A method, device, electronic equipment, and automobile for door obstacle avoidance control.
By performing obstacle recognition and coordinate generation on the 3D point cloud map of the target parking space, the problem of inaccurate radar sensor recognition was solved, and precise obstacle avoidance control of the vehicle door was achieved.
Patent Information
- Application Number
- CN202410072734.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-17
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2044-01-17
AI Technical Summary
Existing automated door control systems suffer from inaccurate radar sensor recognition of garage pillar edges, which can lead to doors accidentally triggering anti-collision functions or hitting obstacles, making it difficult to achieve accurate obstacle avoidance.
By identifying obstacles in the 3D point cloud map of the target parking space, an obstacle coordinate map is generated, the position and distance between the car door and the obstacle are determined, and the car door is controlled to stop opening when the distance is less than a set threshold.
It improved the accuracy of obstacle recognition, enabled precise control of the car doors, successfully avoided obstacles, and prevented collisions.
Smart Images

Figure CN117868637B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent control technology, and in particular to a door obstacle avoidance control method, device, electronic device, and automobile. Background Technology
[0002] With the development of automotive intelligence, users have placed higher demands on vehicle comfort, and automatic door opening and closing is one such example. Current automated door control typically uses radar sensors to detect the surrounding environment of the door to ensure it can be opened safely.
[0003] However, radar sensors can misidentify rough ground noise as obstacles, especially the edges of garage pillars. Because garage pillar edges reflect very little electromagnetic waves back to the radar sensor—most are reflected away by the flat surfaces on either side—they are considered weak targets by the radar sensor. The signal-to-noise ratio (SNR) of the reflected electromagnetic waves is very low, similar to that of rough ground noise. This makes it easy to misidentify rough ground noise as garage pillar edges, or vice versa. This can sometimes lead to the door's anti-collision function being falsely triggered, and at other times the door opening and colliding with the garage pillar edge.
[0004] Therefore, the accuracy of directly detecting obstacles using radar sensors is low, making it difficult to precisely control the car doors so that they can successfully avoid obstacles. Summary of the Invention
[0005] To address the aforementioned technical problems, embodiments of this application provide a door obstacle avoidance control method, device, electronic device, and automobile, which can accurately identify obstacles and then precisely control the door based on the obtained first obstacle coordinate map, enabling the door to successfully avoid obstacles.
[0006] The technical solution of this application is implemented as follows:
[0007] In a first aspect, embodiments of this application provide a door obstacle avoidance control method, including:
[0008] Determine the 3D point cloud map corresponding to the target parking space of the vehicle;
[0009] Obstacle identification is performed on the three-dimensional point cloud map to obtain the first obstacle coordinate map corresponding to the target parking space;
[0010] Based on the first obstacle coordinate map, the position of the target obstacle is determined, and the target obstacle includes obstacles in the door opening area when the vehicle is parked in the target parking space;
[0011] Based on the position of the target obstacle, determine the distance between the vehicle door and the target obstacle;
[0012] During the process of controlling the opening of the vehicle door, if it is determined that the distance is less than or equal to a set threshold, the door is controlled to stop opening.
[0013] In some embodiments, determining the three-dimensional point cloud map corresponding to the target parking space of the vehicle includes:
[0014] During the process of determining that the vehicle is reversing into the target parking space, the radar sensor on the vehicle is controlled to scan the target parking space to obtain the three-dimensional point cloud map corresponding to the target parking space.
[0015] In some embodiments, the three-dimensional point cloud map includes a first three-dimensional point cloud map and a second three-dimensional point cloud map. The first three-dimensional point cloud map is obtained by scanning the target parking space using a radar sensor on the rear door of the vehicle, and the second three-dimensional point cloud map is obtained by scanning the target parking space using a radar sensor on the front door of the vehicle.
[0016] The step of performing obstacle recognition on the three-dimensional point cloud map to obtain a first obstacle coordinate map corresponding to the target parking space includes:
[0017] Obstacle identification is performed on the first three-dimensional point cloud map and the second three-dimensional point cloud map respectively to obtain a second obstacle coordinate map corresponding to the first three-dimensional point cloud map and a third obstacle coordinate map corresponding to the second three-dimensional point cloud map;
[0018] The second obstacle coordinate map and the third obstacle coordinate map are fused together to obtain the first obstacle coordinate map.
[0019] In some embodiments, the step of performing obstacle identification on the first three-dimensional point cloud map and the second three-dimensional point cloud map respectively to obtain a second obstacle coordinate map corresponding to the first three-dimensional point cloud map and a third obstacle coordinate map corresponding to the second three-dimensional point cloud map includes:
[0020] The first three-dimensional point cloud map is input into a pre-constructed obstacle recognition model to obtain the first obstacle recognition result output by the obstacle recognition model;
[0021] The second three-dimensional point cloud map is input into the pre-built obstacle recognition model to obtain the second obstacle recognition result output by the obstacle recognition model;
[0022] Based on the first obstacle identification result, the second obstacle coordinate map is determined, and based on the second obstacle identification result, the third obstacle coordinate map is determined.
[0023] In some embodiments, determining the position of the target obstacle based on the first obstacle coordinate map includes:
[0024] Based on the first obstacle coordinate map, determine whether there are obstacles in the door opening area;
[0025] If it is determined that there is an obstacle in the door opening area, the position of the obstacle in the door opening area is determined based on the first obstacle coordinate map;
[0026] The location of the obstacle existing in the door opening area is taken as the location of the target obstacle.
[0027] In some embodiments, determining the distance between the vehicle door and the target obstacle based on the position of the target obstacle includes:
[0028] Control the radar sensor on the car door to detect the position of the car door;
[0029] Based on the detected positions of the vehicle door and the target obstacle, the distance between the vehicle door and the target obstacle is determined.
[0030] In some embodiments, the door obstacle avoidance control method further includes:
[0031] If the distance is determined to be less than or equal to the set threshold, a door obstacle avoidance warning is issued.
[0032] Secondly, embodiments of this application provide a door obstacle avoidance control device, comprising:
[0033] The first determining module is used to determine the three-dimensional point cloud map corresponding to the target parking space of the vehicle.
[0034] The recognition module is used to identify obstacles in the three-dimensional point cloud map and obtain the first obstacle coordinate map corresponding to the target parking space;
[0035] The second determining module is used to determine the position of the target obstacle based on the first obstacle coordinate map, wherein the target obstacle includes obstacles in the door opening area when the vehicle is parked in the target parking space;
[0036] The third determining module is used to determine the distance between the vehicle door and the target obstacle based on the position of the target obstacle;
[0037] The control module is used to control the door to stop opening when the distance is determined to be less than or equal to a set threshold during the process of controlling the opening of the vehicle door.
[0038] Thirdly, embodiments of this application provide an electronic device, including a memory and a processor, wherein the memory is used to store executable data instructions; and the processor is used to execute the executable data instructions stored in the memory to implement the door obstacle avoidance control method as described in the first aspect.
[0039] Fourthly, embodiments of this application provide an automobile, the automobile including a vehicle body and an electronic device as described in the third aspect, the electronic device being disposed on the vehicle body.
[0040] The vehicle door obstacle avoidance control method, device, electronic device, and vehicle provided in this application embodiment identify obstacles by performing obstacle recognition on a three-dimensional point cloud map corresponding to the target parking space of the vehicle, obtaining a first obstacle coordinate map corresponding to the target parking space. Then, based on the first obstacle coordinate map, the position of the target obstacle is determined. The position of the target obstacle includes the position of obstacles in the door opening area when the vehicle is parked in the target parking space. Then, based on the position of the target obstacle, the distance between the door and the target obstacle is determined. Finally, during the process of controlling the opening of the vehicle door, if it is determined that the distance between the door and the target obstacle is less than or equal to a set threshold, the door is controlled to stop opening. Since this application identifies obstacles by performing obstacle recognition on a three-dimensional point cloud map corresponding to the target parking space, compared with the technology of directly detecting obstacles using radar sensors, it can improve the accuracy of obstacle recognition. Therefore, based on the position of obstacles in the door opening area included in the first obstacle coordinate map obtained by obstacle recognition, the door opening is precisely controlled, so that the door can successfully avoid obstacles. Attached Figure Description
[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0042] Figure 1 One of the flowcharts of a door obstacle avoidance control method provided in this application embodiment;
[0043] Figure 2 A second schematic flowchart illustrating a door obstacle avoidance control method provided in an embodiment of this application;
[0044] Figure 3 A third schematic flowchart illustrating a door obstacle avoidance control method provided in this application embodiment;
[0045] Figure 4This is a schematic diagram of the structure of a door obstacle avoidance control device provided in an embodiment of this application;
[0046] Figure 5 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0047] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0048] It should be noted that in the description of the embodiments of this application, the terms "first," "second," etc., are used to distinguish similar objects and are not used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited. For example, the first object can be one or more.
[0049] The following description, in conjunction with the accompanying drawings of the embodiments of this application, provides an exemplary description of the door obstacle avoidance control method, device, electronic equipment, and automobile provided in the embodiments of this application.
[0050] Figure 1 This is one of the flowcharts illustrating a door obstacle avoidance control method provided in an embodiment of this application, such as... Figure 1 As shown, the method includes:
[0051] S101. Determine the three-dimensional point cloud map corresponding to the target parking space of the vehicle.
[0052] In this embodiment of the application, a radar sensor can be used to scan the target parking space of the vehicle to obtain a three-dimensional point cloud map corresponding to the target parking space.
[0053] In some embodiments, the target parking space of the vehicle can be scanned by any radar sensor located in the area where the target parking space is located, thereby obtaining a three-dimensional point cloud map corresponding to the target parking space.
[0054] In some embodiments, determining the three-dimensional point cloud map corresponding to the target parking space of the vehicle includes:
[0055] During the process of determining that the vehicle is reversing into the target parking space, the radar sensor on the vehicle is controlled to scan the target parking space to obtain the three-dimensional point cloud map corresponding to the target parking space.
[0056] In this embodiment, during the process of a vehicle reversing into a parking space, the radar sensor on the vehicle scans the target parking space to obtain a three-dimensional point cloud map corresponding to the target parking space. It is understood that by scanning the target parking space with the radar sensor on the vehicle reversing into the parking space, a three-dimensional point cloud map of the target parking space at the current moment can be obtained. This allows the obstacle coordinate map subsequently obtained based on the three-dimensional point cloud map to accurately reflect the obstacle information in the area where the target parking space is located at the current moment.
[0057] S102. Obstacle identification is performed on the three-dimensional point cloud map to obtain the first obstacle coordinate map corresponding to the target parking space.
[0058] In this embodiment of the application, a target recognition algorithm in machine learning can be used to identify obstacles in the three-dimensional point cloud map corresponding to the target parking space, thereby obtaining the first obstacle coordinate map corresponding to the target parking space.
[0059] It should be noted that the first obstacle coordinate map includes the location information of each obstacle.
[0060] S103. Based on the first obstacle coordinate map, determine the position of the target obstacle, wherein the target obstacle includes obstacles in the door opening area when the vehicle is parked in the target parking space.
[0061] In this embodiment of the application, when the vehicle is parked in the target parking space and before the door is opened, the specific location of the obstacle in the door opening area of the vehicle can be determined based on the first obstacle coordinate map, that is, the location of the target obstacle.
[0062] In some embodiments, after a vehicle parks in a target parking space, the door opening area of the vehicle can be determined by the specific location where the vehicle is parked, and then the location information of the obstacles included in the door opening area can be determined based on the first obstacle coordinate map corresponding to the target parking space.
[0063] In some embodiments, determining the position of the target obstacle based on the first obstacle coordinate map includes:
[0064] Based on the first obstacle coordinate map, determine whether there are obstacles in the door opening area;
[0065] If it is determined that there is an obstacle in the door opening area, the position of the obstacle in the door opening area is determined based on the first obstacle coordinate map;
[0066] The location of the obstacle existing in the door opening area is taken as the location of the target obstacle.
[0067] Understandably, once a vehicle is parked in the target parking space, the door opening area can be determined. Then, based on the first obstacle coordinate map corresponding to the target parking space, it can be determined whether there are obstacles in the door opening area. If it is determined that there are obstacles in the door opening area, the location information of the obstacles in the door opening area can be determined based on the first obstacle coordinate map.
[0068] S104. Based on the position of the target obstacle, determine the distance between the vehicle door and the target obstacle.
[0069] In some embodiments, after the vehicle stops in the target parking space, the position of the door can be detected, and then the distance between the door and the target obstacle can be determined based on the position of the target obstacle and the detected position of the door.
[0070] In some embodiments, determining the distance between the vehicle door and the target obstacle based on the position of the target obstacle includes:
[0071] Control the radar sensor on the car door to detect the position of the car door;
[0072] Based on the detected positions of the vehicle door and the target obstacle, the distance between the vehicle door and the target obstacle is determined.
[0073] In this embodiment, after the vehicle stops in the target parking space, the position of the door is detected in real time by the radar sensor on the door, and the distance between the door and the target obstacle is determined in real time based on the position of the door and the position of the target obstacle.
[0074] S105. During the process of controlling the opening of the vehicle door, if it is determined that the distance is less than or equal to a set threshold, the door is controlled to stop opening.
[0075] In this embodiment of the application, during the process of controlling the opening of the vehicle door, the distance between the door and the target obstacle can be determined in real time; if when the door is opened to a certain position, it is determined that the distance between the door and the target obstacle is less than or equal to a set threshold, then the door is controlled to stop opening, so as to avoid the door hitting the target obstacle.
[0076] It should be noted that the threshold values set in this application embodiment can be adaptively set based on actual applications, and this application embodiment does not impose specific limitations on them. For example, the threshold value can be 1 cm, 2 cm, or 2.5 cm, etc.
[0077] In some embodiments, after determining that the vehicle is parked in the target parking space, the vehicle door can be controlled to open. During the process of controlling the door to open, the position of the door can be obtained in real time from the positioning device or positioning sensor installed on the door, so as to determine the distance between the position of the door and the position of the target obstacle. If, when the door is determined to be open to a certain position, the distance between the door and the target obstacle is less than or equal to a set threshold, the door is immediately controlled to stop opening to avoid the door hitting the target obstacle.
[0078] It is understood that the door obstacle avoidance control method provided in this application identifies obstacles by performing obstacle recognition on the three-dimensional point cloud map corresponding to the target parking space of the vehicle, obtaining a first obstacle coordinate map corresponding to the target parking space. Then, based on the first obstacle coordinate map, the position of the target obstacle is determined. The position of the target obstacle includes the position of obstacles in the door opening area when the vehicle is parked in the target parking space. Then, based on the position of the target obstacle, the distance between the door and the target obstacle is determined. Finally, during the process of controlling the opening of the vehicle door, if it is determined that the distance between the door and the target obstacle is less than or equal to a set threshold, the door is controlled to stop opening. Since this application identifies obstacles by performing obstacle recognition on the three-dimensional point cloud map corresponding to the target parking space, compared with the technology of directly detecting obstacles using radar sensors, it can improve the accuracy of obstacle recognition. Therefore, based on the position of obstacles in the door opening area included in the first obstacle coordinate map obtained by obstacle recognition, the door opening is precisely controlled, so that the door can successfully avoid obstacles.
[0079] In some embodiments, the three-dimensional point cloud map includes a first three-dimensional point cloud map and a second three-dimensional point cloud map. The first three-dimensional point cloud map is obtained by scanning the target parking space using a radar sensor on the rear door of the vehicle, and the second three-dimensional point cloud map is obtained by scanning the target parking space using a radar sensor on the front door of the vehicle.
[0080] The step of performing obstacle recognition on the three-dimensional point cloud map to obtain a first obstacle coordinate map corresponding to the target parking space includes:
[0081] Obstacle identification is performed on the first three-dimensional point cloud map and the second three-dimensional point cloud map respectively to obtain a second obstacle coordinate map corresponding to the first three-dimensional point cloud map and a third obstacle coordinate map corresponding to the second three-dimensional point cloud map;
[0082] The second obstacle coordinate map and the third obstacle coordinate map are fused together to obtain the first obstacle coordinate map.
[0083] by Figure 2 As an example, such as Figure 2 As shown in the embodiment of this application, a door obstacle avoidance control method includes:
[0084] S201. During the process of determining that the vehicle is reversing into the target parking space, the radar sensor on the rear door of the vehicle is controlled to scan the target parking space to obtain a first three-dimensional point cloud map corresponding to the target parking space, and the radar sensor on the front door of the vehicle is controlled to scan the target parking space to obtain a second three-dimensional point cloud map corresponding to the target parking space.
[0085] S202. Obstacle identification is performed on the first three-dimensional point cloud map and the second three-dimensional point cloud map respectively to obtain a second obstacle coordinate map corresponding to the first three-dimensional point cloud map and a third obstacle coordinate map corresponding to the second three-dimensional point cloud map.
[0086] S203. The second obstacle coordinate map and the third obstacle coordinate map are fused to obtain the first obstacle coordinate map.
[0087] It should be noted that in this embodiment of the application, the second obstacle coordinate map and the third obstacle coordinate map are fused, that is, the obstacle information identified by the front and rear doors is cross-fused to form a more accurate first obstacle coordinate map, thereby improving the accuracy of obstacle identification.
[0088] S204. Based on the first obstacle coordinate map, determine the position of the target obstacle, wherein the target obstacle includes obstacles in the door opening area when the vehicle is parked in the target parking space.
[0089] S205. Based on the position of the target obstacle, determine the distance between the vehicle door and the target obstacle.
[0090] S206. During the process of controlling the opening of the vehicle door, if it is determined that the distance is less than or equal to a set threshold, the door is controlled to stop opening.
[0091] For example, during the process of controlling the opening of the front door of the vehicle, based on the position of the target obstacle in the opening area of the front door, if it is determined that the distance between the front door and the target obstacle is less than or equal to a set threshold, the front door is controlled to stop opening to avoid the front door hitting the target obstacle.
[0092] For example, during the process of controlling the opening of the rear door of a vehicle, based on the position of the target obstacle in the opening area of the rear door, if it is determined that the distance between the rear door and the target obstacle is less than or equal to a set threshold, the rear door is controlled to stop opening to avoid the rear door hitting the target obstacle.
[0093] In some embodiments, the step of performing obstacle identification on the first three-dimensional point cloud map and the second three-dimensional point cloud map respectively to obtain a second obstacle coordinate map corresponding to the first three-dimensional point cloud map and a third obstacle coordinate map corresponding to the second three-dimensional point cloud map includes:
[0094] The first three-dimensional point cloud map is input into a pre-constructed obstacle recognition model to obtain the first obstacle recognition result output by the obstacle recognition model;
[0095] The second three-dimensional point cloud map is input into the pre-built obstacle recognition model to obtain the second obstacle recognition result output by the obstacle recognition model;
[0096] Based on the first obstacle identification result, the second obstacle coordinate map is determined, and based on the second obstacle identification result, the third obstacle coordinate map is determined.
[0097] In this embodiment, an obstacle recognition model can be pre-constructed, which can be trained based on pre-collected sample data. After obtaining the first and second 3D point cloud maps corresponding to the target parking space, the first and second 3D point cloud maps can be input into the pre-constructed obstacle recognition model to obtain the first and second obstacle recognition results output by the obstacle recognition model. Then, based on the first obstacle recognition result, the second obstacle coordinate map can be determined, and based on the second obstacle recognition result, the third obstacle coordinate map can be determined.
[0098] It is understood that the embodiments of this application perform obstacle recognition on the first three-dimensional point cloud map and the second three-dimensional point cloud map respectively based on the pre-built obstacle recognition model. Since the obstacle recognition model is trained based on pre-collected sample data, the accuracy of obstacle recognition can be improved.
[0099] In some embodiments, the door obstacle avoidance control method further includes:
[0100] If the distance is determined to be less than or equal to the set threshold, a door obstacle avoidance warning is issued.
[0101] In this embodiment of the application, if it is determined that the distance between the car door and the target obstacle is less than or equal to a set threshold during the process of controlling the opening of the car door, a door obstacle avoidance warning is issued. The form of the warning is not specifically limited in this embodiment of the application, and may include voice prompts, signal light prompts, or display panel prompts, etc., to inform the vehicle user that there is an obstacle in the door opening area and trigger the door anti-collision function (i.e., stop the door from continuing to perform the opening action) to avoid the door hitting the obstacle.
[0102] Figure 3 This is the third flowchart illustrating a door obstacle avoidance control method provided in this application embodiment, as shown below. Figure 3 As shown, the method includes:
[0103] S301. During the process of reversing into the target parking space, the radar sensor on the rear door scans the target parking space, then constructs a map for identification and forms a coordinate map of the obstacles at the rear door.
[0104] It should be noted that the radar sensor on the rear door scans the target parking space to obtain a three-dimensional point cloud map, and then performs obstacle identification on the three-dimensional point cloud map to form a coordinate map of the obstacles on the rear door.
[0105] S302. As the vehicle continues to reverse into the target parking space, the radar sensor on the front door scans the target parking space, then constructs a map to identify and form a coordinate map of the obstacles at the front door.
[0106] Similarly, the radar sensor on the front door scans the target parking space to obtain a three-dimensional point cloud map, and then performs obstacle identification on the three-dimensional point cloud map to form the obstacle coordinate map of the front door.
[0107] S303, the radar sensors on the rear doors and the radar sensors on the front doors share obstacle coordinate maps, forming an obstacle coordinate map that is a fusion of the obstacle coordinate maps of the rear doors and the front doors.
[0108] It should be noted that the radar sensors on the front and rear doors share obstacle coordinate maps, that is, the obstacle coordinate maps of the rear doors are merged with those of the front doors to form an obstacle coordinate map that can more accurately reflect the location information of obstacles in the target parking space area.
[0109] S304. Based on the obstacle coordinate map fused from the rear door obstacle coordinate map and the front door obstacle coordinate map, during the opening of the vehicle's front door and / or rear door, when it is determined that the distance between the front door and / or rear door and the obstacle is less than or equal to a set threshold, the opening action of the front door and / or rear door shall be stopped.
[0110] It is understood that, in this embodiment of the application, an obstacle coordinate map is pre-constructed for obstacles in the target parking space when the vehicle is parking. To better identify obstacles, the obstacle information detected by the front and rear doors is cross-fused when the vehicle is parking. Specifically, when the vehicle reverses into the parking space, the radar sensor on the rear door first scans the parking space area to form a rear door obstacle coordinate map, and then the radar sensor on the front door scans the parking space area to form a front door obstacle coordinate map. The two radar sensors on the front and rear doors share the obstacle coordinate maps, forming a fused obstacle coordinate map. This fused obstacle coordinate map more accurately reflects the obstacle position information in the parking space area. Based on the position of obstacles in the door opening area included in this fused obstacle coordinate map, the door opening is precisely controlled, enabling the door to successfully avoid obstacles and achieving controllable opening and timely stopping of the vehicle's automatic doors.
[0111] The door obstacle avoidance control device provided in the embodiments of this application is described below. The door obstacle avoidance control device described below can be referred to in correspondence with the door obstacle avoidance control method described above.
[0112] Figure 4 This is a schematic diagram of the structure of a door obstacle avoidance control device provided in an embodiment of this application, as shown below. Figure 4 As shown, the device includes: a first determining module 410, an identification module 420, a second determining module 430, a third determining module 440, and a control module 450; wherein:
[0113] The first determining module 410 is used to determine the three-dimensional point cloud map corresponding to the target parking space of the vehicle.
[0114] The recognition module 420 is used to perform obstacle recognition on the three-dimensional point cloud map to obtain the first obstacle coordinate map corresponding to the target parking space;
[0115] The second determining module 430 is used to determine the position of the target obstacle based on the first obstacle coordinate map, wherein the target obstacle includes obstacles in the door opening area when the vehicle is parked in the target parking space;
[0116] The third determining module 440 is used to determine the distance between the vehicle door and the target obstacle based on the position of the target obstacle;
[0117] The control module 450 is used to control the door to stop opening when it is determined that the distance is less than or equal to a set threshold during the process of controlling the opening of the vehicle door.
[0118] The door obstacle avoidance control device provided in this application identifies obstacles by analyzing a three-dimensional point cloud map corresponding to the target parking space of the vehicle, obtaining a first obstacle coordinate map corresponding to the target parking space. Based on the first obstacle coordinate map, the position of the target obstacle is determined, including the position of obstacles in the door opening area when the vehicle is parked in the target parking space. Then, based on the position of the target obstacle, the distance between the door and the target obstacle is determined. Finally, during the process of controlling the vehicle door to open, if the distance between the door and the target obstacle is determined to be less than or equal to a set threshold, the door is stopped from opening. Because this application identifies obstacles by analyzing a three-dimensional point cloud map corresponding to the target parking space, compared to techniques that directly detect obstacles using radar sensors, it can improve the accuracy of obstacle identification. Furthermore, based on the position of obstacles in the door opening area included in the first obstacle coordinate map obtained from obstacle identification, the door opening is precisely controlled, enabling the door to successfully avoid obstacles.
[0119] In some embodiments, the first determining module 410 is specifically used for:
[0120] During the process of determining that the vehicle is reversing into the target parking space, the radar sensor on the vehicle is controlled to scan the target parking space to obtain the three-dimensional point cloud map corresponding to the target parking space.
[0121] In some embodiments, the three-dimensional point cloud map includes a first three-dimensional point cloud map and a second three-dimensional point cloud map. The first three-dimensional point cloud map is obtained by scanning the target parking space using a radar sensor on the rear door of the vehicle, and the second three-dimensional point cloud map is obtained by scanning the target parking space using a radar sensor on the front door of the vehicle.
[0122] The identification module 420 includes an identification unit and a fusion unit, wherein:
[0123] The recognition unit is used to perform obstacle recognition on the first three-dimensional point cloud map and the second three-dimensional point cloud map respectively, and obtain a second obstacle coordinate map corresponding to the first three-dimensional point cloud map and a third obstacle coordinate map corresponding to the second three-dimensional point cloud map.
[0124] The fusion unit is used to fuse the second obstacle coordinate map and the third obstacle coordinate map to obtain the first obstacle coordinate map.
[0125] In some embodiments, the identification unit is specifically used for:
[0126] The first three-dimensional point cloud map is input into a pre-constructed obstacle recognition model to obtain the first obstacle recognition result output by the obstacle recognition model;
[0127] The second three-dimensional point cloud map is input into the pre-built obstacle recognition model to obtain the second obstacle recognition result output by the obstacle recognition model;
[0128] Based on the first obstacle identification result, the second obstacle coordinate map is determined, and based on the second obstacle identification result, the third obstacle coordinate map is determined.
[0129] In some embodiments, the second determining module 430 is specifically used for:
[0130] Based on the first obstacle coordinate map, determine whether there are obstacles in the door opening area;
[0131] If it is determined that there is an obstacle in the door opening area, the position of the obstacle in the door opening area is determined based on the first obstacle coordinate map;
[0132] The location of the obstacle existing in the door opening area is taken as the location of the target obstacle.
[0133] In some embodiments, the third determining module 440 is specifically used for:
[0134] Control the radar sensor on the car door to detect the position of the car door;
[0135] Based on the detected positions of the vehicle door and the target obstacle, the distance between the vehicle door and the target obstacle is determined.
[0136] In some embodiments, the door obstacle avoidance control device further includes a warning module;
[0137] The warning module is used to issue a door obstacle avoidance warning when it is determined that the distance is less than or equal to the set threshold.
[0138] It should be noted that the door obstacle avoidance control device provided in this application embodiment can realize all the method steps implemented in the above door obstacle avoidance control method embodiment, and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.
[0139] Figure 5 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of this application, such as... Figure 5As shown, the electronic device may include a processor 510, a communications interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communications interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 can execute executable data instructions stored in the memory 530 to implement some or all of the steps in the door obstacle avoidance control method provided in the above embodiments.
[0140] Furthermore, the executable data instructions stored in the aforementioned memory 530 can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of software products. These software products are stored in a storage medium and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0141] This application also provides an automobile, which includes a vehicle body and the aforementioned electronic equipment. The electronic equipment is disposed on the vehicle body to accurately identify obstacles during the opening of the vehicle door and control the vehicle door to avoid the obstacles.
[0142] This application also provides a computer-readable storage medium storing a computer program. When the computer program is run by a processor, it implements some or all of the steps in the door obstacle avoidance control method provided in the above embodiments.
[0143] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer can perform some or all of the steps in the door obstacle avoidance control method provided in the above embodiments.
[0144] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0145] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, embodiments of this application can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage) containing computer-usable program code.
[0146] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0147] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0148] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0149] The above description is merely an optional embodiment of this application and is not intended to limit the scope of protection of this application.
Claims
1. A door obstacle avoidance control method characterized by comprising: include: During the process of reversing the vehicle into the target parking space, the radar sensors on the vehicle are controlled to scan the target parking space to obtain a three-dimensional point cloud map corresponding to the target parking space. The three-dimensional point cloud map includes a first three-dimensional point cloud map and a second three-dimensional point cloud map. The first three-dimensional point cloud map is obtained by scanning the target parking space with the radar sensors on the rear doors of the vehicle, and the second three-dimensional point cloud map is obtained by scanning the target parking space with the radar sensors on the front doors of the vehicle. Obstacle identification is performed on the first three-dimensional point cloud map and the second three-dimensional point cloud map respectively to obtain a second obstacle coordinate map corresponding to the first three-dimensional point cloud map and a third obstacle coordinate map corresponding to the second three-dimensional point cloud map; The second obstacle coordinate map and the third obstacle coordinate map are fused together to obtain the first obstacle coordinate map; Based on the first obstacle coordinate map, the position of the target obstacle is determined, and the target obstacle includes obstacles in the door opening area when the vehicle is parked in the target parking space; Based on the position of the target obstacle, determine the distance between the vehicle door and the target obstacle; During the process of controlling the opening of the vehicle door, if it is determined that the distance is less than or equal to a set threshold, the door is controlled to stop opening.
2. The door obstacle avoidance control method according to claim 1, characterized by, The step of performing obstacle identification on the first 3D point cloud map and the second 3D point cloud map respectively to obtain a second obstacle coordinate map corresponding to the first 3D point cloud map and a third obstacle coordinate map corresponding to the second 3D point cloud map includes: The first three-dimensional point cloud map is input into a pre-constructed obstacle recognition model to obtain the first obstacle recognition result output by the obstacle recognition model; The second three-dimensional point cloud map is input into the pre-built obstacle recognition model to obtain the second obstacle recognition result output by the obstacle recognition model; Based on the first obstacle identification result, the second obstacle coordinate map is determined, and based on the second obstacle identification result, the third obstacle coordinate map is determined.
3. The door obstacle avoidance control method according to any one of claims 1 to 2, characterized by, Determining the position of the target obstacle based on the first obstacle coordinate map includes: Based on the first obstacle coordinate map, determine whether there are obstacles in the door opening area; If it is determined that there is an obstacle in the door opening area, the position of the obstacle in the door opening area is determined based on the first obstacle coordinate map; The location of the obstacle existing in the door opening area is taken as the location of the target obstacle.
4. The door obstacle avoidance control method according to any one of claims 1 to 2, characterized by, Determining the distance between the vehicle door and the target obstacle based on the location of the target obstacle includes: Control the radar sensor on the car door to detect the position of the car door; Based on the detected positions of the vehicle door and the target obstacle, the distance between the vehicle door and the target obstacle is determined.
5. The door obstacle avoidance control method according to any one of claims 1 to 2, characterized by, The method further includes: If the distance is determined to be less than or equal to the set threshold, a door obstacle avoidance warning is issued.
6. A door obstacle avoidance control device characterized by comprising: include: The first determining module is used to control the radar sensors on the vehicle to scan the target parking space during the process of determining that the vehicle is reversing into the target parking space, thereby obtaining a three-dimensional point cloud map corresponding to the target parking space; the three-dimensional point cloud map includes a first three-dimensional point cloud map and a second three-dimensional point cloud map, wherein the first three-dimensional point cloud map is obtained by the radar sensors on the rear doors of the vehicle scanning the target parking space, and the second three-dimensional point cloud map is obtained by the radar sensors on the front doors of the vehicle scanning the target parking space; The recognition module is used to perform obstacle recognition on the first three-dimensional point cloud map and the second three-dimensional point cloud map respectively, to obtain a second obstacle coordinate map corresponding to the first three-dimensional point cloud map and a third obstacle coordinate map corresponding to the second three-dimensional point cloud map; and to fuse the second obstacle coordinate map and the third obstacle coordinate map to obtain a first obstacle coordinate map. The second determining module is used to determine the position of the target obstacle based on the first obstacle coordinate map, wherein the target obstacle includes obstacles in the door opening area when the vehicle is parked in the target parking space; The third determining module is used to determine the distance between the vehicle door and the target obstacle based on the position of the target obstacle; The control module is used to control the door to stop opening when the distance is determined to be less than or equal to a set threshold during the process of controlling the opening of the vehicle door.
7. An electronic device, comprising: include: Memory, used to store executable data instructions; The processor, when executing executable data instructions stored in the memory, implements the door obstacle avoidance control method according to any one of claims 1 to 5.
8. An automobile characterized by comprising: The vehicle includes a vehicle body and an electronic device as described in claim 7, the electronic device being disposed on the vehicle body.
Citation Information
Patent Citations
METHODS AND APPARATUS OF FUSING RADAR / CAMERA OBJECT DATA AND LiDAR SCAN POINTS
US20130242284A1
Vehicle hatch clearance determining system
US20180297519A1
Object detection device and object detection method
WO2023223765A1
