Automatic parking method, device, vehicle and storage medium for vehicle

Abstract

The present application relates to the field of vehicle technology, and in particular to an automatic parking method, device, vehicle and storage medium for a vehicle, wherein the method comprises: when an obstacle vehicle is identified on the left and / or right side of a target parking space, obtaining the sideline angle of the target parking space close to the obstacle vehicle; calculating the expected body angle of the obstacle vehicle according to the sideline angle, and planning the parking path of the vehicle according to the expected body angle of the obstacle vehicle; while controlling the vehicle to enter the target parking space according to the parking path, detecting the actual body angle of the obstacle vehicle, and correcting the body angle of the parked vehicle according to the actual body angle. Therefore, the embodiment of the present application can automatically park with reference to the parking postures of vehicles around the parking space, determine the final parking posture of the vehicle, and effectively reduce the relevant impact between the parking position of the vehicle and other vehicles while achieving safe parking, provide an expected parking posture that is friendly to both the vehicle and the environment, and enhance the user experience.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to an automatic parking method, device, vehicle and storage medium for a vehicle. Background Art

[0002] As the number of cars continues to increase, the parking environment in limited urban space becomes more and more complex, and the problem of parking difficulty becomes more and more prominent. These problems have attracted a lot of attention from the outside world, especially from major OEMs, which has led to the emergence of autonomous valet parking systems.

[0003] As an important part of the autonomous valet parking system, path planning has a significant impact on the parking results. The expected parking target posture points, parking space information, obstacle information, etc. are used as the basis of path planning. Accurate and easy-to-reach parking posture points can greatly improve the efficiency of path planning and improve parking performance. Summary of the invention

[0004] The present application provides an automatic parking method, device, vehicle and storage medium for a vehicle, which can provide a reference angle of the final parking point for parking path planning, and has a certain degree of anti-interference to the noise detected by the sensor to meet the safety requirements of parking; at the same time, it can be combined with the parking environment to provide an expected parking posture that is friendly to both the vehicle and the environment.

[0005] A first aspect of the present application provides an automatic parking method for a vehicle, comprising the following steps: when an obstacle vehicle is identified on the left and / or right side of a target parking space, obtaining the sideline angle of the target parking space close to the obstacle vehicle; calculating the estimated body angle of the obstacle vehicle based on the sideline angle, and planning a parking path for the vehicle based on the estimated body angle of the obstacle vehicle; while controlling the vehicle to enter the target parking space according to the parking path, detecting the actual body angle of the obstacle vehicle, and correcting the body angle of the parked vehicle based on the actual body angle.

[0006] According to the above-mentioned technical means, the embodiment of the present application can automatically park by referring to the parking postures of vehicles around the parking space, and determine the final parking posture of the vehicle. While achieving safe parking, since the parking posture of the vehicle is similar to that of the surrounding vehicles, the correlation impact between the parking position of the vehicle and other vehicles can be effectively reduced, providing an expected parking posture that is friendly to both the vehicle and the environment, thereby improving the user experience.

[0007] Optionally, controlling the vehicle to enter the target parking space according to the parking path and detecting the actual body angle of the obstacle vehicle includes: acquiring an actual depth of the vehicle entering the target parking space; and detecting the actual body angle of the obstacle vehicle when the actual depth is greater than or equal to a first depth threshold.

[0008] According to the above-mentioned technical means, the present application can update the actual body angle of the obstacle vehicle relative to the vehicle when the vehicle reaches a certain position of the target parking space during the warehousing process, ensure the real-time nature of the relevant obstacle vehicle information, and provide the expected parking posture that is friendly to both the vehicle and the environment, thereby improving the intelligence of the solution, enhancing the safety of the warehousing process, and meeting the needs of actual use.

[0009] Optionally, when the actual depth is greater than or equal to a first depth threshold and less than a second depth threshold, detecting the actual body angle of the obstacle vehicle includes: obtaining a fused cluster segment of the obstacle vehicle; identifying a first endpoint in the fused cluster segment that is closest to the vehicle; taking the first endpoint as a seed node, searching for a second endpoint in the fused cluster segment that is closest to the first endpoint along the direction of entry of the vehicle, and obtaining a third endpoint that is in the same segment as the second endpoint along the direction of entry of the vehicle; calculating an angle difference between a first segment between the first endpoint and the second endpoint and a second segment between the second endpoint and the third endpoint, and when the angle difference is less than an angle threshold, adding the second endpoint and the third endpoint to a candidate node set; continuing the search with the third endpoint as a seed node until the angle difference is greater than or equal to the angle threshold, or the last endpoint of the fused cluster segment is searched, and calculating the actual body angle based on the first endpoint, the last endpoint at the end of the search, and the candidate node set.

[0010] According to the above-mentioned technical means, the present application can process the updated fusion information of the obstacle vehicle after the vehicle enters the warehouse, use the ultrasonic vertical parking space obstacle vehicle angle calculation method, and obtain the body angle of the obstacle vehicle through straight line fitting to provide the expected parking posture that is friendly to both the vehicle and the environment.

[0011] Optionally, when the actual depth is greater than or equal to a second depth threshold, detecting the actual body angle of the obstacle vehicle includes: identifying the fourth endpoint in the fused cluster segment that is closest to the vehicle; taking the fourth endpoint as a seed node, searching for the last endpoint of the fused cluster segment along the direction of entry of the vehicle, searching for the fifth endpoint in the fused cluster segment that is closest to the fourth endpoint along the opposite direction of the direction of entry of the vehicle, and obtaining the sixth endpoint of the same segment as the fifth endpoint along the opposite direction; calculating the angle difference between the third segment between the fourth endpoint and the fifth endpoint and the fourth segment between the fifth endpoint and the sixth endpoint, and when the angle difference is less than the angle threshold, adding the fifth endpoint and the sixth endpoint to the candidate node set; continuing the search with the sixth endpoint as a seed node until the angle difference is greater than or equal to the angle threshold, obtaining the inflection point of the body contour of the obstacle vehicle, and calculating the actual body angle according to the inflection point of the body contour, the last endpoint of the fused cluster segment and the candidate node set.

[0012] According to the above-mentioned technical means, the present application can calculate the actual body angle according to the turning point of the body contour, the last endpoint of the fused cluster segment and the set of alternative nodes, keep the update of the body angle of the vehicle and the information fusion, and correct the parking angle according to the actual situation during the parking process, so that the parking posture of the vehicle is similar to that of the surrounding vehicles, effectively reducing the correlation between the parking position of the vehicle and other vehicles, providing an expected parking posture that is friendly to both the vehicle and the environment, improving parking safety, and enhancing user experience.

[0013] Optionally, the actual vehicle body angle is calculated based on the first endpoint, the last endpoint at the end of the search and the alternative node set, including: determining whether the actual distance between the first endpoint and the last endpoint is greater than a first length threshold; if the actual distance is greater than the first length threshold, and there is a line segment greater than a second length threshold in the alternative node set, using the average of the straight line angle fitted by the alternative node set and the line segment angle greater than the second length threshold as the actual vehicle body angle, otherwise, using the straight line angle as the actual vehicle body angle.

[0014] According to the above-mentioned technical means, the present application can determine the actual distance between the first endpoint and the last endpoint, compare it with the first length threshold, and select the description of the actual vehicle body angle according to the actual situation, so that the parking angle calculation result is more accurate, and the parking posture of the vehicle is similar to the parking posture of the surrounding vehicles, effectively reducing the correlation between the parking position of the vehicle and other vehicles, and providing an expected parking posture that is friendly to both the vehicle and the environment, meeting the actual parking needs.

[0015] Optionally, the actual body angle is calculated based on the inflection point of the body contour, the last endpoint of the fused cluster line segment and the alternative node set, including: judging whether the actual distance between the inflection point of the body contour and the last endpoint is greater than a third length threshold; if the actual distance is greater than the third length threshold, and there is a line segment greater than a fourth length threshold in the alternative node set, taking the average of the straight line angle fitted by the alternative node set and the line segment angle greater than the fourth length threshold as the actual body angle, otherwise, taking the straight line angle as the actual body angle.

[0016] According to the above-mentioned technical means, the present application can judge the actual distance between the inflection point of the vehicle body contour and the last endpoint, compare it with the third length threshold, and select the description of the actual vehicle body angle according to the actual situation, so that the parking angle calculation result is more accurate, and the parking posture of the vehicle is similar to the parking posture of the surrounding vehicles, effectively reducing the correlation between the parking position of the vehicle and other vehicles, providing an expected parking posture that is friendly to both the vehicle and the environment, and meeting the actual parking needs.

[0017] Optionally, before calculating the actual vehicle body angle, the method further includes: filtering noise points of the candidate node set according to a preset filtering strategy to obtain a filtered candidate node set.

[0018] Based on the above technical means, the present application can filter the noise points that appear during the detection process, eliminate invalid interference information, reduce redundant calculations of the actual vehicle body angle during noise-free filtering, improve the intelligence of parking and the accuracy of related information, and meet the needs of actual use.

[0019] A second aspect of the present application provides an automatic parking device for a vehicle, comprising: an acquisition module, for acquiring the sideline angle of the target parking space close to the side of the obstacle vehicle when an obstacle vehicle is identified on the left and / or right side of the target parking space; a prediction module, for calculating the predicted body angle of the obstacle vehicle based on the sideline angle, and planning a parking path for the vehicle based on the predicted body angle of the obstacle vehicle; a parking module, for controlling the vehicle to enter the target parking space according to the parking path, while detecting the actual body angle of the obstacle vehicle, and correcting the body angle of the parked vehicle based on the actual body angle.

[0020] Optionally, the parking module is used to: obtain an actual depth of the vehicle entering the target parking space; and detect an actual body angle of the obstacle vehicle when the actual depth is greater than or equal to a first depth threshold.

[0021] Optionally, the parking module is further used to: obtain the fused cluster segment of the obstacle vehicle; identify the first endpoint in the fused cluster segment that is closest to the vehicle; use the first endpoint as a seed node to search for the second endpoint in the fused cluster segment that is closest to the first endpoint along the direction of entry of the vehicle, and obtain a third endpoint that is in the same segment as the second endpoint along the direction of entry of the vehicle; calculate the angle difference between a first segment between the first endpoint and the second endpoint and a second segment between the second endpoint and the third endpoint, and when the angle difference is less than an angle threshold, add the second endpoint and the third endpoint to a set of candidate nodes; continue searching with the third endpoint as a seed node until the angle difference is greater than or equal to the angle threshold, or the last endpoint of the fused cluster segment is searched, and calculate the actual vehicle body angle based on the first endpoint, the last endpoint at the end of the search, and the set of candidate nodes.

[0022] Optionally, the parking module is further used to: determine whether the actual distance between the first endpoint and the last endpoint is greater than a first length threshold; if the actual distance is greater than the first length threshold, and there is a line segment greater than a second length threshold in the alternative node set, use the average of the straight line angle fitted by the alternative node set and the line segment angle greater than the second length threshold as the actual vehicle body angle; otherwise, use the straight line angle as the actual vehicle body angle.

[0023] Optionally, the parking module is further used to: identify the fourth endpoint in the fused cluster segment that is closest to the vehicle; use the fourth endpoint as a seed node to search for the last endpoint of the fused cluster segment along the direction of entry of the vehicle, search for the fifth endpoint in the fused cluster segment that is closest to the fourth endpoint along the opposite direction of the direction of entry of the vehicle, and obtain the sixth endpoint of the same segment as the fifth endpoint along the opposite direction; calculate the angle difference between the third segment between the fourth endpoint and the fifth endpoint and the fourth segment between the fifth endpoint and the sixth endpoint, and when the angle difference is less than an angle threshold, add the fifth endpoint and the sixth endpoint to the candidate node set; continue searching with the sixth endpoint as a seed node until the angle difference is greater than or equal to the angle threshold, obtain the inflection point of the body contour of the obstacle vehicle, and calculate the actual body angle according to the inflection point of the body contour, the last endpoint of the fused cluster segment and the candidate node set.

[0024] Optionally, the parking module is further used to: determine whether the actual distance between the inflection point of the vehicle body contour and the last endpoint is greater than a third length threshold; if the actual distance is greater than the third length threshold, and there is a line segment greater than a fourth length threshold in the alternative node set, the average of the straight line angle fitted by the alternative node set and the line segment angle greater than the fourth length threshold is used as the actual vehicle body angle; otherwise, the straight line angle is used as the actual vehicle body angle.

[0025] Optionally, the parking module is further used to: perform noise filtering on the candidate node set according to a preset filtering strategy to obtain a filtered candidate node set.

[0026] A third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the automatic parking method for the vehicle as described in the above embodiment.

[0027] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the automatic parking method for a vehicle as described in the above embodiment.

[0028] Therefore, this application has at least the following beneficial effects:

[0029] (1) The embodiment of the present application can automatically park the vehicle by referring to the parking postures of the vehicles around the parking space, and determine the final parking posture of the vehicle. While achieving safe parking, since the parking posture of the vehicle is similar to that of the surrounding vehicles, the relevant impact between the parking position of the vehicle and other vehicles can be effectively reduced, providing an expected parking posture that is friendly to both the vehicle and the environment, thereby improving the user experience;

[0030] (2) This application can update the actual body angle of the obstacle vehicle relative to the vehicle when the vehicle reaches a certain position in the target parking space during the parking process, ensuring the real-time information of the relevant obstacle vehicle, so as to provide the desired parking posture that is friendly to the vehicle and the environment, improve the intelligence of the solution, enhance the safety of the parking process, and meet the needs of actual use;

[0031] (3) After the vehicle enters the parking space, the present application can process the updated fusion information of the obstacle vehicle, use the ultrasonic vertical parking space obstacle vehicle angle calculation method, and obtain the body angle of the obstacle vehicle through linear fitting to provide the desired parking posture that is friendly to both the vehicle and the environment;

[0032] (4) The present application can calculate the actual body angle based on the body contour inflection point, the last endpoint of the fused cluster line segment and the candidate node set, keep updating the body angle of the vehicle and information fusion, and correct the parking angle according to the actual situation during the parking process, so that the parking posture of the vehicle is similar to that of the surrounding vehicles, effectively reducing the correlation between the parking position of the vehicle and other vehicles, providing an expected parking posture that is friendly to both the vehicle and the environment, improving parking safety, and enhancing user experience;

[0033] (5) The present application can determine the actual distance between the first endpoint and the last endpoint, compare it with the first length threshold, and select the description of the actual vehicle body angle according to the actual situation, so that the parking angle calculation result is more accurate, and the parking posture of the vehicle is similar to the parking posture of surrounding vehicles, which effectively reduces the correlation between the parking position of the vehicle and other vehicles, provides an expected parking posture that is friendly to both the vehicle and the environment, and meets the actual parking needs;

[0034] (6) The present application can determine the actual distance between the turning point of the vehicle body contour and the last endpoint, compare it with the third length threshold, and select the description of the actual vehicle body angle according to the actual situation, so that the parking angle calculation result is more accurate, and the parking posture of the vehicle is similar to the parking posture of surrounding vehicles, which effectively reduces the correlation between the parking position of the vehicle and other vehicles, provides an expected parking posture that is friendly to both the vehicle and the environment, and meets the actual parking needs;

[0035] (7) The present application can filter out noise points that appear during the detection process, eliminate invalid interference information, reduce redundant calculations of the actual vehicle body angle when filtering without noise points, improve the intelligence of parking and the accuracy of related information, and meet the needs of actual use.

[0036] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0038] Figure 1 A flowchart of an automatic parking method for a vehicle provided according to an embodiment of the present application;

[0039] Figure 2 A schematic diagram of ultrasonic parking space and obstacle vehicle fusion information initially released during the parking space search phase according to an embodiment of the present application;

[0040] Figure 3A schematic diagram of Cluster line segment information fused with the detected obstacle vehicle when the vehicle is outside the parking space during the parking phase according to an embodiment of the present application;

[0041] Figure 4 A schematic diagram of searching for an initial seed node according to fusion information of a detected left obstacle vehicle after a vehicle has just entered a parking space in accordance with an embodiment of the present application;

[0042] Figure 5 A schematic diagram of finding an initial seed node according to the fusion information of the detected left obstacle vehicle when a vehicle enters a deep garage according to an embodiment of the present application;

[0043] Figure 6 A schematic diagram of removing abnormal initial seed nodes when noise exists in the detected obstacle vehicle fusion information according to an embodiment of the present application;

[0044] Figure 7 A schematic diagram of an updated angle of an obstacle vehicle after a vehicle has just entered the parking phase according to an embodiment of the present application;

[0045] Figure 8 It is a schematic diagram of an updated obstacle vehicle angle when a vehicle is stored deep in a garage according to an embodiment of the present application;

[0046] Fig. 9 A schematic diagram of a real and effective obstacle vehicle angle provided according to an embodiment of the present application;

[0047] Fig.10 Another schematic diagram of removing abnormal initial seed nodes when noise exists in the detected obstacle vehicle fusion information according to an embodiment of the present application;

[0048] Fig.11 Another schematic diagram of a real and effective obstacle vehicle angle provided according to an embodiment of the present application;

[0049] Fig.12 An exemplary diagram of an automatic parking device for a vehicle provided according to an embodiment of the present application;

[0050] Fig.13 It is a schematic diagram of the structure of a vehicle provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0051] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0052] The following will describe the automatic parking method, device, vehicle and storage medium of the vehicle according to the embodiments of the present application with reference to the accompanying drawings.

[0053] Specifically, Figure 1 A schematic flow chart of an automatic parking method for a vehicle provided in an embodiment of the present application.

[0054] like Figure 1 As shown, the automatic parking method of the vehicle includes the following steps:

[0055] In step S101, when it is identified that there is an obstructing vehicle on the left and / or right side of the target parking space, the sideline angle of the target parking space close to the obstructing vehicle is obtained.

[0056] Among them, the embodiments of the present application can use at least one method to realize the identification of the obstacle vehicle and the acquisition of the sideline angle of the obstacle vehicle. For example, the embodiments of the present application can process the initially detected obstacle information based on the vehicle's camera and ultrasonic input to realize the identification of the obstacle vehicle and the acquisition of the sideline angle of the obstacle vehicle; the target parking space refers to an empty parking space where the vehicle can be parked, which can be manually confirmed by the user or automatically identified and confirmed by the vehicle, and there is no specific limitation on this.

[0057] It can be understood that during the parking process, when the vehicle begins to prepare for parking and is still outside the garage, the embodiment of the present application can first plan the target parking space for parking and identify the information of possible obstacle vehicles in the surrounding area; when there is an obstacle vehicle on either side of the target parking space, the side line angle of the obstacle vehicle relative to the target parking space is obtained for subsequent planning of the parking plan.

[0058] Specifically, the embodiment of the present application can obtain several fixed-point coordinates of the ultrasonic parking space, for example, 4 fixed-point coordinates (P0, P1, P2, P3) can be obtained, and the Cluster line segment can be used to characterize the fusion information of the obstacle vehicle, wherein each line segment contains the obstacle ID, the endpoint coordinates (x, y) and the width and height information. The embodiment of the present application can establish a coordinate system based on the above information and according to the actual situation, and no specific limitation is made to this; when the vehicle is outside the garage, the embodiment of the present application can obtain the angles of the obstacle vehicles that may exist on the left and right sides according to the initial parking space coordinate information. For example, when there are obstacle vehicles on both sides, the angles of the obstacle vehicles on both sides can be obtained at the same time; specifically as follows:

[0059] (1) Figure 2 As shown, when the vehicle is searching for a parking space, the perception system obtains the parking space information and the obstacle vehicle fusion cluster line segment;

[0060] (2) During the parking phase, if Figure 3 As shown, the vehicle is outside the warehouse, that is:

[0061] |Veh y | <Deep threshold

[0062] Among them, Veh y is the y coordinate of the center of the vehicle's rear axle, Deep threshold Since the sensor does not fully detect the obstructed vehicles in the garage, at this stage, the angles of the obstructed vehicles on both sides are determined based on the initially released ultrasonic parking spaces P0P2 and P1P3 angles (if there is an obstructed vehicle on only one side, the corresponding ultrasonic parking space sideline segment angle is used as the reference angle).

[0063] In step S102, the estimated body angle of the obstacle vehicle is calculated according to the edge angle, and the parking path of the vehicle is planned according to the estimated body angle of the obstacle vehicle.

[0064] It is understandable that the embodiment of the present application can use the Cluster line segment obtained in the above step S101 and the above edge line angle to calculate the expected body angle of the obstacle vehicle to obtain the expected angle value of the obstacle vehicle relative to the vehicle, which is used to generate the expected parking path of the vehicle.

[0065] In step S103, while controlling the vehicle to drive into the target parking space according to the parking path, the actual body angle of the obstacle vehicle is detected, and the body angle of the parked vehicle is corrected according to the actual body angle.

[0066] It is understandable that when parking, the embodiment of the present application can execute the parking path predicted in the above step S102 to park before the vehicle enters the target parking space; and while the vehicle enters the target parking space according to the predicted parking path, the body angle of the obstacle vehicle relative to the vehicle is detected, and the vehicle is controlled to correct the parking position of the vehicle based on the actual angle.

[0067] In an embodiment of the present application, the vehicle is controlled to enter the target parking space according to the parking path, and the actual body angle of the obstacle vehicle is detected, including: obtaining the actual depth of the vehicle entering the target parking space; when the actual depth is greater than or equal to the first depth threshold, detecting the actual body angle of the obstacle vehicle.

[0068] The first depth threshold can be set according to actual conditions and is not specifically limited thereto.

[0069] It can be understood that the embodiment of the present application can set a first depth threshold to determine the degree to which the vehicle enters the parking path. When the vehicle enters the parking space, the updated fusion information of the obstacle vehicle is processed to eliminate invalid interference information and obtain the final fusion information of the vehicle side body.

[0070] In an embodiment of the present application, when the actual depth is greater than or equal to a first depth threshold and less than a second depth threshold, the actual body angle of the obstacle vehicle is detected, including: obtaining a fused cluster segment of the obstacle vehicle; identifying the first endpoint in the fused cluster segment that is closest to the vehicle; taking the first endpoint as a seed node, searching the fused cluster segment for the second endpoint that is closest to the first endpoint along the direction of entry of the vehicle, and obtaining a third endpoint that is in the same segment as the second endpoint along the direction of entry of the vehicle; calculating the angle difference between the first segment between the first endpoint and the second endpoint and the second segment between the second endpoint and the third endpoint, and when the angle difference is less than the angle threshold, adding the second endpoint and the third endpoint to the candidate node set; continuing the search with the third endpoint as the seed node until the angle difference is greater than or equal to the angle threshold, or the last endpoint of the fused cluster segment is searched, and calculating the actual body angle based on the first endpoint, the last endpoint at the end of the search, and the candidate node set.

[0071] The second depth threshold and the angle threshold may be specifically set according to actual conditions, and no specific limitation is made thereto.

[0072] Specifically, in Figure 4 In the example of a vehicle with a single-side obstacle, when the vehicle starts parking, the Deep threshold When the following is true, the embodiment of the present application can be considered that the sensor has a good detection of the front of the vehicle obstacle vehicle; therefore, the embodiment of the present application can search for the point closest to the vehicle in the fusion Cluster line segment of the left obstacle vehicle, and obtain the minimum value of the straight line formed by the endpoint to the midpoint of the ultrasonic parking space P0P1 and P2P3, that is, P in the figure leftmin . leftmin Search downward for the closest fused Cluster endpoint in the Y direction (parking space depth direction) for the seed node, which is P5 in the figure, and obtain the other endpoint P6 of the same line segment. leftmin The node is located in front of the parking space and is detected during the parking space search phase and the parking entry phase. Therefore, the embodiment of the present application does not need to verify the initial seed node located in front of the parking space. leαftmin The angle difference α of P5 in the parking coordinate system is:

[0073] α<Δangle,

[0074] Wherein, Δangle is the angle threshold; when the above angle difference is less than the angle threshold, the embodiment of the present application can add the Cluster line segment P5P6 to the candidate node set for calculating the angle of the obstacle vehicle; at the same time, the seed node is updated to P6, and the nearest Cluster line segment is continued to be searched downward. Figure 4 P6 is the termination node.

[0075] In an embodiment of the present application, the actual vehicle body angle is calculated based on the first endpoint, the last endpoint at the end of the search, and the alternative node set, including: determining whether the actual distance between the first endpoint and the last endpoint is greater than a first length threshold; if the actual distance is greater than the first length threshold, and there is a line segment greater than the second length threshold in the alternative node set, the average of the straight line angle fitted by the alternative node set and the line segment angle greater than the second length threshold is used as the actual vehicle body angle, otherwise, the straight line angle is used as the actual vehicle body angle.

[0076] Among them, the first length threshold is smaller than the second length threshold. The first length threshold and the second length threshold can be specifically set according to actual conditions, and no specific limitation is made to this.

[0077] Specifically, in Figure 4 If P leftmin The distance from P6 is greater than the length threshold, that is:

[0078]

[0079] in, is the y coordinate of the initial growth node, is the y coordinate of point P6. The embodiment of the present application can calculate whether the length of a single Cluster line segment in the candidate node set is greater than If it is satisfied, the angle of the obstacle car is the average of the angle of the straight line fitted by the candidate node set and the angle of this Cluster segment. If it is not satisfied, the angle of the obstacle car is the angle of the straight line fitted by the candidate node set.

[0080] In an embodiment of the present application, when the actual depth is greater than or equal to a second depth threshold, the actual body angle of the obstacle vehicle is detected, including: identifying the fourth endpoint in the fused cluster segment that is closest to the vehicle; taking the fourth endpoint as a seed node, searching for the last endpoint of the fused cluster segment along the direction of entry of the vehicle, searching for the fifth endpoint in the fused cluster segment that is closest to the fourth endpoint along the opposite direction of entry of the vehicle, and obtaining the sixth endpoint of the same segment as the fifth endpoint along the opposite direction; calculating the angle difference between the third segment between the fourth endpoint and the fifth endpoint and the fourth segment between the fifth endpoint and the sixth endpoint, and when the angle difference is less than the angle threshold, adding the fifth endpoint and the sixth endpoint to the candidate node set; continuing the search with the sixth endpoint as the seed node until the angle difference is greater than or equal to the angle threshold, obtaining the inflection point of the body contour of the obstacle vehicle, and calculating the actual body angle according to the inflection point of the body contour, the last endpoint of the fused cluster segment and the candidate node set.

[0081] Specifically, the embodiments of the present application can be as follows Figure 5As shown in the figure, taking the vehicle with one side obstacle as an example, the vehicle enters the garage deeper, and the detection of the vehicle with side obstacle is more complete. The same as above is used to find the initial seed node, P leftmin is the initial seed node, and P is searched through downward growth. bottom Node, and add the corresponding Cluster line segment endpoint to the candidate node. leftmin If the node is in the middle of the parking space, the embodiment of the present application can search upwards for nodes and update the seed node to P lefttop At the same time, the angle α>Δangle with the next (upward) Cluster line segment is calculated, and because P top Located at the upper part of the parking space, the embodiment of the present application can determine P top Point is the turning point of the body contour, and P lefttop To P bottom The Cluster endpoint is added to the candidate node.

[0082] In an embodiment of the present application, the actual body angle is calculated based on the inflection point of the body contour, the last endpoint of the fused cluster segment and the alternative node set, including: judging whether the actual distance between the inflection point of the body contour and the last endpoint is greater than a third length threshold; if the actual distance is greater than the third length threshold, and there is a line segment greater than the fourth length threshold in the alternative node set, the average of the straight line angle fitted by the alternative node set and the line segment angle greater than the fourth length threshold is used as the actual body angle, otherwise, the straight line angle is used as the actual body angle.

[0083] Among them, the third length threshold is smaller than the fourth length threshold, and the third length threshold and the fourth length threshold can be specifically set according to actual conditions, and no specific limitation is made to this.

[0084] Specifically, the embodiment of the present application can also calculate the vehicle angle of the obstacle vehicle, which is Figure 7 Center Line left From the perspective of Figure 5 The vehicle angle of the obstacle vehicle is Figure 8 Center Line left Angle Figure 6 The vehicle angle of the obstacle vehicle is Fig. 9 Center Line right Angle Fig.10 The vehicle angle of the obstacle vehicle is Fig.11 Center Line right angle.

[0085] In the embodiment of the present application, before calculating the actual vehicle body angle, it also includes: filtering noise points of the candidate node set according to a preset filtering strategy to obtain a filtered candidate node set.

[0086] Specifically, the embodiment of the present application can also filter out noise points that appear during the detection process. Figure 6 As shown, P right is the initial seed node. Since there is no Cluster line segment downward, the embodiment of the present application can search for candidate nodes upward. Since α>Δangle and P8P9 are located in the middle of the parking space, and β>Δangle is calculated with P9 as the seed node, and P right The Cluster line segment and P 10 P 11 The angle difference is less than Δangle, so the embodiment of the present application may not select Cluster line segment P8P9 into the candidate node set. Continue to search upward and update P 11 is a new seed node. Since γ>Δangle, and P top Point is located at the top of the parking space, so at this time P top Point is the turning point of the vehicle body. Fig.10 As shown, for the initial seed point P on the right right , the point is located in the middle of the parking space, and there is no other Cluster line segment on the lower side. In this embodiment of the application, the candidate node can be searched upwards, α>Δangle, and P9 point is temporarily updated as a new seed node. A new seed node is searched upwards, β<Δangle, and P is recognized. right For an abnormal point, P9 is used as the new seed point and the search continues upward until P12 (turning point) is added to the candidate node set.

[0087] In summary, at the beginning of parking, the vehicle is still outside the garage, has not entered the target parking space, and has not fully detected the garage. At this time, the embodiment of the present application can determine the angle of the obstacle vehicle based on the angle of the initially detected ultrasonic parking space; when the vehicle begins to adjust to enter the garage, that is, when the distance between the center of the rear axle of the vehicle and the distance to the parking space is less than the threshold, the embodiment of the present application can ensure that the sensor fully detects the front and body of the vehicle, eliminates invalid information and obtains the fusion information of the obstacle vehicle of interest.

[0088] According to the above-mentioned automatic parking method for a vehicle, the embodiment of the present application has at least the following beneficial effects:

[0089] (1) The embodiment of the present application can automatically park the vehicle by referring to the parking postures of the vehicles around the parking space, and determine the final parking posture of the vehicle. While achieving safe parking, since the parking posture of the vehicle is similar to that of the surrounding vehicles, the relevant impact between the parking position of the vehicle and other vehicles can be effectively reduced, providing an expected parking posture that is friendly to both the vehicle and the environment, thereby improving the user experience;

[0090] (2) This application can update the actual body angle of the obstacle vehicle relative to the vehicle when the vehicle reaches a certain position in the target parking space during the parking process, ensuring the real-time information of the relevant obstacle vehicle, so as to provide the desired parking posture that is friendly to the vehicle and the environment, improve the intelligence of the solution, enhance the safety of the parking process, and meet the needs of actual use;

[0091] (3) After the vehicle enters the parking space, the present application can process the updated fusion information of the obstacle vehicle, use the ultrasonic vertical parking space obstacle vehicle angle calculation method, and obtain the body angle of the obstacle vehicle through linear fitting to provide the desired parking posture that is friendly to both the vehicle and the environment;

[0092] (4) The present application can calculate the actual body angle based on the body contour inflection point, the last endpoint of the fused cluster line segment and the candidate node set, keep updating the body angle of the vehicle and information fusion, and correct the parking angle according to the actual situation during the parking process, so that the parking posture of the vehicle is similar to that of the surrounding vehicles, effectively reducing the correlation between the parking position of the vehicle and other vehicles, providing an expected parking posture that is friendly to both the vehicle and the environment, improving parking safety, and enhancing user experience;

[0093] (5) The present application can determine the actual distance between the first endpoint and the last endpoint, compare it with the first length threshold, and select the description of the actual vehicle body angle according to the actual situation, so that the parking angle calculation result is more accurate, and the parking posture of the vehicle is similar to the parking posture of surrounding vehicles, which effectively reduces the correlation between the parking position of the vehicle and other vehicles, provides an expected parking posture that is friendly to both the vehicle and the environment, and meets the actual parking needs;

[0094] (6) The present application can determine the actual distance between the turning point of the vehicle body contour and the last endpoint, compare it with the third length threshold, and select the description of the actual vehicle body angle according to the actual situation, so that the parking angle calculation result is more accurate, and the parking posture of the vehicle is similar to the parking posture of surrounding vehicles, which effectively reduces the correlation between the parking position of the vehicle and other vehicles, provides an expected parking posture that is friendly to both the vehicle and the environment, and meets the actual parking needs;

[0095] (7) The present application can filter out noise points that appear during the detection process, eliminate invalid interference information, reduce redundant calculations of the actual vehicle body angle when filtering without noise points, improve the intelligence of parking and the accuracy of related information, and meet the needs of actual use.

[0096] Next, the automatic parking device for a vehicle according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0097] Fig.12 It is a block diagram of an automatic parking device for a vehicle according to an embodiment of the present application.

[0098] like Fig.12 As shown, the automatic parking device 10 of the vehicle includes: an acquisition module 100 , a prediction module 200 and a parking module 300 .

[0099] Among them, the acquisition module 100 is used to obtain the sideline angle of the target parking space close to the side of the obstacle vehicle when an obstacle vehicle is identified on the left and / or right side of the target parking space; the prediction module 200 is used to calculate the expected body angle of the obstacle vehicle based on the sideline angle, and plan the parking path of the vehicle based on the expected body angle of the obstacle vehicle; the parking module 300 is used to control the vehicle to enter the target parking space according to the parking path, while detecting the actual body angle of the obstacle vehicle, and correcting the body angle of the parked vehicle according to the actual body angle.

[0100] In the embodiment of the present application, the parking module 300 is used to: obtain the actual depth of the vehicle entering the target parking space; when the actual depth is greater than or equal to the first depth threshold, detect the actual body angle of the obstacle vehicle.

[0101] In the embodiment of the present application, the parking module 300 is further used to: obtain the fused cluster segment of the obstacle vehicle; identify the first endpoint in the fused cluster segment that is closest to the vehicle; use the first endpoint as a seed node to search for the second endpoint in the fused cluster segment that is closest to the first endpoint along the direction of entry of the vehicle, and obtain the third endpoint that is in the same segment as the second endpoint along the direction of entry of the vehicle; calculate the angle difference between the first segment between the first endpoint and the second endpoint and the second segment between the second endpoint and the third endpoint, and when the angle difference is less than an angle threshold, add the second endpoint and the third endpoint to the candidate node set; continue searching with the third endpoint as a seed node until the angle difference is greater than or equal to the angle threshold, or the last endpoint of the fused cluster segment is searched, and calculate the actual vehicle body angle based on the first endpoint, the last endpoint at the end of the search, and the candidate node set.

[0102] In the embodiment of the present application, the parking module 300 is further used to: determine whether the actual distance between the first endpoint and the last endpoint is greater than a first length threshold; if the actual distance is greater than the first length threshold, and there is a line segment greater than the second length threshold in the alternative node set, the average of the straight line angle fitted by the alternative node set and the line segment angle greater than the second length threshold is used as the actual vehicle body angle; otherwise, the straight line angle is used as the actual vehicle body angle.

[0103] In the embodiment of the present application, the parking module 300 is further used to: identify the fourth endpoint in the fused cluster segment that is closest to the vehicle; use the fourth endpoint as a seed node to search for the last endpoint of the fused cluster segment along the direction of entry of the vehicle, search for the fifth endpoint in the fused cluster segment that is closest to the fourth endpoint along the opposite direction of the vehicle's entry, and obtain the sixth endpoint of the same segment as the fifth endpoint along the opposite direction; calculate the angle difference between the third segment between the fourth endpoint and the fifth endpoint and the fourth segment between the fifth endpoint and the sixth endpoint, and when the angle difference is less than an angle threshold, add the fifth endpoint and the sixth endpoint to the candidate node set; continue searching with the sixth endpoint as a seed node until the angle difference is greater than or equal to the angle threshold, obtain the inflection point of the body contour of the obstacle vehicle, and calculate the actual body angle based on the inflection point of the body contour, the last endpoint of the fused cluster segment and the candidate node set.

[0104] In the embodiment of the present application, the parking module 300 is further used to: determine whether the actual distance between the inflection point of the vehicle body contour and the last endpoint is greater than a third length threshold; if the actual distance is greater than the third length threshold, and there is a line segment greater than the fourth length threshold in the alternative node set, the average of the straight line angle fitted by the alternative node set and the line segment angle greater than the fourth length threshold is used as the actual vehicle body angle; otherwise, the straight line angle is used as the actual vehicle body angle.

[0105] It should be noted that the above explanation of the embodiment of the automatic parking method for a vehicle is also applicable to the automatic parking device for a vehicle in this embodiment, and will not be repeated here.

[0106] According to the automatic parking device for a vehicle proposed in the embodiment of the present application, the vehicle can be automatically parked by referring to the parking postures of the vehicles around the parking space to determine the final parking posture of the vehicle. While achieving safe parking, since the parking posture of the vehicle is similar to that of the surrounding vehicles, the correlation impact between the parking position of the vehicle and other vehicles can be effectively reduced, providing an expected parking posture that is friendly to both the vehicle and the environment, thereby improving the user experience.

[0107] Fig.13 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0108] A memory 1301 , a processor 1302 , and a computer program stored in the memory 1301 and executable on the processor 1302 .

[0109] When the processor 1302 executes the program, the automatic parking method for the vehicle provided in the above embodiment is implemented.

[0110] Optionally, the vehicle further comprises:

[0111] The communication interface 1303 is used for communication between the memory 1301 and the processor 1302 .

[0112] The memory 1301 is used to store computer programs that can be executed on the processor 1302 .

[0113] The memory 1301 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0114] If the memory 1301, the processor 1302 and the communication interface 1303 are implemented independently, the communication interface 1303, the memory 1301 and the processor 1302 can be connected to each other through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.13 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0115] Optionally, in a specific implementation, if the memory 1301, the processor 1302 and the communication interface 1303 are integrated on a chip, the memory 1301, the processor 1302 and the communication interface 1303 can communicate with each other through an internal interface.

[0116] The processor 1302 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0117] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned automatic parking method for a vehicle.

[0118] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0119] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0120] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0121] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0122] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0123] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for automatic parking of a vehicle, characterized in that: The following steps are involved: When an obstructing vehicle is identified on the left and / or right side of the target parking space, obtaining a sideline angle of the target parking space close to the obstructing vehicle; Calculating the estimated body angle of the obstacle vehicle according to the edge angle, and planning the parking path of the vehicle according to the estimated body angle of the obstacle vehicle; While controlling the host vehicle to drive into the target parking space according to the parking path, detecting the actual body angle of the obstacle vehicle, and correcting the body angle of the parked host vehicle according to the actual body angle; The controlling the vehicle to enter the target parking space according to the parking path and detecting the actual body angle of the obstacle vehicle includes: Obtaining the actual depth of the vehicle entering the target parking space; When the actual depth is greater than or equal to a first depth threshold, detecting an actual body angle of the obstacle vehicle; When the actual depth is greater than or equal to a first depth threshold and less than a second depth threshold, detecting the actual body angle of the obstacle vehicle includes: Obtaining a fused cluster line segment of the obstacle vehicle; Identifying a first endpoint of the fused cluster line segment that is closest to the vehicle; Taking the first endpoint as a seed node, searching for a second endpoint in the fused cluster line segment that is closest to the first endpoint along the vehicle's approach direction, and acquiring a third endpoint that is in the same line segment as the second endpoint along the vehicle's approach direction; Calculate an angle difference between a first line segment between the first endpoint and the second endpoint and a second line segment between the second endpoint and the third endpoint, and when the angle difference is less than an angle threshold, add the second endpoint and the third endpoint to a candidate node set; The search is continued with the third endpoint as a seed node until the angle difference is greater than or equal to the angle threshold, or the last endpoint of the fused cluster segment is searched, and the actual vehicle body angle is calculated according to the first endpoint, the last endpoint at the end of the search, and the candidate node set.

2. The method according to claim 1, characterized in that When the actual depth is greater than or equal to a second depth threshold, detecting the actual body angle of the obstacle vehicle includes: Identifying a fourth endpoint of the fused cluster line segment that is closest to the vehicle; Taking the fourth endpoint as a seed node, searching for the last endpoint of the fused cluster segment along the direction in which the vehicle enters, searching for the fifth endpoint in the fused cluster segment that is closest to the fourth endpoint along the opposite direction of the vehicle entering, and obtaining a sixth endpoint that is in the same segment as the fifth endpoint along the opposite direction; Calculating an angle difference between a third line segment between the fourth endpoint and the fifth endpoint and a fourth line segment between the fifth endpoint and the sixth endpoint, and when the angle difference is less than an angle threshold, adding the fifth endpoint and the sixth endpoint to the candidate node set; The search is continued with the sixth endpoint as the seed node until the angle difference is greater than or equal to the angle threshold, and the turning point of the body contour of the obstacle vehicle is obtained. The actual body angle is calculated according to the turning point of the body contour, the last endpoint of the fused cluster segment and the candidate node set.

3. The method according to claim 1, characterized in that The calculating the actual vehicle body angle according to the first endpoint, the last endpoint at the end of the search, and the candidate node set includes: Determine whether the actual distance between the first endpoint and the last endpoint is greater than a first length threshold; If the actual distance is greater than the first length threshold and there is a line segment greater than the second length threshold in the alternative node set, the average of the straight line angle fitted by the alternative node set and the line segment angle greater than the second length threshold is used as the actual vehicle body angle; otherwise, the straight line angle is used as the actual vehicle body angle.

4. The method according to claim 2, characterized in that: The calculating the actual vehicle body angle according to the vehicle body contour inflection point, the last endpoint of the fused cluster line segment and the candidate node set includes: Determining whether the actual distance between the inflection point of the vehicle body contour and the last endpoint is greater than a third length threshold; If the actual distance is greater than the third length threshold and there is a line segment greater than the fourth length threshold in the alternative node set, the average of the straight line angle fitted by the alternative node set and the line segment angle greater than the fourth length threshold is used as the actual vehicle body angle; otherwise, the straight line angle is used as the actual vehicle body angle.

5. The method according to any one of claims 1 to 4, characterized in that: Before calculating the actual vehicle body angle, it also includes: Noise filtering is performed on the candidate node set according to a preset filtering strategy to obtain a filtered candidate node set.

6. An automatic parking device for a vehicle, the device being used to implement the automatic parking method for a vehicle as claimed in any one of claims 1 to 5, characterized in that: include: An acquisition module, configured to acquire a sideline angle of the target parking space close to a side of the obstructing vehicle when an obstructing vehicle is identified to the left and / or right of the target parking space; An estimation module, used to calculate the estimated body angle of the obstacle vehicle according to the edge line angle, and plan the parking path of the vehicle according to the estimated body angle of the obstacle vehicle; The parking module is used to control the vehicle to enter the target parking space according to the parking path, detect the actual body angle of the obstacle vehicle, and correct the body angle of the parked vehicle according to the actual body angle.

7. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the automatic parking method for a vehicle as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the automatic parking method for a vehicle as described in any one of claims 1 to 5.

Images