display screen in front of the left rear passenger, the display screen in front of the right rear passenger, and even the car window can be used as a display screen. A head-up display, also known as a head-up display system, is mainly used to display driving information such as speed and navigation on a display device in front of the driver (such as the windshield). This reduces the driver's eye-shift time, avoids pupil changes caused by eye-shifting, and improves driving safety and comfort. Examples of HUDs include combiner-HUD (C-HUD) systems, windshield-HUD (W-HUD) systems, and augmented reality HUD (AR-HUD) systems.

[0071] Some or all of the functions of vehicle 100 can be controlled by computing platform 150. Computing platform 150 may include processors 151 to 15n. A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In reconfigurable hardware circuits, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement some or all of the functions of the aforementioned units. Furthermore, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. In addition, the computing platform 150 may also include a memory for storing instructions. Some or all of the processors 151 to 15n can call the instructions in the memory to implement the corresponding functions.

[0072] Optionally, the structure of the vehicle 100 described above is merely illustrative. In actual applications, various components of the vehicle 100 may be added or removed as needed.

[0073] Figure 2This is a schematic diagram of a vehicle cockpit scenario provided in an embodiment of this application. The smart cockpit includes one or more in-vehicle displays (or in-vehicle screens), including but not limited to display screen 201 (or central control screen), display screen 202 (or passenger entertainment screen), display screen 203 (or driver's headrest rear screen), display screen 204 (or passenger headrest rear screen), display screen 205 (or second-row entertainment screen) mounted on the cockpit ceiling, and an instrument panel. Further, displays 201 to 205 can display a graphical user interface (GUI), which may include icons for one or more applications, and / or one or more cards. For example, Figure 1 The display device 130 shown can be one or more of displays 201 to 205. In some possible implementations, display 201 can also be a long screen extending into the passenger area. Furthermore, display 205 can be a projection screen associated with a projector, which can be associated with a desktop launcher to manage applications projected onto the projection screen. This embodiment of the application includes collision risk detection during or after the display 205 is unfolded.

[0074] It should be understood that the method for controlling the display in the following embodiments is based on... Figure 2 The embodiments shown are based on a 5-seater vehicle, but are not limited to this. For example, for a 7-seater sport / suburban utility vehicle (SUV), the cabin may include a central control screen, a passenger entertainment screen, a screen behind the driver's headrest, a screen behind the passenger's headrest, entertainment screens in the left-hand area of ​​the third row, and entertainment screens in the right-hand area of ​​the third row. As another example, for a bus, the cabin may include front and rear entertainment screens; or, the cabin may include a display screen in the driver's area and an entertainment screen in the passenger area. Furthermore, the following embodiments use a left-hand drive vehicle (i.e., the driver is on the left side of the vehicle) as an example; in actual implementation, the vehicle may also be a right-hand drive vehicle (i.e., the driver is on the right side of the vehicle).

[0075] As mentioned earlier, with the continuous development of intelligent connected vehicles, more and more car smart cockpits are now equipped with foldable entertainment screens in the rear, including LCD screens and projection screens. Because these rear screens occupy a significant amount of space in the cabin and move when unfolded, the risk of collisions between the rear screens and occupants, seats, etc., is greatly increased. Collisions between foldable screens and occupants pose a threat to passenger safety, while collisions between foldable screens and other components in the cabin can cause damage to the screens and other parts of the vehicle.

[0076] This application provides a collision avoidance method, device, and vehicle. By collecting data from multiple sensors within the cabin, the collision risk between the screen and obstacles can be determined. When the collision risk meets preset conditions, a collision avoidance operation can be performed. This helps avoid the collision risk between the foldable screen and obstacles, thereby helping to prevent damage to the screen or other devices and reducing occupant safety risks.

[0077] Figure 3 A schematic flowchart of a collision avoidance method 300 provided in an embodiment of this application is shown. This method 300 can be executed by the vehicle 100; or, this method 300 can be executed by the computing platform 150; or, this method 300 can be executed by a processor, chip, or circuit in the computing platform 150. The method 300 includes:

[0078] S310, in response to receiving a first command, controls the unfolding of a first screen, which is a foldable screen or curtain inside the cockpit.

[0079] For example, the first instruction can be a user's voice command, such as "Xiao A Xiao A, open the screen", or "Xiao A Xiao A, open the foldable screen".

[0080] For example, the first instruction could be an input from a user clicking a button, which could be a button to unfold a foldable screen or curtain inside the cockpit.

[0081] For example, the button can be a physical button or a virtual button.

[0082] The first screen above can be Figure 2 The display screen 205 shown is shown.

[0083] S320 acquires data collected by multiple sensors in the cockpit and obtains the weight of each sensor among the multiple sensors.

[0084] Optionally, the multiple sensors include a vision sensor and a distance sensor. The weights for each sensor are obtained, including: obtaining a first weight for the vision sensor and a second weight for the distance sensor based on the lighting conditions inside the cockpit; or obtaining a third weight for the vision sensor and a fourth weight for the distance sensor based on the distance between the first obstacle and the first screen. This allows different weights to be assigned to the vision sensor and the distance sensor in different scenarios, helping to improve the accuracy of the determined collision risk.

[0085] Optionally, the vision sensor may include a 2D vision sensor or a 3D vision sensor.

[0086] Optionally, the distance sensor includes at least one of an infrared sensor, an ultrasonic sensor, or a millimeter-wave sensor.

[0087] Optionally, when the lighting conditions indicate that the light intensity inside the cabin is greater than or equal to a preset light intensity, the first weight is greater than the second weight; or, when the lighting conditions indicate that the light intensity inside the cabin is less than or equal to the preset light intensity, the first weight is less than or equal to the second weight. This leverages the higher reliability of visual sensors under good lighting conditions, helping to improve the accuracy of the determined collision risk.

[0088] Optionally, when the distance between the first obstacle and the first screen is less than or equal to a first preset distance, the third weight is less than the fourth weight; or, when the distance between the first obstacle and the first screen is greater than the first preset distance, the third weight is greater than or equal to the fourth weight. This leverages the high accuracy of distance sensors (e.g., ultrasonic sensors) in close-range detection, helping to improve the accuracy of determining the collision risk.

[0089] Optionally, the multiple sensors include a third sensor, which is used to detect whether the first screen collides with the first obstacle. Before the collision between the first obstacle and the first screen, the third sensor has a weight corresponding to the fifth weight; or, if the collision occurs, the third sensor has a weight corresponding to the sixth weight; wherein the fifth weight is less than the sixth weight. This leverages the higher accuracy of the third sensor in detecting collisions, helping to improve the accuracy of determining the collision risk.

[0090] For example, the third sensor is a capacitive sensor or a force sensor.

[0091] The purpose of the above sensors is to monitor the relative distance and movement trends of the occupants' seats and the foldable screen in real time. It should be understood that not all of the above sensors are required in the embodiments of this application; a single sensor or a combination of some sensors may be used. For example, the specific uses of different sensors are as follows:

[0092] 2D vision sensors: These sensors acquire images of the cabin in real time and use algorithms to determine one or more of the following: occupant presence, human posture, and 3D human position. For example, 2D vision sensors can be deployed on either side of the rear cabin or directly above the foldable screen, depending on the vehicle model, with the aim of capturing images of the entire rear cabin as much as possible.

[0093] 3D vision sensor: Acquires real-time 3D point cloud data within the cockpit, calculating the distance between the human body and the foldable screen (or curtain), as well as the human body's movement speed and trend. For example, the 3D vision sensor can be positioned directly above the foldable screen to acquire complete point cloud data within the cockpit.

[0094] Infrared sensor: By emitting and receiving infrared light, it detects the proximity and direction of movement of a person to the foldable screen. For example, infrared sensors can be deployed on the foldable screen itself and above it.

[0095] Ultrasonic sensors: These emit ultrasonic signals and detect the distance between the foldable screen and obstacles such as people or seats by using the echo signals. For example, ultrasonic sensors can be deployed in the same locations as infrared sensors.

[0096] Millimeter-wave sensors: These calculate the distance between the foldable screen and obstacles such as people and seats by receiving transmitted millimeter-wave signals. For example, millimeter-wave sensors can be deployed in the same locations as infrared sensors.

[0097] Capacitive sensors: These detect contact between a human body and the sensor by measuring changes in capacitance. For example, capacitive sensors can be deployed and integrated into foldable screens, primarily at the point of contact between the human body and the screen; multiple sensors can be deployed in this way.

[0098] Capacitive sensor: It detects the obstruction of the screen's unfolding by detecting abnormal changes in the current of the motor that drives the foldable screen. When the foldable screen comes into contact with a person or a seat, the unfolding of the foldable screen is obstructed, and the force sensor can detect the abnormal changes in the motor current.

[0099] S330 determines the first collision risk between the first screen and the first obstacle based on data collected by multiple sensors and the weight of each sensor.

[0100] Optionally, the first collision risk between the first screen and the first obstacle is determined based on the data collected by multiple sensors and the weight corresponding to each sensor among the multiple sensors, including: performing data fusion on the data collected by multiple sensors according to the weight corresponding to each sensor among the multiple sensors to obtain fused data; and determining the first collision risk between the first screen and the first obstacle based on the fused data.

[0101] For example, data fusion is performed on the data collected by multiple sensors according to the weights corresponding to each sensor in the multiple sensors to obtain fused data, including: using a Bayesian inference method to perform data fusion on the data collected by multiple sensors according to the weights corresponding to each sensor in the multiple sensors to obtain fused data.

[0102] Optionally, determining the first collision risk between the first screen and the first obstacle includes: determining the distance between the first screen and the first obstacle; wherein, if the first collision risk meets a preset condition, performing an anti-collision operation includes: performing an anti-collision operation if the distance is less than or equal to a second preset distance.

[0103] In this embodiment, when the distance between the first screen and the first obstacle is less than a second preset distance, a collision avoidance operation can be performed. This reduces the risk of collision between the first screen and the first obstacle. For example, if the first obstacle is an occupant, injury to the occupant can be avoided; if the first obstacle is other components within the cabin (e.g., a seat), damage to the screen or other components can be avoided.

[0104] Optionally, determining a first collision risk between the first screen and the first obstacle includes: determining the movement trend of the first obstacle; wherein, when the first collision risk meets preset conditions, performing an anti-collision operation includes: performing an anti-collision operation when the movement trend of the first obstacle indicates that the first obstacle is moving toward the first screen.

[0105] In this embodiment, when the first obstacle moves toward the first screen, a collision avoidance operation can be performed. This reduces the risk of collision between the first screen and the first obstacle.

[0106] Optionally, determining the first collision risk between the first screen and the first obstacle includes: determining the distance between the first screen and the first obstacle and determining the movement trend of the first obstacle; wherein, when the first collision risk meets preset conditions, performing an anti-collision operation includes: performing an anti-collision operation when the distance is less than or equal to a second preset distance and the movement trend of the first obstacle indicates that the first obstacle is moving toward the first screen.

[0107] Optionally, determining the first collision risk between the first screen and the first obstacle includes: inputting data collected by at least one of the multiple sensors into a prediction model to obtain the first collision risk.

[0108] S340 performs a collision avoidance operation when the first collision risk meets preset conditions.

[0109] Optionally, if the first collision risk meets the preset conditions, an anti-collision operation is performed, including: if it is determined based on the data collected by the third sensor that a collision has occurred between the first screen and the first obstacle, controlling the first screen to move a distance in the opposite direction to the unfolding direction and controlling the alarm device to indicate that a collision has occurred between the first screen and the first obstacle; in response to obtaining the user's first instruction and determining based on the data collected by the third sensor that a collision has occurred between the first screen and the first obstacle, ignoring the first instruction, and the first instruction instructing the first screen to unfold.

[0110] In this embodiment, if the first screen collides with the first obstacle, the first screen can be controlled to move a distance in the opposite direction of its unfolding direction and an alarm can be issued to the user; if the first screen continues to collide with the first obstacle when the user's first command is received, the first command can be ignored. This avoids damage to the screen or other devices (e.g., seats), or avoids injury to occupants.

[0111] Optionally, in response to receiving a first instruction from the user and determining, based on data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle, ignoring the first instruction includes: upon receiving the first instruction and determining, based on data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle, ignoring the first instruction.

[0112] Optionally, if the first collision risk meets the preset conditions, an anti-collision operation is performed, including: if the first collision risk meets the preset conditions during the unfolding of the first screen, controlling the unfolding speed of the first screen, or controlling the first screen to move a distance in the opposite direction of the unfolding direction, or controlling the first screen to stop unfolding.

[0113] Optionally, if the first collision risk meets a preset condition during the unfolding of the first screen, the unfolding speed of the first screen is controlled, including: if the first collision risk meets a preset condition during the unfolding of the first screen and the first obstacle is a seat, the unfolding speed of the first screen is controlled according to the speed at which the seat moves.

[0114] Optionally, if the first collision risk meets preset conditions during the unfolding of the first screen, the unfolding speed of the first screen is controlled, including: if the first collision risk meets preset conditions during the unfolding of the first screen and the first obstacle is a seat, the speed at which the seat moves is controlled according to the unfolding speed of the first screen. In this way, without affecting the unfolding speed of the first screen, a collision between the seat and the first screen can be avoided by adjusting the speed at which the seat moves.

[0115] Optionally, if the first collision risk meets a preset condition during the unfolding of the first screen, the first screen is controlled to move a distance in the opposite direction of the unfolding direction, including: if the first collision risk meets a preset condition during the unfolding of the first screen and the first screen has already collided with the first obstacle, the first screen is controlled to move a distance in the opposite direction of the unfolding direction.

[0116] Optionally, the anti-collision operation includes: when the first collision risk meets the preset conditions during the unfolding of the first screen, controlling the alarm device to indicate that there is a collision risk between the first screen and the first obstacle; in response to obtaining the user's second instruction and when there is a collision risk between the first screen and the first obstacle, controlling the first screen to continue unfolding and updating the preset conditions, and the second instruction instructing the first screen to unfold.

[0117] For example, the alarm device can be a sound-emitting device or an ambient light.

[0118] In this embodiment of the application, if the user's second instruction is obtained after the control alarm device alarms the user and there is still a risk of collision between the first screen and the first obstacle when the second instruction is obtained, then the first screen can be controlled to continue to unfold and the preset condition can be updated.

[0119] Optionally, the preset condition includes that the distance between the first screen and the first obstacle is less than or equal to a second preset distance. When a second instruction from the user is received and the distance between the first screen and the first obstacle is less than or equal to the second preset distance, the first screen can be controlled to unfold at a preset speed and the preset condition can be updated to that the distance between the first screen and the first obstacle is less than or equal to a third preset distance, where the third preset distance is less than the second preset distance.

[0120] For example, the second preset distance can be 50cm, and the third preset distance can be 30cm.

[0121] Optionally, method 300 further includes: during the collision avoidance operation, determining a second collision risk between the first screen and the first obstacle based on the weight of each sensor and the data collected by each sensor; if the second collision risk does not meet the preset conditions, controlling the first screen to continue unfolding at a preset speed.

[0122] For example, if the first collision risk meets a preset condition during the unfolding of the first screen, the unfolding speed of the first screen can be controlled to decrease from a preset unfolding speed to the first unfolding speed. If, during the unfolding of the first screen at the first unfolding speed, a second collision risk between the first screen and the first obstacle is detected to not meet the preset condition, the unfolding speed of the first screen can be controlled to return to the preset unfolding speed.

[0123] In this embodiment, if the collision risk between the first screen and the first obstacle does not meet preset conditions during the collision avoidance operation, the first screen can be controlled to continue unfolding at a preset speed. Thus, when the risk is detected to be eliminated, the first screen can be automatically controlled to continue unfolding without requiring the user to issue another unfolding command, thereby improving the user's driving experience.

[0124] Optionally, determining the first collision risk between the first screen and the first obstacle includes: inputting data collected by at least one of the multiple sensors into a prediction model to obtain the motion trajectory of the first obstacle over a future period; and determining the first collision risk between the first screen and the first obstacle based on the unfolding trajectory of the first screen and the motion trajectory of the first obstacle.

[0125] In this embodiment of the application, by inputting data collected by at least one of the multiple sensors into the prediction model, the motion trajectory of the first obstacle over a future period of time can be obtained, thereby determining the collision risk based on the unfolding trajectory of the first screen and the motion trajectory of the first obstacle.

[0126] Optionally, determining the first collision risk between the first screen and the first obstacle includes: inputting data collected by at least one of the multiple sensors into a prediction model to obtain the first collision risk between the first screen and the first obstacle.

[0127] For example, Figure 4 A schematic block diagram of a collision avoidance system 400 provided in an embodiment of this application is shown. The collision avoidance system 400 includes a collision risk assessment module 410 and an intelligent control module 420. The collision risk assessment module 410 includes a sensor data fusion module 411 and a collision risk prediction module 412. The intelligent control module 420 includes a screen unfolding speed control module 421, a seat movement control module 422, and a voice broadcast reminder module 423. The collision risk assessment module 410 can acquire data collected by one or more sensors in the perception system 110.

[0128] For example, the sensor data fusion module 411 can acquire data collected by multiple sensors and the weight corresponding to each sensor. The sensor data fusion module 411 can send the data collected by multiple sensors and the weight corresponding to each sensor to the collision risk prediction module 412. The collision risk prediction module 412 can assess the collision risk between the foldable screen and obstacles based on the data collected by multiple sensors and the weight corresponding to each sensor, obtaining a risk assessment result. The collision risk assessment module 410 can send the risk assessment result to the intelligent control module 420. The intelligent control module 420 can control the foldable screen, seat, or voice broadcast reminder module to interact with the user based on the risk assessment result.

[0129] Alternatively, the sensor data fusion module 411 can fuse the data collected by multiple sensors based on the weights corresponding to each sensor, obtaining fused data. The sensor data fusion module 411 can then send the fused data to the collision risk prediction module 412. The collision risk prediction module 412 can then assess the collision risk between the foldable screen and obstacles based on the fused data, obtaining a risk assessment result.

[0130] The above steps S320 can be executed by the sensor data fusion module 411; steps S330 can be executed by the collision risk prediction module 412, or steps S330 can be executed by both the sensor data fusion module 411 and the collision risk prediction module 412; steps S340 can be executed by the intelligent control module 420.

[0131] For example, the sensor data fusion module 411, since it involves sensor data from multiple modalities, can perform multimodal data fusion. For instance, the sensor data fusion module 411 can fuse data collected by multiple sensors spatially and temporally.

[0132] For example, the sensor data fusion module 411 can perform spatial data fusion, including coordinate transformation and fusion of point cloud data.

[0133] Coordinate transformation: Since different sensors are positioned in different locations, their coordinate systems are also different. By using the known positions and relative coordinate systems of the sensors, data transformation is performed to map all sensor data to a unified cockpit coordinate system (e.g., the world coordinate system).

[0134] Fusion of point cloud data: By using point cloud registration algorithms (such as the iterative closest point (ICP) algorithm), 3D data from different sensors are fused to form complete cabin spatial information. For example, 3D human pose is obtained from image data, and fusion is performed based on the 3D human pose and 3D point cloud data.

[0135] For example, the sensor data fusion module 411 can perform time-series data fusion. Since each sensor continuously samples throughout the data acquisition process, historical data and current data can be fused to obtain more comprehensive spatial data. Methods for time-series data fusion include, but are not limited to, time-series weighted averaging and motion trajectory prediction.

[0136] Time-series weighted average: For data with continuous motion, weighted averaging of historical data can smooth the current state and reduce interference from instantaneous changes and sensor errors.

[0137] Motion trajectory prediction: Based on historical data, machine learning algorithms (such as Long Short-Term Memory (LSTM) networks) can predict human motion trajectories. For example, the sensor data fusion module 411 can input 3D point cloud data, ultrasonic or infrared data into the prediction model to predict the motion trajectory of obstacles over a future period. The sensor data fusion module 411 can send the motion trajectory of the obstacle and the unfolding trajectory of the foldable screen to the collision risk prediction module 412, so that the collision risk prediction module 412 can determine the collision risk between the obstacle and the foldable screen based on the motion trajectory of the obstacle and the unfolding trajectory of the foldable screen.

[0138] For example, the sensor data fusion module 411 can perform weighted and multimodal fusion on data collected by multiple sensors (e.g., by fusing data collected by multiple sensors using a Bayesian inference method).

[0139] Weighted fusion: This method involves assigning different weights to sensors based on their accuracy and reliability. For example, ultrasonic sensors have high accuracy at close range, while vision sensors have high reliability under good lighting conditions.

[0140] Bayesian filtering: By using Bayesian inference methods, data from different sensors are probabilistically fused.

[0141] For example, the collision risk prediction module 412 can determine the collision risk between the foldable screen and an obstacle using the data fused by the sensor data fusion module 411. For instance, the collision risk prediction module 412 can classify the collision level of the foldable screen into low risk, medium risk, and high risk.

[0142] For example, the collision risk prediction module 412 can assess collision risk based on the distance between the foldable screen and an obstacle and / or the obstacle's movement trend. For instance, using fused data, it can calculate the distance between the foldable screen and obstacles such as people in real time, and assess collision risk based on a distance threshold between the foldable screen and the obstacle, where the distance threshold needs to be calibrated according to the specific in-vehicle conditions. Another example is using fused data to calculate the relative speed of the foldable screen relative to a person, and assessing collision risk based on this relative speed. Yet another example is using fused data to calculate the obstacle's movement trend, and assessing collision risk based on this movement trend.

[0143] For example, the collision risk prediction module 412 can input the fused data into a large model, neural network, or end-to-end model to obtain the aforementioned distance, relative speed, or obstacle motion trend.

[0144] If the vehicle's computing power allows, deep learning methods (such as LSTM networks) can be used to predict collision risks.

[0145] For example, the specific definition of collision risk is as follows:

[0146] Low risk: The distance between the foldable screen and obstacles such as people is greater than the safe distance threshold, and the obstacles such as people do not show a significant tendency to move towards the foldable screen.

[0147] Medium risk: The distance between the foldable screen and obstacles such as people is less than or equal to the safe distance threshold, or obstacles such as people have a clear tendency to move towards the foldable screen.

[0148] For example, the safe distance threshold for sedans can be 30cm. And for SUVs, the safe distance threshold can be 50cm.

[0149] High risk: The distance between the foldable screen and obstacles such as people is less than or equal to the danger distance threshold, or the capacitive sensor detects obvious contact, or the force sensor detects that the screen is obstructed from unfolding.

[0150] For example, the danger distance threshold for sedans can be 20cm. For SUVs, the danger distance threshold can be 40cm.

[0151] For example, the intelligent control module 420 may perform one or more of the following functions based on the collision risk: intelligent control of the foldable screen, intelligent control of the seat, and voice prompts.

[0152] For example, if the collision risk prediction module 412 determines that the current risk is low, the screen unfolding speed control module 421 can control the screen to unfold normally at a preset speed, and the voice broadcast reminder module 423 will not control the sound-emitting device to give a voice reminder.

[0153] For example, if the collision risk prediction module 412 determines that the current risk level is medium, the screen unfolding speed control module 421 can control the screen to pause unfolding. After the screen unfolding stops, the collision risk prediction module 412 can continue to detect the collision risk. If the collision risk drops to low risk, the screen unfolding speed control module 421 can control the screen to unfold normally at a preset speed. If the collision risk prediction module 412 continuously detects a medium or high risk level within 10 seconds from the time the screen unfolding is paused, the collision risk prediction module 412 can determine that the conditions for screen unfolding are not met and control the screen to collapse.

[0154] For example, if the collision risk prediction module 412 determines that the current risk is medium (e.g., the distance between obstacles such as human bodies and the foldable screen is less than or equal to the safe distance threshold), the voice broadcast reminder module 423 can control the sound device in the cockpit to broadcast an alarm tone, such as "Collision hazard detected, please maintain a safe distance, do you want to continue unfolding?"

[0155] For example, if the collision risk prediction module 412 determines that the current situation is at a medium risk (e.g., obstacles such as human bodies have a clear tendency to move towards the foldable screen), the voice broadcast reminder module 423 can control the sound device in the cockpit to broadcast an alarm sound, such as "The screen is unfolding, please do not move violently, do you want to continue unfolding?"

[0156] If the user instructs the screen to continue unfolding, the screen unfolding speed control module 421 can treat the medium-risk situation as a low-risk situation, that is, continue to control the screen to unfold at the preset speed. Alternatively, if the user instructs the screen to stop unfolding, the screen unfolding speed control module 421 can control the screen to retract. Or, if no voice response is received from the user within a preset time, it is treated as a medium-risk situation, that is, the screen can remain in the stopped unfolding state.

[0157] Alternatively, if the risk of collision between the foldable screen and an obstacle is high when the user instructs the screen to continue unfolding, then the user's instruction can be ignored.

[0158] For example, if the collision risk prediction module 412 determines that the current situation is high-risk, the screen unfolding speed control module 421 can control the screen to move in the opposite direction a short distance (designed according to different vehicle models and screen types). After the screen moves in the opposite direction a short distance, the collision risk prediction module 412 can continue to detect the collision risk. If the collision risk decreases to low risk, the screen unfolding speed control module 421 can continue to control the screen to unfold at a preset speed. If the collision risk prediction module 412 continuously detects a medium or high risk within 10 seconds after pausing the screen unfolding, the screen unfolding speed control module 421 can determine that the conditions for screen unfolding are not currently met and control the screen to retract.

[0159] For example, if the collision risk prediction module 412 determines that the current situation is high-risk (e.g., the foldable screen and obstacles such as people have reached the dangerous distance threshold), the voice broadcast reminder module 423 can control the sound device in the cockpit to broadcast an alarm sound, such as "Danger, the screen has stopped unfolding, please keep a safe distance from the screen".

[0160] For example, if the collision risk prediction module 412 determines that the current situation is high-risk (e.g., obvious contact is detected by data collected by the capacitive sensor), the voice broadcast reminder module 423 can control the sound device in the cockpit to broadcast an alarm sound, such as "Contact detected, the screen has paused its unfolding, please keep a safe distance from the screen".

[0161] For example, if the collision risk prediction module 412 determines that the current situation is at high risk (for example, the screen unfolding is obstructed by the data collected by the force sensor), the voice broadcast reminder module 423 can control the sound device in the cockpit to broadcast an alarm sound, such as "The screen unfolding is obstructed. Please ensure that there are no obstacles around."

[0162] The above example illustrates the three-level collision rating system, but the embodiments in this application are not limited to this. Collision rating detection is a dynamic process that changes over time. The sampling frequency can be designed based on the vehicle's computing power and the sensor's sampling frequency. The collision rating updates, screen controls, and voice prompts can also be continuously updated accordingly.

[0163] The above embodiments illustrate the detection of collision risks and the execution of corresponding anti-collision operations using a foldable screen (or screen) during its unfolding process. The following describes the execution of corresponding anti-collision operations after the foldable screen (or screen) is unfolded. The detection of collision risks after the foldable screen is unfolded can refer to the above-described detection of collision risks during the screen's unfolding process, and will not be repeated here.

[0164] For example, once the foldable screen is unfolded, the collision risk can be divided into the following three levels:

[0165] Low risk: The cabin is empty or there is no strenuous activity, and the distance between the seat and the screen is greater than the safe distance threshold.

[0166] Medium risk: There is significant vigorous activity among occupants in the cabin, or the distance between the seat and the screen is less than or equal to the safe distance threshold.

[0167] High risk: The capacitive sensor detects obvious contact, or the force sensor detects that the screen is obstructed from unfolding.

[0168] For example, the intelligent control module 420 can perform intelligent control of the foldable screen, intelligent control of the seat, and voice prompts based on the collision risk.

[0169] For example, if the collision risk prediction module 412 determines that the current risk is low, the screen unfolding speed control module 421 keeps the foldable screen unfolding at a preset speed and the voice broadcast reminder module 423 does not give a voice reminder to the user.

[0170] For example, if the collision risk prediction module 412 determines that the current risk is medium (e.g., the occupants are engaging in significant strenuous activity), the voice broadcast reminder module 423 can issue a voice reminder, such as "The screen is in the unfolded state, please do not engage in strenuous activity."

[0171] For example, if the collision risk prediction module 412 determines that the current risk is medium (e.g., the distance between the seat and the screen is less than or equal to the safe distance threshold), the seat movement control module 422 can control the seat to stop moving and the voice broadcast reminder module 423 can give a voice reminder, such as "The screen is in the unfolded state, the seat can no longer move backward."

[0172] For example, if the collision risk prediction module 412 determines that the current situation is high-risk, the voice broadcast reminder module 423 can issue a voice reminder, such as "A collision has occurred, please pay attention to safety. And pause the movement of the relevant hands."

[0173] Figure 5 A schematic block diagram of a collision avoidance device 500 provided in an embodiment of this application is shown. The device 500 includes: a control unit 520, configured to control a first screen to unfold in response to a first instruction received by an acquisition unit 510; the first screen being a foldable screen or curtain within the cockpit; the acquisition unit 510, further configured to acquire data collected by multiple sensors within the cockpit and acquire the weight corresponding to each of the multiple sensors; a determination unit 530, configured to determine a first collision risk between the first screen and a first obstacle based on the data collected by the multiple sensors and the weight corresponding to each of the multiple sensors; and a collision avoidance operation execution unit 540, configured to execute a collision avoidance operation when the first collision risk meets preset conditions.

[0174] Optionally, the multiple sensors include a vision sensor and a distance sensor, wherein the acquisition unit 510 is configured to: acquire a first weight corresponding to the vision sensor and a second weight corresponding to the distance sensor based on the lighting conditions inside the cockpit; or, acquire a third weight corresponding to the vision sensor and a fourth weight corresponding to the distance sensor based on the distance between the first obstacle and the first screen.

[0175] Optionally, when the lighting conditions indicate that the light intensity inside the cabin is greater than or equal to a preset light intensity, the first weight is greater than the second weight; or, when the lighting conditions indicate that the light intensity inside the cabin is less than or equal to a preset light intensity, the first weight is less than or equal to the second weight.

[0176] Optionally, when the distance between the first obstacle and the first screen is less than or equal to the first preset distance, the third weight is less than the fourth weight; or, when the distance between the first obstacle and the first screen is greater than the first preset distance, the third weight is greater than or equal to the fourth weight.

[0177] Optionally, the multiple sensors include a third sensor, which is used to detect whether the first screen collides with the first obstacle. Before the first obstacle collides with the first screen, the third sensor has a weight of the fifth weight; or, if the first obstacle collides with the first screen, the third sensor has a weight of the sixth weight; wherein the fifth weight is less than the sixth weight.

[0178] Optionally, the control unit 520 is configured to, when the determining unit determines, based on data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle, control the first screen to move a distance in the direction opposite to the unfolding direction and control the alarm device to indicate that a collision has occurred between the first screen and the first obstacle; the acquisition unit 510 is further configured to, in response to the acquisition unit acquiring a first instruction from the user and the determining unit determining, based on data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle, ignore the first instruction, which instructs the first screen to unfold.

[0179] Optionally, the determining unit 530 is used to determine the distance between the first screen and the first obstacle; the anti-collision operation execution unit is used to perform an anti-collision operation when the distance is less than or equal to a second preset distance.

[0180] Optionally, the determining unit 530 is used to determine the movement trend of the first obstacle; the anti-collision operation execution unit is used to perform an anti-collision operation when the movement trend of the first obstacle indicates that the first obstacle is moving toward the first screen.

[0181] Optionally, the anti-collision operation execution unit 540 is used to: control the unfolding speed of the first screen, or control the first screen to move a distance in the opposite direction of the unfolding direction, or control the first screen to stop unfolding if the first collision risk meets the preset conditions during the unfolding process of the first screen.

[0182] Optionally, the control unit 520 is configured to: when the first collision risk meets preset conditions during the unfolding of the first screen, control the alarm device to indicate that there is a collision risk between the first screen and the first obstacle; and in response to the acquisition unit acquiring a second instruction from the user, control the first screen to continue unfolding and update the preset conditions, wherein the second instruction instructs the first screen to unfold.

[0183] Optionally, the determining unit 530 is used to determine the second collision risk between the first screen and the first obstacle based on the weight of each sensor and the data collected by each sensor during the anti-collision operation execution by the anti-collision operation execution unit; the control unit is used to control the first screen to continue unfolding at a preset speed if the second collision risk does not meet the preset conditions.

[0184] Optionally, the determining unit 530 is configured to: input data collected by at least one of the multiple sensors into a prediction model to obtain the motion trajectory of the first obstacle over a future period of time; and determine the first collision risk between the first screen and the first obstacle based on the unfolding trajectory of the first screen and the motion trajectory of the first obstacle.

[0185] It should be understood that the division of units in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units in the device can be implemented by a processor calling software; for example, the device includes a processor connected to memory, which stores instructions. The processor calls the instructions stored in memory to implement any of the above methods or to implement the functions of each unit in the device. The processor can be, for example, a general-purpose processor, such as a CPU or microprocessor, and the memory can be internal or external to the device. Alternatively, the units in the device can be implemented as hardware circuits. The functions of some or all units can be implemented through the design of the hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all units are implemented through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a PLD, such as an FPGA, which can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby implementing the functions of some or all units. All units of the above devices can be implemented entirely through processor calling software, or entirely through hardware circuits, or partially through processor calling software with the remaining parts implemented through hardware circuits.

[0186] In this application embodiment, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a CPU, microprocessor, GPU, or DSP. In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented as an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the processor loading instructions to implement the functions of some or all of the above units. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, or DPU.

[0187] As can be seen, each unit in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0188] Furthermore, the units in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these units are integrated together and implemented as a System-on-Chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the units in the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and AI processor, CPU and GPU, etc.

[0189] This application also provides an anti-collision device, which includes a processing unit and a storage unit. The storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit to cause the device to perform the methods or steps described in the above embodiments.

[0190] Optionally, if the collision avoidance device is located in the vehicle, the aforementioned processing unit may be Figure 1 The processors shown are 151-15n.

[0191] This application embodiment also provides a collision avoidance system, which may include a computing platform and a sensing system, and the computing platform may include the above-described collision avoidance device 500.

[0192] Optionally, the sensing system includes a visual sensor and a distance sensor.

[0193] Optionally, the sensing system includes a capacitive sensor or a force sensor.

[0194] This application also provides a vehicle that may include the above-described collision avoidance device 500 or collision avoidance system.

[0195] This application also provides a computer program product, which includes computer program code that, when run on a computer, causes the computer to perform the methods described in the above embodiments.

[0196] This application also provides a computer-readable medium storing program code that, when run on a computer, causes the computer to perform the methods described in the above embodiments.

[0197] This application also provides a chip, which includes circuitry for performing the methods described in the above embodiments.

[0198] In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software. The method disclosed in the embodiments of this application can be directly implemented by a hardware processor, or by a combination of hardware and software modules within the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, power-on erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are omitted here.

[0199] It should be understood that in the embodiments of this application, the memory may include read-only memory and random access memory, and provides instructions and data to the processor.

[0200] It should also be understood that, in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0201] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein 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.

[0202] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0203] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of 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 system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0204] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0205] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0206] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0207] 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 technical scope disclosed in this application should be covered. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A collision avoidance method, characterized in that, include: In response to receiving a first command, control the first screen to unfold, wherein the first screen is a foldable screen or curtain inside the cockpit; Acquire data collected by multiple sensors within the cockpit and obtain the weight corresponding to each of the multiple sensors; Based on the data collected by the multiple sensors and the weight of each sensor, the first collision risk between the first screen and the first obstacle is determined. If the first collision risk meets the preset conditions, a collision avoidance operation is performed.

2. The method according to claim 1, characterized in that, The multiple sensors include vision sensors and distance sensors. The step of obtaining the weight corresponding to each of the plurality of sensors includes: Based on the lighting conditions inside the cockpit, obtain the first weight corresponding to the visual sensor and the second weight corresponding to the distance sensor; or... Based on the distance between the first obstacle and the first screen, obtain the three weights corresponding to the visual sensor and the fourth weight corresponding to the distance sensor.

3. The method according to claim 2, characterized in that, When the lighting conditions indicate that the light intensity inside the cabin is greater than or equal to a preset light intensity, the first weight is greater than the second weight; or... When the lighting conditions indicate that the light intensity inside the cabin is less than the preset light intensity, the first weight is less than or equal to the second weight.

4. The method according to claim 2, characterized in that, When the distance between the first obstacle and the first screen is less than or equal to the first preset distance, the third weight is less than the fourth weight; or, When the distance between the first obstacle and the first screen is greater than the first preset distance, the third weight is greater than or equal to the fourth weight.

5. The method according to claim 1, characterized in that, The plurality of sensors includes a third sensor, which is used to detect whether the first screen collides with the first obstacle. Before the first obstacle collides with the first screen, the weight corresponding to the third sensor is the fifth weight; or, when the first obstacle collides with the first screen, the weight corresponding to the third sensor is the sixth weight. The fifth weight is less than the sixth weight.

6. The method according to claim 5, characterized in that, The step of performing a collision avoidance operation when the first collision risk meets the preset conditions includes: If it is determined from the data collected by the third sensor that a collision has occurred between the first screen and the first obstacle, the first screen is controlled to move a certain distance in the opposite direction to the unfolding direction and the alarm device is controlled to indicate that a collision has occurred between the first screen and the first obstacle. In response to receiving a first instruction from the user and determining, based on data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle, the first instruction is ignored, and the first instruction instructs the first screen to unfold.

7. The method according to any one of claims 1 to 6, characterized in that, Determining the first collision risk between the first screen and the first obstacle includes: Determine the distance between the first screen and the first obstacle; Wherein, the step of performing a collision avoidance operation when the first collision risk meets the preset conditions includes: If the distance is less than or equal to the second preset distance, the anti-collision operation is performed.

8. The method according to any one of claims 1 to 7, characterized in that, Determining the first collision risk between the first screen and the first obstacle includes: Determine the movement trend of the first obstacle; Wherein, the step of performing a collision avoidance operation when the first collision risk meets the preset conditions includes: The anti-collision operation is performed when the movement trend of the first obstacle indicates that the first obstacle is moving toward the first screen.

9. The method according to any one of claims 1 to 8, characterized in that, The step of performing a collision avoidance operation when the first collision risk meets the preset conditions includes: If the first collision risk meets the preset conditions during the unfolding of the first screen, the unfolding speed of the first screen is controlled, or the first screen is controlled to move a distance in the opposite direction of the unfolding direction, or the first screen is controlled to stop unfolding.

10. The method according to any one of claims 1 to 9, characterized in that, The process of performing the anti-collision operation includes: If the first collision risk meets the preset condition during the unfolding of the first screen, the control alarm device will indicate that there is a collision risk between the first screen and the first obstacle. In response to receiving a second instruction from the user, the system controls the first screen to continue expanding and updates the preset conditions, wherein the second instruction instructs the first screen to expand.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: During the collision avoidance operation, a second collision risk between the first screen and the first obstacle is determined based on the weight of each sensor and the data collected by each sensor. If the second collision risk does not meet the preset conditions, the first screen is controlled to continue unfolding at a preset speed.

12. The method according to any one of claims 1 to 11, characterized in that, Determining the first collision risk between the first screen and the first obstacle includes: The data collected by at least one of the multiple sensors is input into the prediction model to obtain the trajectory of the first obstacle over a future period of time. Based on the unfolding trajectory of the first screen and the movement trajectory of the first obstacle, a first collision risk between the first screen and the first obstacle is determined.

13. A collision avoidance device, characterized in that, include: The control unit is used to control the first screen to unfold in response to the acquisition unit acquiring the first instruction. The first screen is a foldable screen or curtain in the cockpit. The acquisition unit is also used to acquire data collected by multiple sensors in the cockpit and to acquire the weight of each sensor among the multiple sensors; The determining unit is configured to determine the first collision risk between the first screen and the first obstacle based on the data collected by the plurality of sensors and the weight corresponding to each of the plurality of sensors. The collision avoidance operation execution unit is used to perform a collision avoidance operation when the first collision risk meets the preset conditions.

14. The apparatus according to claim 13, characterized in that, The multiple sensors include vision sensors and distance sensors. The acquisition unit is used for: Based on the lighting conditions inside the cockpit, obtain the first weight corresponding to the visual sensor and the second weight corresponding to the distance sensor; or... Based on the distance between the first obstacle and the first screen, obtain the three weights corresponding to the visual sensor and the fourth weight corresponding to the distance sensor.

15. The apparatus according to claim 14, characterized in that, When the lighting conditions indicate that the light intensity inside the cabin is greater than or equal to a preset light intensity, the first weight is greater than the second weight; or... When the lighting conditions indicate that the light intensity inside the cabin is less than the preset light intensity, the first weight is less than or equal to the second weight.

16. The apparatus according to claim 14, characterized in that, When the distance between the first obstacle and the first screen is less than or equal to the first preset distance, the third weight is less than the fourth weight; or, When the distance between the first obstacle and the first screen is greater than the first preset distance, the third weight is greater than or equal to the fourth weight.

17. The apparatus according to claim 13, characterized in that, The plurality of sensors includes a third sensor, which is used to detect whether the first screen collides with the first obstacle. Before the first obstacle collides with the first screen, the weight corresponding to the third sensor is the fifth weight; or, when the first obstacle collides with the first screen, the weight corresponding to the third sensor is the sixth weight. The fifth weight is less than the sixth weight.

18. The apparatus according to claim 17, characterized in that, The control unit is configured to, when the determining unit determines, based on the data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle, control the first screen to move a distance in the direction opposite to the unfolding direction and control the alarm device to indicate that a collision has occurred between the first screen and the first obstacle. The acquisition unit is further configured to ignore the first instruction when the acquisition unit acquires the user's first instruction and the determination unit determines, based on the data collected by the third sensor, that a collision has occurred between the first screen and the first obstacle, and the first instruction instructs the first screen to unfold.

19. The apparatus according to any one of claims 13 to 18, characterized in that, The determining unit is used to determine the distance between the first screen and the first obstacle; The anti-collision operation execution unit is used to perform the anti-collision operation when the distance is less than or equal to the second preset distance.

20. The apparatus according to any one of claims 13 to 19, characterized in that, The determining unit is used to determine the movement trend of the first obstacle; The anti-collision operation execution unit is used to execute the anti-collision operation when the movement trend of the first obstacle indicates that the first obstacle is moving towards the first screen.

21. The apparatus according to any one of claims 13 to 20, characterized in that, The anti-collision operation execution unit is used for: If the first collision risk meets the preset conditions during the unfolding of the first screen, the unfolding speed of the first screen is controlled, or the first screen is controlled to move a distance in the opposite direction of the unfolding direction, or the first screen is controlled to stop unfolding.

22. The apparatus according to any one of claims 13 to 21, characterized in that, The control unit is used for: If the first collision risk meets the preset condition during the unfolding of the first screen, the control alarm device will indicate that there is a collision risk between the first screen and the first obstacle. In response to the acquisition unit receiving a second instruction from the user, the first screen is controlled to continue expanding and the preset conditions are updated, wherein the second instruction instructs the first screen to expand.

23. The apparatus according to any one of claims 13 to 22, characterized in that, The determining unit is used to determine the second collision risk between the first screen and the first obstacle based on the weight corresponding to each sensor and the data collected by each sensor during the process of the anti-collision operation execution unit performing the anti-collision operation; The control unit is configured to control the first screen to continue unfolding at a preset speed if the second collision risk does not meet the preset conditions.

24. The apparatus according to any one of claims 13 to 23, characterized in that, The determining unit is used for: The data collected by at least one of the multiple sensors is input into the prediction model to obtain the trajectory of the first obstacle over a future period of time. Based on the unfolding trajectory of the first screen and the movement trajectory of the first obstacle, a first collision risk between the first screen and the first obstacle is determined.

25. A collision avoidance device, characterized in that, include: Memory, used to store computer programs; A processor for executing a computer program stored in the memory to cause the apparatus to perform the method as described in any one of claims 1 to 12.

26. A collision avoidance system, characterized in that, It includes a sensing system and a computing platform, wherein the computing platform includes the apparatus as described in any one of claims 13 to 25.

27. A vehicle, characterized in that, Includes the apparatus as described in any one of claims 13 to 25, or the system as described in claim 26.

28. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by a processor, cause the processor to implement the method as described in any one of claims 1 to 12.

29. A computer program product, characterized in that, The computer program product includes computer program code that, when run on a computer, causes the computer to perform the method as described in any one of claims 1 to 12.

30. A chip, characterized in that, The chip includes circuitry for performing the method as described in any one of claims 1 to 12.

Images