Reparking method, system and equipment and storage medium

Abstract

The embodiment of the invention relates to the technical field of intelligent driving, and discloses a reparking method, system and device and a storage medium, and the method comprises the steps: receiving the image information and position information of a target parking space; the availability of the target parking space is analyzed according to the image information and the position information; when the target parking space is available, requesting to establish a re-parking path according to the image information and the position information of the target parking space; and based on the reparking path, an instruction for executing reparking is sent out. According to the technical scheme, a driver does not need to return to the vehicle and restart the parking process, the vehicle can autonomously perform reparking operation, and the intelligent level and use convenience of the parking system are improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of intelligent driving technology, and in particular, to a re-parking method, system, device, and storage medium. Background Art

[0002] Currently, automatic parking technology has been widely applied in the vehicle field, and its core process includes three stages: parking space detection, path planning, and control execution. After the driver selects a target parking space through in-vehicle sensors or manually, the vehicle automatically or semi-automatically completes the parking operation.

[0003] However, the current technology still has the following defects: The existing automatic parking system terminates operation after the vehicle parks in the initial target parking space, and cannot continuously monitor the surrounding environment or respond to the appearance of a subsequent better parking space. If the driver discovers a more ideal parking space, such as a parking space closer to the destination, more spacious, or safer, etc., they need to return to the vehicle and restart the parking process, resulting in redundant operations and low efficiency. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide a re-parking method, system, device, and storage medium. By applying the technical solution of the present invention, the vehicle can autonomously perform re-parking operations without the driver returning to the vehicle and restarting the parking process, improving the intelligent level and usability of the parking system.

[0005] According to one aspect of the embodiments of the present invention, a re-parking method is provided, and the method includes: Receiving image information and position information of a target parking space; Analyzing the availability of the target parking space according to the image information and position information; When the target parking space is available, requesting to establish a re-parking path according to the image information and position information of the target parking space; Based on the re-parking path, issuing an instruction to execute re-parking.

[0006] In an optional manner, the image information includes: target parking space marking information, environmental reference objects; and / or The position information includes: obtaining the satellite positioning coordinates of the target parking space, or the fusion positioning coordinates after compensating for positioning drift by combining satellite positioning coordinates and IMU data.

[0007] In an optional manner, the analyzing the availability of the target parking space according to the image information and position information includes: Identifying the markings of the target parking space and environmental reference objects in the image information; Calculating the size of the effective space of the target parking space, and comparing the preset vehicle size with the size of the effective space; Output the availability of the target parking space according to the comparison result.

[0008] In an alternative manner, the identifying the markings of the target parking space and environmental reference objects in the image information includes the following sub-steps: Identify the markings of the parking space and obstacles from the image information according to a preset target detection and instance segmentation model; Determine the effective length information and effective width information of the target parking space according to the markings of the parking space and the obstacles.

[0009] In an alternative manner, the calculating the size of the effective space of the target parking space and comparing the preset vehicle size with the size of the effective space includes the following sub-steps: Judge the number of target parking spaces and calculate the size of the effective space of each target vehicle; Filter out the target parking spaces that do not meet the requirements according to the preset vehicle size; Calculate the optimal target parking space according to the obstacle density around the markings of the remaining target parking spaces and the distance from the target position.

[0010] In an alternative manner, the analyzing the availability of the target parking space according to the image information and position information is local analysis or cloud analysis.

[0011] In an alternative manner, the requesting to establish a re-parking path according to the image information and position information of the target parking space includes the following sub-steps: Convert the position information into a vehicle coordinate system; Match the image information and the real-time image of the on-vehicle camera through visual odometry to dynamically calibrate the position of the target parking space; Generate a collision-free path according to the position of the target parking space through a preset path planning algorithm.

[0012] In an alternative manner, after issuing an instruction to execute re-parking based on the re-parking path, it further includes: Detect the environment around the vehicle; If it is confirmed that there is no obstacle in the environment around the vehicle, execute the re-parking instruction; If there is an obstacle in the environment around the vehicle, re-plan the parking path.

[0013] In an alternative manner, after issuing the instruction to execute re-parking, it further includes: Calculate the steering wheel angle according to the path curvature of the parking path; Confirm that the center line of the vehicle is aligned with the center line of the parking space, and when the distance between the front and rear of the vehicle and the obstacles reaches a preset value, the vehicle stops driving.

[0014] In an alternative manner, after issuing the instruction to perform re-parking, the following steps are further included: After the parking is completed, a notice of successful parking is issued.

[0015] According to the second aspect of the embodiments of the present invention, a control system is provided, which at least includes: A target parking space information acquisition module, configured to acquire image information and position information of a target parking space; and A vehicle control module, configured to receive the image information and position information of the target parking space, analyze the availability of the target parking space according to the image information and position information, and when the target parking space is available, request to establish a re-parking path according to the image information and position information of the target parking space, and based on the re-parking path, issue an instruction to perform re-parking.

[0016] In an alternative manner, the vehicle control module includes: A path planning module, configured to establish a re-parking path according to the image information and position information of the target parking space; and A target parking space availability analysis module, configured to analyze the availability of the target parking space according to the image information and position information, and the target parking space availability analysis module is a cloud processing module.

[0017] In an alternative manner, the control system further includes an environment perception module, and the environment perception module includes: A camera, configured to detect the color and shape of the target parking space marking; A millimeter-wave radar, configured to detect the distance between the vehicle and an obstacle and identify low obstacles; An ultrasonic radar, configured to detect the surrounding environment of the vehicle.

[0018] According to the third aspect of the embodiments of the present invention, a re-parking device is provided, including: A processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete mutual communication through the communication bus; The memory is used to store at least one executable instruction, and when the executable instruction is executed by the processor, the steps in the above-mentioned re-parking method are implemented to perform a re-parking operation on the vehicle.

[0019] According to the fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, and the computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the above-mentioned re-parking method is implemented.

[0020] The present invention receives the image information and position information of a target parking space captured by a driver, analyzes the availability of the target parking space based on the image information and position information, and when the target parking space is available, requests to generate a re-parking path based on the image information and position information of the target parking space and the spatial relationship between the current vehicle pose and the target position. Based on the re-parking path, an instruction to execute re-parking is issued. In this way, without the driver returning to the vehicle and restarting the parking process, the vehicle can autonomously perform the re-parking operation, improving the intelligence level and usability of the parking system.

[0021] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to be able to understand the technical means of the embodiment of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and understandable, the following specifically describes the specific implementation manners of the present invention. Brief Description of the Drawings

[0022] The drawings are only used to illustrate the embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 A flowchart showing the first embodiment of the re-parking method provided by the present invention; Figure 2 A timing diagram showing the first embodiment of the re-parking method provided by the present invention; Figure 3 A flowchart showing the sub-steps in step 120 of the first embodiment of the re-parking method provided by the present invention; Figure 4 A timing diagram showing another embodiment of the re-parking method provided by the present invention; Figure 5 A flowchart showing the sub-steps in step 130 of the first embodiment of the re-parking method provided by the present invention; Figure 6 A structural diagram showing an embodiment of the control system provided by the present invention; Figure 7 A flowchart showing the implementation of the re-parking method provided by the present invention. Detailed Description of the Embodiments

[0023] Hereinafter, the exemplary embodiments of the present invention will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein.

[0024] Embodiment 1: Figure 1The flowchart of the first embodiment of the re-parking method of the present invention is shown. This method is executed by the vehicle control system. It can be understood that re-parking refers to the process in which after the vehicle has completed parking, the driver or the vehicle control system discovers a better target parking space, and then controls the vehicle to perform the re-parking action to park the vehicle in the better target parking space.

[0025] As Figure 1 shown, the method includes the following steps: Step 110: Receive the image information and position information of the target parking space.

[0026] Among them, the image information is used to identify the parking space boundary and the spatial distribution of obstacles. It can be an image or video taken by a specific terminal device of the environment where the target parking space to be parked is located, and the geometric features of the parking space markings and the distribution of surrounding reference objects obtained from the image or video according to the algorithm. The position information is used to determine the approximate position of the target parking space. Specifically, it can refer to the spatial coordinate data of the target parking space, which can be implemented by a satellite positioning module and provide a reference for path planning.

[0027] The terminal device for obtaining the image information and / or position information can be a terminal with image acquisition ability and satellite positioning ability, such as a mobile phone, etc.

[0028] For example, take a photo or record a video of the area around the target parking space with a mobile phone, and record the satellite positioning information or specific spatial coordinate information of the photo-taking location during the photo-taking or video-recording process. After receiving this information, the vehicle control system can perform parking space identification and positioning identification.

[0029] Step 120: Analyze the availability of the target parking space according to the image information and position information.

[0030] Among them, the distribution state of the parking space markings and obstacles of the target parking space is identified through the image information, and the geographical location of the target parking space is identified through the position information. The availability of the target parking space is analyzed by integrating the image information and position information.

[0031] This availability refers to whether the vehicle can successfully park in the target parking space through path planning. During the identification process, the size of the parking space line and obstacles can be determined from the image information through a preset image analysis algorithm, and at the same time, it is determined whether a path can be planned according to the positioning information, and the possibility of successful parking is comprehensively judged. If it is determined that it can be successfully parked, it means that the target parking space is available and the subsequent parking steps can be executed. Otherwise, the target parking space is not available and the re-parking step is not performed.

[0032] Step 130: When the target parking space is available, request to establish a re-parking path according to the image information and position information of the target parking space.

[0033] Among them, when it is analyzed that the target parking space is available, a collision-free re-parking path that satisfies the kinematic constraints is generated based on the image information and position information of the target parking space and the spatial relationship between the current vehicle pose and the target position.

[0034] For example, based on the positioning information of the current parking space and the target parking space, a driving path is initially established, and then the attitude heading for parking in the target parking space and the distance from surrounding obstacles, such as the vehicle next to it, are determined according to the information of the obstacles around the parking space, and finally a re-parking path is formed.

[0035] Step 140: Based on the re-parking path, issue an instruction to execute re-parking.

[0036] Among them, the vehicle control system generates a drive instruction according to the re-parking path parameters and issues an instruction to the vehicle to execute re-parking, so as to realize the autonomous movement of the vehicle to the target parking space.

[0037] Please refer to the appendix Figure 2 The appendix Figure 2 is the timing diagram of the first embodiment of the re-parking method of the present invention. In a feasible embodiment, the execution of the above re-parking method can be understood by referring to the appendix Figure 2 The execution of the re-parking method can be a control system. At the same time, the objects cooperating with it are the user, the terminal device for acquiring image information and positioning information, and also the vehicle for specifically realizing parking. Each object can realize the re-parking step through the timing diagram in the appendix Figure 2 After the user discovers a better parking space, the terminal device collects the image information and positioning information of the target parking space. The terminal device sends the above information to the control system. The control system analyzes the availability of the target parking space. When the target parking space is available, the control system on the one hand feeds back the parking space availability structure to the terminal device, and on the other hand calculates the re-parking path and controls the vehicle to execute the re-parking step. It can be understood that in some embodiments, after the vehicle completes parking, the parking result is notified by sending a notice.

[0038] Compared with the prior art, after the above method completes the automatic parking operation, if the driver discovers a better parking space, the control system receives the image information and position information of the target parking space taken by the driver, and then analyzes the availability of the target parking space according to the image information and position information. When the target parking space is available, a re-parking path is generated based on the image information and position information of the target parking space and the spatial relationship between the current vehicle pose and the target position, and an instruction to execute re-parking is issued based on the re-parking path. In this way, without the driver returning to the vehicle and restarting the parking process, the vehicle can autonomously perform the re-parking operation, improving the intelligent level and use convenience of the parking system.

[0039] ​

[0040] In some embodiments, the image information includes: target parking space marking information, environmental reference objects; and / or the position information includes: obtaining the satellite positioning coordinates of the target parking space, or the fused positioning coordinates after combining the satellite positioning coordinates and IMU data to assist in compensating for positioning drift.

[0041] In this embodiment, the target parking space marking information refers to the geometric parameters of the parking space boundary markings obtained through image recognition technology. In a preferred embodiment, the YOLOv5 object detection model can be combined with the DeepLabv3+ segmentation model for pixel-level marking recognition to establish the spatial reference of the parking space. The environmental reference objects refer to the physical markers that exist fixedly around the parking space. Specifically, the SIFT feature matching algorithm can be used to identify stable features such as columns, wall corners, and vehicles parked in adjacent parking spaces to form spatial anchor points in the relative coordinate system. The size (length × width) and orientation (such as the angle with the lane) of the parking space can be calculated through image recognition.

[0042] The fused positioning coordinates can be the comprehensive positioning result after aligning the IMU data (such as gyroscope and accelerometer data, etc.) that the positioning terminal device can obtain with the satellite positioning data through the extended Kalman filter algorithm. The fused positioning data can greatly improve the positioning coordinate accuracy. Specifically, in some scenarios with poor satellite positioning signals, a six-axis IMU module can be used for dead reckoning compensation when the satellite signal is lost.

[0043] For example, the positioning terminal device can be a mobile phone. When the driver gets out of the car, it starts to record IMU data. Until it finds the target parking space to be parked in again, it records the target parking space information. At this time, the terminal device performs dead reckoning according to the recorded IMU design and calculates the spatial coordinate data of the target parking space in combination with the satellite positioning information at the initial position. It can be understood that the recording of the target parking space information can be taking pictures or performing preset operations on the terminal, etc.

[0044] For another example, in the case of good satellite positioning signals, the mobile terminal GPS can be called to obtain the rough coordinates of the target parking space, and the gyroscope or accelerometer of the mobile terminal can be combined to assist in compensating for GPS drift, improving the accuracy of the initial positioning to ±0.3 meters.

[0045] At the same time, if the parking environment is a parking space that has been mapped, the positioning accuracy can also be improved to ±0.1 meters by combining the visual SLAM algorithm.

[0046] Please combine Figure 3 , Figure 3 which shows the flow diagram of the sub-steps in step 120 of the re-parking method of the present invention.

[0047] In step 120, analyzing the availability of the target parking space based on the image information and location information further includes the following sub-steps: Step 121: Identify the markings of the target parking space and environmental reference objects in the image information.

[0048] Among them, marking recognition refers to extracting the parking space boundary markings through visual detection technology, and environmental reference objects refer to fixed obstacles or ground markings around the parking space, which can be specifically extracted through a multi-sensor fusion algorithm and are used to correct the calculation error of the effective space of the parking space.

[0049] Step 122: Calculate the size of the effective space of the target parking space and compare the preset vehicle size with the size of the effective space.

[0050] Among them, the calculation of the effective space size refers to quantifying the actual available area of the parking space through three-dimensional space modeling technology, which can be specifically implemented by using stereo vision and geometric transformation algorithms to eliminate the measurement error caused by perspective distortion. Specifically, it includes at least the lateral length and longitudinal length of the target parking space. At the same time, the preset vehicle size can be obtained by the user's pre-setting, which includes information such as the length, width, height, and turning radius of the vehicle, and can be specifically stored in the vehicle control unit for establishing a benchmark for judging the adaptability of the parking space. During the comparison process, the comparison is mainly carried out through the lateral length and longitudinal length of the target parking space. Of course, in specific cases, information such as height and turning radius can also be considered to more accurately determine the availability of the target parking space.

[0051] Step 123: Output the availability of the target parking space according to the comparison result.

[0052] Among them, the output process can be a flag information representing that parking is possible or a flag information indicating that parking is not possible.

[0053] For example, if the effective space size is greater than the preset vehicle size, it is determined that the target parking space is available; if the effective space size is less than the preset vehicle size, it is determined that the target parking space is not available. For example, if the effective space size is 5.3 meters in length and 2.5 meters in width, and the preset vehicle size is 4.3 meters in length and 1.8 meters in width, it is determined that this parking space is available. This avoids the problem of misjudging the size of the target parking space and resulting in the failure of re-parking.

[0054] In some embodiments, in step 121, identifying the markings of the target parking space and environmental reference objects in the image information includes the following sub-steps: Identify the markings and obstacles of the parking space from the image information according to the preset target detection and instance segmentation model; Determine the effective length information and effective width information of the target parking space according to the markings and obstacles of the parking space.

[0055] In this embodiment, the object detection and instance segmentation model refers to a deep learning model that can simultaneously complete object localization and pixel-level segmentation. Specifically, it can be implemented using architectures such as Mask R-CNN or YOLO, and is used to distinguish parking space markings from other interfering objects and identify the precise contours of obstacles.

[0056] The effective length information and effective width information refer to the actual available space parameters after deducting the influence of obstacles. Specifically, it can be achieved by calculating the minimum distance between the geometric center of the marking and the edge of the obstacle, so as to avoid including invalid areas in the available space.

[0057] Specifically, the object detection and instance segmentation model performs pixel-by-pixel segmentation on the input image, accurately extracts the boundary of the parking space marking, and simultaneously identifies the category and position of the obstacle. For example, when the marking is partially blocked by fallen leaves, the model completes the marking contour through continuous features; when the obstacle is located at the edge of the marking, the model calculates the distance from the outer edge of the obstacle to the inner side of the marking and dynamically adjusts the size of the effective space. For dynamic obstacles, such as temporarily placed cones, the model updates the obstacle position information through real-time detection to ensure the real-time nature of the effective space calculation.

[0058] In some embodiments, if the image information includes multiple parking spaces, a multi-parking space optimization step can be performed. Specifically, in step 122, calculate the size of the effective space of the target parking space, and compare the preset vehicle size with the size of the effective space, including the following sub-steps: Judge the number of target parking spaces and calculate the size of the effective space of each target vehicle; Filter out the target parking spaces that do not meet the requirements according to the preset vehicle size; Calculate the optimal target parking space according to the obstacle density around the remaining target parking space markings and the distance from the target position.

[0059] In this embodiment, the size of the effective space refers to the actual length and width available for the vehicle to park in the target parking space. The obstacle density refers to the number and distribution state of obstacles per unit area, which can be specifically achieved by statistical millimeter-wave radar point cloud data, and the safety risk is evaluated by calculating the distribution density of obstacles within a preset range around the parking space. The target position refers to the destination coordinates set by the user, which can be specifically achieved by the longitude and latitude data input by the in-vehicle navigation system, and the convenience is evaluated by calculating the straight-line distance between the candidate parking space and the target position.

[0060] For example, when the preset vehicle size is 4.8 meters in length and 1.8 meters in width, parking spaces with an effective length less than 5 meters or an effective width less than 2.2 meters will be excluded. Finally, a comprehensive score is given to the parking spaces that meet the size requirements. For example, the obstacle density weight accounts for 60% and the distance weight accounts for 40%. The parking space with the highest total score is determined as the optimal choice through weighted calculation.

[0061] In some embodiments, the control system has two main functions, specifically calculating the availability of the target parking space and planning the reparking path from the current location to the target parking space. The step of analyzing the availability of the target parking space based on the image information and location information can be local analysis or cloud analysis.

[0062] In this embodiment, local analysis refers to the real-time processing of image and location data on the in-vehicle computing unit. Specifically, an embedded processor can be used to run a preset algorithm model to identify and perform spatial calculations on parking space markings and obstacles, thereby avoiding the latency risk brought by network transmission and maintaining the timeliness of availability judgment under offline or weak network conditions.

[0063] Cloud analysis refers to uploading the image and location data to a remote server for processing. Specifically, a distributed computing cluster can be used to execute a deep learning model to perform multi-dimensional data fusion analysis on complex environments. Using cloud analysis can reduce the requirements for local computing power.

[0064] When cloud analysis is adopted, reference can be made to Appendix Figure 4 In this case, the control system includes a path planning module configured locally and a cloud analysis module configured in the cloud. Among them, the path planning module is mainly responsible for planning the reparking path from the current location to the target parking space, while the cloud analysis module is responsible for calculating the availability of the target parking space. In addition, in order to obtain better path planning, sensors and an environment perception system can also be configured to perform obstacle recognition during the path planning process. During the execution of the reparking step, the driver uses a terminal device to take an image of the target parking space and obtain GPS positioning, and uploads the image information and positioning information of the target parking space to the cloud analysis and processing module of the control system through the terminal device. The cloud analysis module analyzes the availability of the target parking space and feeds back the analysis result to the mobile terminal. If the parking space is available, the driver then sends the image information and positioning information of the target parking space to the path planning module through the mobile terminal. The path planning module plans the reparking path based on the obstacle information sensed by the sensors and the environment perception system, and controls the vehicle to perform the reparking action.

[0065] Please refer to Figure 5 and Figure 5 which shows the flow schematic diagram of the sub-steps in step 130 of the reparking method of the present invention.

[0066] In step 130, when requesting to establish a reparking path based on the image information and location information of the target parking space, the following sub-steps are further included: Step 131: Convert the location information into the vehicle coordinate system; Step 132: Match the image information with the real-time image of the in-vehicle camera through visual odometry to dynamically calibrate the position of the target parking space; Step 133: Generate a collision-free path according to the target parking space position through a preset path planning algorithm.

[0067] In this embodiment, vehicle coordinate system conversion refers to mapping satellite positioning coordinates or integrated positioning coordinates into a relative coordinate system with the current vehicle position as the origin, based on in-vehicle high-precision maps or RTK-GPS.

[0068] Specifically, a coordinate transformation matrix or homogeneous coordinate transformation method can be used to achieve this, thereby eliminating the difference between absolute positioning data and the actual motion posture of the vehicle. Visual odometry dynamic calibration refers to calculating the vehicle's motion displacement through continuous frame image feature point matching. Specifically, the ORB feature detection and optical flow tracking algorithm can be used to achieve this, thereby forming a real-time closed-loop correction mechanism. Collision-free path generation refers to trajectory planning based on the vehicle kinematic model and obstacle distribution. Specifically, it can be achieved by using the A or Hybrid A algorithm.

[0069] Through the above technical solutions, this application can effectively eliminate the positioning deviation caused by environmental dynamic changes and ensure the real-time accuracy of the target parking space coordinates.

[0070] In step 140, after issuing an instruction to execute re-parking based on the re-parking path, it further includes: Detect the vehicle's surrounding environment; If it is confirmed that there are no obstacles in the vehicle's surrounding environment, execute the re-parking instruction; If there are obstacles in the vehicle's surrounding environment, re-plan the parking path.

[0071] In this embodiment, on-vehicle sensors are used to collect real-time obstacle information on the parking path. Specifically, it can be achieved by fusing millimeter-wave radar and ultrasonic radar, and the reliability of obstacle detection is improved through multi-sensor data fusion.

[0072] Establish an environmental safety verification mechanism. Specifically, it can be achieved by using path space occupancy calculation and dynamic collision detection algorithms. By analyzing the position relationship between the vehicle's motion trajectory and obstacles in real time, the feasibility of the path is judged. If there are obstacles in the surrounding environment, re-plan the parking path.

[0073] Specifically, after issuing the execution instruction, first activate the surround-view camera and radar sensor for continuous environmental monitoring. When a moving obstacle or a new static obstacle is detected on the parking path, immediately trigger the path re-planning process. By comparing the geometric relationship between the obstacle contour and the vehicle's minimum turning radius, a new path that meets the collision-free constraint is generated. If the environmental state meets the preset safety threshold, maintain the original path to execute the parking operation.

[0074] In step 140, after issuing an instruction to execute re-parking, it further includes: Calculate the steering wheel angle based on the path curvature of the parking path; Confirm that the vehicle center line is aligned with the parking space center line, and the distances between the front and rear of the vehicle and the obstacles. When the distances reach the preset values, the vehicle stops driving.

[0075] In this embodiment, during the path execution phase, the vehicle control system parses the curvature change of the parking path in real time, and converts the curvature value into the corresponding steering wheel angle control amount according to the kinematic model. During this process, the curvature detection module continuously scans the path geometric features and updates the steering angle parameters every specific time window to ensure that the steering action is synchronized with the path shape.

[0076] When approaching the target parking space, the visual positioning system activates the center line alignment detection function, generates a lateral position correction command by comparing the spatial deviation between the projection of the vehicle central axis and the center point of the parking space marking. At the same time, multiple groups of distance sensors continuously collect the real-time distances between the front and rear ends of the vehicle and the obstacles. When the detection data simultaneously meet that the lateral position deviation is less than the set threshold and the distance values in all directions are higher than the preset safety value, the braking system triggers the automatic parking command.

[0077] Specifically, when performing the parking operation, calculate the steering wheel angle according to the path curvature through the EPS (Electric Power Steering) system, and the ESP (Electronic Stability Program) controls the vehicle speed (parking speed < 5 km / h). When the wheel speed sensor and the surround view camera confirm that the vehicle center line is aligned with the parking space center line (error < 10 cm), the ultrasonic sensor detects the front and rear distances, and stop the parking operation when the rear of the vehicle is 30 cm away from the obstacle behind.

[0078] In step 140, after issuing the instruction to execute the re-parking, it further includes: Send a notice of successful parking after parking is completed.

[0079] In this embodiment, a status feedback signal is generated through the communication link between the vehicle control system and the mobile terminal. Specifically, it can be implemented by using the in-vehicle infotainment system to display prompt information, the mobile phone application to push messages, or the vehicle lights to flash. This feature establishes a visual feedback channel for the operation result, converting the physical state of parking completion into an identifiable information flow.

[0080] Through the above technical solutions, this application realizes the real-time synchronization of the parking operation status, enabling the driver to remotely confirm the parking result without having to be in close contact with the vehicle.

[0081] Embodiment 2: As Figure 6 shown, Figure 6 shows a schematic structural diagram of an embodiment of the control system of the present invention. A controller system 1 includes at least: a target parking space information acquisition module 10 and a vehicle control module 20.

[0082] Among them, the target parking space information acquisition module 10 is used to acquire the image information and position information of the target parking space; the vehicle control module 20 is used to receive the image information and position information of the target parking space, analyze the availability of the target parking space according to the image information and position information, and when the target parking space is available, request to establish a re-parking path according to the image information and position information of the target parking space, and based on the re-parking path, issue an instruction to execute re-parking.

[0083] The vehicle control module 20 is specifically used to execute the following method steps: Step 110: Receive the image information and position information of the target parking space; Step 120: Analyze the availability of the target parking space according to the image information and position information; Step 130: When the target parking space is available, request to establish a re-parking path according to the image information and position information of the target parking space; Step 140: Based on the re-parking path, issue an instruction to execute re-parking.

[0084] In some embodiments, the vehicle control module 20 includes a path planning module 21 and a target parking space availability analysis module 22.

[0085] Among them, the path planning module 21 is used to establish a re-parking path according to the image information and position information of the target parking space. The target parking space availability analysis module 22 is used to analyze the availability of the target parking space according to the image information and position information.

[0086] It should be noted that the target parking space availability analysis module 22 can be configured as a data analysis module in the cloud, and the specific form is a cloud server, etc., and can also be a dedicated analysis module configured locally for image information analysis and data processing.

[0087] In some embodiments, the control system 1 further includes an environment perception module 30, and the environment perception module 30 includes a camera 31, a millimeter wave radar 32, and an ultrasonic radar 33.

[0088] Among them, the camera 31 is used to detect the color and shape of the target parking space marking. The millimeter wave radar 32 is used to detect the distance between the vehicle and the obstacle and identify low obstacles. The ultrasonic radar 33 is used to detect the surrounding environment of the vehicle.

[0089] The above system receives the image information and position information of the target parking space captured by the driver, analyzes the availability of the target parking space based on the image information and position information, and when the target parking space is available, requests to generate a re-parking path based on the image information and position information of the target parking space and the spatial relationship between the current vehicle pose and the target position, and issues an instruction to execute re-parking based on the re-parking path. In this way, without the driver returning to the vehicle and restarting the parking process, the vehicle can perform re-parking operations autonomously, improving the intelligence level and usability of the parking system.

[0090] Embodiment 3: Figure 7 The structure diagram of the embodiment of the re-parking device of the present invention is shown. The specific implementation of the re-parking device in the specific embodiment of the present invention is not limited.

[0091] As Figure 7 shown, a re-parking device may include: a processor 701, a communications interface 702, a memory 703, and a communication bus 704.

[0092] Among them: the processor 701, the communications interface 702, and the memory 703 communicate with each other through the communication bus 704. The communications interface 702 is used to communicate with network elements of other devices such as a control system or other servers. The processor 701 is used to execute a program, and when executed, it implements the steps in the re-parking method described above to perform re-parking operations on the vehicle.

[0093] Specifically, the program 710 may include program code, and the program code includes computer-executable instructions.

[0094] Specifically, the processor 701 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors 701 included in the re-parking device may be of the same type of processor 701, such as one or more CPUs; or may be of different types of processors 701, such as one or more CPUs and one or more ASICs.

[0095] The memory 703 is used to store the program. The memory 703 may include high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0096] The program 710 can specifically be called by the processor 701 to enable the re-parking device to perform the following operations: Receive the image information and location information of the target parking space; Analyze the availability of the target parking space based on the image information and location information; When the target parking space is available, request to establish a re-parking path based on the image information and location information of the target parking space; Based on the re-parking path, issue an instruction to execute re-parking.

[0097] In an alternative embodiment, the program 710 is called by the processor 701 to cause the re-parking device to execute the steps and specific sub-steps in the embodiment.

[0098] The above device receives the image information and location information of the target parking space captured by the driver, then analyzes the availability of the target parking space based on the image information and location information. When the target parking space is available, it requests to generate a re-parking path based on the image information and location information of the target parking space and the spatial relationship between the current vehicle pose and the target position. Based on the re-parking path, it issues an instruction to execute re-parking. In this way, without the driver returning to the vehicle and restarting the parking process, the vehicle can autonomously perform re-parking operations, improving the intelligence level and usability of the parking system.

[0099] Embodiment 4: The embodiment of the present invention provides a computer-readable storage medium, and the storage medium stores at least one executable instruction. When the executable instruction runs on the re-parking device, it causes the re-parking device to execute the re-parking method in any of the above method embodiments.

[0100] The executable instruction can specifically be used to cause the re-parking device to perform the following operations: Receive the image information and location information of the target parking space; Analyze the availability of the target parking space based on the image information and location information; When the target parking space is available, request to establish a re-parking path based on the image information and location information of the target parking space; Based on the re-parking path, issue an instruction to execute re-parking.

[0101] By receiving the image information and location information of the target parking space captured by the driver, then analyzing the availability of the target parking space based on the image information and location information. When the target parking space is available, it requests to generate a re-parking path based on the image information and location information of the target parking space and the spatial relationship between the current vehicle pose and the target position. Based on the re-parking path, it issues an instruction to execute re-parking. In this way, without the driver returning to the vehicle and restarting the parking process, the vehicle can autonomously perform re-parking operations, improving the intelligence level and usability of the parking system.

[0102] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Additionally, embodiments of the present invention are not directed to any particular programming language.

[0103] In the specification provided herein, numerous specific details are set forth. However, it will be understood that embodiments of the present invention may be practiced without these specific details. Similarly, in order to streamline the present invention and assist in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. Among them, the claims following the specific implementation manner are hereby expressly incorporated into the specific implementation manner, where each claim itself is a separate embodiment of the present invention.

[0104] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and disposed in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive.

[0105] It should be noted that the above embodiments illustrate the present invention rather than limit the present invention, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim listing several devices, several of these devices may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A re-parking method, characterized in that, Including: Receiving the image information and location information of the target parking space; Analyzing the availability of the target parking space according to the image information and location information; When the target parking space is available, requesting to establish a re-parking path according to the image information and location information of the target parking space; Based on the re-parking path, issuing an instruction to execute re-parking.

2. The re-parking method according to claim 1, characterized in that The image information includes: target parking space marking information, environmental reference objects; and / or The location information includes: obtaining the satellite positioning coordinates of the target parking space, or the fused positioning coordinates after compensating for positioning drift by combining satellite positioning coordinates and IMU data.

3. The re-parking method according to claim 1, wherein The analyzing the availability of the target parking space according to the image information and location information includes: Identifying the markings of the target parking space and environmental reference objects in the image information; Calculating the size of the effective space of the target parking space, and comparing the preset vehicle size with the size of the effective space; Outputting the availability of the target parking space according to the comparison result.

4. The re-parking method according to claim 3, characterized in that, The identifying the markings of the target parking space and environmental reference objects in the image information includes the following sub-steps: Identifying the parking space markings and obstacles from the image information according to a preset target detection and instance segmentation model; Determining the effective length information and effective width information of the target parking space according to the parking space markings and the obstacles.

5. The re-parking method according to claim 3, wherein The calculating the size of the effective space of the target parking space, and comparing the preset vehicle size with the size of the effective space includes the following sub-steps: Judging the number of target parking spaces and calculating the size of the effective space of each target vehicle; Filtering out the target parking spaces that do not meet the requirements according to the preset vehicle size; Calculating the optimal target parking space according to the obstacle density around the remaining target parking space markings and the distance from the target position.

6. The re-parking method according to claim 1, wherein The analyzing the availability of the target parking space according to the image information and location information is local analysis or cloud analysis.

7. The re-parking method according to claim 1, wherein, The requesting to establish a re-parking path according to the image information and location information of the target parking space includes the following sub-steps: Converting the location information into a vehicle coordinate system; Matching the image information and the real-time picture of the on-vehicle camera through visual odometry to dynamically calibrate the position of the target parking space; Generating a collision-free path according to the target parking space position through a preset path planning algorithm.

8. The re-parking method according to claim 1, wherein, After issuing the instruction to execute re-parking based on the re-parking path, it further includes: Detecting the vehicle surrounding environment; Confirming that there is no obstacle in the vehicle surrounding environment and then executing the re-parking instruction; If there is an obstacle in the vehicle surrounding environment, re-planning the parking path.

9. The re-parking method according to claim 8, wherein After issuing the instruction to execute re-parking, it further includes: Calculating the steering wheel angle according to the path curvature of the parking path; Confirming that the vehicle center line is aligned with the parking space center line, and when the distance between the front and rear of the vehicle and the obstacles reaches a preset value, the vehicle stops driving.

10. The re-parking method according to claim 1, wherein After issuing the instruction to execute re-parking, it further includes: Sending a notice of successful parking after parking is completed.

11. A control system, characterized in that, At least including: A target parking space information acquisition module for acquiring the image information and location information of the target parking space; And A vehicle control module, configured to receive image information and position information of a target parking space, analyze the availability of the target parking space according to the image information and the position information, and when the target parking space is available, request to establish a re-parking path according to the image information and the position information of the target parking space, and based on the re-parking path, issue an instruction to execute re-parking.

12. The control system according to claim 11, wherein The vehicle control module includes: A path planning module, configured to establish a re-parking path according to the image information and the position information of the target parking space; and A target parking space availability analysis module, configured to analyze the availability of the target parking space according to the image information and the position information, and the target parking space availability analysis module is a cloud processing module.

13. The control system according to claim 11, wherein, The control system further includes an environment perception module, and the environment perception module includes: A camera, configured to detect the color and shape of the target parking space markings; A millimeter-wave radar, configured to detect the distance between the vehicle and an obstacle and identify low obstacles; An ultrasonic radar, configured to detect the surrounding environment of the vehicle.

14. A re-parking device, characterized in that, It includes: A processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete communication with each other through the communication bus; The memory is used to store at least one executable instruction, and when the executable instruction is executed by the processor, it realizes the steps in the re-parking method described in any one of claims 1 to 10 to perform a re-parking operation on the vehicle.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the device where the computer-readable storage medium is located executes the computer program, it realizes the re-parking method described in any one of claims 1 to 10.

Images