A method, device, and vehicle for preventing pinching in a motion device.

Abstract

This application provides a method, device, and vehicle for preventing pinching of a motion device. The process of switching the motion device from an unlocked state to a fully locked state includes a first pause phase and / or a first engagement phase. The method includes: acquiring sensing information indicating information about obstacles located within a first range of the motion device; determining, based on the sensing information, whether there is a risk of pinching injury, indicating the risk that the motion device may pinch the obstacle; controlling the motion device to execute the first engagement phase when there is no risk of pinching injury; or, controlling the motion device to execute the first pause phase for a first duration when there is a risk of pinching injury. By setting a first pause phase and / or a first engagement phase during the process of switching the motion device from an unlocked state to a fully locked state, and determining the engagement process of the motion device based on the risk of pinching injury, the risk of the motion device pinching the user or obstacle is effectively reduced, and the safety of the motion device is improved.

Description

Technical Field

[0001] This application relates to the field of motion devices, and more specifically, to a method, device, and vehicle for preventing pinching in motion devices. Background Technology

[0002] Many vehicles are now equipped with power doors, power hoods, and other motion control devices. Taking power doors as an example, the following problems exist in actual use: the traction force at the end of the closing phase is relatively large and the travel is short. When a user's limbs are near the door gap or gripping the door edge to close the door, solutions relying on motor stall or Hall current surges to detect whether a user's limbs are near the door gap exhibit response lag. For solutions relying on cameras for detection, changes in lighting, camera damage, or obstruction may lead to missed detections, potentially causing user injury.

[0003] Therefore, how to reduce the risk of motion devices getting stuck on obstacles and improve the user experience of motion devices has become an urgent problem to be solved. Summary of the Invention

[0004] This application provides a method, device, and vehicle for preventing pinching of a motion device. By acquiring sensory information to determine the risk of pinching injury, and determining the suction process of the motion device based on the magnitude of the pinching injury risk, it is beneficial to optimize the operating mechanism of the motion device and improve the safety and user experience of the motion device.

[0005] In a first aspect, a method for preventing pinching of a motion device is provided. The process of switching the motion device from an unlocked state to a fully locked state includes a first pause phase and / or a first engagement phase. The method includes: acquiring sensing information indicating information about an obstacle located within a first range of the motion device; determining, based on the sensing information, whether there is a risk of pinching injury, the risk of pinching injury indicating the risk that the motion device may pinch the obstacle; controlling the motion device to perform the first engagement phase when there is no risk of pinching injury; or, controlling the motion device to perform the first pause phase for a first duration when there is a risk of pinching injury.

[0006] For example, obstacles may include people (users), animals (such as the user's pet), objects, etc. The risks of the motion device getting caught in an obstacle include the risk of injury when a person or animal is caught in the motion device, and the risk of damage to the motion device caused by an object obstructing it during the suction process.

[0007] When there is no risk of pinching injury, the motion device can engage directly without pausing, improving the smoothness of the closing process. When there is a risk of pinching injury, the motion device can pause engagement and resume engagement only after the risk is eliminated, or it can stop engagement altogether. Based on the above technical solutions, determining the engagement process of the motion device according to the presence or absence of pinching injury risk helps optimize the operating mechanism of the motion device, reduces the risk of the motion device pinching obstacles, and improves the safety of the vehicle's motion device.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, the process includes a first pause phase and a first engagement phase. The control of the motion device to perform the first engagement phase includes: when there is no risk of pinching injury, the control of the motion device to perform the first pause phase for a second duration, the second duration being shorter than the first duration; after the first pause phase ends, the control of the motion device to perform the first engagement phase.

[0009] Based on the above technical solution, when the motion device sequentially executes the first pause stage and the first engagement stage during the process of switching to the fully locked state, engagement can be performed after a short pause when there is no risk of pinching injury. Compared with the engagement process when there is a risk of pinching injury, by shortening the duration of the first pause stage, the engagement process can be optimized, thereby improving the smoothness of the motion device during the closing process.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the motion device is the motion device of a vehicle, and the method further includes: acquiring state information of other components of the vehicle; determining whether there is a risk of pinching injury based on the perception information, including: determining whether there is a risk of pinching injury based on the perception information and the state information of other components.

[0011] For example, the moving device could be a vehicle door, hood, tailgate, sunroof, etc. When acquiring sensory information and determining whether there is a risk of pinching injury based on that information, the state of other vehicle components may affect the content of the sensory information. For instance, assuming the moving device is a rear door, the opening angle of the front door on the same side as the moving device might affect the acquisition of visual information associated with that device; during the acquisition of audio information, music played by the vehicle might interfere with the audio information.

[0012] Based on the above technical solution, by comprehensively analyzing the status information and perception information of other vehicle components, the accuracy of pinch risk detection can be improved, and misjudgments caused by incomplete or interfered single perception information can be reduced.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, the moving device is a first door, the other components are a second door on the same side as the first door, the status information is the opening and closing information of the second door, and the presence or absence of a pinching risk is determined based on the sensing information and the status information of the other components, including: determining whether there is a pinching risk based on the sensing information and the opening and closing information.

[0014] In the above technical solution, by acquiring the opening and closing information of other doors on the same side as the motion device, and comprehensively analyzing their impact on the detection of the motion device, the assessment of the risk of pinching injury is further optimized, and the comprehensiveness and accuracy of the detection of the risk of pinching injury are improved.

[0015] In conjunction with the first aspect, in some implementations of the first aspect, the first door is the rear door, the second door is the front door on the same side as the rear door, and the perception information includes audio information and visual information. The visual information is acquired by a camera device located on the side of the front of the vehicle on the same side as the first door and facing the rear of the vehicle. Based on the perception information and the opening and closing information, it is determined whether there is a risk of pinching injury, including: when the opening and closing information indicates that the opening angle of the front door is greater than or equal to an angle threshold, it is determined whether there is a risk of pinching injury based on the audio information.

[0016] Based on the above technical solution, when the opening angle of the front door is too large and the visual detection of the rear door is blocked by the front door, using audio information as the main criterion for judging the risk of pinching can ensure the availability and reliability of the anti-pinch function of the motion device and reduce the safety hazards caused by visual detection failure.

[0017] In conjunction with the first aspect, in some implementations of the first aspect, the perceived information includes visual information. Based on the perceived information, determining whether there is a risk of pinching includes: based on the visual information, determining the degree of overlap between the obstacle and the preset danger zone of the motion device, wherein the preset danger zone is the space area within a preset distance around the edge of the motion device or the gap between the motion device and the outer frame; and based on the degree of overlap information, determining whether there is a risk of pinching.

[0018] Based on the above technical solution, by analyzing the degree of overlap between the obstacle and the preset danger zone of the motion device, the existence of pinch risk can be quantitatively assessed, which helps to improve the accuracy and reliability of pinch risk detection.

[0019] In conjunction with the first aspect, in some implementations of the first aspect, the obstacle includes the user, and the overlap information indicates the number of markers on the user's limbs located within a preset danger zone. Based on the overlap information, it is determined whether there is a risk of pinching injury, including: determining whether there is a risk of pinching injury based on the number and a preset number threshold.

[0020] Based on the above technical solution, by marking and counting the number of key points on the user's limbs, the degree of danger of the user's limbs in the preset risk zone can be accurately identified, thereby further improving the safety of the exercise device.

[0021] In conjunction with the first aspect, in certain implementations of the first aspect, the perceived information includes visual information, and determining whether there is a risk of pinching based on the perceived information includes: determining a first distance between the obstacle and the edge of the motion device, and / or a second distance between the obstacle and the gap between the motion device and the outer frame, based on the visual information; and determining whether there is a risk of pinching based on the first distance and / or the second distance.

[0022] Based on the above technical solution, by measuring the distance between the obstacle and the edge or gap of the motion device, the risk of pinching injury can be quantitatively assessed, which helps to improve the flexibility and reliability of the assessment of the risk of pinching injury.

[0023] In conjunction with the first aspect, in some implementations of the first aspect, when there is a risk of pinching injury, the method further includes at least one of the following: providing risk information to the motion device; controlling the motion device to move in the opposite direction to the current direction of motion.

[0024] For example, controlling the motion device to move in the opposite direction to the current motion direction means increasing the distance between the motion device and the outer frame or increasing the opening angle of the motion device.

[0025] Based on the above technical solution, when there is a risk of pinching injury, by prompting the user or controlling the movement of the motion device in the opposite direction, it is ensured that the motion device can take safety measures quickly and effectively when the risk is detected, thereby improving the safety of the motion device.

[0026] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: when the confidence level of the perceived information is less than or equal to a confidence threshold, or when the sensor used to acquire the perceived information malfunctions, controlling the motion device to execute a first pause phase for a third duration, wherein the third duration is greater than the first duration, and / or, the third duration is greater than the duration of the first pause phase when the confidence level is greater than the confidence threshold.

[0027] For example, taking images as perceived information, when the camera is obstructed, severely damaged, or backlit, the confidence level of the image is less than the confidence threshold; taking audio information as an example, when the noise inside the vehicle is too high, it is difficult to distinguish the semantics indicated by the audio information, and the confidence level of the audio information is less than the confidence threshold.

[0028] During the first pause phase, which is executed for the third duration, multiple sensing information can be acquired and multiple pinch risk detections can be performed, or the device can wait for the obstacle to move away from it. Based on the above technical solution, it is ensured that the motion device can still operate with a high degree of safety even if the sensing information is inaccurate or the sensor is malfunctioning, thus avoiding the risk of pinching due to detection errors.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, the perceived information includes at least one of the following: image, point cloud information, thermal imaging information, infrared light information, and audio information.

[0030] Based on the above technical solution, by integrating multiple sensing data such as images, point cloud information, thermal imaging information, and infrared light information, the accuracy and robustness of pinch risk detection are comprehensively improved. This helps to reduce the limitations of a single sensing method, thereby improving the accuracy of pinch risk detection.

[0031] In conjunction with the first aspect, in some implementations of the first aspect, acquiring sensing information includes: acquiring sensing information based on sensors corresponding to the location of the motion device.

[0032] Based on the above technical solution, by using sensors corresponding to the location of the motion device to obtain sensing information, the accuracy and reliability of pinch risk detection can be improved, thereby enhancing the practicality of the anti-pinch function of the motion device.

[0033] In conjunction with the first aspect, in some implementations of the first aspect, the motion device is a motion device for the first device, and acquiring sensing information includes: receiving sensing information sent by a second device that is communicatively connected to the first device.

[0034] Assuming the first device is a vehicle, the second device can be a user's terminal device (such as a mobile phone, watch, or earphones). The vehicle can acquire the perception information from the terminal device in real time. Optionally, the second device can be a camera device around the vehicle, such as a camera installed in a home garage or a camera on a charging station. This can reduce blind spots between obstacles and moving devices by providing images from multiple angles, which helps to more accurately assess the risk of pinching.

[0035] Based on the above technical solution, using the sensing information detected by the second device and combining it with the sensing information of the first device corresponding to the motion device helps to improve the comprehensiveness and accuracy of the sensing information.

[0036] Secondly, an anti-pinch device for a motion device is provided. The process of the motion device switching from an unlocked state to a fully locked state includes a first pause phase and / or a first engagement phase. The device includes: an acquisition unit for acquiring sensing information, the sensing information indicating information about obstacles located within a first range of the motion device; a processing unit for determining, based on the sensing information, whether there is a risk of pinching injury, the pinching risk indicating the risk of the motion device pinching the obstacle; and a control unit for controlling the motion device to perform the first engagement phase when there is no risk of pinching injury; or, controlling the motion device to perform the first pause phase for a first duration when there is a risk of pinching injury.

[0037] In conjunction with the second aspect, in some implementations of the second aspect, the process includes a first pause phase and a first engagement phase. The control unit is specifically used to: control the motion device to execute the first pause phase for a second duration when there is no risk of pinching injury, the second duration being shorter than the first duration; and control the motion device to execute the first engagement phase after the first pause phase ends.

[0038] In conjunction with the second aspect, in some implementations of the second aspect, the motion device is the motion device of a vehicle, and the acquisition unit is further configured to: acquire state information of other components of the vehicle; the processing unit is specifically configured to: determine whether there is a risk of pinching injury based on the perception information and the state information of other components.

[0039] In conjunction with the second aspect, in some implementations of the second aspect, the moving device is the first door, the other components are the second door on the same side as the first door, and the status information is the opening and closing information of the second door. The processing unit is specifically used to: determine whether there is a risk of pinching injury based on the sensing information and the opening and closing information.

[0040] In conjunction with the second aspect, in some implementations of the second aspect, the first door is the rear door, the second door is the front door on the same side as the rear door, and the perception information includes audio information and visual information. The visual information is acquired by a camera device located on the side of the front of the vehicle on the same side as the first door and facing the rear of the vehicle. The processing unit is specifically used to: determine whether there is a risk of pinching injury based on the audio information when the opening angle of the front door is greater than or equal to the angle threshold indicated by the opening and closing information.

[0041] In conjunction with the second aspect, in some implementations of the second aspect, the perceived information includes visual information. The processing unit is specifically used to: determine the degree of overlap between the obstacle and the preset danger zone of the motion device based on the visual information. The preset danger zone is the space area within a preset distance around the edge of the motion device or the gap between the motion device and the outer frame; and determine whether there is a risk of pinching injury based on the degree of overlap information.

[0042] In conjunction with the second aspect, in some implementations of the second aspect, the obstacle includes the user, and the overlap information indicates the number of markers on the user's limbs located within a preset danger zone. The processing unit is specifically used to: determine whether there is a risk of pinching injury based on the number and a preset number threshold.

[0043] In conjunction with the second aspect, in some implementations of the second aspect, the perceived information includes visual information, and the processing unit is specifically used to: determine, based on the visual information, a first distance between the obstacle and the edge of the motion device, and / or a second distance between the obstacle and the gap between the motion device and the outer frame; and determine, based on the first distance and / or the second distance, whether there is a risk of pinching injury.

[0044] In conjunction with the second aspect, in some implementations of the second aspect, when there is a risk of pinching injury, the control unit is also used to perform at least one of the following: providing risk information to the motion device; controlling the motion device to move in the opposite direction to the current direction of motion.

[0045] In conjunction with the second aspect, in some implementations of the second aspect, the control unit is further configured to: control the motion device to execute a first pause phase for a third duration when the confidence level of the perceived information is less than or equal to a confidence threshold, or when the sensor used to acquire the perceived information malfunctions, wherein the third duration is greater than the first duration, and / or the third duration is greater than the duration of the first pause phase when the confidence level is greater than the confidence threshold.

[0046] In conjunction with the second aspect, in some implementations of the second aspect, the perceived information includes at least one of the following: image, point cloud information, thermal imaging information, infrared light information, and audio information.

[0047] In conjunction with the second aspect, in some implementations of the second aspect, the acquisition unit is specifically used to: acquire sensing information based on a sensor corresponding to the location of the motion device.

[0048] In conjunction with the second aspect, in some implementations of the second aspect, the motion device is the motion device of the first device, and the acquisition unit is specifically used to: receive sensing information sent by the second device that is communicatively connected to the first device.

[0049] Thirdly, an anti-pinch device for a motion device is provided, comprising: a processor for executing a computer program stored in a memory, such that the device performs the method in any possible implementation of the first aspect described above.

[0050] In conjunction with the third aspect, in some implementations of the third aspect, the device also includes a memory.

[0051] Fourthly, a computer program product is provided, comprising: computer program code, which, when executed on a computer or processor, causes the computer or processor to perform the method in any possible implementation of the first aspect.

[0052] It should be noted that the above computer program code can be stored in whole or in part on a storage medium, which can be packaged together with the processor or packaged separately from the processor.

[0053] Fifthly, a computer-readable storage medium is provided, the computer-readable medium storing instructions that, when executed by a processor, cause the processor to implement the method in any possible implementation of the first aspect.

[0054] In a sixth aspect, a chip is provided that includes circuitry for performing the method in any of the possible implementations of the first aspect described above.

[0055] In a seventh aspect, a vehicle is provided that includes means as in any possible implementation of the second or third aspect, or includes a computer-readable storage medium as in any possible implementation of the fifth aspect, or includes a chip as in any possible implementation of the sixth aspect, or is loaded with a computer program product as in any possible implementation of the fourth aspect.

[0056] The beneficial effects not described in detail in aspects two through seven above can be referred to the description in aspect one, and will not be repeated here. Attached Figure Description

[0057] Figure 1 This is a schematic diagram of a vehicle 100 according to an embodiment of this application.

[0058] Figure 2 This is a schematic diagram of a system architecture according to an embodiment of this application.

[0059] Figure 3 This is a schematic diagram of a system architecture according to an embodiment of this application.

[0060] Figure 4 This is a flowchart illustrating an anti-pinch method 400 according to an embodiment of this application.

[0061] Figure 5 This is a schematic diagram of a scenario according to an embodiment of this application.

[0062] Figure 6 This is a schematic diagram of a scenario according to an embodiment of this application.

[0063] Figure 7 This is a schematic diagram of a scenario according to an embodiment of this application.

[0064] Figure 8 This is a timing diagram of an embodiment of this application.

[0065] Figure 9 This is a timing diagram of an embodiment of this application.

[0066] Figure 10 This is a flowchart illustrating an anti-pinch method 1000 according to an embodiment of this application.

[0067] Figure 11 This is a schematic diagram of an anti-pinch device 1100 according to an embodiment of this application. Detailed Implementation

[0068] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this embodiment, unless otherwise stated, "multiple" means two or more. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0069] The terminology used in the following embodiments is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” and “this” are intended to also include expressions such as “one or more,” unless the context clearly indicates otherwise. It should also be understood that in the following embodiments of this application, “at least one” and “one or more” refer to one, two, or more than two. The term “and / or” is used to describe the relationship between related objects, indicating that three relationships can exist; for example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character “ / ” generally indicates that the preceding and following related objects are in an “or” relationship.

[0070] The motion device in this application refers to a device that moves using an electric motor. Taking a vehicle as an example, the motion device includes doors, a front hatch, a tailgate, a sunroof, etc. For industrial vehicles and logistics vehicles, it can include cargo tailgates, sliding doors, refrigerated truck doors, and cargo hatch covers of automated guided vehicles (AGVs) that close via electric mechanisms. Furthermore, in the fields of intelligent buildings or rail transit, the motion device can be an automatic swing door, subway platform screen doors, platform screen doors, barrier-free lifting platforms, or elevator doors. For equipment in low-altitude vehicles or cabin structures, the motion device can be an electric hatch, a fairing, or other movable structure with a suction or quick-closing stroke.

[0071] Taking an electric door as an example, during the closing process, the electric door needs to switch from a pre-locked state to a fully locked state via electric suction. Electric suction refers to the motor-driven process that pulls the door cover mechanism to the fully locked state after the electric door is pre-locked. Electric suction can be divided into multiple stages, with different power in each stage, and there may be a fixed pause time between each stage. The pre-locked state can also be called the half-locked state, indicating that the door cover mechanism of the moving device has reached a pre-closed state that can trigger electric suction. The fully locked state indicates the completely closed state after the moving device has completed suction. Alternatively, the pre-locked state indicates that the door cover mechanism is in the pre-locked position, which is the position where the door cover mechanism is close to closed but not fully locked; the fully locked state indicates that the door cover mechanism is in the fully locked position.

[0072] During the closing process of electric gates, for some gates with a fixed pause time, the user needs to wait a while after moving away from the edge of the gate before it reaches the fully locked state. This makes the closing process less smooth and may affect the user experience. Furthermore, relying solely on visual detection to determine whether an electric gate is trapping an obstacle may lead to missed or incorrect detections in poor lighting conditions or when the sensor's line of sight is obstructed.

[0073] Therefore, this application proposes a method, device, and vehicle for preventing pinching of a motion device. The suction process of the motion device can be determined based on whether there is a risk of pinching injury, which helps to optimize the operation process of the motion device and improve its safety and user experience.

[0074] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0075] Figure 1This is a functional schematic diagram of a vehicle 100 provided in an embodiment of this application. The vehicle 100 may include a perception system 110 and a computing platform 120. The perception system 110 may include one or more sensors that detect information about the surrounding environment of the vehicle 100. For example, the perception system 110 may include a positioning system, which may be a Global Positioning System (GPS), a BeiDou system, or another positioning system. As another example, the perception system 110 may include one or more of the following: a weather sensor, an inertial measurement unit (IMU), an accelerometer, a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0076] Some or all of the functions of vehicle 100 can be controlled by computing platform 120. Computing platform 120 may include processors 121, 122 to 12n (n being a positive integer). 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 processor loading instructions to implement related functions. In addition, it can also be hardware circuits designed for artificial intelligence, which can be understood as a type of ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. Furthermore, the computing platform 120 may also include a memory for storing instructions. Some or all of the processors 121 to 12n can call and execute the instructions in the memory to achieve the corresponding functions.

[0077] The human-computer interaction system 130 includes a device for receiving user instructions and a device for providing prompts to the user. The device for receiving user instructions may include at least one of the following: a sound receiving device for receiving user voice instructions, such as a microphone, transceiver, etc.; or a device for receiving instructions input by the user through a screen, such as a human-computer interface (HMI); or a camera device for receiving instructions such as user body posture. The prompting device may include at least one of the following: a sound-emitting device and a display device. More specifically, the sound-emitting device may include a speaker, audio radiator, or other device that plays audio. Taking a vehicle as an example, display devices are mainly divided into two categories: the first is an in-vehicle display screen; the second is a projection display screen, such as a head-up display (HUD).

[0078] 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.

[0079] The vehicle 100 in this application may include road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment, etc. For example, vehicle 100 can be a vehicle, which is a vehicle in a broad sense, including transportation vehicles (such as commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (such as forklifts, trailers, tractors, AGVs, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), logistics and special vehicles, agricultural equipment (such as lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, unmanned vehicles, etc. The embodiments of this application do not specifically limit the type of vehicle 100. In some implementations, the aforementioned vehicle may also include intelligent terminals that can be ridden by humans, or the aforementioned vehicle may also include intelligent terminals such as mobile robots.

[0080] Figure 2 This diagram illustrates a system architecture according to an embodiment of this application. Figure 2 As shown, the system of this application can adopt the implementation process of "perception input - visual / audio processing - actuator operation", and is divided into a perception layer, a processing layer and an execution layer.

[0081] Taking the car door and hood as motion devices as an example, the perception layer includes side cameras, a front camera, a multi-zone microphone, and door sensors. The side cameras may include a side-view camera mounted on the side of the vehicle, covering the door and door gaps; or a side-view wide-angle camera located in the exterior rearview mirror. The front camera may include a front fisheye camera mounted at the front of the vehicle, used to detect the surrounding environment, the user's location, and the user's body movements during the hood closing process; or a front-view short-range camera mounted at the front of the vehicle, used for close-range blind spot detection, and can work in conjunction with the front fisheye camera to ensure the camera's field of view covers the edge of the hood and the area where the user stands near the front of the vehicle. A sound zone refers to a spatial area within the vehicle divided by a microphone array, used for the directional recognition and processing of voice and abnormal sounds. Multiple sound zones are preset within the vehicle, each corresponding to a specific spatial range. In this embodiment, the multi-zone microphone includes a sound zone corresponding to the user's position. Door status sensors are used to collect status information of the doors or hood, such as identifying whether the doors or hood are in a pre-locked or fully locked state, and determining the opening angle of the doors or hood. The sensors in the perception layer can send the collected perception information to the processing layer. This perception information includes images captured by cameras (such as images of the doors and hood), audio information captured by microphones, and status information of the electric doors collected by the door status sensors.

[0082] The processing layer is divided into a visual link and an audio link. The visual link may include a digital video processor / data path (DVP) and a second processing module. The DVP receives images output from the camera device in the perception layer, while the second processing module processes and analyzes the images, queries the first processing module for the status information of the door or hood, and outputs control commands to the closing actuator in the execution layer. In the audio link, automatic speech recognition (ASR) receives audio information from the perception layer and determines the audio content. The event detection module identifies keywords and abnormal sounds in the user's speech and outputs the risk events corresponding to the pinching risk.

[0083] The visual and audio links can work together or independently. In one implementation, the processing layer can first determine whether there is a risk of pinching injury based on the visual link, and then determine whether there is a risk of pinching injury based on the audio link if the visual link is abnormal.

[0084] The first processing module receives status information from the doors or hood and can also be used for timing scheduling during the transition of the motion device to the fully locked state. The second processing module performs human detection based on the image (including overall position detection, distance detection, hand detection, etc.), outputs visual risk results, and determines the anti-pinch strategy and drive control commands for the engagement actuator.

[0085] The actuator layer includes the door or hood closing mechanism. After receiving the drive control command sent by the second processing module, the closing mechanism controls the door or hood to operate.

[0086] Figure 3 This diagram illustrates another system architecture according to an embodiment of this application. The contents of the perception layer and execution layer can be found in [reference needed]. Figure 2 Description of the corresponding embodiments. For example... Figure 3 As shown, the first processing module in the processing layer may include a vision processing module and an audio processing module, which are used to process visual information and audio information, respectively. The second processing module can determine the anti-pinch strategy and the drive control command of the suction actuator based on the visual risk results output by the vision processing module, the risk events output by the audio processing module, and the status information of the door or hood.

[0087] The first processing module and the second processing module described above may correspond to different controllers, different chips, or different processors. Optionally, the first processing module and the second processing module may correspond to different functional modules within the same chip or the same processor. In one possible implementation, the first processing module may be a body domain controller or a central domain controller (CDC), and the second processing module may be an intelligent domain vision processing (IDVP) unit.

[0088] Optionally, the functions of the CDC can be split into multiple electronic control units (ECUs), which can then synchronize their states and coordinate control via in-vehicle Ethernet or scalable service-oriented middleware over IP (SOME / IP). For example, the multiple ECUs could correspond to the body domain and the cockpit domain, respectively.

[0089] Optionally, the first processing module and / or the second processing module mentioned above can be processing modules in a cloud server. The cloud server can obtain the perception information sent by the vehicle-side perception layer, determine the drive control command for engaging the actuator, and then send the drive control command to the vehicle side.

[0090] Figure 4 This diagram illustrates a schematic flowchart of an anti-pinch method 400 for a motion device according to an embodiment of this application. The method 400 can be executed by a device including the motion device, or by the vehicle 100, or by the computing platform 120, or by a system-on-a-chip (SoC) within the computing platform 120, or by a processor, chip, or circuit within the computing platform 120, or by a CDC.

[0091] The process of a moving device switching from an unlocked state to a fully locked state includes a first pause phase and / or a first engagement phase. The unlocked state indicates that the moving device is in a non-fixed, movable state. For electrically controlled moving devices such as doors and hoods, this process may include switching from a pre-locked state to a fully locked state. Taking a door as an example, a user can trigger the door to enter a pre-locked state by using buttons or controls related to closing the door, voice control, gesture control, or manually pushing the door.

[0092] For example, the anti-pinch method 400 may include: S410: Acquire sensory information indicating information about obstacles located within a first range of the motion device.

[0093] For example, in this application, an obstacle refers to an obstacle that hinders the normal movement of the motion device, such as a person (user), an animal (e.g., the user's pet), an object, etc.

[0094] In one possible implementation, the perceived information includes at least one of the following: images, point cloud information, thermal imaging information, infrared light information, and audio information.

[0095] For example, sensors used to acquire sensory information include camera devices, radar (e.g., millimeter-wave radar), infrared sensors, thermal imaging sensors, sound receiving devices, and time-of-flight (ToF) sensors. Among these, the camera device, radar, infrared sensor, thermal imaging sensor, and ToF sensor are used to acquire visual information, which can be used to identify user actions and / or determine the distance between the user and the moving device. The sound receiving device is used to acquire the user's audio information.

[0096] For example, the first range can be determined based on the capability range of the sensor. For instance, the first range can be determined based on the field of view covered by the image captured by the camera device. Alternatively, the first range can be a predetermined fixed area around the moving device. For example, assuming the moving device is a car door, the first range can include the area inside the vehicle cabin and the area 1 meter around the vehicle.

[0097] In one possible implementation, step S410 may specifically include: acquiring sensing information based on a sensor corresponding to the location of the motion device.

[0098] Taking a car door as an example, the sensors corresponding to the location of the door may include a side-facing camera located on the same side of the door and capable of capturing images of the door, and a sound-receiving device corresponding to the sound zone closest to the door. Taking the hood as an example, the sensors corresponding to the location of the hood include a forward-facing camera.

[0099] Optionally, step S410 may specifically include: acquiring perception information based on a sensor corresponding to the location of the obstacle.

[0100] For example, when a user is inside the vehicle, audio information can be obtained through a sound receiving device corresponding to the sound zone closest to the user, and images of the user and the vehicle door can be obtained through a camera inside the cabin.

[0101] It should be noted that the relative position (or relative distance, relative angle, etc.) between the sensor and the moving device in this application can be fixed or variable. For example, the sensor can be a side-view camera, and the range of the image captured by the side-view camera remains constant. For a side-view wide-angle camera located on the exterior rearview mirror, when the front door is opened at different angles, the range of the image captured by the side-view wide-angle camera changes, thus changing the angle and area of ​​the moving device captured.

[0102] In one possible implementation, the motion device is the motion device of the first device, and step S410 may specifically include: receiving sensing information sent by a second device that is communicatively connected to the first device.

[0103] Taking a vehicle as the first device as an example, the second device can be a user-worn terminal device, such as a mobile phone, earphones, or a watch. For example, when a user uses the upper limb wearing the watch to disable the motion control, the watch can obtain more accurate information about the user's movements; similarly, when a user makes an abnormal cry related to a pinching injury, the earphones can obtain clearer audio information about the user.

[0104] The second device can be a sensor located around the first device. Taking a vehicle as an example, the second device can be a camera device around the vehicle, such as a camera installed in a home garage, a camera at a charging station, or a camera from another vehicle located near the vehicle and belonging to the same user (which can be determined by the user's login information on the vehicle's infotainment system).

[0105] By combining the sensory information obtained from various sensors around the motion device, it is easier to comprehensively and accurately assess the risk of pinching injury. By combining the images captured by the camera devices around the first device, blind spots in the field of vision can be reduced when assessing the risk of pinching injury.

[0106] S420: Based on the perceived information, determine whether there is a risk of pinching injury. The risk of pinching injury indicates the risk that the motion device will pinch an obstacle.

[0107] The risks associated with the motion device being caught in an obstacle include the risk of injury to a human or animal when caught in the device, and the risk of damage to the device when it is obstructed by an object during the suction process.

[0108] In one possible implementation, the perceived information includes visual information, and step S420 may specifically include: determining the degree of overlap between the obstacle and the preset danger zone of the motion device based on the visual information, wherein the preset danger zone is the space area within a preset distance around the edge of the motion device or the gap between the motion device and the outer frame; and determining whether there is a risk of pinching injury based on the degree of overlap information.

[0109] For example, for a car door, the preset danger zone can be the space within a preset distance around the edge of the door, or the space within a preset distance around the door gap between the door and the door frame; for a hood, the preset danger zone can be the space within a preset distance around the gap between the hood and the front frame. The size of this preset distance can vary for different motion devices.

[0110] Taking an image as an example, the position and shape of obstacles and moving devices can be mapped to a unified coordinate system, and the degree of overlap information can be determined based on this coordinate system. For example, the degree of overlap information can refer to the overlapping area, extension length, and overlapping position of the obstacle and the preset danger zone. For instance, when the extension length of the obstacle within the preset danger zone is greater than or equal to a preset length, a risk of pinching injury is determined. Another example, taking the front hatch as an example, it can be determined whether the overlapping position of the obstacle and the preset danger zone is located at the latch of the front hatch; the probability of pinching injury at the latch is higher than at other locations. Yet another example, when the overlapping area is greater than a preset area threshold, a risk of pinching injury is determined.

[0111] In one possible implementation, the obstacle includes the user, and the overlap information indicates the number of marked points of the user's limbs located within a preset danger zone. Based on the overlap information, it is determined whether there is a risk of pinching injury, including: determining whether there is a risk of pinching injury based on the number and a preset number threshold.

[0112] For example, multiple points on a human limb can be calibrated using a human detection model. The number of points can vary for different parts of the body. For instance, dense points can be set for fingers, which are more prone to pinching injuries, while points can be set only for the outer side of the arm for other parts of the upper limb.

[0113] The risk of pinching injury can be determined based on the number of marked points within a preset danger zone. For example, if the number is greater than or equal to a certain threshold, a pinching injury risk is identified; if the number is less than the threshold, the user's risk of injury is low, and it can be determined that there is no pinching injury risk.

[0114] In one possible implementation, the perceived information includes visual information, and step S420 may specifically include: determining a first distance between the obstacle and the edge of the motion device, and / or a second distance between the obstacle and the gap between the motion device and the outer frame, based on the visual information; and determining whether there is a risk of pinching injury based on the first distance and / or the second distance.

[0115] Taking an image as an example, the position and shape of obstacles and motion devices can be mapped to a unified coordinate system, and a first distance and a second distance can be determined based on this coordinate system. For example, the first distance and the second distance are the shortest distances between the outer contour of the obstacle and its edges and gaps, respectively.

[0116] The first distance and the second distance can be used individually as criteria for determining the risk of pinching injury, or they can be used together. Taking the combined determination as an example, when either the first distance or the second distance is less than or equal to its corresponding distance threshold, it is determined that there is a risk of pinching injury; when both the first distance and the second distance are greater than their corresponding distance thresholds, it is determined that there is no risk of pinching injury.

[0117] In one possible implementation, the motion device is the motion device of a vehicle, and the method 400 further includes: acquiring the status information of other components of the vehicle; this step S420 may specifically include: determining whether there is a risk of pinching injury based on the sensing information and the status information of other components.

[0118] For example, the moving device could be a vehicle door, hood, tailgate, sunroof, etc. When acquiring sensory information and determining whether there is a risk of pinching injury based on that information, the state of other vehicle components may affect the content of the sensory information. For instance, assuming the moving device is a rear door, the opening angle of the front door on the same side as the moving device might affect the acquisition of visual information associated with it; during the acquisition of audio information, music played by the vehicle might interfere with the audio information. Processing and analyzing sensory information when it is interfered with can be time-consuming. By combining the state information of other components with the sensory information, the efficiency of determining the risk of pinching injury can be improved.

[0119] In one possible implementation, the moving device is a first door, the other components are a second door on the same side as the first door, the status information is the opening and closing information of the second door, and the presence or absence of pinching risk is determined based on the sensing information and the status information of the other components, including: determining whether there is a pinching risk based on the sensing information and the opening and closing information.

[0120] For example, the opening and closing information of the second door may include the opening and closing state, opening and closing angle, etc. Assuming that the perception information includes visual information collected by a camera, and the position and orientation of the camera are associated with the first and second doors, when the second door is opened, it affects the camera's observation of the first door. Therefore, based on the opening and closing information of the second door and the perception information, it can be determined whether there is a risk of pinching injury, thereby improving the accuracy of pinching risk detection.

[0121] In one possible scenario, the first door is the rear door, and the second door is the front door on the same side as the rear door. The perception information includes audio information and visual information. The visual information is acquired by a camera device located on the side of the front of the vehicle on the same side as the first door and facing the rear of the vehicle. Based on the perception information and the opening and closing information, it is determined whether there is a risk of pinching injury, including: when the opening and closing information indicates that the opening angle of the front door is greater than or equal to the angle threshold, it is determined whether there is a risk of pinching injury based on the audio information.

[0122] The vehicle can acquire the opening angle of the front door on the same side as the rear door. Assuming the camera (side-view camera) is located on the side of the front of the vehicle, and the image acquisition direction is towards the rear of the vehicle (reference...),... Figure 5 (Solid arrow in the text). For example... Figure 5 As shown in (a), when the front door is closed, or the opening angle of the front door is less than the angle threshold A, the observation path of the side-view camera on the side where the rear door is located is unobstructed, and it can capture images including the rear door; Figure 5As shown in (b), when the opening angle is greater than or equal to the angle threshold A, the opening of the front door causes the field of view of the side rearview camera to be unable to cover the area of ​​the rear door edge and door gap when the rear door reaches the pre-locked state. Therefore, the presence of a pinching risk is determined primarily based on audio information. For example, audio information of the user collected by the microphones in the corresponding and adjacent audio zones of the rear door can be obtained, and the presence of a pinching risk can be determined based on this audio information.

[0123] For example, the angle threshold may be the minimum opening angle of the front door that prevents the camera from capturing the back door, or the minimum opening angle that causes the area occupied by the back door within the field of view captured by the camera to be less than a preset area, or the minimum opening angle that makes the occupancy rate of the camera greater than or equal to the occupancy rate threshold.

[0124] In one possible scenario, visual information is acquired via a camera device (e.g., a side-facing wide-angle camera) located on the exterior rearview mirror on the same side as the first door and facing the rear of the vehicle. Figure 6 As shown in (a), when the front door is closed or the opening angle of the front door is less than the angle threshold B, the camera device can capture an image including the rear door; Figure 6 As shown in (b), when the opening angle is greater than or equal to the angle threshold B, the opening of the front door causes the shooting direction of the side wide-angle camera to change, so that the field of view of the side wide-angle camera cannot cover the area of ​​the door edge and door gap of the rear door. In this scenario, audio detection can be prioritized.

[0125] In one possible scenario, the first door is the front door, and the second door is the rear door on the same side as the front door. Visual information is acquired by a camera located on the side of the rear of the vehicle on the same side as the first door and facing the front of the vehicle. Based on the perception information and opening and closing information, it is determined whether there is a risk of pinching injury, including: when the opening and closing information indicates that the opening angle of the rear door is greater than or equal to the angle threshold, it is determined whether there is a risk of pinching injury based on the audio information.

[0126] The vehicle can acquire the opening angle of the rear door on the same side as the front door. Assuming the camera (side rearview camera) is located on the side of the rear of the vehicle, and the image acquisition direction is towards the front of the vehicle (reference...). Figure 7 (Solid arrow in the text). For example... Figure 7 As shown in (a), when the rear door is closed, or when the opening angle of the rear door is less than the angle threshold C, the observation path of the side-view camera on the side where the front door is located is unobstructed, and it can capture images including the front door; Figure 7 As shown in (b), when the opening angle is greater than or equal to the angle threshold C, the opening of the rear door causes the field of view of the side front view camera to be unable to cover the area of ​​the rear door edge and door gap when the front door reaches the pre-lock state. The risk of pinching is judged based on audio information first.

[0127] In one implementation, the existence of a pinching risk can be determined directly based on visual risk results determined from visual information, or based on risk events determined from audio information. For example, a pinching risk is determined when the visual risk results indicate that the first distance and / or the second distance are respectively less than their corresponding distance thresholds, or when the number of markers indicating that the user's limbs are located within a preset danger zone is greater than a number threshold. Taking audio detection as an example, the sound receiving device can operate throughout the entire closing process. Multiple microphones in the sound zones near the car door can synchronously or time-divisionally input the collected raw audio information into the ASR to determine the content of the speech and identify whether the user's speech includes preset command words (e.g., "stop," "it hurts," "I'm pinched") or pinching-related abnormal sounds (e.g., shouts, exclamations). When a command word or abnormal sound is identified, a pinching risk is determined. The audio detection in this application does not require wake-up.

[0128] In one implementation, when the perceived information includes multiple types of information, these types of information can be fused to determine the risk of pinching injury. For example, images are used to identify the shape and location of obstacles, point cloud information provides three-dimensional spatial data to accurately locate obstacles, thermal imaging information is used to detect the specific location and outline of a person or animal, and infrared light information is used to measure the distance between the obstacle and the moving device. For instance, images, point cloud information, and thermal imaging information can be fused for judgment, thereby determining the accurate location of a person or animal. Another example is that different weights can be assigned to different types of information, and decisions can be made according to the weights when differences exist between the different types of information. Yet another example is that features can be extracted and encoded from each type of information separately, and the feature vectors corresponding to each type of information can be input into a pre-trained neural network model to obtain the corresponding judgment result of pinching injury risk.

[0129] In one implementation, the risk probability corresponding to the pinching risk can be calculated based on perceived information. If the risk probability is greater than a risk threshold, a pinching risk is determined to exist; if the risk probability is less than or equal to the risk threshold, a pinching risk is determined not to exist. Taking a first distance as an example, different risk probabilities can be determined based on the magnitude of the first distance, with a higher risk probability corresponding to a smaller first distance. Combining the first distance and overlap information, the magnitude of the first distance corresponds to risk probability A, and the number of user limb markers within a preset danger zone corresponds to risk probability B. Risk probabilities A and B can be assigned different weights, and a fused risk probability can be obtained according to the weights, risk probability A, and risk probability B. The presence of a pinching risk is determined by comparing the fused risk probability with the risk threshold.

[0130] S430: When there is no risk of pinching injury, the control motion device performs the first engagement phase.

[0131] S440: When there is a risk of pinching injury, the motion control device performs a first pause phase for a first duration.

[0132] In one possible implementation, the process includes a first pause phase and a first engagement phase. Step S430 specifically includes: when there is no risk of pinching injury, controlling the motion device to perform the first pause phase for a second duration, the second duration being shorter than the first duration; after the first pause phase ends, controlling the motion device to perform the first engagement phase.

[0133] For example, the movement mode of the motion device can be adjusted according to whether there is a risk of pinching injury. When there is no risk of pinching injury, the motion device can be directly controlled to perform the first engagement phase without interruption, or it can be controlled to perform the first engagement phase after a short pause. When there is a risk of pinching injury, engagement can be paused, and the motion device can be controlled to perform a first pause phase for a first duration, after which the motion device can be controlled to perform the first engagement phase; alternatively, subsequent execution of the first engagement phase can be stopped. After the first engagement phase ends, the motion device is in a fully locked state.

[0134] For some motion devices that engage in stages using multiple power levels, the transition from the unlocked state to the fully locked state may include a second engagement stage. Before the first engagement stage, the power or engagement force of the second engagement stage is less than that of the first engagement stage. In this scenario, when there is no risk of pinching injury, the second engagement stage and the first engagement stage can be executed sequentially and continuously; alternatively, the motion device can be controlled to execute a first pause stage for a second duration, followed by the second engagement stage and the first engagement stage; or, if it is determined that the engagement force corresponding to the second engagement stage is relatively small and the risk to the obstacle and the motion device itself when the motion device pinches the obstacle is relatively small, the motion device can be controlled to execute a first pause stage for a second duration after executing the second engagement stage, followed by the first engagement stage. When there is a risk of pinching injury, the motion device can be controlled to execute a first pause stage for a first duration, followed by the second engagement stage and the first engagement stage; alternatively, the motion device can be controlled to execute the second engagement stage first, then execute a first pause stage for a first duration, and finally execute the first engagement stage.

[0135] Some motion devices, due to their structural design, inherently have pauses for mechanical preparation, structural switching, system verification, etc. To ensure the completion of these preparations, the duration of these inherent pauses has a certain redundancy. The duration of the inherent pause is determined by the type of motion device and the type of equipment corresponding to it (e.g., the model of a vehicle that includes multiple motion devices). For this type of motion device, the solution of this application, when there is no risk of pinching injury, can set a second duration shorter than the duration corresponding to the inherent pause, thereby shortening the pause duration when there is no risk of pinching injury, making the motion device close more smoothly. Alternatively, when there is a risk of pinching injury, the motion device can be controlled to perform the first pause stage according to the duration corresponding to the original inherent pause, or the first duration can be set longer than the duration corresponding to the inherent pause (i.e., extending the pause time compared to the inherent pause when there is no risk of pinching injury), balancing safety and user experience.

[0136] The following example, using timing data, illustrates the attraction process of the motion device in this application.

[0137] Taking an electric door with a motion device as an example, after the electric door is unlocked, such as Figure 8 As shown, 0 to T1 indicates that the electric door is controlled to run to the pre-lock state; T1 to T2 indicates that the electric door maintains the pre-lock state and is preparing to execute the closing of stage 1; T2 to T3 indicates that the electric door is controlled to execute the closing of stage 1 (corresponding to the second closing stage); T3 to T4 indicates that IDVP queries CDC, combines perception information to judge the risk of pinching, and at this stage, voice reminders can be given to the user simultaneously, such as "The front trunk is closing, please pay attention to safety" (corresponding to the first pause stage); when it is determined that there is no risk of pinching, T4 to T5 indicates that the electric door is controlled to execute the closing of stage 2 (corresponding to the first closing stage), and finally at time T5, the electric door runs to the fully locked state.

[0138] like Figure 9As shown, during the process of the electric door switching from the unlocked state to the fully locked state, the sequence is as follows: detection delay window, stage 1, pause window, and stage 2. The detection delay window represents the time period reserved for initiating the door closing or checking for pinching risks to accommodate the user's normal closing or leaving the vehicle, or it can be the time period corresponding to the electric door switching from the unlocked state to the pre-locked state. Within the pause window, IDVP queries CDC and combines it with perception information to determine the pinching risk. The query duration is shorter than the pause window duration. For motion devices with inherent pauses, the pause window corresponds to the inherent pause, and the duration of this pause window can be adjusted according to whether there is a pinching risk. When a pinching risk is determined, the pause window duration can be maintained or extended. During this stage, the pinching risk can be checked multiple times until the pinching risk is eliminated, after which stage 2 is executed. When no pinching risk is determined, stage 2 can be executed directly after the query, shortening the pause window duration.

[0139] For example, the detection delay window duration can be 0.9s, 1s, or 1.2s; the duration of stage 1 can be 100ms, 150ms, or 200ms; the pause window duration can be 800ms, 1s, or 1200ms; and the duration of stage 2 can be 1s, 1100ms, or 1200ms. The durations of stage 1, stage 2, and the pause window can be determined based on the structure of the motion device.

[0140] In one possible implementation, the method 400 further includes: when the confidence level of the perceived information is less than or equal to a confidence threshold, or when the sensor used to acquire the perceived information malfunctions, controlling the motion device to perform a first pause phase for a third duration, wherein the third duration is greater than the first duration, and / or the third duration is greater than the duration of the first pause phase when the confidence level is greater than the confidence threshold.

[0141] Taking perceived information, including images, as an example, its confidence level can be determined by the image's sharpness, the completeness of the edges of moving objects in the image, the occlusion rate of moving objects or obstacles in the image, and the image's brightness (whether the image is overexposed or too dark). Taking audio information as an example, its confidence level can be determined by the audio's signal-to-noise ratio, sound source localization variance, volume, and noise intensity. Taking point cloud information as an example, its confidence level can be determined by the point cloud density.

[0142] For example, taking the acquisition of perceptual information through a camera device as an example, if the camera device is obstructed, damaged, in backlight, or in a dark or unlit scene, causing the image confidence level to be less than or equal to the confidence threshold, or if the camera device itself or the transmission link of the visual information corresponding to the camera device malfunctions (e.g., Figure 2When the visual link is abnormal, or the DVP or second processing module is unavailable or unavailable, the first pause phase can be executed for a third duration. In this scenario, the duration of the first pause phase can be longer than the duration of the first pause phase when there is no risk of pinching injury, or longer than the duration of the first pause phase when the confidence level is greater than the confidence level threshold. For motion devices with inherent pauses, the third duration can be longer than the duration corresponding to the inherent pause.

[0143] Optionally, different confidence thresholds can be set according to the type of perceived information. For example, the confidence thresholds for visual information and audio information can be different.

[0144] In one possible implementation, the process may further include a second pause phase, which precedes the first pause phase and / or the second engaging phase. Assuming the moving device is an electric door, the second pause phase can be set immediately after the moving device reaches the pre-locked state. The moving device first undergoes the second pause phase before engaging, thus adapting to the user's normal closing action and avoiding the accidental pinching sensation caused by the moving device engaging directly after reaching the pre-locked state. Combined with... Figure 8 Or as shown in Figure 0, this second pause phase can precede phase 1.

[0145] In one possible implementation, when there is a risk of pinching injury, the method 400 further includes at least one of the following: providing risk information to the motion device; and controlling the motion device to move in the opposite direction to the current direction of motion.

[0146] This risk information is used to alert users to the possibility of the motion device getting caught in an obstacle. For example, it can prompt users to move their limbs or objects away from the motion device. By displaying risk information or controlling the motion device to move in the opposite direction, the risk of the motion device getting caught in an obstacle can be reduced.

[0147] For example, risk information can be displayed through a prompting device associated with the exercise device. This prompting device can be a speaker, display screen, or other similar device of the first device including the exercise device, or it can be a user's terminal device connected to the first device or the exercise device, such as vibrating through the user's watch or playing the corresponding voice message through the user's mobile phone or headphones.

[0148] The above solution can reduce missed detections and detection delays caused by relying on a single sensor during the pinch risk detection process. By determining different closing procedures based on the pinch risk detection results, it can balance safety and user experience. For moving devices with inherent pauses, it reduces false triggers and unnecessary pauses in normal user scenarios such as closing the door and leaving the vehicle. When there is no risk of pinching people or objects, it allows skipping the existing fixed pause stage and directly completing the closing process. When there is a risk, it performs anti-pinch and warning actions before closing, thereby optimizing the closing process.

[0149] The duration of each pause phase and various thresholds in this application can be set based on experience, calibrated through testing or simulation of the motion device, or customized by the user. Taking a vehicle with multiple motion devices as an example, different motion devices can correspond to different durations and thresholds, and the duration of the pause phase and various thresholds can be set according to the vehicle model.

[0150] Taking the electric door of a vehicle as an example, Figure 10 This diagram illustrates a flow chart of an anti-pinch method 1000 according to an embodiment of this application. (In conjunction with...) Figure 8 , Figure 9 and Figure 10 The anti-pinch method 1000 may include: S1010: Controls the electric door's closing actuator to operate in a pre-locked state.

[0151] For example, after the electric door's suction actuator reaches the pre-lock state, the CDC can record the current moment (corresponding to...). Figure 4 (t0 in the middle), to start the subsequent anti-pinch process.

[0152] S1020: Controls the electric door to maintain the pre-locked state.

[0153] The time period corresponding to this step is used to cover normal actions such as the user's hand leaving the door handle and the body backing away. During this stage, the magnetic traction can be not performed or only low-power standby can be maintained to avoid the user experiencing accidental pinching when the door is engaged immediately after pre-locking.

[0154] For example, in combination Figure 8 This step corresponds to the pre-lock holding or preparation phase from T1 to T2. Combined with... Figure 9 This step corresponds to the detection delay window.

[0155] S1030: Control the electric door execution phase 1.

[0156] S1040: Determine if there is a risk of pinching injury.

[0157] For example, S1050 can be executed when there is a risk of pinching injury; otherwise, S1070 can be executed.

[0158] For example, this step can be executed synchronously with S1030, or it can be executed during the pause phase after S1030 ends (see reference). Figure 8 and Figure 9 ).by Figure 9 For example, this step means that IDVP queries CDC within the pause window to obtain the status information of the electric door and determines whether there is a risk of pinching based on the perception information, including whether there are obstacles around the electric door, the distance between the obstacles and the door edge or door gap, and whether there are obstacles in the preset danger zone.

[0159] Taking images as an example of perceived information, after acquiring the image, the human body and the vehicle body are mapped to the vehicle coordinate system. The first distance between the human body and the edge of the electric door, or the second distance between the human body and the edge of the electric door and the door gap between the human body and the door frame, or the degree of overlap between the human body and the preset danger zone of the electric door, are calculated. Based on at least one of the first distance, the second distance, and the degree of overlap, it is determined whether there is a risk of pinching injury.

[0160] Visual detection and audio detection can be performed separately or simultaneously. In one implementation, visual detection can be prioritized. If the camera is detected to be obstructed, severely damaged, in extreme backlight, or if the DVP or IDVP is unavailable, the visual detection is marked as invalid, and audio detection is switched to the next step. In another implementation, audio detection can be prioritized. If the in-vehicle noise is too high, causing the confidence level of the audio detection to fall below the confidence threshold, visual detection can be combined for collaborative judgment, or the pause time can be extended.

[0161] S1050: Provides risk information about the electric door and / or controls the electric door to perform anti-pinch operation.

[0162] For example, if the visual risk result of IDVP indicates that the risk of pinching is greater than the risk threshold, the vehicle-associated warning device can be controlled to provide risk information about the power door, such as by broadcasting a voice prompt to the user through the cabin speakers to remove their fingers or move them away from the door gap; and / or, the power door can be controlled to perform anti-pinch operations, such as opening the door in reverse, maintaining the pre-locked state, or extending the pause time.

[0163] S1060: Determine if there is a risk of pinching injury.

[0164] For example, after providing risk information and / or controlling the electric door to perform anti-pinch operation, the system can again determine whether there is a risk of pinching injury based on the sensing information. If there is still a risk of pinching injury, S1050 can be executed; if the risk of pinching injury has been eliminated, S1070 can be executed.

[0165] S1070: Control the electric door execution stage 2.

[0166] For example, if the visual risk result from IDVP indicates that the risk of pinching has been eliminated, and no audio risk event information has been received, the duration of the pause window can be shortened, or the pause window can be skipped and Phase 2 can be executed directly. After Phase 2 ends, the electric door is in a fully locked state.

[0167] Figure 11The diagram illustrates an anti-pinch device 1100 for a motion device according to an embodiment of this application. The process of the motion device switching from an unlocked state to a fully locked state includes a first pause phase and / or a first engagement phase. The device 1100 includes: an acquisition unit 1110 for acquiring sensing information, the sensing information indicating information about obstacles located within a first range of the motion device; a processing unit 1120 for determining, based on the sensing information, whether there is a risk of pinching injury, the pinching risk indicating the risk of the motion device pinching the obstacle; and a control unit 1130 for controlling the motion device to perform the first engagement phase when there is no risk of pinching injury; or, controlling the motion device to perform the first pause phase for a first duration when there is a risk of pinching injury.

[0168] Optionally, the process includes a first pause phase and a first engagement phase. The control unit 1130 is specifically used to: when there is no risk of pinching injury, control the motion device to perform the first pause phase for a second duration, the second duration being shorter than the first duration; after the first pause phase ends, control the motion device to perform the first engagement phase.

[0169] Optionally, the motion device is the motion device of the vehicle, and the acquisition unit 1110 is further configured to: acquire the status information of other components of the vehicle; the processing unit 1120 is specifically configured to: determine whether there is a risk of pinching injury based on the perception information and the status information of other components.

[0170] Optionally, the motion device is the first door, and the other components are the second door on the same side as the first door. The status information is the opening and closing information of the second door. The processing unit 1120 is specifically used to: determine whether there is a risk of pinching injury based on the sensing information and the opening and closing information.

[0171] Optionally, the first door is the rear door, and the second door is the front door on the same side as the rear door. The perception information includes audio information and visual information. The visual information is acquired by a camera located on the side of the front of the vehicle on the same side as the first door and facing the rear of the vehicle. The processing unit 1120 is specifically used to: determine whether there is a risk of pinching injury based on the audio information when the opening angle of the front door is greater than or equal to the angle threshold indicated by the opening and closing information.

[0172] Optionally, the perceived information includes visual information. The processing unit 1120 is specifically used to: determine the degree of overlap between the obstacle and the preset danger zone of the motion device based on the visual information. The preset danger zone is the space area within a preset distance around the edge of the motion device or the gap between the motion device and the outer frame; and determine whether there is a risk of pinching injury based on the degree of overlap information.

[0173] Optionally, the obstacle includes the user, and the overlap information indicates the number of markers on the user's limbs located within a preset danger zone. The processing unit 1120 is specifically used to: determine whether there is a risk of pinching injury based on the number and a preset number threshold.

[0174] Optionally, the perceived information includes visual information, and the processing unit 1120 is specifically used to: determine a first distance between the obstacle and the edge of the motion device, and / or a second distance between the obstacle and the gap between the motion device and the outer frame, based on the visual information; and determine whether there is a risk of pinching injury based on the first distance and / or the second distance.

[0175] Optionally, when there is a risk of pinching injury, the control unit 1130 is also configured to perform at least one of the following: provide risk information about the motion device; control the motion device to move in the opposite direction to the current direction of motion.

[0176] Optionally, the control unit 1130 is further configured to: control the motion device to perform a first pause phase for a third duration when the confidence level of the perceived information is less than or equal to a confidence threshold, or when the sensor used to acquire the perceived information malfunctions, wherein the third duration is greater than the first duration, and / or the third duration is greater than the duration of the first pause phase when the confidence level is greater than the confidence threshold.

[0177] Optionally, the perceived information includes at least one of the following: image, point cloud information, thermal imaging information, infrared light information, and audio information.

[0178] Optionally, the acquisition unit 1110 is specifically used to: acquire sensing information based on a sensor corresponding to the location of the motion device.

[0179] Optionally, the motion device is the motion device of the first device, and the acquisition unit 1110 is specifically used to: receive sensing information sent by the second device that is communicatively connected to the first device.

[0180] The functions implemented by the above units can be implemented by different processors, or by the same processor, or some functions can be implemented by the same processor. This application does not limit this.

[0181] 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 circuit, which can be 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 a configuration file, 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.

[0182] 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. 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 as a System-on-a-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.

[0183] This application also provides an anti-pinch device for a motion device, the device comprising: a memory for storing a computer program; and a processor for executing the computer program stored in the memory, so that the device can perform any of the methods described in the above embodiments.

[0184] If the device is located in a vehicle, the processor described above can be... Figure 1 The processors shown are 121-12n.

[0185] This application also provides a computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to implement any of the methods described in the above embodiments.

[0186] This application also provides a computer program product, which includes computer program code that, when run on a computer or processor, causes the computer or processor to perform any of the methods described in the above embodiments.

[0187] This application also provides a chip that includes circuitry that can be used to perform any of the methods described in the above embodiments.

[0188] This application also provides a vehicle that may include the device 1100, the computer-readable storage medium, the chip, or a computer program product.

[0189] 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 units within the processor. The software units 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; 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.

[0190] In this embodiment of the application, the memory may include read-only memory and random access memory, and provides instructions and data to the processor.

[0191] 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.

[0192] 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.

[0193] Those skilled in the art will 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for preventing pinching in a motion device, characterized in that, The process of the motion device switching from the unlocked state to the fully locked state includes a first pause phase and / or a first engagement phase, and the method includes: Acquire sensory information, the sensory information indicating information about obstacles located within a first range of the motion device; Based on the perceived information, it is determined whether there is a risk of pinching injury, wherein the risk of pinching injury indicates the risk that the motion device will pinch the obstacle; When there is no risk of pinching injury, the motion device is controlled to perform the first suction phase; or, when there is a risk of pinching injury, the motion device is controlled to perform the first pause phase for a first duration.

2. The method according to claim 1, characterized in that, The process includes a first pause phase and a first engagement phase, wherein controlling the motion device to execute the first engagement phase includes: When there is no risk of pinching injury, the motion device is controlled to perform the first pause phase for a second duration, the second duration being shorter than the first duration. After the first pause phase ends, the motion device is controlled to perform the first suction phase.

3. The method according to claim 1 or 2, characterized in that, The motion device is a vehicle motion device, and the method further includes: Obtain the status information of other components of the vehicle; The step of determining whether there is a risk of pinching injury based on the perceived information includes: Based on the perceived information and the status information of the other components, determine whether the risk of pinching injury exists.

4. The method according to claim 3, characterized in that, The moving device is a first door, the other components are a second door on the same side as the first door, and the status information is the opening and closing information of the second door. The step of determining whether the risk of pinching exists based on the sensed information and the status information of the other components includes: Based on the perceived information and the opening / closing information, determine whether the risk of pinching injury exists.

5. The method according to claim 4, characterized in that, The first door is a rear door, and the second door is a front door on the same side as the rear door. The perceived information includes audio information and visual information. The visual information is acquired by a camera located on the side of the front of the vehicle, facing the rear of the vehicle, on the same side as the first door. The step of determining whether the risk of pinching exists based on the perceived information and the opening / closing information includes: When the opening and closing information indicates that the opening angle of the front door is greater than or equal to the angle threshold, the presence of the risk of pinching injury is determined based on the audio information.

6. The method according to any one of claims 1 to 5, characterized in that, The perceived information includes visual information, and determining whether there is a risk of pinching injury based on the perceived information includes: Based on the visual information, the degree of overlap between the obstacle and the preset danger zone of the motion device is determined. The preset danger zone is the space area within a preset distance around the edge of the motion device or the gap between the motion device and the outer frame. Based on the overlap information, determine whether the risk of pinching injury exists.

7. The method according to claim 6, characterized in that, The obstacle includes the user, and the overlap information indicates the number of marked points of the user's limbs located within the preset danger zone. Determining whether the risk of pinching injury exists based on the overlap information includes: Based on the quantity and a preset quantity threshold, determine whether the risk of pinching injury exists.

8. The method according to any one of claims 1 to 7, characterized in that, The perceived information includes visual information, and determining whether there is a risk of pinching injury based on the perceived information includes: Based on the visual information, determine a first distance between the obstacle and the edge of the motion device, and / or a second distance between the obstacle and the gap between the motion device and the outer frame; Based on the first distance and / or the second distance, determine whether the risk of pinching injury exists.

9. The method according to any one of claims 1 to 8, characterized in that, When the risk of pinching injury exists, the method further includes at least one of the following: The device provides risk information. Control the motion device to move in the opposite direction to the current motion direction.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: When the confidence level of the perceived information is less than or equal to the confidence threshold, or when the sensor used to acquire the perceived information malfunctions, the motion device is controlled to execute the first pause phase for a third duration, wherein the third duration is greater than the first duration, and / or the third duration is greater than the duration of the first pause phase when the confidence level is greater than the confidence threshold.

11. The method according to any one of claims 1 to 10, characterized in that, The perceived information includes at least one of the following: image, point cloud information, thermal imaging information, infrared light information, and audio information.

12. The method according to any one of claims 1 to 11, characterized in that, The acquisition of perceived information includes: The sensing information is acquired based on sensors corresponding to the location of the motion device.

13. The method according to any one of claims 1 to 12, characterized in that, The motion device is the motion device of the first device, and the acquisition of sensing information includes: Receive the sensing information sent by a second device that is communicatively connected to the first device.

14. An anti-pinch device for a motion device, characterized in that, The process of the motion device switching from the unlocked state to the fully locked state includes a first pause phase and / or a first engagement phase, the device comprising: An acquisition unit is configured to acquire sensing information, the sensing information indicating information about obstacles located within a first range of the motion device; The processing unit is configured to determine, based on the perceived information, whether there is a risk of pinching injury, wherein the risk of pinching injury indicates the risk that the motion device may pinch the obstacle; The control unit is configured to control the motion device to perform the first engagement phase when there is no risk of pinching injury; or, when there is a risk of pinching injury, control the motion device to perform the first pause phase for a first duration.

15. The apparatus according to claim 14, characterized in that, The process includes a first pause phase and a first engagement phase, and the control unit is specifically used for: When there is no risk of pinching injury, the motion device is controlled to perform the first pause phase for a second duration, the second duration being shorter than the first duration. After the first pause phase ends, the motion device is controlled to perform the first suction phase.

16. The apparatus according to claim 14 or 15, characterized in that, The motion device is a vehicle motion device, and the acquisition unit is further configured to: Obtain the status information of other components of the vehicle; The processing unit is specifically used for: Based on the perceived information and the status information of the other components, determine whether the risk of pinching injury exists.

17. The apparatus according to claim 16, characterized in that, The moving device is a first door, the other components are a second door on the same side as the first door, and the status information is the opening and closing information of the second door. The processing unit is specifically used for: Based on the perceived information and the opening / closing information, determine whether the risk of pinching injury exists.

18. The apparatus according to claim 17, characterized in that, The first door is a rear door, and the second door is a front door on the same side as the rear door. The perceived information includes audio information and visual information. The visual information is acquired by a camera located on the side of the front of the vehicle, facing the rear of the vehicle, on the same side as the first door. The processing unit is specifically used for: When the opening and closing information indicates that the opening angle of the front door is greater than or equal to the angle threshold, the presence of the risk of pinching injury is determined based on the audio information.

19. The apparatus according to any one of claims 14 to 18, characterized in that, The perceived information includes visual information, and the processing unit is specifically used for: Based on the visual information, the degree of overlap between the obstacle and the preset danger zone of the motion device is determined. The preset danger zone is the space area within a preset distance around the edge of the motion device or the gap between the motion device and the outer frame. Based on the overlap information, determine whether the risk of pinching injury exists.

20. The apparatus according to claim 19, characterized in that, The obstacle includes the user, and the overlap information indicates the number of marked points on the user's limbs located within the preset danger zone. The processing unit is specifically used for: Based on the quantity and a preset quantity threshold, determine whether the risk of pinching injury exists.

21. The apparatus according to any one of claims 14 to 20, characterized in that, The perceived information includes visual information, and the processing unit is specifically used for: Based on the visual information, determine a first distance between the obstacle and the edge of the motion device, and / or a second distance between the obstacle and the gap between the motion device and the outer frame; Based on the first distance and / or the second distance, determine whether the risk of pinching injury exists.

22. The apparatus according to any one of claims 14 to 21, characterized in that, In the event of the aforementioned risk of pinching injury, the control unit is further configured to perform at least one of the following: The device provides risk information. Control the motion device to move in the opposite direction to the current motion direction.

23. The apparatus according to any one of claims 14 to 22, characterized in that, The control unit is also used for: When the confidence level of the perceived information is less than or equal to the confidence threshold, or when the sensor used to acquire the perceived information malfunctions, the motion device is controlled to execute the first pause phase for a third duration, wherein the third duration is greater than the first duration, and / or the third duration is greater than the duration of the first pause phase when the confidence level is greater than the confidence threshold.

24. The apparatus according to any one of claims 14 to 23, characterized in that, The perceived information includes at least one of the following: image, point cloud information, thermal imaging information, infrared light information, and audio information.

25. The apparatus according to any one of claims 14 to 24, characterized in that, The acquisition unit is specifically used for: The sensing information is acquired based on sensors corresponding to the location of the motion device.

26. The apparatus according to any one of claims 14 to 25, characterized in that, The motion device is the motion device of the first device, and the acquisition unit is specifically used for: Receive the sensing information sent by a second device that is communicatively connected to the first device.

27. An anti-pinch device for a motion device, characterized in that, include: A processor for executing a computer program stored in memory to cause the apparatus to perform the method as described in any one of claims 1 to 13.

28. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 13.

29. A chip, characterized in that, The chip includes circuitry for performing the method as described in any one of claims 1 to 13.

30. A computer program product, characterized in that, The computer program product includes: computer program code, which, when executed by a processor, implements the method as described in any one of claims 1 to 13.

31. A vehicle, characterized in that, Includes the apparatus as described in any one of claims 14 to 27, or the computer-readable storage medium as described in claim 28, or the chip as described in claim 29, or the computer program product as described in claim 30.

Images