Vehicle door anti-collision system and method and vehicle

Abstract

The invention discloses a vehicle door anti-collision system and method and a vehicle, and relates to the technical field of automobiles. According to a specific implementation mode of the system, a vehicle-mounted sensor, a suspension controller and a vehicle door limiting stopper are electrically connected with a vehicle controller; the vehicle-mounted sensor is used for collecting environment information around the vehicle; the vehicle controller generates a suspension control instruction and / or a vehicle door control instruction comprising an avoidance strategy, wherein the avoidance strategy comprises a coordination action time sequence; the suspension controller adjusts the suspension height and / or the suspension angle of the vehicle according to the coordination action time sequence so as to change the ground clearance and / or the roll angle of the vehicle body; and the vehicle door limiting device limits the maximum opening angle of the corresponding vehicle door to be a safety angle threshold value according to the coordination action time sequence. The implementation mode does not depend on operation of a driver and passengers, and car door collision is actively avoided.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and more particularly to a door anti-collision system, method, and vehicle. Background Technology

[0002] With the increase in car ownership, parking scenarios are becoming increasingly complex. When a vehicle is parked parallel to the roadside, the driver or passengers often have difficulty accurately judging the distance between the door and the road shoulder when opening the door. This can easily cause the door to hit an obstacle in the door's opening trajectory, resulting in damage or deformation of the door.

[0003] In the process of realizing this invention, the inventors discovered that the prior art has at least the following problems: door collision protection relies entirely on the timely reaction of the driver and passengers, which cannot fundamentally solve the problem of door collision. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a vehicle door anti-collision system, method, vehicle, device, and computer-readable medium to actively avoid vehicle door collisions.

[0005] A door collision avoidance system includes: an on-board sensor, a vehicle controller, a suspension controller, and a door limiter, wherein the on-board sensor, the suspension controller, and the door limiter are electrically connected to the vehicle controller. The on-board sensor is used to collect environmental information around the vehicle; The vehicle controller is used to receive and cache the environmental information collected by the on-board sensors; Based on the visual language action model, the driver's parking intention is identified according to the environmental information, and it is determined whether the vehicle has entered the parking operation stage. When it is determined that the vehicle has entered the parking operation stage, the current time is recorded as the parking start time, and the corresponding environmental information is marked as the first environmental information. During the parking operation process starting from the moment the vehicle begins to stop, the environmental information of consecutive frames is monitored and compared in real time, and the final stopping position of the vehicle is predicted based on the visual language action model. Based on the predicted final stopping position, combined with the cached first environmental information and real-time environmental information, the visual language action model generates final environmental data including the spatial relationship between the final stopping position and surrounding obstacles. Based on the final environmental data, the physical properties of the obstacles are identified, and suspension control commands and / or door control commands including avoidance strategies are generated according to the physical properties. The avoidance strategies include coordinated action timing. The suspension controller receives the suspension control command and, in response to the suspension control command, adjusts the vehicle's suspension height and / or suspension angle according to the coordinated action sequence to change the vehicle's ground clearance and / or roll angle. The door limiter receives the door control command and, in response to the door control command, limits the maximum opening angle of the corresponding door to a safe angle threshold according to the coordinated action sequence.

[0006] The vehicle controller further constructs a three-dimensional spatial map of the obstacle based on the final environmental data, wherein the physical properties include rigidity, flexibility, or height. Based on the three-dimensional spatial map, a corresponding avoidance strategy is determined for each door of the vehicle, and the avoidance strategy includes: The first strategy is to raise the suspension height via the suspension controller when the obstacle is a low, rigid obstacle, so that the lower edge of the door can pass over the obstacle. The second strategy is to limit the door opening angle by means of the door limiter when the obstacle is a columnar obstacle that overlaps with the height of the door. The third strategy, when the obstacles are multiple types of obstacles that are continuously distributed, generates the coordinated action sequence, which includes first adjusting the suspension height to avoid low-level obstacles and then limiting the door angle to avoid high-level obstacles.

[0007] The vehicle controller is further configured to activate a dynamic monitoring mode if, after generating the final environmental data, it is identified that the physical properties of the obstacle are those of a moving object. In the dynamic monitoring mode, if the obstacle is detected to have disappeared or its position has changed within a preset time, the final environmental data is updated, and the suspension control command and / or the door control command is modified.

[0008] The system also includes a human-machine interaction device, which is electrically connected to the vehicle controller. The vehicle controller is further configured to generate and output a warning command including the avoidance strategy after generating the final environmental data; The human-computer interaction device is used to receive the warning command, and to display a highlighted frame on the obstacle through an augmented reality head-up display. At the same time, it uses ambient lighting with a preset color and breathing frequency to alert the risky side door, and emits a voice prompt through a speaker.

[0009] The vehicle-mounted sensors include one or more of solid-state LiDAR, surround-view cameras, and millimeter-wave radar, and the vehicle controller fuses data from multiple types of vehicle-mounted sensors into the environmental information through a sensor fusion algorithm.

[0010] The system also includes monitoring sensors and seat adjusters, which are electrically connected to the vehicle controller. The monitoring sensor is used to collect the attitude and intention information of the driver and passengers after the vehicle finally stops. The vehicle controller is further configured to receive posture and intention information collected by the monitoring sensors, and to identify the occupant's intention to open the door and body posture when leaving the seat based on the visual language action model. If the body posture exceeds the preset body posture range, a seat adjustment command is generated and output. The seat adjuster receives the seat adjustment command and, in response to the seat adjustment command, adjusts the seat position and / or backrest angle to adjust the occupant's body posture.

[0011] The vehicle controller is further configured to monitor the actual movement trajectory of the door during the door opening process in real time through the on-board sensors after generating the suspension control command and the door control command. The actual movement trajectory of the car door is compared with the preset movement trajectory, and the real-time deviation is calculated. If the real-time deviation exceeds the allowable range, a compensation control command is generated, and a dynamic damping adjustment command is sent to the door limiter based on the compensation control command to change the door opening damping and adjust the door to the preset motion trajectory.

[0012] The vehicle controller further uploads the final environmental data, the execution result of the avoidance strategy, and the driver feedback information to the server; so that the server iteratively updates the parameters of the visual language action based on one or more of the final environmental data, the execution result of the avoidance strategy, and the driver feedback information. Receive the update parameters of the visual language action model, and update the visual language action model using the update parameters.

[0013] According to a second aspect of the present invention, a method for preventing collisions with a vehicle door is provided, comprising: The vehicle-mounted sensors collect environmental information around the vehicle. The vehicle controller, based on the visual language and action model, identifies the driver's parking intention based on the environmental information and determines whether the vehicle has entered the parking operation stage. When the vehicle controller determines that the vehicle has entered the parking operation stage, it records the current time as the parking start time and marks the corresponding environmental information as the first environmental information. During the parking operation process of the vehicle starting from the parking start time, it monitors and compares the environmental information of consecutive frames in real time, and predicts the final stopping position of the vehicle based on the visual language action model. The vehicle controller, based on the predicted final stopping position and combined with the cached first environmental information and real-time environmental information, generates final environmental data including the spatial relationship between the final stopping position and surrounding obstacles through the visual language action model. Based on the final environmental data, it identifies the physical attributes of the obstacles and generates suspension control commands and / or door control commands including avoidance strategies according to the physical attributes. The avoidance strategy includes a coordinated action sequence. The suspension controller adjusts the vehicle's suspension height and / or suspension angle according to the coordinated action sequence to change the vehicle's ground clearance and / or roll angle. The door limiter limits the maximum opening angle of the corresponding door to a safe angle threshold according to the coordinated action sequence.

[0014] According to a third aspect of the present invention, a vehicle is provided, including the door anti-collision system as described above.

[0015] According to a fourth aspect of the present invention, a vehicle door anti-collision electronic device is provided, comprising: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors perform the methods described above.

[0016] According to a fifth aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method as described above.

[0017] One embodiment of the above invention has the following advantages or beneficial effects: the on-board sensors, suspension controller, and door limiters interact with the vehicle controller. By utilizing the on-board sensors to collect environmental information around the vehicle, and when the vehicle is parked, by comparing the environmental information before and after parking, suspension control commands and / or door control commands are generated. This enables automatic adjustment of the vehicle suspension and limitation of the door opening angle, thereby actively avoiding door collisions.

[0018] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0019] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein: Figure 1 This is a schematic diagram of the structure of a vehicle door anti-collision system according to an embodiment of the present invention; Figure 2 This is a schematic flowchart of a vehicle door anti-collision method according to an embodiment of the present invention; Figure 3This is a schematic diagram illustrating the application of a door anti-collision system according to an embodiment of the present invention; Figure 4 This is an exemplary system architecture diagram in which embodiments of the present invention can be applied; Figure 5 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0020] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0021] To proactively avoid collisions with car doors, the following technical solutions from the embodiments of the present invention can be adopted.

[0022] See Figure 1 , Figure 1 This is a schematic diagram of a vehicle door collision avoidance system according to an embodiment of the present invention. The vehicle door collision avoidance system includes an on-board sensor 10, a vehicle controller 20, a suspension controller 30, and a door limiter 40. As an example, the on-board sensor 10 includes a solid-state LiDAR mounted on the roof of the vehicle. The vehicle controller 20 is located near the driver's seat. The suspension controller is located near the vehicle frame. The door limiter 40 is located at each door of the vehicle.

[0023] The vehicle sensor 10, suspension controller 30 and door limiter 40 are electrically connected to the vehicle controller 40.

[0024] The vehicle-mounted sensor 10 is used to collect environmental information about the vehicle's surroundings. As an example, the vehicle-mounted sensor 10 includes one or more of solid-state LiDAR, surround-view cameras, and millimeter-wave radar, and the vehicle controller 20 fuses data from multiple types of vehicle-mounted sensors into environmental information using a sensor fusion algorithm. In other words, the environmental information can be obtained by fusing data from multiple sensors. Utilizing multiple sensors helps improve the accuracy of the environmental information.

[0025] The vehicle controller 20 analyzes the environmental information collected by the vehicle sensors 10 and combines it with the Vision-Language-Action (VLA) model to determine suspension control commands and / or door control commands.

[0026] Specifically, the vehicle controller 20 is used to receive and buffer environmental information collected by the on-board sensors 10. For example, the environmental information is stored in a memory connected to the vehicle controller 20.

[0027] A visual language and action model is set in the vehicle controller 20. Environmental information is input into the visual language and action model to identify the driver's parking intention and determine whether the vehicle has entered the parking operation stage. If the driver's parking intention is present and the vehicle speed is less than the parking operation threshold, it is determined whether the vehicle has entered the parking operation stage.

[0028] When it is determined that the vehicle has entered the parking operation phase, the current time is recorded as the parking start time, and the corresponding environmental information is marked as the first environmental information. The first environmental information is the environmental information corresponding to the parking start time.

[0029] During the parking process, starting from the moment the vehicle begins to stop, environmental information from consecutive frames is monitored and compared in real time. Based on a visual language action model, the final stopping position of the vehicle is predicted. By comparing the environmental information from consecutive frames, the characteristics of obstacles near the vehicle can be identified.

[0030] Based on the predicted final stopping position, and combining cached initial environmental information and real-time environmental information, a visual language action model is used to generate final environmental data, including the spatial relationship between the final stopping position and surrounding obstacles. As an example, the spatial relationship between surrounding obstacles includes the horizontal distance between obstacles and the door, and the vertical distance between obstacles and the edge of the door.

[0031] Based on the final environmental data, the physical properties of obstacles are identified, and suspension control commands and / or door control commands, including avoidance strategies, are generated according to these physical properties. The avoidance strategies include a coordinated action sequence. For example, the coordinated action sequence may involve executing suspension control commands first, followed by door control commands.

[0032] The suspension controller 30 receives suspension control commands and, in response to the suspension control commands, adjusts the vehicle's suspension height and / or suspension angle according to the coordinated action sequence to change the vehicle's ground clearance and / or roll angle.

[0033] The door limiter 40 receives the door control command and responds to it by limiting the maximum opening angle of the corresponding door to a safe angle threshold according to the coordinated action sequence.

[0034] In the above embodiments, by monitoring the environmental information around the vehicle in real time during the parking operation and predicting the final stopping position based on a visual language action model, a leap from reactive response to proactive prediction is achieved. Because the relative positional relationship between the vehicle and obstacles can be predicted in advance, more time is available for accurate calculation and strategy optimization, significantly improving the accuracy and reliability of door collision avoidance.

[0035] In one embodiment of the present invention, by identifying the physical properties of obstacles, an avoidance strategy can be selected based on the characteristics of different obstacles. These physical properties include rigidity or height. Specifically: Based on the final environmental data, the vehicle controller 20 constructs a three-dimensional spatial map of obstacles and determines a corresponding avoidance strategy for each door of the vehicle according to the three-dimensional spatial map. The avoidance strategies include: The first strategy is to raise the suspension height via the suspension controller when the obstacle is a low, rigid obstacle, so that the lower edge of the door can pass over the obstacle. For example, low, rigid obstacles include road shoulders.

[0036] The second strategy is to limit the door opening angle using a door limiter when the obstacle is a pillar-shaped obstacle that overlaps with the height of the door. For example, pillar-shaped obstacles include pillars, walls, or adjacent vehicles.

[0037] The third strategy, when the obstacles are multiple types of obstacles distributed continuously, generates a coordinated action sequence that includes first adjusting the suspension height to avoid low-lying obstacles, and then limiting the door angle to avoid high-lying obstacles. For example, the obstacles include green belts.

[0038] In the above embodiments, based on the physical properties of the obstacle, a corresponding avoidance strategy is set for each door of the vehicle to improve the targeting of door collision avoidance.

[0039] In one embodiment of the invention, when the obstacle is mobile, dynamic detection is required to modify the suspension control commands and / or door control commands.

[0040] After generating the final environmental data, if the vehicle controller 20 identifies an obstacle as a moving object, it activates the dynamic monitoring mode. For example, if the position of an obstacle changes based on a comparison of the final environmental data and the initial environmental information, the obstacle is identified as a moving object. The frequency of environmental information collection by the onboard sensors is increased to activate the dynamic monitoring mode.

[0041] In dynamic monitoring mode, if an obstacle is detected to have disappeared or its position has changed within a preset time, the final environmental data is updated to improve its accuracy. Based on the updated final environmental data, suspension control commands and / or door control commands are modified to avoid misoperation and increase operational accuracy.

[0042] In one embodiment of the present invention, a human-machine interface (HMI) device is used to implement a door collision warning system to promptly alert the driver and passengers. As an example, the HMI device is installed inside the vehicle compartment. For instance, the HMI device includes an augmented reality head-up display (HUD) and ambient lighting. The HUD is positioned above the driver's and / or passenger's seats, and the ambient lighting is positioned near the vehicle doors. The HMI device is electrically connected to the vehicle controller.

[0043] After generating the final environmental data, the vehicle controller 20 generates and outputs a warning command that includes an avoidance strategy.

[0044] The human-machine interface receives warning commands and displays a highlighted frame overlaid on the obstacle within the corresponding door's field of vision via an augmented reality head-up display. For example, an obstacle might be marked with a red highlighted frame on the augmented reality head-up display. Simultaneously, the ambient light corresponding to the door closest to the obstacle uses a preset color and breathing frequency to indicate the door at risk. For example, the ambient light might be controlled with a red color and the breathing frequency of its on / off state to indicate the presence of an obstacle near the door. Additionally, voice prompts can be issued via a speaker.

[0045] In the above embodiments, images, lights, and sounds are used to alert the vehicle door to the presence of obstacles, thereby reducing the risk of door collisions.

[0046] In one embodiment of the invention, the driver and passenger are seated in a car seat and need to change their posture, such as leaning forward to move towards the door handle, when opening the car door. Monitoring sensors are used to monitor the driver's and passenger's posture and intentions. To improve the comfort of the driver and passenger when operating the door, the car seat can be adjusted.

[0047] The monitoring sensor and seat adjuster are electrically connected to the vehicle controller 20. For example, the monitoring sensor is located near the vehicle seat, and the seat adjuster is located at the vehicle seat.

[0048] After the vehicle comes to a complete stop, the monitoring sensors collect the posture and intention information of the driver and passengers. For example, the monitoring sensors acquire the posture and intention information of the driver and passengers through the collected images.

[0049] The vehicle controller 20 receives posture and intent information collected by the monitoring sensors, inputs the posture and intent information into the visual language action model, and identifies the occupant's intention to open the door and the body posture of leaving the seat.

[0050] If the body posture exceeds the preset body posture range, such as leaning forward more than 10 degrees, a seat adjustment command will be generated and output. The seat adjuster receives seat adjustment commands and, in response to these commands, adjusts the seat position and / or backrest angle to adjust the occupant's body posture when leaving the seat.

[0051] In the above embodiments, monitoring sensors and seat adjusters are used to automatically adjust the seats for the driver and passengers, improving the comfort of the driver and passengers operating the vehicle doors.

[0052] In one embodiment of the present invention, considering that deviations in the actual movement trajectory of the car door during the opening process can easily lead to a car door collision, corrections can be made by monitoring the actual movement trajectory of the car door.

[0053] Specifically, after generating suspension control commands and door control commands, the vehicle controller 20 monitors the actual movement trajectory of the door during the door opening process in real time through the on-board sensor 10.

[0054] The actual movement trajectory of the car door is compared with the preset movement trajectory to calculate the real-time deviation. The preset movement trajectory is determined based on the suspension height and / or suspension angle, as well as the maximum opening angle of the car door.

[0055] If the real-time deviation exceeds the allowable range, a compensation control command is generated. The compensation control command sends a dynamic damping adjustment command to the door limiter 40 to change the door opening damping and adjust the door to the preset motion trajectory.

[0056] In the above embodiment, the actual movement trajectory of the car door during the opening process is detected to ensure that the car door opens according to the preset movement trajectory.

[0057] In one embodiment of the present invention, the visual language action model in the vehicle controller 20 is updated to improve the accuracy of the visual language action model calculation. Specifically, the vehicle controller 20 uploads final environmental data, the execution result of the avoidance strategy, and driver feedback information to the server. This allows the server to iteratively update the parameters of the visual language action based on one or more of the final environmental data, the execution result of the avoidance strategy, and the driver feedback information. The server then sends the updated parameters of the visual language action model to the vehicle controller 20 to update the visual language action model of the vehicle controller 20.

[0058] See Figure 2 , Figure 2 This is a flowchart illustrating a vehicle door anti-collision method according to an embodiment of the present invention, specifically including: S201. The vehicle-mounted sensor collects environmental information around the vehicle. The vehicle controller, based on the visual language action model, identifies the driver's parking intention based on the environmental information and determines whether the vehicle has entered the parking operation stage.

[0059] The vehicle-mounted sensors include one or more of solid-state LiDAR, surround-view cameras, and millimeter-wave radar, and the vehicle controller fuses data from multiple types of vehicle-mounted sensors into the environmental information through a sensor fusion algorithm.

[0060] S202. When the vehicle controller determines that the vehicle has entered the parking operation stage, it records the current time as the parking start time and marks the corresponding environmental information as the first environmental information. During the parking operation process of the vehicle starting from the parking start time, it monitors and compares the environmental information of consecutive frames in real time, and predicts the final stopping position of the vehicle based on the visual language action model.

[0061] S203. Based on the predicted final stopping position, the vehicle controller, combined with the cached first environmental information and real-time environmental information, generates final environmental data including the spatial relationship between the final stopping position and surrounding obstacles through the visual language action model. Based on the final environmental data, the controller identifies the physical attributes of the obstacles and generates suspension control commands and / or door control commands including avoidance strategies according to the physical attributes. The avoidance strategy includes a coordinated action sequence.

[0062] In one embodiment of the present invention, the vehicle controller further constructs a three-dimensional spatial map of the obstacle based on the final environmental data, wherein the physical properties include rigidity or height; Based on the three-dimensional spatial map, a corresponding avoidance strategy is determined for each door of the vehicle, and the avoidance strategy includes: The first strategy is to raise the suspension height via the suspension controller when the obstacle is a low, rigid obstacle, so that the lower edge of the door can pass over the obstacle. The second strategy is to limit the door opening angle by means of the door limiter when the obstacle is a columnar obstacle that overlaps with the height of the door. The third strategy, when the obstacles are multiple types of obstacles that are continuously distributed, generates the coordinated action sequence, which includes first adjusting the suspension height to avoid low-level obstacles and then limiting the door angle to avoid high-level obstacles.

[0063] In one embodiment of the present invention, the vehicle controller is further configured to activate a dynamic monitoring mode if the physical properties of the obstacle are identified as a moving object after the final environmental data is generated. In the dynamic monitoring mode, if the obstacle is detected to have disappeared or its position has changed within a preset time, the final environmental data is updated, and the suspension control command and / or the door control command is modified.

[0064] In one embodiment of the present invention, the system further includes a monitoring sensor and a seat adjuster, the monitoring sensor and the seat adjuster being electrically connected to the vehicle controller, respectively; The monitoring sensor is used to collect the attitude and intention information of the driver and passengers after the vehicle finally stops. The vehicle controller is further configured to receive posture and intention information collected by the monitoring sensors, and to identify the occupant's intention to open the door and body posture when leaving the seat based on the visual language action model. If the body posture exceeds the preset body posture range, a seat adjustment command is generated and output. The seat adjuster receives the seat adjustment command and, in response to the seat adjustment command, adjusts the seat position and / or backrest angle to adjust the occupant's body posture.

[0065] In one embodiment of the present invention, the vehicle controller is further configured to monitor the actual movement trajectory of the door during the door opening process in real time through the on-board sensor after generating the suspension control command and the door control command. The actual movement trajectory of the car door is compared with the preset movement trajectory, and the real-time deviation is calculated. If the real-time deviation exceeds the allowable range, a compensation control command is generated, and a dynamic damping adjustment command is sent to the door limiter based on the compensation control command to change the door opening damping and adjust the door to the preset motion trajectory.

[0066] S204. The suspension controller adjusts the vehicle's suspension height and / or suspension angle according to the coordinated action sequence to change the vehicle's ground clearance and / or roll angle. The door limiter limits the maximum opening angle of the corresponding door to a safe angle threshold according to the coordinated action sequence.

[0067] In one embodiment of the present invention, the system further includes a human-machine interaction device, which is electrically connected to the vehicle controller; The vehicle controller is further configured to generate and output a warning command including the avoidance strategy after generating the final environmental data; The human-computer interaction device is used to receive the warning command, and to display a highlighted frame on the obstacle through an augmented reality head-up display. At the same time, it uses ambient lighting with a preset color and breathing frequency to alert the risky side door, and emits a voice prompt through a speaker.

[0068] In one embodiment of the present invention, the vehicle controller further uploads the final environmental data, the execution result of the avoidance strategy, and the driver feedback information to the server; so that the server iteratively updates the parameters of the visual language action based on one or more of the final environmental data, the execution result of the avoidance strategy, and the driver feedback information. Receive the update parameters of the visual language action model, and update the visual language action model using the update parameters.

[0069] The door collision avoidance system in this invention can be applied to vehicles. During actual vehicle use, this invention can reduce the likelihood of door collisions with obstacles, thus actively avoiding door collisions.

[0070] See Figure 3 , Figure 3 This is a schematic diagram illustrating the application of a door anti-collision system according to an embodiment of the present invention.

[0071] 301. The lidar detects and stores the surrounding environment.

[0072] Vehicle-mounted sensors include LiDAR. LiDAR collects environmental information about the vehicle's surroundings and transmits this information to the vehicle controller.

[0073] 302. The vehicle-mounted visual language action model determines whether the vehicle has entered a parking state.

[0074] The vehicle controller is based on a visual language action model. It identifies the driver's parking intention based on environmental information and determines that the vehicle has entered the parking operation stage, i.e., the parking state.

[0075] 303. Parking warning and collision avoidance system activated.

[0076] When the vehicle controller determines that the vehicle has entered the parking operation stage, it activates the parking warning and collision avoidance system, which causes the vehicle controller to record the current time as the parking start time and mark the corresponding environmental information as the first environmental information.

[0077] 304. Calculate and confirm the final parking status of the vehicle.

[0078] During the parking operation process, starting from the moment the vehicle begins to stop, the vehicle controller monitors and compares environmental information from consecutive frames in real time, and predicts the final stopping position of the vehicle based on the visual language action model.

[0079] 305. Visual language action generation for environmental data used in parking warning.

[0080] Based on the predicted final stopping position, the vehicle controller combines the cached first environmental information and real-time environmental information to generate final environmental data, including the spatial relationship between the final stopping position and surrounding obstacles, through the visual language action model. The final environmental data is the environmental data used for parking warning.

[0081] 306. Visual language actions adjust vehicle status based on environmental data, such as suspension height and door opening angle.

[0082] Based on the final environmental data, the vehicle controller identifies the physical properties of the obstacle and generates suspension control commands and / or door control commands that include an avoidance strategy, based on the physical properties. The avoidance strategy includes a coordinated action sequence.

[0083] The suspension controller adjusts the vehicle's suspension height and / or suspension angle according to the coordinated action sequence to change the vehicle's ground clearance and / or roll angle.

[0084] According to the coordinated action sequence, the door limiter restricts the maximum opening angle of the corresponding door to a safe angle threshold.

[0085] 307. Provide warnings and reminders to occupants via screens, ambient lighting, and speakers.

[0086] The system uses an augmented reality head-up display to overlay highlighted frames on obstacles, ambient lighting with preset colors and breathing frequencies to alert the side door to the risk, and voice prompts through speakers.

[0087] Figure 4 An exemplary system architecture 400 is shown for which the door collision avoidance method or door collision avoidance system of the present invention can be applied.

[0088] like Figure 4 As shown, the vehicle system architecture 400 may include various systems, such as a driving control system 401, a power system 402, a sensor system 403, a control system 404, a lane change assist system 405, one or more peripheral devices 406, a power supply 407, a computer system 408, and a user interface 409. The door collision avoidance method provided in this embodiment can be implemented through interaction with the aforementioned systems, or through control of the systems by external devices, or through operation of the systems by a robot driving the vehicle. Optionally, the vehicle system architecture 400 may include more or fewer systems, and each system may include multiple components. Furthermore, each system and component of the vehicle system architecture 400 may be interconnected via wired or wireless means.

[0089] The vehicle system architecture 400 includes a driving control system 401, which can be in a fully or partially automated driving mode. For example, the driving control system 401 can automatically control the vehicle's movement based on control signals or control commands without human interaction, interaction with external devices, or interaction with a robot driving the vehicle.

[0090] The powertrain 402 may include components that provide power to the vehicle. For example, the powertrain 402 may include an engine, an energy source, a transmission, wheels, tires, etc. The engine may be an internal combustion engine, an electric motor, an air-compressed engine, or other combinations of engines, such as a hybrid engine consisting of a gasoline engine and an electric motor, or a hybrid engine consisting of an internal combustion engine and an air-compressed engine. The engine converts the energy source into mechanical energy to supply the transmission. Examples of energy sources may include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other electrical sources. The energy source may also provide energy to other systems in the vehicle. Furthermore, the transmission may include a gearbox, a differential, a drive shaft, and a clutch, etc.

[0091] Sensor system 403 may include sensors for sensing the vehicle's surrounding environment (such as sensors for detecting the presence of obstacles) and pressure sensors for sensing the presence of passengers in the seats. Examples include a positioning system (which may be a Global Positioning System (GPS), BeiDou Navigation Satellite System, or other positioning systems), radar, a laser rangefinder, an inertial measurement unit (IMU), and cameras. The positioning system can be used to determine the vehicle's geographical location. The IMU is used to sense changes in the vehicle's position and orientation based on inertial acceleration. In one embodiment, the IMU may be a combination of an accelerometer and a gyroscope. Radar can use radio signals to sense objects in the vehicle's surrounding environment. In some embodiments, in addition to sensing objects, radar can also be used to sense the speed and / or direction of travel of objects.

[0092] To detect environmental information and objects outside the vehicle, cameras can be configured at appropriate locations on the vehicle's exterior. For example, to acquire environmental images of the vehicle's sides, a camera can be mounted on the side mirror. The camera can be a still or video camera.

[0093] The control system 404 may include software systems for implementing vehicle driving control, such as systems for analyzing the vehicle's surrounding environment, pretensioning seat belts, route planning, obstacle avoidance, and image analysis. The control system 404 may also include hardware systems such as an accelerator, steering wheel system, seat belt system, airbag system, and peripheral devices (such as projection equipment and displays). Furthermore, the control system 404 may add or replace components other than those shown and described. Alternatively, some of the components shown above may be reduced.

[0094] In addition, the control system 404 can also interact with external sensors, other autonomous driving devices, other computer systems, or users via peripheral devices 406. Peripheral devices 406 may include wireless communication systems, on-board computers, microphones and / or speakers, cameras, and projectors, etc.

[0095] In some embodiments, peripheral device 406 provides a means for user interaction with the control system 404 via a user interface. For example, an onboard computer may provide information to a user of the vehicle. The user interface may also operate the onboard computer to receive user input. The onboard computer may be operated via a touchscreen. In other cases, peripheral device may provide a means for communicating with other devices located within the vehicle. For example, a microphone may receive audio (e.g., voice commands or other audio input) from a user of the control system. Similarly, a speaker may output audio to a user of the control system.

[0096] Wireless communication systems can communicate wirelessly with one or more devices, either directly or via a communication network. For example, wireless communication systems can use networks such as cellular networks, WiFi, and wireless local area networks (WLANs), or they can use infrared links, Bluetooth, or ZigBee to communicate directly with devices. Other wireless protocols include those used in various autonomous driving communication systems.

[0097] Power source 407 can provide power to various components of the vehicle. Power source 407 can be a rechargeable lithium battery or a lead-acid battery.

[0098] The computer system 408 controls some or all of the vehicle control functions for ramp entry scenarios. The computer system 408 may include at least one processor that executes instructions stored in a non-transitory computer-readable medium such as memory. The computer system 408 provides the aforementioned control system with execution code that implements vehicle control for ramp entry scenarios.

[0099] The processor can be any conventional processor, such as a commercially available central processing unit (CPU). Alternatively, the processor can be a special-purpose device such as an application-specific integrated circuit (ASIC) or other hardware-based processor. Those skilled in the art will understand that the processor, computer, or memory can actually include multiple processors, computers, or memories that may or may not be stored in the same physical housing. For example, memory can be a hard disk drive or other storage media located in a housing different from that of a computer. Therefore, references to processors or computers will be understood to include references to a collection of processors or computers or memories that may or may not operate in parallel. Unlike using a single processor to perform the steps described herein, some components, such as steering and deceleration components, may each have their own processor that performs only determinations related to the component's specific function.

[0100] User interface 409 is used to provide information to or receive information from a user of the vehicle. Optionally, user interface 409 may include one or more input / output devices within a set of peripheral devices 406, such as wireless communication systems, on-board computers, microphones, and speakers.

[0101] It should be understood that the components described above are merely an example. In actual applications, components in the various modules or systems mentioned above may be added or removed as needed. Figure 4 This should not be construed as a limitation on the embodiments of this application.

[0102] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer system 500 suitable for implementing a terminal device of the present invention. Figure 5 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0103] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the system 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0104] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0105] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs the functions defined above in the system of this invention.

[0106] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0107] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0108] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include: The vehicle-mounted sensors collect environmental information around the vehicle. The vehicle controller, based on a visual language action model, identifies the driver's parking intention based on the environmental information and determines whether the vehicle has entered the parking operation stage. When the vehicle controller determines that the vehicle has entered the parking operation stage, it records the current time as the parking start time and marks the corresponding environmental information as the first environmental information. During the parking operation process of the vehicle starting from the parking start time, it monitors and compares the environmental information of consecutive frames in real time, and predicts the final stopping position of the vehicle based on the visual language action model. The vehicle controller, based on the predicted final stopping position, combines the first environmental information and real-time environmental information to generate final environmental data including the spatial relationship between the final stopping position and surrounding obstacles through the visual language action model. Based on the final environmental data, it identifies the physical attributes of the obstacles and generates suspension control commands and / or door control commands including avoidance strategies according to the physical attributes. The avoidance strategy includes a coordinated action sequence. The suspension controller adjusts the vehicle's suspension height and / or suspension angle according to the coordinated action sequence to change the vehicle's ground clearance and / or roll angle. The door limiter limits the maximum opening angle of the corresponding door to a safe angle threshold according to the coordinated action sequence.

[0109] According to the technical solution of this invention, the on-board sensors, suspension controller, and door limiters interact with the vehicle controller. The on-board sensors collect environmental information around the vehicle. When the vehicle is parked, by comparing the environmental information before and after parking, suspension control commands and / or door control commands are generated. This enables automatic adjustment of the vehicle suspension and limitation of the door opening angle, thereby actively avoiding door collisions.

[0110] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention. It should be noted that the acquisition, storage, and application of user personal information involved in the technical solutions of this disclosure comply with relevant laws and regulations and do not violate public order and good morals.

Claims

1. A vehicle door anti-collision system, characterized in that, include: The vehicle includes an on-board sensor, a vehicle controller, a suspension controller, and a door limiter, wherein the on-board sensor, the suspension controller, and the door limiter are electrically connected to the vehicle controller. The on-board sensor is used to collect environmental information around the vehicle; The vehicle controller is used to receive and cache the environmental information collected by the on-board sensors; Based on the visual language action model, the driver's parking intention is identified according to the environmental information, and it is determined whether the vehicle has entered the parking operation stage. When it is determined that the vehicle has entered the parking operation stage, the current time is recorded as the parking start time, and the corresponding environmental information is marked as the first environmental information. During the parking operation process starting from the moment the vehicle begins to stop, the environmental information of consecutive frames is monitored and compared in real time, and the final stopping position of the vehicle is predicted based on the visual language action model. Based on the predicted final stopping position, combined with the first environmental information and real-time environmental information, the visual language action model generates final environmental data including the spatial relationship between the final stopping position and surrounding obstacles. Based on the final environmental data, the physical properties of the obstacles are identified, and suspension control commands and / or door control commands including avoidance strategies are generated according to the physical properties. The avoidance strategies include coordinated action timing. The suspension controller receives the suspension control command and, in response to the suspension control command, adjusts the vehicle's suspension height and / or suspension angle according to the coordinated action sequence to change the vehicle's ground clearance and / or roll angle. The door limiter receives the door control command and, in response to the door control command, limits the maximum opening angle of the corresponding door to a safe angle threshold according to the coordinated action sequence.

2. The door anti-collision system according to claim 1, characterized in that, The vehicle controller further constructs a three-dimensional spatial map of the obstacle based on the final environmental data, wherein the physical properties include rigidity or height; Based on the three-dimensional spatial map, a corresponding avoidance strategy is determined for each door of the vehicle, and the avoidance strategy includes: The first strategy is to raise the suspension height via the suspension controller when the obstacle is a low, rigid obstacle, so that the lower edge of the door can pass over the obstacle. The second strategy is to limit the door opening angle by means of the door limiter when the obstacle is a columnar obstacle that overlaps with the height of the door. The third strategy, when the obstacles are multiple types of obstacles that are continuously distributed, generates the coordinated action sequence, which includes first adjusting the suspension height to avoid low-level obstacles and then limiting the door angle to avoid high-level obstacles.

3. The door anti-collision system according to claim 1, characterized in that, The vehicle controller is further configured to activate a dynamic monitoring mode if, after generating the final environmental data, it is identified that the physical properties of the obstacle are those of a moving object. In the dynamic monitoring mode, if the obstacle is detected to have disappeared or its position has changed within a preset time, the final environmental data is updated, and the suspension control command and / or the door control command is modified.

4. The door anti-collision system according to claim 1, characterized in that, The system also includes a human-machine interaction device, which is electrically connected to the vehicle controller. The vehicle controller is further configured to generate and output a warning command including the avoidance strategy after generating the final environmental data; The human-computer interaction device is used to receive the warning command, and to display a highlighted frame on the obstacle through an augmented reality head-up display. At the same time, it uses ambient lighting with a preset color and breathing frequency to alert the risky side door, and emits a voice prompt through a speaker.

5. The door anti-collision system according to claim 1, characterized in that, The vehicle-mounted sensors include one or more of solid-state LiDAR, surround-view cameras, and millimeter-wave radar, and the vehicle controller fuses data from multiple types of vehicle-mounted sensors into the environmental information through a sensor fusion algorithm.

6. The door anti-collision system according to claim 1, characterized in that, The system also includes monitoring sensors and seat adjusters, which are electrically connected to the vehicle controller. The monitoring sensor is used to collect the attitude and intention information of the driver and passengers after the vehicle finally stops. The vehicle controller is further configured to receive posture and intention information collected by the monitoring sensors, and to identify the occupant's intention to open the door and body posture when leaving the seat based on the visual language action model. If the body posture exceeds the preset body posture range, a seat adjustment command is generated and output. The seat adjuster receives the seat adjustment command and, in response to the seat adjustment command, adjusts the seat position and / or backrest angle to adjust the occupant's body posture.

7. The door anti-collision system according to claim 1, characterized in that, The vehicle controller is further configured to monitor the actual movement trajectory of the door during the door opening process in real time through the on-board sensors after generating the suspension control command and the door control command. The actual movement trajectory of the car door is compared with the preset movement trajectory, and the real-time deviation is calculated. If the real-time deviation exceeds the allowable range, a compensation control command is generated, and a dynamic damping adjustment command is sent to the door limiter based on the compensation control command to change the door opening damping and adjust the door to the preset motion trajectory.

8. The door anti-collision system according to claim 1, characterized in that, The vehicle controller further uploads the final environmental data, the execution result of the avoidance strategy, and the driver feedback information to the server; so that the server iteratively updates the parameters of the visual language action based on one or more of the final environmental data, the execution result of the avoidance strategy, and the driver feedback information. Receive the update parameters of the visual language action model, and update the visual language action model using the update parameters.

9. A method for preventing collisions with a vehicle door, characterized in that, include: The vehicle-mounted sensors collect environmental information around the vehicle. The vehicle controller, based on a visual language action model, identifies the driver's parking intention based on the environmental information and determines whether the vehicle has entered the parking operation stage. When the vehicle controller determines that the vehicle has entered the parking operation stage, it records the current time as the parking start time and marks the corresponding environmental information as the first environmental information. During the parking operation process of the vehicle starting from the parking start time, it monitors and compares the environmental information of consecutive frames in real time, and predicts the final stopping position of the vehicle based on the visual language action model. The vehicle controller, based on the predicted final stopping position and combined with the cached first environmental information and real-time environmental information, generates final environmental data including the spatial relationship between the final stopping position and surrounding obstacles through the visual language action model. Based on the final environmental data, it identifies the physical attributes of the obstacles and generates suspension control commands and / or door control commands including avoidance strategies according to the physical attributes. The avoidance strategy includes a coordinated action sequence. The suspension controller adjusts the vehicle's suspension height and / or suspension angle according to the coordinated action sequence to change the vehicle's ground clearance and / or roll angle. The door limiter limits the maximum opening angle of the corresponding door to a safe angle threshold according to the coordinated action sequence.

10. A vehicle, characterized in that, Includes the door collision avoidance system as described in any one of claims 1 to 8.

Images