Control method and device and storage medium

Abstract

The embodiment of the invention provides a control method and device and a storage medium, and relates to the field of automatic control. The control method comprises the following steps: determining initial boundary information of a space parking area which can be used by the mobile equipment according to a target object detected by the mobile equipment; determining target boundary information of the space parking area according to the initial boundary information and an environment sensing result corresponding to the space parking area; and controlling the movable equipment to run according to the target boundary information. Wherein the target object is an object of a preset type determined based on first environment data collected by the mobile device at a first moment, and the first environment data at least comprises first image data; the environment perception result is a result generated based on second environment data collected by the mobile device at a second moment after the first moment.

Description

Technical Field

[0001] The present disclosure relates to the field of automatic control technology, and more particularly, to a control method, device, and storage medium. Background Art

[0002] For mobile devices such as vehicles, autonomous driving technology can be used to control them to enter specific docking areas, such as parking spaces and charging stations. For example, based on environmental data collected by sensors, mobile devices can perform scene perception to identify available docking areas and automatically control the mobile device to enter the docking area. Therefore, the accuracy and robustness of docking area recognition are crucial to the control of mobile devices. Summary of the Invention

[0003] In view of this, the embodiments of the present disclosure propose a new technical solution for controlling a movable device.

[0004] According to a first aspect of an embodiment of the present disclosure, a control method is provided, the method comprising:

[0005] determining initial boundary information of a spatial docking area that can be used by the movable device based on a target object detected by the movable device; wherein the target object is an object of a preset type determined based on first environmental data collected by the movable device at a first moment, the first environmental data including at least first image data;

[0006] determining target boundary information of the spatial docking area according to the initial boundary information and an environmental perception result corresponding to the spatial docking area; wherein the environmental perception result is a result generated based on second environmental data collected by the movable device at a second moment after the first moment;

[0007] The movable device is controlled to travel according to the target boundary information.

[0008] Optionally, the second environmental data includes second image data collected by the movable device at the second moment, and the environmental perception result includes a passable area generated based on the second image data, and / or the second environmental data includes ultrasonic data collected by the movable device at the second moment, and the environmental perception result includes ultrasonic point cloud data generated based on the ultrasonic data.

[0009] Optionally, the initial boundary information includes at least a first initial boundary located on a first side of the spatial docking area, and the target boundary information includes at least a first target boundary located on the first side, and the first target boundary is different from the first initial boundary.

[0010] Optionally, determining target boundary information of the spatial docking area according to the initial boundary information and an environment perception result corresponding to the spatial docking area includes:

[0011] determining, based on a distance between each initial boundary in the initial boundary information and the movable device, the first initial boundary located on a first side of the spatial docking area;

[0012] The first target boundary is determined according to the first initial boundary and the environment perception result to obtain the target boundary information.

[0013] Optionally, the second moment includes at least a third moment and a fourth moment after the first moment, and the first initial boundary determined at the third moment is different from the first initial boundary determined at the fourth moment.

[0014] Optionally, there are multiple target objects; and determining the first target boundary according to the first initial boundary and the environment perception result includes:

[0015] determining a first target object corresponding to the first initial boundary from the plurality of target objects;

[0016] determining boundary information of the first target object according to the environmental perception result;

[0017] The first target boundary is determined according to the boundary information of the first target object.

[0018] Optionally, the environmental perception result includes a passable area; and determining target boundary information of the spatial docking area according to the initial boundary information and the environmental perception result corresponding to the spatial docking area includes:

[0019] Determining whether there is an obstacle in the space docking area according to the passable area;

[0020] When the obstacle exists in the spatial docking area, at least a portion of the initial boundary information of the spatial docking area is updated according to the position of the obstacle to obtain the target boundary information, so that the obstacle is located outside the target boundary information of the spatial docking area.

[0021] Optionally, the environmental perception result includes the traversable area and the ultrasonic point cloud data; and determining the target boundary information of the spatial docking area according to the initial boundary information and the environmental perception result corresponding to the spatial docking area includes:

[0022] Acquire fused boundary information corresponding to the initial boundary information based on the traversable area and the ultrasonic point cloud data;

[0023] At least a portion of the initial boundary information of the spatial docking area is updated according to the fused boundary information to obtain target boundary information of the spatial docking area.

[0024] According to a second aspect of an embodiment of the present disclosure, a control device is provided, comprising a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the method as described in the first aspect.

[0025] According to a third aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method according to the first aspect is implemented.

[0026] Based on the control method provided by the embodiment of the present disclosure, the initial boundary information of the spatial docking area can be detected more promptly, and the target boundary information of the spatial docking area can be determined based on the environmental perception results, thereby improving the accuracy of spatial docking area detection, so that the spatial docking area can be accurately and timely determined, and the control reliability of the movable device is improved.

[0027] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0029] Figure 1 The present invention is a schematic diagram of an intelligent connected system to which the method provided by the embodiment of the present disclosure can be applied.

[0030] Figure 2 is based on Figure 1 The illustrated embodiment provides a schematic diagram of a movable device.

[0031] Figure 3 It is a flow chart of a control method provided by an embodiment of the present disclosure.

[0032] Figure 4 It is a schematic diagram of a space docking area provided in an embodiment of the present disclosure.

[0033] Figure 5 It is a schematic diagram of another spatial docking area provided in an embodiment of the present disclosure.

[0034] Figure 6 This is a schematic diagram of another spatial docking area provided in an embodiment of the present disclosure.

[0035] Figure 7 This is a schematic diagram of another spatial docking area provided in an embodiment of the present disclosure.

[0036] Figure 8 This is a schematic diagram of ultrasonic boundary points and passable area boundary points provided by an embodiment of the present disclosure.

[0037] Figure 9 according to Figure 8 The illustrated embodiment provides a schematic diagram of fusing boundary points.

[0038] Figure 10 It is a structural diagram of a control device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0040] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0041] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the above technologies, methods, and equipment should be considered part of the specification.

[0042] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0043] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0044] The elements involved in the embodiments of the present disclosure may represent part or all of the elements. For example, the elements involved in the embodiments of the present disclosure may be at least a part of the elements or may be all of the elements.

[0045] The elements involved in the embodiments of the present disclosure may be one or more, for example, "one", "the", "above", "said", "aforementioned", etc., which are used to indicate that the corresponding element is mentioned for the first time or is mentioned again, and does not have the meaning of limiting the quantity.

[0046] It should be noted that the collection, storage, use, processing, transmission, provision, disclosure, and deletion of data involved in this disclosure are all carried out in compliance with the relevant data protection laws and policies of the country or region where they are located, and with the full authorization of the corresponding data owner.

[0047] First, the application scenarios of the embodiments of the present disclosure are described.

[0048] Figure 1 Schematic diagram of an intelligent connected system 100 to which the method provided by the embodiment of the present disclosure can be applied. Figure 1 As shown, the intelligent connected system 100 may include: a mobile device 101, a server 102, and a user terminal 103.

[0049] In some examples, the movable device 101 can be a movable device such as a vehicle, a robot, or a ship, for example, a vehicle with an autonomous driving function, a robot that can move autonomously, etc. Among them, autonomous driving is also called unmanned driving or intelligent driving. Vehicles with autonomous driving functions can achieve driving tasks such as environmental perception, decision planning, and control execution. The level of autonomous driving can refer to the automotive intelligence classification standard formulated by the Society of Automotive Engineers (SAE). For example, L0 is manual driving, L1 is assisted driving, L2 is partial autonomous driving, L3 is conditional autonomous driving, L4 is highly autonomous driving, and L5 is fully autonomous driving. The above classification method of autonomous driving levels is only for example, and the embodiments of this disclosure do not limit the classification standards and levels of autonomous driving.

[0050] In some examples, the server 102 can be a single server or a distributed server cluster consisting of multiple servers, and its deployment method can include a local server or a cloud server. The server 102 can communicate with the mobile device 101 and / or the user terminal 103 based on the communication network and provide various services to the mobile device 101 and / or the user terminal 103. For example, the server can receive perception data sent by the mobile device and provide services such as high-precision maps, data analysis, decision-making planning, etc. to the mobile device. For another example, the server can receive query instructions or control instructions sent by the user terminal and provide corresponding services to the user.

[0051] In some examples, the user terminal 103 can be any form of electronic device that provides services to users, such as a personal computer, a laptop computer, a smart tablet, a smart phone, a smart wearable device, etc. The user can interact with the mobile device or server through the human-computer interaction terminal configured by the mobile device 101, or can interact with the mobile device or server through the user terminal 103, for example, querying the status and / or parameters of the mobile device through the user terminal, or controlling the mobile device to perform set tasks and / or modify configuration parameters, etc.; wherein the user terminal runs an application based on the intelligent network system to realize interaction with the mobile device or server, and the application can be a local application, a web application, or a small program, etc., which is not limited here.

[0052] In some examples, the above application running on the user terminal can provide authentication or authorization services for the user. The user who is successfully authenticated and granted the corresponding authority can query and / or control the removable device within the scope of the granted authority.

[0053] The mobile device 101, the server 102, and the user terminal 103 can communicate with each other through a communication link provided by a communication network 104. The communication network 104 may include one or more networks of any type. For example, the communication network 104 may include a network providing communication such as the Internet, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), a public switched telephone network (PSTN), a satellite communication network, Wi-Fi, 2G, 3G, 4G, 5G, 6G, NB-IoT, eMTC, infrared, Bluetooth, NFC, or a combination of the above multiple networks. The communication networks between the mobile device 101 and the server 102, between the user terminal 103 and the server 102, and between the user terminal 103 and the mobile device 101 may be the same or different.

[0054] It should be noted that Figure 1 The structure of the intelligent connected system 100 shown in FIG is merely illustrative. The intelligent connected system in the embodiments of the present disclosure is not limited to the above structure and may include more or fewer devices as needed, and devices may be combined or separated. For example, the intelligent connected system may not include user terminals and / or servers; for another example, user terminals and servers may be deployed together.

[0055] Figure 2 is based on Figure 1 The embodiment shown is a schematic diagram of a mobile device 101. Figure 2As shown, the mobile device 101 may include a perception component 1011, a computing platform 1012, an execution component 1013, etc. The perception component 1011, the computing platform 1012, and the execution component 1013 may be connected via a bus or other means.

[0056] In some examples, the perception component 1011 can be used to collect information about the movable device itself or outside of it. The perception component 1011 may include at least one of a visual sensing unit, a radar, a positioning and navigation unit, an inertial measurement unit (IMU), or other sensing units. The visual sensor unit may include one or more cameras, the radar may include at least one of a lidar, a millimeter-wave radar, an ultrasonic radar, or other radars, and the positioning and navigation unit may include at least one of a GPS system, a Beidou system, or other global positioning systems.

[0057] In some examples, the computing platform 1012 may include a device with computing capabilities, which is used to process the perception information collected by the perception component 1011 to obtain control information, and send corresponding control instructions to the execution component 1013 to enable the execution component 1013 to perform corresponding actions, thereby achieving control of the mobile device 101. For example, the computing platform 1012 can perform one or more of the following actions on the mobile device: positioning and mapping (Simultaneous Localization and Mapping, SLAM), information collection and processing, decision-making, planning, and control, thereby achieving autonomous control of the mobile device. The computing platform 1012 may include at least one processor and at least one memory, and each processor may execute instructions stored in the memory individually or collectively to implement the method provided in the embodiments of the present disclosure. The processor in the embodiment of the present disclosure may include a central processing unit (CPU), a graphic processing unit (GPU), a neural-network processing unit (NPU), a tensor processing unit (TPU), a data processing unit (DPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), a microcontroller unit (MCU), or at least one of other processors. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. In addition to storing instructions, the memory can also store data, such as high-precision maps, path information, the location, direction, speed, and other data of movable devices. The data stored in the memory can be retrieved and used by the processor.

[0058] In some examples, the computing platform of the mobile device can independently perform computing tasks, or can communicate with a server to complete computing tasks. For example, the computing platform of the mobile device can cooperate with the server to complete corresponding computing tasks.

[0059] The computing platform 1012 can be set in the mobile device 101, and part or all of the computing platform 1012 can also be set in the server corresponding to the mobile device. For example, some functions of the computing platform 1012 with higher real-time requirements are set in the mobile device, and other functions with lower real-time requirements are set in the server corresponding to the mobile device.

[0060] In some examples, the execution component 1013 is used to execute corresponding actions based on the control of the computing platform 1012, so that the movable device 101 completes the movement task. The execution component 1013 may include, for example, a power component, a brake component, a transmission component, a steering component, and the like.

[0061] It should be noted that Figure 2 The structure of the mobile device 101 shown in the figure is merely illustrative. The mobile device in the embodiments of the present disclosure is not limited to the above structure and may include more or fewer components as needed. The device may also be combined or split. For example, the mobile device may not include the computing platform described above. For another example, the mobile device may also include a communication component, an interface component, a multimedia component, an input component, an output component, etc.

[0062] The embodiments of the present disclosure can be applied to scenarios of automatic control of movable devices, especially scenarios of controlling movable devices to enter docking areas. The docking areas of movable devices can be divided into marked docking areas and spatial docking areas, wherein the marked docking areas can be pre-demarcated docking areas with clear line markings, which are easy to manage and use. The spatial docking area can refer to a docking area that does not have clear line markings but can be used by movable devices. For vehicles, the marked docking area is also a marked parking space, and the spatial docking area is also a spatial parking space. Spatial parking spaces usually exist on the roadside without clear line markings.

[0063] Since there are no clear line markings in the spatial docking area, the detection and identification of the spatial docking area needs to rely on the surrounding environment information. It is limited by the sensor's detection accuracy of the surrounding environment. The detection accuracy of different sensors is different. The relative position relationship between the same sensor and the spatial docking area will also affect the detection accuracy.

[0064] In related technologies, ultrasound can be used to detect spatial docking areas. However, due to the limited detection distance of ultrasound, the detection accuracy of obstacles far away from the movable device is limited, which affects the accuracy and timeliness of the detection of the spatial docking area.

[0065] In response to the problems of the related art, the embodiments of the present disclosure provide a control method, which first generates a spatial docking area that can be used by the movable device based on a preset type of target object in the first image data collected by the movable device at the first moment, and then corrects the boundary information of the spatial docking area based on the environmental perception result at the second moment to obtain the corrected spatial docking area, and controls the movable device to travel into the corrected spatial docking area. In this way, compared with the use of ultrasonic sensors for spatial docking area identification in the related art, the technical solution of this embodiment can detect the spatial docking area more promptly, and further correct the boundary information of the spatial docking area based on the environmental perception result, thereby improving the accuracy of spatial docking area detection, so that the spatial docking area can be accurately and timely determined, and the control reliability of the movable device is improved.

[0066] Figure 3 This is a flow chart of a control method provided by an embodiment of the present disclosure. Figure 1 The mobile device and / or server shown is executed. Figure 3 As shown, the control method of this embodiment may include the following steps S310 to S330.

[0067] Step S310 : determining initial boundary information of a spatial docking area that can be used by the movable device according to a target object detected by the movable device.

[0068] The target object may be an object of a preset type determined based on the first environmental data and the first image data collected by the movable device at the first moment. For example, the target object may include one or more of a static movable device, a wall, a pillar, and a curb.

[0069] In some examples, the first environmental data includes at least first image data captured by the mobile device at a first moment. For example, feature extraction and object recognition can be performed based on the first image data to determine the target object.

[0070] In other examples, the first environmental data may include first image data and first ultrasonic data collected by the mobile device at a first moment. For example, feature extraction may be performed on the first image data to obtain image features, and feature extraction may be performed on the first ultrasonic data to obtain point cloud features. The image features and point cloud features may be fused to obtain fused features, and then object identification may be performed based on the fused features to determine the target object.

[0071] The first moment can be any sampling moment at which the mobile device collects environmental data via a sensor carried by the mobile device. For example, the mobile device periodically collects environmental data around the mobile device via a sensor at a preset time interval, and any moment at which environmental data is collected can serve as the first moment. In this embodiment, the sensor carried by the mobile device may include a visual sensor that can collect image data, such as the first image data collected at the first moment.

[0072] In this step, an empty area available for docking in the space detectable by the movable device's visual sensor can be determined based on the target object, and this empty area used for docking can be used as the spatial docking area. The length of the available spatial docking area is greater than the length of the movable device, and the width is greater than the width of the movable device, so that the movable device can enter and dock. It should be noted that the spatial docking area can refer to a docking area that is not clearly marked with lines but is available for use by the movable device. For a vehicle, this spatial docking area can be a spatial parking space.

[0073] In some examples, the initial boundary information of the above-mentioned spatial docking area can be used to determine the boundaries or corner points of the spatial docking area. For example, if the spatial docking area is a quadrilateral, the initial boundary information of the spatial docking area can include the four boundaries of the quadrilateral, and each boundary can be determined by two corner points of two quadrilaterals.

[0074] Figure 4 This is a schematic diagram of a space docking area provided by an embodiment of the present disclosure. Figure 4 As shown, the spatial docking area 403 is a quadrilateral area, which may include four corner points A, B, C, and D, and four boundaries AB, CD, AD, and BC in the four directions of up, down, left, and right determined based on the four corner points. The initial boundary information of the spatial docking area 403 may be determined based on two target objects (including a first object 401 and a second object 402) detected by the movable device 101. The first object 401 and the second object 402 may both be static movable devices. The method of determining the spatial docking area available for the movable device based on the target objects may include: determining the boundaries of the two target objects, judging the distance between the two target objects based on the boundaries of the two target objects, if the distance between the two target objects is less than or equal to the width of the movable device, it can be determined that there is no available spatial docking area between the two target objects; conversely, if the distance between the two target objects is greater than the width of the movable device, it can be determined that there is a spatial docking area available for the movable device. The boundary of the spatial docking area can be determined based on the boundaries of the two target objects.

[0075] In some examples, the target object may include a target object detection box, which may be a quadrilateral detection box, and the boundary of the target object may be determined based on the corner points of the target object detection box. For example, the target object detection box information of each target object may include the center position pos_center, the orientation yaw, the length length, and the width width of the target object. Based on this information, the coordinates of the four corner points of the target object may be calculated.

[0076] It should be noted that the above-mentioned horizontal and vertical directions can be determined with the center point of the spatial docking area as the origin. For example, the two-dimensional device coordinate system of the movable device is established with the center point of the spatial docking area as the coordinate origin, the length direction of the spatial docking area as the longitudinal direction, and the width direction of the spatial docking area as the transverse direction, so as to determine the above-mentioned longitudinal and transverse directions. Taking the vertical docking area (such as a vertical parking space) as an example, the longitudinal and transverse directions are two directions perpendicular to each other. In this embodiment, the method for determining the four directions of up, down, left and right can be: take the direction of the spatial docking area facing the movable device as the top, and in clockwise direction, the four directions are up, right, down and left. It can be understood that the four directions of up, down, left and right can also be determined by other methods.

[0077] by Figure 4 For example, if the distance between the upper right corner point of the first object 401 on the left and the upper left corner point of the second object 402 on the right of the two target objects is less than or equal to the width of the movable device 101, then there is no usable spatial docking area between the first object and the second object; otherwise, there may be a usable spatial docking area, such as the spatial docking area 403 in the figure. At this time, the four corner points of the spatial docking area can be determined based on the upper right corner point and lower right corner point of the first object 401 on the left and the upper left corner point and lower left corner point of the second object 402 on the right, thereby determining the boundary of the spatial docking area.

[0078] For example, the upper right corner and lower right corner of the first object 401 on the left and the upper left corner and lower left corner of the second object 402 on the right can be directly used as the four corner points of the spatial docking area to determine the boundary of the spatial docking area.

[0079] For another example, the left corner point of the spatial docking area can depend on the coordinates of the upper right corner point and the lower right corner point of the first object 401 on the left, and the minimum of the absolute values ​​of the horizontal positions is taken as the horizontal coordinate of the left corner point; the right corner point of the spatial docking area can depend on the coordinates of the upper left corner point and the lower left corner point of the second object 402 on the right, and the minimum of the absolute values ​​of the horizontal positions is taken as the horizontal coordinate of the right corner point.

[0080] In this way, the corner points of the spatial docking area can be determined based on the corner points of the target object, thereby determining the spatial docking area.

[0081] It should be noted that the sensors carried by the movable device may include visual sensors and / or ultrasonic sensors. The maximum detection distance of the visual sensor is greater than the maximum detection distance of the ultrasonic sensor. For example, the maximum detection distance of the visual sensor is 25 meters, and the maximum detection distance of the ultrasonic sensor is 5 meters. Thus, compared with the use of ultrasonic sensors for spatial docking area identification in the related art, this embodiment determines the spatial docking area based on the preset type of target object in the first image data collected by the visual sensor in step S310. It can identify spatial docking areas at a farther distance. In the case of fewer spatial docking areas, it can identify available spatial docking areas earlier, thereby improving the timeliness of spatial docking area identification, thereby controlling the movable device to travel to the spatial docking area.

[0082] Step S320 : determining target boundary information of the spatial docking area according to the initial boundary information and the environmental perception result corresponding to the spatial docking area.

[0083] The environmental perception result may be a result generated based on second environmental data collected by the mobile device at a second moment after the first moment. The second moment may be any sampling moment after the first moment. The second environmental data may include environmental data collected by one or more sensors carried by the mobile device at the second moment. If the second environmental data includes environmental data collected by multiple sensors, the collection moments of different sensors may be aligned, that is, the environmental data collected by different sensors correspond to the same timestamp.

[0084] In some examples, the second environmental data may include second image data collected by the movable device at the second moment, and the environmental perception result may include a freespace generated based on the second image data. In this way, the target boundary information of the spatial docking area can be determined based on the initial boundary information and the freespace. For example, the initial boundary information of the spatial docking area can be corrected based on the freespace to obtain the target boundary information, so as to improve the accuracy of the boundary information of the spatial docking area.

[0085] In other examples, the second environmental data may include ultrasonic data collected by the mobile device at the second moment, and the environmental perception result may include ultrasonic point cloud data generated based on the ultrasonic data. In this way, target boundary information of the spatial docking area can be determined based on the initial boundary information and the ultrasonic point cloud data. For example, the initial boundary information of the spatial docking area can be modified based on the ultrasonic point cloud data to obtain the target boundary information, thereby improving the accuracy of the boundary information of the spatial docking area.

[0086] In some other examples, the second environmental data may include second image data and ultrasonic data, and the environmental perception result may include a passable area and ultrasonic point cloud data. In this way, the target boundary information of the spatial docking area can be determined based on the initial boundary information, the passable area and the ultrasonic point cloud data. For example, the initial boundary information of the spatial docking area can be corrected once based on the passable area to obtain temporary boundary information, and then the temporary boundary information of the spatial docking area can be corrected twice based on the ultrasonic point cloud data to obtain the target boundary information of the spatial docking area; for another example, the initial boundary information of the spatial docking area can be corrected once based on the ultrasonic point cloud data to obtain temporary boundary information, and then the temporary boundary information of the spatial docking area can be corrected twice based on the passable area to obtain the target boundary information of the spatial docking area; for another example, the passable area and the ultrasonic point cloud data can be fused to obtain fused boundary information, and then the initial boundary information of the spatial docking area can be corrected based on the fused boundary information to obtain the target boundary information of the spatial docking area.

[0087] In some examples, after determining the initial boundary information of the available spatial docking area in step S310, the movable device can be controlled to travel toward the spatial docking area based on the initial boundary information. In the process of controlling the vehicle to travel toward the spatial docking area, the target boundary information of the spatial docking area can be determined based on the initial boundary information and the environmental perception result. Step S320 can be performed multiple times. For example, the second moment includes multiple sampling moments after the first moment, and step S320 is performed at each second moment to determine the target boundary information of the spatial docking area until the movable device enters the spatial docking area.

[0088] It should be noted that the detection accuracy of ultrasonic sensors is greater than that of visual sensors. For example, the typical detection accuracy of ultrasonic sensors can be ±1cm, while the typical detection accuracy of visual sensors can be ±10cm or ±30cm. In addition, the detection accuracy of visual sensors is easily affected by conditions such as distance and lighting, resulting in further reduction in detection accuracy. It can be seen that although visual sensors can detect the spatial docking area earlier, the detection accuracy is limited. Therefore, when the movable device approaches the spatial docking area, the target boundary information of the spatial docking area can be further and more accurately determined based on the ultrasonic sensor and / or visual sensor to obtain a more accurate spatial docking area.

[0089] It should be noted that the target boundary information may be the same as or different from the initial boundary information. For example, the target boundary information may be obtained by modifying the initial boundary information.

[0090] In some examples, the initial boundary information includes at least a first initial boundary located on a first side of the spatial docking area, and the target boundary information includes at least a first target boundary located on the first side, where the first target boundary is different from the first initial boundary. The first side may be at least one of the top, bottom, left, or right sides of the spatial docking area. Optionally, the target boundaries in the target boundary information, excluding the first target boundary, may be the same as the initial boundaries in the initial boundary information, excluding the first initial boundary.

[0091] In this way, at least the initial boundary of the first side of the initial boundary information can be corrected, so as to more accurately determine the target boundary information of the spatial docking area.

[0092] Step S330: Control the movable device to travel according to the target boundary information.

[0093] For example, the target area to be entered by the vehicle can be determined based on the target boundary information of the spatial docking area, a path from the vehicle's current position to the spatial docking area can be planned, and the movable device can be controlled to travel based on the planned path to enter the spatial docking area.

[0094] Based on the above steps S310 to S330, initial boundary information of the spatial docking area that can be used by the mobile device is first generated based on the target object of the preset type in the first environmental data including at least the first image data collected by the mobile device at the first moment. Then, based on the initial boundary information and the environmental perception results at the second moment, the target boundary information of the spatial docking area is determined, and the movement of the mobile device is controlled based on the target boundary information. In this way, compared with the use of ultrasonic sensors for spatial docking area identification in the related art, the technical solution of this embodiment can detect the spatial docking area more promptly and determine more accurate target boundary information of the spatial docking area based on the environmental perception results, thereby improving the accuracy of spatial docking area detection, thereby accurately and promptly determining the spatial docking area and improving the control reliability of the mobile device.

[0095] In some embodiments of the present disclosure, the specific manner in which step S320 determines the target boundary information of the spatial docking area based on the initial boundary information and the environmental perception result corresponding to the spatial docking area may include the following steps S321 and S322:

[0096] Step S321 : determining a first initial boundary located at a first side of the spatial docking area according to the distance between each initial boundary in the initial boundary information of the spatial docking area and the movable device.

[0097] In some examples, the first initial boundary may be at least one of multiple initial boundaries of the spatial docking area, and the first side may be at least one of the top, bottom, left, or right sides of the spatial docking area. Optionally, the first initial boundary may also be referred to as an initial boundary to be revised.

[0098] In some examples, the first initial boundary may be a location boundary whose distance from the movable device is less than or equal to a preset threshold. The preset threshold may be a pre-set distance threshold for a credible environmental perception result. For example, if the environmental perception result is ultrasonic point cloud data, the preset threshold may be a distance threshold for a credible ultrasonic point cloud data, such as 5 meters.

[0099] In other examples, the position boundary closest to the movable device among the multiple initial boundaries of the spatial docking area can be used as the first initial boundary. For example, the multiple initial boundaries of the spatial docking area may include a left position boundary and a right position boundary. When the movable device is located on the left side of the spatial docking area, the distance between the left position boundary and the movable device is smaller than the distance between the right position boundary and the movable device. In this case, the left position boundary can be used as the first initial boundary. Conversely, when the movable device is located on the right side of the spatial docking area, the distance between the right position boundary and the movable device is smaller than the distance between the left position boundary and the movable device. In this case, the right position boundary can be used as the first initial boundary.

[0100] In some examples, the first initial boundary determined at different times may be different. For example, the second time mentioned above includes at least a third time and a fourth time after the first time, and the first initial boundary determined at the third time is different from the first initial boundary determined at the fourth time.

[0101] Taking the example of multiple initial boundaries of the spatial docking area including the left position boundary and the right position boundary, if at the third moment, the movable device is located on the left side of the spatial docking area, the determined first initial boundary may be the left position boundary; conversely, if at the fourth moment, the movable device is located on the right side of the spatial docking area, the determined first initial boundary may be the right position boundary.

[0102] In this way, determining different target boundaries at different times can improve the accuracy of the target boundaries of the spatial docking area and avoid the problem of determining all boundaries of the spatial docking area at the same time, which may result in some boundaries being far away and inaccurate.

[0103] Step S322: determining a first target boundary according to the first initial boundary and the environment perception result to obtain target boundary information of the spatial docking area.

[0104] The first target boundary and the first initial boundary may be the same or different. For example, the first target boundary may be obtained by modifying the first initial boundary.

[0105] In some examples, the first initial boundary may be corrected to obtain a first target boundary, and target boundary information of the spatial docking area may be determined based on the corrected first target boundary.

[0106] In some examples, only the first initial boundary may be corrected, while the other initial boundaries among the multiple initial boundaries except the first initial boundary are not corrected. That is, the target boundary information is obtained based on the first target boundary and the other initial boundaries among the multiple initial boundaries except the first initial boundary information.

[0107] It should be noted that the first target boundary can be determined by determining the horizontal and vertical coordinates of the corner points of the first target boundary, thereby obtaining the first target boundary. In other words, the target boundary can be corrected by correcting the horizontal and vertical coordinates of the corner points of the target boundary, thereby re-determining a new target boundary.

[0108] In some examples, the spatial docking area determined based on the target boundary information still needs to meet the conditions for the movable device to be usable. For example, the length of the spatial docking area is greater than the length of the movable device, and the width is greater than the width of the movable device.

[0109] In some examples, there are multiple target objects, and each location boundary of the spatial docking area is determined based on the boundary information of the target object corresponding to that location boundary. In step S322, a first target object corresponding to the first initial boundary can be determined from the multiple target objects; boundary information of the first target object can be determined based on the environmental perception result; and a first target boundary can be determined based on the boundary information of the first target object. For example, the first initial boundary can be modified based on the boundary information of the first target object to obtain the first target boundary.

[0110] Likewise Figure 4 For example, if the first initial boundary is the left boundary of the spatial docking area, the first target object corresponding to the first initial boundary may be the first object 401 located on the left side of the spatial docking area. If the first initial boundary is the right boundary of the spatial docking area, the first target object corresponding to the first initial boundary may be the second object 402 located on the right side of the spatial docking area. When the movable device is located on the left side of the spatial docking area, the first object 401 is used as the first target object, and the boundary information (such as boundaries and / or corner points) of the first object 401 is determined according to the environmental perception result, so that the first target boundary can be used.

[0111] In this way, the first target object corresponding to the first initial boundary can be determined, and the boundary information of the first target object can be determined, thereby determining the target boundary information of the spatial docking area.

[0112] The above-mentioned environmental perception results include passable areas and / or ultrasonic point cloud data. The following describes methods for determining target boundary information of a spatial docking area based on the passable areas or ultrasonic point cloud data.

[0113] In some embodiments, the environmental perception results may include a traversable area, which may have a preset maximum detection range. For example, the maximum detection range of the traversable area may be 25.6 meters in front of the movable device, and 12.8 meters to the rear, left, and right of the movable device. The detection accuracy of the traversable area may reach 10 cm. The boundary of the traversable area may be determined based on the location of obstacles within the maximum detection range. For example, the boundary of the traversable area may be determined based on the boundary of obstacles within the maximum detection range.

[0114] After preliminarily determining the initial boundary information of the spatial docking area that the mobile device can use based on the target object detected by the mobile device, during the process of the mobile device moving toward the spatial docking area, when the mobile device is located on the left side of the spatial docking area, for example, when passing the target object on the left, the mobile device and the first target object on the left are aligned, and the first initial boundary and the first target boundary can be determined as the left position boundary. The boundary information of the first target object is determined based on the passable area, and the first target boundary of the spatial docking area (i.e., the left target boundary) is determined based on the boundary information of the first target object, thereby obtaining the target boundary information of the spatial docking area. During this process, the left boundary of the spatial docking area (e.g., the left corner coordinates) can be corrected. When the mobile device is located on the right side of the spatial docking area, for example, when passing the target object on the right, the mobile device and the right target object are aligned, and the first initial boundary and the first target boundary can be determined as the right position boundary. The boundary information of the first target object is determined based on the passable area, and the first target boundary of the spatial docking area (i.e., the right target boundary) is determined based on the boundary information of the first target object, thereby obtaining the target boundary information of the spatial docking area. During this process, the right boundary of the spatial docking area (e.g., the right corner coordinates) can be corrected. Determining the first target boundary based on the first initial boundary may include: in a first coordinate system corresponding to the spatial docking area, revising the horizontal and vertical coordinates of corner points of the target boundary based on a boundary line of the passable area to ensure that no obstacles exist within the spatial docking area. The horizontal axis (X-axis) of the first coordinate system may be the length direction of the spatial docking area, and the vertical axis (Y-axis) may be the width direction of the spatial docking area. Both the horizontal and vertical axes pass through the center point of the spatial docking area, with the center point being the coordinate origin.

[0115] In some examples, it is possible to determine whether there is an obstacle in the spatial docking area based on the passable area. If there is an obstacle in the spatial docking area, at least a portion of the initial boundary information of the spatial docking area is updated based on the position of the obstacle to obtain the target boundary information, so that the obstacle is located outside the target boundary information of the spatial docking area. For example, when a movable device passes through a gap between two target objects, it is possible to determine whether there is an obstacle in the spatial docking area based on the passable area. If there is an obstacle, at least a portion of the initial boundary information of the spatial docking area can be updated based on the position of the obstacle to obtain the target boundary information, so that the obstacle is located outside the target boundary information of the spatial docking area, that is, no obstacle is present in the updated spatial docking area.

[0116] In some examples, due to the large scope of the passable area, when determining the target boundary information of the spatial docking area based on the passable area, a portion of the passable area can be used. For example, the area within a preset distance from the target boundary of the spatial docking area can be used as the portion of the passable area. The preset distance can be any preset value, such as 1.2 meters or 2.6 meters. The preset distance can be determined based on the width or length of the movable device, for example, half the width of the movable device or half the length of the movable device.

[0117] In other embodiments, the environmental perception result may include ultrasonic point cloud data, and the detection accuracy of the ultrasonic point cloud data may be 1 cm. After the initial boundary information of the spatial docking area that can be used by the mobile device is preliminarily determined based on the target object detected by the mobile device, during the process of the mobile device moving toward the spatial docking area, when the mobile device is located on the left side of the spatial docking area, for example, when passing the target object on the left, the perspective of the mobile device and the first target object on the left is aligned, and the first initial boundary and the first target boundary can be determined as the left position boundary, and the left boundary of the spatial docking area (for example, the left corner coordinates) is corrected based on the ultrasonic point cloud data; when the mobile device is located on the right side of the spatial docking area, for example, when passing the target object on the right, the perspective of the mobile device and the right target object is aligned, and the boundary information of the first target object can be determined based on the ultrasonic point cloud data. Based on the boundary information of the first target object, the first target boundary of the spatial docking area (i.e., the left target boundary) is determined, thereby obtaining the target boundary information of the spatial docking area. In this process, the right boundary of the spatial docking area (for example, the right corner coordinates) can be corrected. It should be noted that the ultrasonic point cloud data may include a positioning point (Localization Point, LP point) and an object (Object, Obj), and the object may be a detection object obtained by clustering the ultrasonic point cloud data.

[0118] In other embodiments, the environmental perception results may include traversable areas and ultrasonic point cloud data. The target boundary information of the spatial docking area can be determined based on the initial boundary information, the traversable area, and the ultrasonic point cloud data. For example, the initial boundary information of the spatial docking area can be first corrected based on the traversable area to obtain temporary boundary information. This temporary boundary information can then be corrected again based on the ultrasonic point cloud data to obtain the target boundary information of the spatial docking area. In this way, the detection accuracy of the spatial docking area can be further improved through these two corrections.

[0119] Furthermore, based on the target boundary information of the spatial docking area determined by the passable area and / or ultrasonic point cloud data, if the width and length of the spatial docking area still meet the docking requirements of the movable device, the spatial docking area can continue to be used. For example, if it is determined based on the target boundary information that the length of the spatial docking area is greater than the length of the movable device and the width is greater than the width of the movable device, it can be determined that the spatial docking area still meets the docking requirements of the movable device, that is, it can be used as a spatial docking area for the movable device. On the contrary, if it is determined based on the target boundary information that the length of the spatial docking area is less than the length of the movable device or the width is less than the width of the movable device, it can be determined that the spatial docking area cannot be used, the spatial docking area can be abandoned, and a new spatial docking area can be found based on the target object.

[0120] It should be noted that Figure 4 The double-boundary vertical space docking area (i.e., a vertical space docking area with target objects on both sides) is used as an example for explanation. For the single-boundary vertical space docking area (i.e., a vertical space docking area with a target object on only one side), the method used is similar. The difference is that the boundary information of the side without the target object can be confirmed based on preset information. For example, the boundary of the side without the target object is parallel to the boundary of the side with the target object and the distance is a preset distance. Figure 5 is a schematic diagram of another spatial docking area provided by an embodiment of the present disclosure, such as Figure 5 As shown, the spatial docking area 503 can be a single-boundary vertical spatial docking area. The movable device 101 detects that there is a preset type of target object 501 on the left side of the spatial docking area 503. The left side boundary of the spatial docking area 503 can be determined based on the target object. There is no preset type of target object on its right side. If no obstacle is detected on the right side based on vision or ultrasound, the right side boundary can be determined based on the preset distance. Otherwise, if an obstacle is detected on the right side (such as a target object of a non-preset type), the right side boundary can be determined based on the position of the obstacle.

[0121] Furthermore, Figure 6This is a schematic diagram of another type of space docking area provided by the embodiment of the present disclosure. Figure 6 As shown, the space docking area 603 can be a double-boundary horizontal space docking area, and the method of determining the initial boundary information and target boundary information of the space docking area is as follows: Figure 4 Similarly, the mobile device 101 detects a first object 601 on the left side of the spatial docking area 603 and a second object 603 on the right side thereof, and determines a boundary of the spatial docking area 603 based on the two target objects. Figure 7 This is a schematic diagram of another space docking area provided by the embodiment of the present disclosure. Figure 7 As shown, the space docking area 703 can be a single-boundary horizontal space docking area, and the method of determining the initial boundary information and target boundary information of the space docking area is as follows: Figure 5 Similarly. If the movable device 101 detects that there is a target object 701 of a preset type on the left side of the spatial docking area 703, the left boundary of the spatial docking area 703 can be determined based on the target object. If there is no target object of the preset type on the right side, if no obstacle is detected on the right side based on vision or ultrasound, the right boundary can be determined based on a preset distance. Otherwise, if an obstacle is detected on the right side (e.g., a target object of a non-preset type), the right boundary can be determined based on the position of the obstacle.

[0122] In some embodiments of the present disclosure, the above-mentioned environmental perception results include passable areas and ultrasonic point cloud data, and the passable areas and ultrasonic point cloud data can be fused to determine the target boundary information of the spatial docking area. For example, based on the passable area and ultrasonic point cloud data, fused boundary information corresponding to the boundary of the spatial docking area is obtained; and the target boundary information of the spatial docking area is determined based on the initial boundary information and the fused boundary information. For example, at least a part of the initial boundary information of the spatial docking area can be updated based on the fused boundary information to obtain the target boundary information of the spatial docking area. In this way, by fusing the passable area and ultrasonic point cloud data and then determining the target boundary information of the spatial docking area, the accuracy of the spatial docking area detection can be further increased.

[0123] In some examples, a specific method of obtaining fused boundary information corresponding to the boundary of the spatial docking area based on the traversable area and the ultrasonic point cloud data may include the following steps S11 and S12:

[0124] Step S11 : performing object detection based on the ultrasonic point cloud data to obtain boundary information of a second target object located at the boundary of the spatial docking area.

[0125] In some examples, object detection can be performed on a first area including the spatial docking area and its surrounding area using clustering, deep learning, or other means based on ultrasonic point cloud data to obtain boundary information for one or more detected objects (Obj) within the first area. Furthermore, boundary information for a second target object located at the boundary of the spatial docking area can be obtained based on the boundary information of the detected objects. For example, if there are multiple detected objects, the boundary information of the detected object closest to the boundary of the spatial docking area can be used as the boundary information of the second target object.

[0126] In this example, the ultrasonic point cloud data may include multiple data points, one data point represents a spatial position point, and each data point includes the position coordinates of the spatial position point represented. In addition, each data point may also include the reflection intensity of the spatial position point represented, etc., which is not limited here. Furthermore, the above-mentioned detection object may be a detection object obtained by clustering, deep learning, and other means of detecting data points in the ultrasonic point cloud data. The detection object may be expressed as a "single point", as a "line segment", or as an "area" with a set shape, wherein a detection object in the form of a "single point" is represented by a single data point, a detection object in the form of a "line segment" can be represented by two data points corresponding to two endpoints, and a detection object in the form of an "area" with a set shape can be represented by multiple data points corresponding to multiple corner points, and the line segment between the corner points is the boundary of the area.

[0127] In other examples, the multiple data points of the ultrasonic point cloud data may include two types of data points: positioning points (LP points) and sampling points on the detection object. The two types of data points can be projected onto a first area including the spatial docking area and its surrounding areas to obtain boundary information of a second target object located at the boundary of the spatial docking area.

[0128] The positioning point can be a data point obtained from the ultrasonic point cloud data based on a triangulation positioning algorithm. Here, the data point obtained based on the triangulation positioning algorithm is also called a triangulation positioning point. The triangulation positioning point has the characteristic of precise location, which is conducive to improving the fusion accuracy.

[0129] Step S12: Fusing the boundary information of the second target object and the boundary information of the passable area to obtain fused boundary information.

[0130] In some examples, fusion can be performed based on the fusion weight of the boundary information. Different fusion weights can be set for the boundary information of the second target object and the boundary information of the passable area. For example, due to the high accuracy of ultrasonic detection, the fusion weight of the boundary information of the second target object can be greater than the fusion weight of the boundary information of the passable area. In this way, the accuracy of the fused boundary information can be improved. The boundary information of the second target object determined based on the ultrasonic point cloud data can be expressed as multiple ultrasonic boundary points. The fusion weight of the boundary information of the second target object can be expressed as the fusion weight of each ultrasonic boundary point. The closer the ultrasonic boundary point is to the movable device, the greater its fusion weight. The boundary information of the passable area can also be expressed as multiple passable area boundary points. Optionally, a pre-trained deep learning model can be used to determine the fusion weight of each boundary point, and the boundary information of the second target object and the boundary information of the passable area can be fused to obtain fused boundary information.

[0131] In other examples, the boundary information of the second target object can be represented as one or more boundary lines, each of which can be represented as a line segment with two ultrasonic boundary points as endpoints; the boundary information of the passable area can be represented as multiple passable area boundary points. In step S12, based on the two ultrasonic boundary points of the boundary line in the boundary information of the second target object, the closest passable area boundary point corresponding to these two endpoints can be found, and the passable area boundary point between the two ultrasonic boundary points can be replaced with the ultrasonic boundary point of the second target object; further, based on the distance relationship between the ultrasonic boundary point and the passable area boundary point and the center point of the movable device, the corresponding boundary points are filled in or subtracted to form the final fused boundary points, and the fused boundary information is determined based on the fused boundary points.

[0132] In other examples, the boundary information of the second target object determined based on the ultrasonic point cloud data can be represented by multiple ultrasonic boundary points; and the boundary information of the passable area can be represented by multiple passable area boundary points. The ultrasonic boundary points and the passable area boundary points can be projected into a first area including the spatial docking area and its surrounding area. Based on the horizontal / vertical distances between the ultrasonic boundary points and the center point of the movable device, and the horizontal / vertical distances between the passable area boundary points and the center point of the movable device, fused boundary points are determined, and fused boundary information is determined based on the fused boundary points.

[0133] Figure 8 Schematic diagram of ultrasonic boundary points and passable area boundary points provided by the embodiment of the present disclosure. Figure 8As shown, the spatial docking area 803 and the surrounding area are represented as a spatial grid. The white grid represents a spatial grid without obstacles; the red grid and the blue grid are the boundary points of the passable area, representing different types of objects, red for pillars and blue for walls; the green grid is the ultrasonic boundary point. Figure 9 according to Figure 8 A schematic diagram of a fused boundary point provided by the illustrated embodiment. The yellow grid represents the fused boundary point, which is obtained by fusing the ultrasonic boundary point with the passable area boundary point. Based on the fused boundary point, fused boundary information can be determined and the spatial docking area 803 can be corrected.

[0134] By adopting any of the above methods, the fusion boundary information can be determined, and the boundary of the spatial docking area can be further corrected based on the fusion boundary information. For example, the target boundaries (such as the left boundary, the right boundary, and the downward boundary) of the spatial docking area can be corrected separately. When correcting the target boundary, you can first find the fusion boundary point closest to the center point of the spatial docking area among the multiple fusion boundary points of the fusion boundary information, determine the fusion boundary line based on the fusion boundary point, and use the fusion boundary line to correct the boundary of the spatial docking area, so as to further improve the accuracy of the spatial docking area.

[0135] Figure 10 This is a schematic diagram of the structure of a control device provided by an embodiment of the present disclosure. Figure 10 As shown, the control device 1000 may include a memory 1010 and a processor 1020. The memory 1010 may be used to store computer instructions, and the processor 1020 may be used to call computer instructions from the memory 1010 to execute all or part of the steps of any method in the aforementioned embodiments of the present disclosure. The processor may be one or more, and the one or more processors may execute instructions individually or collectively. The memory may also be one or more, and the one or more memories may store the aforementioned computer instructions individually or collectively.

[0136] In some examples, the control device may be Figure 1 In other examples, the control device may also be any electronic device, for example, a controller of a mobile device.

[0137] The present disclosure also provides a removable device that may include a memory and a processor. The memory may be used to store computer instructions, and the processor may be used to call computer instructions from the memory to execute all or part of the steps of any of the methods described in the foregoing embodiments of the present disclosure. The processor may be one or more, and the one or more processors may execute instructions individually or collectively. The memory may also be one or more, and the one or more memories may store the aforementioned computer instructions individually or collectively.

[0138] In some examples, the movable device may be a vehicle, which may be an electric vehicle, a hybrid vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle may be an autonomous vehicle or a non-autonomous vehicle. For example, the movable device provided in this embodiment may be Figure 1 or Figure 2 Removable device shown.

[0139] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program implements any of the methods described in the foregoing embodiments of the present disclosure. Optionally, the computer-readable storage medium may be a non-transitory storage medium, but is not limited thereto and may also be a transient storage medium.

[0140] The present disclosure also provides a chip that may include a processing unit that can be used to execute all or part of the steps of any of the methods described in the foregoing embodiments of the present disclosure. The chip may be in the form of an application-specific integrated circuit (ASIC), a system-on-chip (SOC), a field-programmable gate array (FPGA), or the like, and this embodiment is not limited thereto. Optionally, the chip may also include a storage unit that can be used to store computer instructions, and the processing unit may be used to call computer instructions from the storage unit to execute all or part of the steps of any of the methods described in the foregoing embodiments of the present disclosure.

[0141] An embodiment of the present disclosure further provides a computer program product, which may include a computer program. When the computer program is executed by a processor, any method in the aforementioned embodiments of the present disclosure may be implemented.

[0142] The present disclosure may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement any of the methods in the aforementioned embodiments of the present disclosure.

[0143] A computer-readable storage medium can be a tangible device that can hold and store instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination thereof. As used herein, a computer-readable storage medium is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through an electrical wire.

[0144] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0145] The computer program instructions for performing the operation of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, which can include object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions can be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, by utilizing the state information of computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0146] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0147] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine such that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0148] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0149] The flowcharts and block diagrams in the accompanying drawings show the possible implementation architectures, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions. It should be noted that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.

[0150] The embodiments of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terms used herein are chosen to best explain the principles of the embodiments, their practical applications, or improvements to the technology in the marketplace, or to enable other persons skilled in the art to understand the embodiments disclosed herein. The scope of the present disclosure is defined by the appended claims.

Claims

1. A control method, characterized in that: The method comprises: determining initial boundary information of a spatial docking area that can be used by the movable device based on a target object detected by the movable device; wherein the target object is an object of a preset type determined based on first environmental data collected by the movable device at a first moment, the first environmental data including at least first image data; Determining target boundary information of the spatial docking area based on the initial boundary information and an environmental perception result corresponding to the spatial docking area; wherein the environmental perception result is a result generated based on second environmental data collected by the movable device at a second moment after the first moment; The movable device is controlled to travel according to the target boundary information.

2. The method according to claim 1, characterized in that The second environmental data includes second image data collected by the movable device at the second moment, the environmental perception result includes a passable area generated based on the second image data, and / or, The second environmental data includes ultrasonic data collected by the movable device at the second moment, and the environmental perception result includes ultrasonic point cloud data generated based on the ultrasonic data.

3. The method according to claim 1, characterized in that The initial boundary information includes at least a first initial boundary located on a first side of the spatial docking area, and the target boundary information includes at least a first target boundary located on the first side, where the first target boundary is different from the first initial boundary.

4. The method according to claim 3, characterized in that The determining target boundary information of the spatial docking area according to the initial boundary information and the environmental perception result corresponding to the spatial docking area includes: determining, based on a distance between each initial boundary in the initial boundary information and the movable device, the first initial boundary located on a first side of the spatial docking area; The first target boundary is determined according to the first initial boundary and the environment perception result to obtain the target boundary information.

5. The method according to claim 3, characterized in that The second moment includes at least a third moment and a fourth moment after the first moment, and the first initial boundary determined at the third moment is different from the first initial boundary determined at the fourth moment.

6. The method according to claim 3, characterized in that There are multiple target objects; and determining the first target boundary according to the first initial boundary and the environment perception result includes: determining a first target object corresponding to the first initial boundary from the plurality of target objects; determining boundary information of the first target object according to the environmental perception result; The first target boundary is determined according to the boundary information of the first target object.

7. The method according to claim 2, characterized in that The environmental perception result includes a passable area; and determining target boundary information of the spatial docking area according to the initial boundary information and the environmental perception result corresponding to the spatial docking area includes: Determining whether there is an obstacle in the space docking area according to the passable area; When the obstacle exists in the spatial docking area, at least a portion of the initial boundary information of the spatial docking area is updated according to the position of the obstacle to obtain the target boundary information, so that the obstacle is located outside the target boundary information of the spatial docking area.

8. The method according to claim 2, characterized in that The environmental perception result includes the passable area and the ultrasonic point cloud data; and determining the target boundary information of the spatial docking area according to the initial boundary information and the environmental perception result corresponding to the spatial docking area includes: Acquire fused boundary information corresponding to the initial boundary information based on the traversable area and the ultrasonic point cloud data; At least a portion of the initial boundary information of the spatial docking area is updated according to the fused boundary information to obtain target boundary information of the spatial docking area.

9. A control device, characterized in that: The system comprises a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, which implements the method according to any one of claims 1 to 8 when executed by a processor.

Images