Control method, device and equipment of sweeper for lawn cleaning and storage medium

Abstract

The invention relates to the technical field of cleaning equipment, in particular to a lawn cleaning sweeper control method which comprises the steps that sweeping task information and the current position of a sweeper are acquired, sweeping path information is acquired from the sweeping task information, a sweeping starting position is acquired from the sweeping path information, and the sweeping starting position is determined according to the sweeping starting position. Triggering a sweeping starting instruction according to the sweeping starting position and the current position of the sweeper; acquiring to-be-cleaned image information of the cleaning path information in real time, and identifying the to-be-cleaned image information to obtain an obstacle image and a to-be-cleaned garbage image; identifying the obstacle image, generating an obstacle type according to an identification result, and generating an obstacle processing strategy according to the obstacle type; and generating a garbage cleaning control instruction according to the obstacle processing strategy and the to-be-cleaned garbage image, and sending the garbage cleaning control instruction to a corresponding control terminal. The intelligent sweeper for lawn cleaning has the effect of improving the intelligent level of the sweeper for lawn cleaning.

Description

Technical Field

[0001] The present application relates to the technical field of cleaning equipment, and in particular to a control method, device, equipment and storage medium for a lawn cleaning sweeper. Background Art

[0002] At present, with the acceleration of urbanization, road cleaning has become an important part of urban sanitation work. At present, electric road sweepers have been widely used in various cleaning scenarios, but most electric road sweepers still require manual operation and have a low degree of automation, which cannot meet the growing demand for unmanned cleaning.

[0003] Existing electric road sweepers are mainly driven manually for cleaning operations. Some high-end models are equipped with simple automatic driving systems, but they are difficult to promote on a large scale due to the technical maturity and cost issues. In addition, existing road sweepers lack intelligent control during operation and cannot adjust the cleaning strategy in real time according to the ground garbage situation.

[0004] The above-mentioned prior art solutions have the following defects: Manually driven sweepers have problems such as high labor costs, low operating efficiency, and unstable cleaning quality. Existing self-driving sweepers have defects such as high technical complexity, high cost, and insufficient intelligence. Summary of the invention

[0005] In order to improve the intelligence level of a lawn sweeper, the present application provides a lawn sweeper control method, device, equipment and storage medium.

[0006] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A method for controlling a lawn cleaning sweeper, the method comprising: Acquire cleaning task information and the current position of the cleaning vehicle, acquire cleaning path information from the cleaning task information, acquire the cleaning start position from the cleaning path information, and trigger a cleaning start instruction according to the cleaning start position and the current position of the cleaning vehicle; Acquire the image information to be cleaned of the cleaning path information in real time, identify the image information to be cleaned, and obtain the obstacle image and the garbage image to be cleaned; Recognize the obstacle image, generate an obstacle type according to the recognition result, and generate an obstacle handling strategy according to the obstacle type; A garbage cleaning control instruction is generated according to the obstacle handling strategy and the garbage image to be cleaned, and the garbage cleaning control instruction is sent to a corresponding control terminal.

[0007] By adopting the above technical solution, by acquiring the cleaning task information and the current position of the cleaning vehicle, combined with the cleaning starting point position in the cleaning path information, the cleaning vehicle can automatically trigger the cleaning start command, thereby realizing unmanned operation, greatly reducing labor costs, and improving the efficiency of the cleaning work; the image information of the area to be cleaned in the cleaning path information is acquired in real time and identified, which can not only quickly distinguish between obstacle images and images of garbage to be cleaned, but also generate corresponding obstacle handling strategies according to the type of obstacles, thereby enhancing the adaptability of the cleaning vehicle to complex environments, and thus effectively ensuring the safety of the cleaning operation; at the same time, the garbage cleaning control command generated based on the obstacle handling strategy and the image of the garbage to be cleaned is sent to the control terminal, so that the cleaning vehicle can dynamically adjust the cleaning mode according to the actual situation, avoid work interruption caused by obstacles, and improve the cleaning quality and efficiency.

[0008] In a preferred example, the present application may be further configured as follows: the obstacle type includes abnormal object information, the obstacle image is identified, the obstacle type is generated according to the identification result, and the obstacle handling strategy is generated according to the obstacle type, specifically including: Acquire the foreign object size information corresponding to each of the abnormal object information, and determine the weight range of the foreign object according to the foreign object size information; A foreign object crossing instruction and / or a foreign object bypassing instruction is generated according to the foreign object weight range and the foreign object size information, and the obstacle handling strategy is generated according to the foreign object crossing instruction and / or the foreign object bypassing instruction.

[0009] By adopting the above technical scheme, by acquiring the image information to be cleaned on the cleaning path in real time and identifying the image information, the obstacle image and the garbage image to be cleaned are obtained, and the obstacle image is further identified to generate the obstacle type. Furthermore, for the obstacle type containing abnormal object information, the foreign object size information corresponding to each abnormal object information is firstly acquired, and the foreign object weight range is judged according to the foreign object size information, so as to generate the foreign object crossing instruction and / or the foreign object bypass instruction according to the foreign object weight range and the foreign object size information, and then form the corresponding obstacle handling strategy, so that the handling method of the sweeper can be reasonably selected according to the specific size and weight of the obstacle, so as to ensure that the sweeper can effectively avoid the obstacle when encountering the abnormal object, and reduce the impact on the cleaning efficiency, thereby improving the intelligence of the sweeper, and also enabling the cleaning task to be completed efficiently and safely without human intervention, thereby improving the adaptability and work efficiency of the sweeper.

[0010] In a preferred example, the present application may be further configured as follows: the obstacle type includes pedestrian image information, the obstacle image is identified, the obstacle type is generated according to the identification result, and the obstacle handling strategy is generated according to the obstacle type, specifically including: Obtaining pedestrian distance information and a corresponding pedestrian status image corresponding to each pedestrian from the pedestrian image information; The pedestrian avoidance probability is obtained by analyzing the pedestrian distance information and the pedestrian status image, and the obstacle handling strategy is generated according to the pedestrian avoidance probability.

[0011] By adopting the above technical solution, through processing pedestrian image information, the pedestrian distance information and pedestrian status image corresponding to each pedestrian can be obtained in real time, and based on the comprehensive analysis of the pedestrian distance information and pedestrian status image, the pedestrian avoidance probability is generated, and then the corresponding obstacle handling strategy is generated, so as to ensure that the sweeper can take reasonable avoidance measures when encountering pedestrians, thereby improving the safety performance of the sweeper, and further enhancing the adaptability of the sweeper in complex environments; through in-depth mining of pedestrian distance information and pedestrian status images, it is possible to more accurately evaluate the possible behaviors of pedestrians, so as to adjust the driving path of the sweeper in time, and effectively avoid potential safety hazards, so that the intelligent avoidance mechanism can enable the sweeper to better protect the safety of pedestrians while performing cleaning operations, thereby achieving dual protection of cleaning operations and pedestrian safety.

[0012] In a preferred example, the present application may be further configured as follows: the pedestrian avoidance probability is obtained by analyzing the pedestrian distance information and the pedestrian status image, and the obstacle handling strategy is generated according to the pedestrian avoidance probability, specifically including: Filter the pedestrian status images corresponding to the distances below a preset value according to the pedestrian distance information as the pedestrian posture data to be analyzed; Acquire pedestrian gaze data from each of the pedestrian posture data to be analyzed, acquire a pedestrian gaze target according to the pedestrian gaze data, and generate the pedestrian avoidance probability according to the pedestrian gaze target; A cleaning prompt sound is triggered according to the pedestrian avoidance probability, and the pedestrian avoidance probability is generated again, and the obstacle handling strategy is generated according to the regenerated pedestrian avoidance probability.

[0013] By adopting the above technical solution, when the sweeper is performing a cleaning task, by acquiring the pedestrian status image in real time and combining it with the pedestrian distance information, the pedestrian's behavioral intention can be accurately analyzed, that is, the pedestrian posture data that is closer to the sweeper is screened out based on the pedestrian distance information, thereby improving the pertinence and timeliness of the analysis. Furthermore, the pedestrian's gaze data is extracted from the pedestrian posture data to be analyzed, and the pedestrian's gaze target is determined based on the pedestrian's gaze data, so that the sweeper can accurately judge whether the pedestrian is paying attention to the sweeper and its moving path, thereby predicting his possible behavior. For example, if the pedestrian's gaze target is the sweeper, his avoidance probability will be significantly reduced; conversely, if the pedestrian's gaze target deviates from the sweeper, his avoidance probability will increase accordingly, thereby not only improving the accuracy of the pedestrian avoidance probability, but also enhancing the system's ability to handle pedestrian obstacles. Furthermore, based on the pedestrian avoidance probability generated for the first time, the sweeper's reminder sound is triggered to remind pedestrians to pay attention. Subsequently, the pedestrian avoidance probability is generated again and compared with the first probability. The sweeper's action strategy is adjusted according to the difference between the two probabilities. For example, if the probability generated for the second time is significantly lower, it proves that the pedestrian has noticed the sweeper and is ready to avoid it; if the second probability has no obvious change or even increases, the system will take more conservative detours or other avoidance measures.

[0014] In a preferred example, the present application may be further configured as follows: generating a garbage cleaning control instruction according to the obstacle handling strategy and the garbage image to be cleaned, and sending the garbage cleaning control instruction to a corresponding control terminal, specifically including: Acquire lawn humidity data in real time according to the cleaning path information, and acquire initial cleaning power from the garbage cleaning control instruction; The power variation trend is calculated according to the lawn humidity data, the initial cleaning power is adjusted according to the power variation trend, and the garbage cleaning control instruction is updated according to the adjustment result.

[0015] By adopting the above technical solution, the lawn humidity data in the cleaning path information is obtained in real time, and the power change trend is calculated according to the humidity data, so as to adjust the initial cleaning power. When the lawn humidity is low, the system can automatically reduce the initial cleaning power to avoid dust caused by excessive power. When the lawn humidity is high, the initial cleaning power is appropriately increased to ensure the cleaning efficiency. This dynamic adjustment mechanism can not only optimize the cleaning effect according to different humidity environments, but also significantly reduce dust during the cleaning process and improve the overall cleaning quality.

[0016] The second object of the invention is achieved by the following technical solutions: A lawn cleaning sweeper control device, the lawn cleaning sweeper control device comprising: A path planning module is used to obtain cleaning task information and the current position of the cleaning vehicle, obtain cleaning path information from the cleaning task information, obtain a cleaning start position from the cleaning path information, and trigger a cleaning start instruction according to the cleaning start position and the current position of the cleaning vehicle; A path recognition module is used to obtain the image information to be cleaned of the cleaning path information in real time, recognize the image information to be cleaned, and obtain an obstacle image and a garbage image to be cleaned; An obstacle processing module, used to identify the obstacle image, generate an obstacle type according to the identification result, and generate an obstacle processing strategy according to the obstacle type; The cleaning control module is used to generate a garbage cleaning control instruction according to the obstacle handling strategy and the garbage image to be cleaned, and send the garbage cleaning control instruction to a corresponding control terminal.

[0017] By adopting the above technical solution, by acquiring the cleaning task information and the current position of the cleaning vehicle, combined with the cleaning starting point position in the cleaning path information, the cleaning vehicle can automatically trigger the cleaning start command, thereby realizing unmanned operation, greatly reducing labor costs, and improving the efficiency of the cleaning work; the image information of the area to be cleaned in the cleaning path information is acquired in real time and identified, which can not only quickly distinguish between obstacle images and images of garbage to be cleaned, but also generate corresponding obstacle handling strategies according to the type of obstacles, thereby enhancing the adaptability of the cleaning vehicle to complex environments, and thus effectively ensuring the safety of the cleaning operation; at the same time, the garbage cleaning control command generated based on the obstacle handling strategy and the image of the garbage to be cleaned is sent to the control terminal, so that the cleaning vehicle can dynamically adjust the cleaning mode according to the actual situation, avoid work interruption caused by obstacles, and improve the cleaning quality and efficiency.

[0018] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the control method of the lawn cleaning sweeper are implemented.

[0019] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned lawn sweeper control method are implemented.

[0020] In summary, the present application includes at least one of the following beneficial technical effects: 1. By obtaining the cleaning task information and the current position of the cleaning vehicle, and triggering the cleaning start command according to the cleaning starting position, the cleaning task is automatically started, which improves the start efficiency of the cleaning operation; 2. By acquiring the image information to be cleaned in the cleaning path information in real time and identifying the obstacle image and the garbage image to be cleaned, the cleaning vehicle's perception and response speed to environmental changes during operation are improved, thereby enhancing the safety and efficiency of the cleaning operation; 3. Generate different processing strategies according to the obstacle type, including foreign object crossing instructions and foreign object detour instructions, which effectively avoids the collision between the sweeper and the obstacle and ensures the operation safety and cleaning continuity of the sweeper in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a flow chart of a method for controlling a lawn cleaning vehicle in an embodiment of the present application; Figure 2 is a flowchart for implementing step S30 of the method for controlling a lawn cleaning sweeper in one embodiment of the present application; Figure 3 is another implementation flow chart of step S30 of the method for controlling a lawn cleaning sweeper in one embodiment of the present application; Figure 4 This is a flowchart for implementing step S322 of the method for controlling a lawn cleaning sweeper in one embodiment of the present application; Figure 5 This is a flowchart for implementing step S40 of the method for controlling a lawn cleaning sweeper in one embodiment of the present application; Figure 6 This is a principle block diagram of a control system for a lawn cleaning sweeper in one embodiment of the present application; Figure 7 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The present application is further described in detail below in conjunction with the accompanying drawings.

[0023] In one embodiment, if Figure 1 As shown, the present application discloses a control method for a lawn cleaning sweeper, which specifically includes the following steps: S10: Obtain cleaning task information and the current position of the cleaning vehicle, obtain cleaning path information from the cleaning task information, obtain the cleaning starting position from the cleaning path information, and trigger a cleaning start instruction according to the cleaning starting position and the current position of the cleaning vehicle.

[0024] In this embodiment, the cleaning task information refers to information recording the location of the lawn that the cleaning vehicle specifically cleans.

[0025] Specifically, when it is necessary to start cleaning the lawn, for example, when a certain lawn needs to be cleaned regularly, the cleaning task information is triggered according to the location of the lawn that needs to be cleaned, and the cleaning task information carries pre-set cleaning path information, so that after the cleaning start instruction is triggered, the cleaning vehicle can be controlled to clean along the cleaning path information.

[0026] Furthermore, after obtaining the cleaning task information, the current position of the cleaning vehicle is obtained as the current position of the cleaning vehicle, and the starting position of cleaning the lawn is obtained from the cleaning path information as the cleaning start position, and the cleaning start instruction is triggered according to the cleaning start position and the current position of the cleaning vehicle, and the cleaning vehicle is controlled to move from the current position to the cleaning start position before starting cleaning. Optionally, if the cleaning vehicle is parked at a fixed position, such as a fixed charging position, each time it is on standby, it can be determined whether the cleaning vehicle is at a fixed charging position. If so, the cleaning start position can be the current position of the cleaning vehicle.

[0027] S20: Acquire the image information of the cleaning path information in real time, identify the image information to be cleaned, and obtain the obstacle image and the garbage image to be cleaned.

[0028] Specifically, when the sweeper starts cleaning, it moves forward along the cleaning path information and captures the image information to be cleaned in real time, that is, the image of the lawn in front of the sweeper's path, and identifies the image to be cleaned to obtain images of obstacles that the sweeper cannot clean and images of garbage to be cleaned on the lawn, as the obstacle images and images of garbage to be cleaned.

[0029] S30: Identify the obstacle image, generate the obstacle type according to the identification result, and generate the obstacle handling strategy according to the obstacle type.

[0030] Specifically, the type of the identified obstacle image is identified to obtain the corresponding obstacle type, and corresponding processing strategies are generated according to different types of obstacles, including replanning the path around the obstacle, crossing over the obstacle, or other processing methods.

[0031] S40: Generate a garbage cleaning control instruction according to the obstacle handling strategy and the image of the garbage to be cleaned, and send the garbage cleaning control instruction to the corresponding control terminal.

[0032] Specifically, after generating an obstacle handling strategy and an image of garbage to be cleaned, a corresponding cleaning control instruction is generated and sent to the control terminal of the sweeper to control the sweeper to clean the garbage according to the position corresponding to the image of garbage to be cleaned during the movement, and when encountering an obstacle, take corresponding measures according to the obstacle handling strategy.

[0033] In this embodiment, by acquiring the cleaning task information and the current position of the cleaning vehicle, combined with the cleaning starting point position in the cleaning path information, the cleaning vehicle can automatically trigger the cleaning start command, thereby realizing unmanned operation, greatly reducing labor costs, and improving the efficiency of the cleaning work; the image information of the area to be cleaned in the cleaning path information is acquired in real time and identified, which can not only quickly distinguish between obstacle images and images of garbage to be cleaned, but also generate corresponding obstacle handling strategies according to the type of obstacles, thereby enhancing the adaptability of the cleaning vehicle to complex environments, and thus effectively ensuring the safety of the cleaning operation; at the same time, the garbage cleaning control instructions generated based on the obstacle handling strategy and the image of the garbage to be cleaned are sent to the control terminal, so that the cleaning vehicle can dynamically adjust the cleaning mode according to the actual situation, avoid work interruptions caused by obstacles, and improve the cleaning quality and efficiency.

[0034] In one embodiment, the obstacle type includes abnormal object information, such as Figure 2 As shown, in step S30, the obstacle image is identified, the obstacle type is generated according to the identification result, and the obstacle handling strategy is generated according to the obstacle type, which specifically includes: S311: Obtain the foreign object size information corresponding to each abnormal object information, and determine the foreign object weight range according to the foreign object size information.

[0035] Specifically, the type of the foreign object is obtained from the abnormal object information, such as protruding stones, large garbage and other types, and the foreign object size information is calculated according to the size in the corresponding obstacle image, and the corresponding foreign object weight range is estimated in combination with the type of the foreign object.

[0036] S312: Generate a foreign object crossing instruction and / or a foreign object bypassing instruction according to the foreign object weight range and foreign object size information, and generate an obstacle handling strategy according to the foreign object crossing instruction and / or the foreign object bypassing instruction.

[0037] Specifically, the weight range and size information of the foreign object are used to determine whether the sweeper can cross over the surface of the foreign object. If so, the foreign object crossing instruction is triggered; if not, the foreign object bypass instruction is triggered, and then the obstacle handling strategy is generated. For example, if the obstacle is a protruding stone with a large surface angle, and the sweeper cannot cross it, the obstacle bypass instruction is triggered to bypass the obstacle and return to the cleaning path.

[0038] In one embodiment, the obstacle type includes pedestrian image information, such as Figure 3 As shown, in step S30, the obstacle image is identified, the obstacle type is generated according to the identification result, and the obstacle handling strategy is generated according to the obstacle type, which specifically includes: S321: Obtain pedestrian distance information and a corresponding pedestrian status image corresponding to each pedestrian from the pedestrian image information.

[0039] In this embodiment, the pedestrian distance information refers to the distance between each pedestrian in the pedestrian image information and the cleaning vehicle. The pedestrian state image refers to an image recording the current action posture of the pedestrian.

[0040] Specifically, if the obstacle is determined to be a pedestrian, that is, the pedestrian image information is obtained, then it is determined whether the pedestrian has noticed that the sweeper is sweeping. The distance between each pedestrian and the sweeper is obtained by the position of each pedestrian in the pedestrian image information, as the pedestrian distance information, and the pedestrian's action in the image is used as the pedestrian status image.

[0041] S322: Analyze the pedestrian distance information and the pedestrian status image to obtain the pedestrian avoidance probability, and generate an obstacle handling strategy based on the pedestrian avoidance probability.

[0042] Specifically, according to the pedestrian distance information, the pedestrian currently blocking the path of the sweeper is screened out, and the pedestrian state image of the pedestrian is obtained, and the pedestrian state image is identified to obtain the pedestrian's current action, and then the pedestrian avoidance probability is obtained. For example, if the pedestrian passes through the path, the pedestrian avoidance probability is definitely avoided. If the pedestrian stays on the path, or moves toward the sweeper along the cleaning path, the pedestrian avoidance probability is difficult to avoid. Then, the obstacle handling strategy is triggered according to the pedestrian avoidance probability.

[0043] In one embodiment, if Figure 4 As shown, in step S322, the pedestrian distance information and the pedestrian status image are analyzed to obtain the pedestrian avoidance probability, and the obstacle handling strategy is generated according to the pedestrian avoidance probability, which specifically includes: S3221: Filter pedestrian status images corresponding to distances lower than a preset value according to the pedestrian distance information as pedestrian posture data to be analyzed.

[0044] Specifically, a pedestrian status image whose distance information of the pedestrian is lower than a preset value is obtained by screening, and the current motion posture of the pedestrian is identified from the pedestrian status image as the pedestrian posture data.

[0045] S3222: Obtain pedestrian gaze data from each pedestrian posture data to be analyzed, obtain the pedestrian's gaze target based on the pedestrian gaze data, and generate a pedestrian avoidance probability based on the pedestrian's gaze target.

[0046] Specifically, the gaze direction of each pedestrian is identified from each pedestrian posture data as the pedestrian gaze data, and then the target of the pedestrian's gaze is determined, such as a mobile phone, a street sweeper, or other scenery, as the pedestrian's gaze target. Furthermore, if the pedestrian's gaze target does not include the street sweeper and the pedestrian stays on the sweeping path or moves toward the street sweeper along the sweeping path, the probability of avoiding the pedestrian who is difficult to avoid is generated.

[0047] S3223: triggering a cleaning reminder sound according to the pedestrian avoidance probability, and regenerating the pedestrian avoidance probability, and generating an obstacle handling strategy according to the regenerated pedestrian avoidance probability.

[0048] Specifically, if the generated pedestrian avoidance probability is difficult to avoid, the cleaning reminder sound is triggered to prompt the pedestrian to avoid. After the cleaning reminder sound is triggered, the pedestrian avoidance probability of the pedestrian is judged again. If the pedestrian avoids the sweeper or moves away from the sweeper's path, the obstacle handling strategy ends. If the pedestrian avoidance probability of the pedestrian is still difficult to avoid, a detour corresponding obstacle handling strategy is generated.

[0049] In one embodiment, if Figure 5 As shown, in step S40, a garbage cleaning control instruction is generated according to the obstacle handling strategy and the garbage image to be cleaned, and the garbage cleaning control instruction is sent to the corresponding control terminal, specifically including: S41: Acquire lawn humidity data in real time according to the cleaning path information, and obtain the initial cleaning power from the garbage cleaning control instruction.

[0050] Specifically, by pre-installing a humidity sensor on the bottom of the sweeper, when the sweeper is sweeping along the sweeping path, the corresponding lawn humidity data is obtained in real time, and the operating power of the current sweeper's cleaning device is obtained as the initial cleaning power.

[0051] S42: Calculate the power change trend according to the lawn humidity data, adjust the initial cleaning power according to the power change trend, and update the garbage cleaning control instruction according to the adjustment result.

[0052] Specifically, based on the lawn humidity data, the operating power adjustment of the cleaning device is calculated in real time. That is, when the lawn humidity is low, if the cleaning power is too large, it will cause dust, and the operating power needs to be lowered accordingly. Then, the power change trend is calculated based on the lawn humidity data, and the initial cleaning power is adjusted in real time based on the power change trend, and the garbage cleaning control instructions are updated according to the adjustment results.

[0053] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0054] In one embodiment, a lawn cleaning sweeper control device is provided, and the lawn cleaning sweeper control device corresponds to the lawn cleaning sweeper control method in the above embodiment. Figure 6 As shown, the lawn cleaning sweeper control device includes a path planning module, a path recognition module, an obstacle processing module and a cleaning control module. The detailed description of each functional module is as follows: The path planning module is used to obtain the cleaning task information and the current position of the cleaning vehicle, obtain the cleaning path information from the cleaning task information, obtain the cleaning start position from the cleaning path information, and trigger the cleaning start instruction according to the cleaning start position and the current position of the cleaning vehicle; A path recognition module is used to obtain the image information to be cleaned of the cleaning path information in real time, recognize the image information to be cleaned, and obtain the obstacle image and the garbage image to be cleaned; The obstacle processing module is used to identify the obstacle image, generate the obstacle type according to the identification result, and generate the obstacle processing strategy according to the obstacle type; The cleaning control module is used to generate garbage cleaning control instructions according to the obstacle handling strategy and the garbage image to be cleaned, and send the garbage cleaning control instructions to the corresponding control terminal.

[0055] Optionally, the obstacle type includes abnormal object information, and the obstacle processing module includes: The foreign object identification submodule is used to obtain the foreign object size information corresponding to each abnormal object information, and determine the weight range of the foreign object according to the foreign object size information; The first obstacle handling submodule is used to generate a foreign object crossing instruction and / or a foreign object bypassing instruction according to the foreign object weight range and foreign object size information, and to generate an obstacle handling strategy according to the foreign object crossing instruction and / or the foreign object bypassing instruction.

[0056] Optionally, the obstacle type includes pedestrian image information, and the obstacle processing module includes: The pedestrian recognition submodule is used to obtain the pedestrian distance information and the corresponding pedestrian status image of each pedestrian from the pedestrian image information; The second obstacle handling submodule is used to analyze the pedestrian distance information and the pedestrian status image to obtain the pedestrian avoidance probability, and generate an obstacle handling strategy according to the pedestrian avoidance probability.

[0057] Optionally, the second obstacle processing submodule includes: A pedestrian posture recognition unit, used to select pedestrian status images corresponding to a distance lower than a preset value according to the pedestrian distance information as pedestrian posture data to be analyzed; A pedestrian gaze recognition unit is used to obtain pedestrian gaze data from each pedestrian posture data to be analyzed, obtain the pedestrian gaze target according to the pedestrian gaze data, and generate the pedestrian avoidance probability according to the pedestrian gaze target; The avoidance prompt unit is used to trigger the cleaning prompt sound according to the pedestrian avoidance probability, and regenerate the pedestrian avoidance probability, and generate an obstacle handling strategy according to the regenerated pedestrian avoidance probability.

[0058] Optionally, the cleaning control module includes: The humidity recognition submodule is used to obtain lawn humidity data in real time according to the cleaning path information and obtain the initial cleaning power from the garbage cleaning control instruction; The power regulation submodule is used to calculate the power change trend according to the lawn humidity data, adjust the initial cleaning power according to the power change trend, and update the garbage cleaning control instruction according to the adjustment result.

[0059] The specific definition of the lawn cleaning sweeper control device can be found in the definition of the lawn cleaning sweeper control method mentioned above, which will not be repeated here. Each module in the above lawn cleaning sweeper control device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0060] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a control method for a lawn sweeper is implemented.

[0061] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Obtain cleaning task information and the current position of the cleaning vehicle, obtain cleaning path information from the cleaning task information, obtain the cleaning start position from the cleaning path information, and trigger the cleaning start instruction according to the cleaning start position and the current position of the cleaning vehicle; Acquire the image information to be cleaned of the cleaning path information in real time, identify the image information to be cleaned, and obtain the obstacle image and the garbage image to be cleaned; Identify the obstacle image, generate the obstacle type according to the identification result, and generate the obstacle handling strategy according to the obstacle type; A garbage cleaning control instruction is generated according to the obstacle handling strategy and the garbage image to be cleaned, and the garbage cleaning control instruction is sent to the corresponding control terminal.

[0062] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Obtain cleaning task information and the current position of the cleaning vehicle, obtain cleaning path information from the cleaning task information, obtain the cleaning start position from the cleaning path information, and trigger the cleaning start instruction according to the cleaning start position and the current position of the cleaning vehicle; Acquire the image information to be cleaned of the cleaning path information in real time, identify the image information to be cleaned, and obtain the obstacle image and the garbage image to be cleaned; Identify the obstacle image, generate the obstacle type according to the identification result, and generate the obstacle handling strategy according to the obstacle type; A garbage cleaning control instruction is generated according to the obstacle handling strategy and the garbage image to be cleaned, and the garbage cleaning control instruction is sent to the corresponding control terminal.

[0063] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0064] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0065] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for controlling a lawn sweeper, characterized in that: The lawn cleaning sweeper control method comprises: Acquire cleaning task information and the current position of the cleaning vehicle, acquire cleaning path information from the cleaning task information, acquire the cleaning start position from the cleaning path information, and trigger a cleaning start instruction according to the cleaning start position and the current position of the cleaning vehicle; Acquire the image information to be cleaned of the cleaning path information in real time, identify the image information to be cleaned, and obtain the obstacle image and the garbage image to be cleaned; Recognize the obstacle image, generate an obstacle type according to the recognition result, and generate an obstacle handling strategy according to the obstacle type; A garbage cleaning control instruction is generated according to the obstacle handling strategy and the garbage image to be cleaned, and the garbage cleaning control instruction is sent to a corresponding control terminal.

2. The lawn sweeper control method according to claim 1, characterized in that: The obstacle type includes abnormal object information, the obstacle image is identified, the obstacle type is generated according to the identification result, and the obstacle handling strategy is generated according to the obstacle type, specifically including: Acquire the foreign object size information corresponding to each of the abnormal object information, and determine the weight range of the foreign object according to the foreign object size information; A foreign object crossing instruction and / or a foreign object bypassing instruction is generated according to the foreign object weight range and the foreign object size information, and the obstacle handling strategy is generated according to the foreign object crossing instruction and / or the foreign object bypassing instruction.

3. The lawn sweeper control method according to claim 1, characterized in that: The obstacle type includes pedestrian image information, and the obstacle image is identified, the obstacle type is generated according to the identification result, and the obstacle handling strategy is generated according to the obstacle type, which specifically includes: Obtaining pedestrian distance information and a corresponding pedestrian status image corresponding to each pedestrian from the pedestrian image information; The pedestrian avoidance probability is obtained by analyzing the pedestrian distance information and the pedestrian status image, and the obstacle handling strategy is generated according to the pedestrian avoidance probability.

4. The lawn cleaning vehicle control method according to claim 3, characterized in that: The analyzing the pedestrian distance information and the pedestrian status image to obtain the pedestrian avoidance probability, and generating the obstacle handling strategy according to the pedestrian avoidance probability, specifically includes: Filter the pedestrian state images corresponding to the distances below a preset value according to the pedestrian distance information as the pedestrian posture data to be analyzed; Acquire pedestrian gaze data from each of the pedestrian posture data to be analyzed, acquire a pedestrian gaze target according to the pedestrian gaze data, and generate the pedestrian avoidance probability according to the pedestrian gaze target; A cleaning prompt sound is triggered according to the pedestrian avoidance probability, and the pedestrian avoidance probability is generated again, and the obstacle handling strategy is generated according to the regenerated pedestrian avoidance probability.

5. The lawn sweeper control method according to claim 1, characterized in that: The generating of a garbage cleaning control instruction according to the obstacle handling strategy and the garbage image to be cleaned, and sending the garbage cleaning control instruction to a corresponding control terminal specifically includes: Acquire lawn humidity data in real time according to the cleaning path information, and acquire initial cleaning power from the garbage cleaning control instruction; The power variation trend is calculated according to the lawn humidity data, the initial cleaning power is adjusted according to the power variation trend, and the garbage cleaning control instruction is updated according to the adjustment result.

6. A lawn sweeper control device, characterized in that: The lawn cleaning sweeper control device comprises: A path planning module is used to obtain cleaning task information and the current position of the cleaning vehicle, obtain cleaning path information from the cleaning task information, obtain a cleaning start position from the cleaning path information, and trigger a cleaning start instruction according to the cleaning start position and the current position of the cleaning vehicle; A path recognition module is used to obtain the image information to be cleaned of the cleaning path information in real time, recognize the image information to be cleaned, and obtain an obstacle image and a garbage image to be cleaned; An obstacle processing module, used to identify the obstacle image, generate an obstacle type according to the identification result, and generate an obstacle processing strategy according to the obstacle type; The cleaning control module is used to generate a garbage cleaning control instruction according to the obstacle handling strategy and the garbage image to be cleaned, and send the garbage cleaning control instruction to a corresponding control terminal.

7. The lawn sweeper control device according to claim 6, characterized in that: The obstacle type includes abnormal object information, and the obstacle processing module includes: A foreign object identification submodule, used to obtain the foreign object size information corresponding to each of the abnormal object information, and determine the weight range of the foreign object according to the foreign object size information; The first obstacle handling submodule is used to generate a foreign object crossing instruction and / or a foreign object bypassing instruction according to the foreign object weight range and the foreign object size information, and to generate the obstacle handling strategy according to the foreign object crossing instruction and / or the foreign object bypassing instruction.

8. The lawn sweeper control device according to claim 6, characterized in that: The obstacle type includes pedestrian image information, and the obstacle processing module includes: A pedestrian recognition submodule, used to obtain pedestrian distance information and a corresponding pedestrian status image corresponding to each pedestrian from the pedestrian image information; The second obstacle handling submodule is used to analyze the pedestrian distance information and the pedestrian status image to obtain the pedestrian avoidance probability, and generate the obstacle handling strategy according to the pedestrian avoidance probability.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the lawn cleaning sweeper control method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the lawn sweeper control method according to any one of claims 1 to 5 are implemented.

Images