Cleaning operation method and device, electronic equipment and storage medium

Abstract

The invention discloses a cleaning operation method and device, electronic equipment and a storage medium, and the method comprises the steps: determining first junk information in a current region in response to any one of road end sensing results and vehicle end sensing results; integrating and processing the first junk information to obtain combined second junk information; and in response to the second garbage information, uploading decision information is generated to control the sweeper. According to the invention, the intelligent operation of pre-judgment and real-time adaptation of the motor sweeper is realized, the sweeping quality and the operation efficiency are improved, the energy and equipment consumption is reduced, and the refined environmental sanitation operation requirements are met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a cleaning operation method and device, an electronic device and a storage medium. BACKGROUND

[0002] The automatic driving cleaning vehicle, as an unmanned sanitation equipment, can realize autonomous obstacle avoidance, road cleaning and remote monitoring through the collaborative operation of the automatic driving system and the AI cloud platform, and is mainly applied to the daily cleaning operation of urban roads, squares and other public places, thereby effectively reducing labor costs and improving operation safety.

[0003] However, in the scenario of urban trunk roads and the like, the cleaning vehicle operation section is long, and the garbage accumulation amount and the garbage type in different areas are significantly different. If a single operation mode such as washing and sweeping or pure sweeping is used throughout the entire section, it is difficult to adapt to the complex road cleaning requirements. Meanwhile, due to the limitations of the hardware conditions such as the water tank capacity and the endurance of the vehicle itself, if a fixed and unchanged operation mode, cleaning intensity and cleaning direction are used, two problems are likely to occur: one is the invalid consumption of energy (water, electricity) and the sweeping device, resulting in resource waste; the other is that some heavily polluted areas are not cleaned thoroughly, affecting the cleaning quality and failing to meet the requirements of fine sanitation operation. SUMMARY

[0004] The embodiments of the present application provide a cleaning operation method, device, electronic device and storage medium to make the road operation more intelligent.

[0005] The embodiments of the present application adopt the following technical solutions:

[0006] In a first aspect, the embodiments of the present application provide a cleaning operation method, wherein the method comprises:

[0007] In response to any one of the road end and vehicle end perception results, determining first garbage information in a current area;

[0008] integrating and processing the first garbage information to obtain second garbage information after merging processing; and

[0009] In response to the second garbage information, generating upper-mounted decision information to control the cleaning vehicle.

[0010] In some embodiments, the determination of the first garbage information in the current area in response to any one of the road end and vehicle end perception results comprises:

[0011] In the case where both the road end and vehicle end perception results exist, the road end perception result is used preferentially; in the case where only one kind of perception result exists, the only existing perception result is used;

[0012] Based on the perception results, the garbage attribute information in each grid cell of the current area is determined as the first garbage information in the current perception area. The garbage attribute information includes at least the garbage quantity, garbage type, and garbage location.

[0013] Wherein, the current sensing area is different in the vehicle-side sensing result and the road-side sensing result. If the road-side sensing result is used first, the non-overlapping part of the vehicle-side sensing area is supplemented by the vehicle-side sensing result, and the overlapping part is based on the road-side sensing result.

[0014] In some embodiments, the roadside includes a roadside camera, and the vehicle side includes a front-end camera and a rear-end camera, and image information is acquired through the roadside camera, the front-end camera, and the rear-end camera;

[0015] The grid is obtained in the following manner:

[0016] Based on BEV, grid information is obtained in the vehicle-end coordinate system or the road-end coordinate system, and the grid information is uniform in the local area and non-uniform in the global area;

[0017] The image information is used to assist in calibrating the positional accuracy of the BEV grid, ensuring that the grid can accurately carry the garbage attribute information in the first garbage information.

[0018] In some embodiments, the garbage attribute information specifically includes:

[0019] Waste type: Assign corresponding waste serial numbers according to category, which serve as the basis for switching operation modes;

[0020] Garbage quantity: 0 indicates empty, 1 indicates a small amount, 2 indicates a large amount;

[0021] Waste location: Based on the unified and transformed vehicle coordinate system, determine whether the waste is located to the left or right of the vehicle's centerline;

[0022] The conversion rule between the vehicle-side coordinate system and the roadside coordinate system is as follows: based on the real-time positioning data of the sweeper, the coordinates of the garbage location in the roadside coordinate system are mapped to the vehicle-side coordinate system.

[0023] In some embodiments, generating upper structure decision information to control the sweeper in response to the second waste information includes:

[0024] Based on the type of waste and the number of grid cells occupied by the waste in the second waste information, a corresponding operation mode is generated;

[0025] The corresponding workload is determined based on the number of grid cells occupied by the waste and the type of waste.

[0026] Execute the job according to the default job direction or a custom job direction;

[0027] Determine the vehicle speed based on the amount of garbage;

[0028] The aforementioned work mode, work intensity, work direction, and vehicle speed are used as basic equipment decision information;

[0029] Configure the work mode switching interval and work direction switching interval to generate complete upper equipment decision information.

[0030] In some embodiments, it also includes:

[0031] Configure the upper sweeping speed according to the default mode, which is associated with the matching relationship between the work intensity, work mode and sweeping speed;

[0032] When the sweeper turns around, the sweeping disc speed should be reduced to the lowest operating value, and the vehicle speed should not be lower than 8km / h;

[0033] When the sweeper is waiting at a red light, the work intensity will be uniformly adjusted to the default intensity to maintain the current work mode;

[0034] When the sweeper is working along the edge, the side to be swept is determined according to the location of the garbage: when sweeping along the left edge, the right sweeping disc and water spray bar are turned off; when sweeping along the right edge, the left sweeping disc and water spray bar are turned off.

[0035] In some embodiments, the process of integrating the first garbage information to obtain the merged second garbage information includes:

[0036] In response to the switching results of the sweeper's operating mode, operating direction and operating speed, the first garbage information of multiple grids is integrated, and the garbage category, garbage quantity and garbage location information of overlapping or related grids are merged into the second garbage information of the same grid.

[0037] In response to the second garbage information, a switching instruction for the operation mode, operation intensity, operation direction, and vehicle speed is generated and issued, and the switching instruction conforms to the preset configuration rules.

[0038] Secondly, embodiments of this application also provide a cleaning operation device, wherein the device includes:

[0039] The first processing module is used to determine the first piece of garbage information in the current area in response to any one of the perception results from the roadside and the vehicle-side.

[0040] The second processing module is used to integrate and process the first garbage information to obtain the merged second garbage information; and

[0041] The third processing module is used to generate upper-level decision information to control the sweeper in response to the second garbage information.

[0042] Thirdly, embodiments of this application also provide an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the above-described method.

[0043] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the above-described method.

[0044] The at least one technical solution adopted in this application embodiment can achieve the following beneficial effects: Responding to either the roadside or vehicle-side perception results, a first piece of garbage information in the current area is determined. This first piece of garbage information serves as initial garbage information and requires further processing and merging. The first piece of garbage information is integrated to obtain a merged second piece of garbage information. This second piece of garbage information serves as the integrated garbage information for the road, thereby making road operations more targeted and improving the level of intelligence. Finally, in response to the second piece of garbage information, upper-mounted decision information is generated to control the sweeper, realizing the fusion of information fed back from roadside and vehicle-side vision devices. This aims to solve the problem that the single operation mode in the prior art cannot adapt to complex scenarios such as urban main roads, easily causing resource waste or incomplete cleaning, and to achieve intelligent operation of the sweeper with "predictive action and real-time adaptation," improving cleaning quality and operational efficiency, reducing energy and equipment consumption, and meeting the needs of refined sanitation operations. Attached Figure Description

[0045] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0046] Figure 1 This is a schematic diagram illustrating the application scenario of the cleaning operation method in the embodiments of this application;

[0047] Figure 2 This is a flowchart illustrating the cleaning operation method in an embodiment of this application;

[0048] Figure 3 This is a schematic diagram illustrating the implementation principle of the cleaning operation method in the embodiments of this application;

[0049] Figure 4 This is a schematic diagram showing the position of the sweeper in the grid in the sweeping operation method of this application embodiment;

[0050] Figure 5 This is a schematic diagram of the grid division of the sweeping vehicle under different cameras in the sweeping operation method of this application embodiment;

[0051] Figure 6 This is a schematic diagram of the cleaning device in the embodiments of this application;

[0052] Figure 7 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0054] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0055] like Figure 1 As shown, it mainly includes vehicle-side and road-side components. The identification scheme adopted is road debris identification and road surface identification. The sensors used for identification include: front and rear cameras of the vehicle and road-side cameras.

[0056] By collecting information through the vehicle's sensors, the presence of litter can be determined. The superstructure switches operating modes and intensity based on the litter information (litter quantity and type). Simultaneously, cloud-based intervention can be used to detect the litter situation in the current area, allowing the superstructure to switch operating modes, intensity, and sweeping speed based on the litter information (litter quantity, type, and location). Based on the target IOU recognition results, the superstructure switches operating modes, intensity, sweeping speed, and direction based on the litter information (litter quantity, location, and type), thereby controlling the sweeper's speed, sweeping discs, and water spray.

[0057] This application provides a cleaning operation method, such as... Figure 2 The diagram shows a cleaning operation method flowchart in an embodiment of this application. The method includes at least the following steps S210 to S230:

[0058] Step S210: In response to either the roadside or vehicle-side perception results, determine the first piece of garbage information in the current area.

[0059] Based on roadside and vehicle-mounted visual sensors, roadside and vehicle-mounted perception results can be acquired, and the garbage information in the current area can be determined. This "first garbage information" can be understood as information on all garbage types, quantities, and locations in each grid cell of the visual image grid within the perception results. This "first garbage information" needs to be as comprehensive as possible.

[0060] Step S220: Integrate and process the first garbage information to obtain the merged second garbage information.

[0061] By integrating the first type of waste information, a second type of waste information can be obtained. This second type of waste information is the result of grid information integration and also includes information such as the type, quantity, and location of the waste. It is important to note that the second type of waste information, as the result of identifying the location, type, and quantity of road waste, can be used to determine the timing, mode, and intensity of the sweeper's sweeping operation, thereby significantly improving the sweeper's intelligent, accurate, energy-saving, and environmentally friendly efficiency.

[0062] Step S230: In response to the second garbage information, generate upper structure decision information to control the sweeper.

[0063] Based on single or multiple sets of information such as garbage type, quantity, and location from the second garbage information, upper-level decision information is generated to control the sweeper. It can be understood that the upper-level decision information for autonomous driving refers to the set of instructions generated by the autonomous driving system after perceiving the environment, based on real-time data and prediction results, to guide vehicle behavior, including core elements such as path planning, motion planning, and behavioral decision-making.

[0064] The above method utilizes roadside and vehicle-side visual data to determine the most suitable sweeping operation for the vehicle. Based on existing visual equipment and sample data, a garbage recognition model is trained. A reasonable grid division scheme can accurately identify road garbage. Finally, by combining the existing functions of the vehicle sweeping mechanism and the road garbage situation, the system achieves maximum intelligence, energy saving, and efficiency.

[0065] Adopting a reasonable grid division scheme can improve the accuracy of spatial positioning. For example, after grid processing, the garbage attributes (type, quantity, location) can be converted into a quantifiable "grid occupancy" indicator, making decision-making logic (such as "switch to high-intensity operation if a large amount of garbage occupies more than 3 grids" or "operate along the left edge if there is garbage in the left grid") easier to implement. At the same time, it can adapt to the dynamic adjustment of the sweeper in scenarios such as turning around, following the edge, and waiting at red lights, ensuring that the decision-making instructions are accurately matched with the actual road conditions.

[0066] Unlike other technologies where sweepers use a full-process sweeping mode, which depletes the water tank quickly, wasting water and requiring refills, this method integrates and processes waste information to generate decision-making information for the sweeper, enabling it to perform corresponding sweeping operations in different areas.

[0067] Unlike other technologies where sweepers operate by sweeping continuously, causing dust to fly up along the roads and affecting urban health, the above method allows for control of the sweeper's brushes, water sprayers, and speed based on the type, quantity, and location of the garbage.

[0068] In one embodiment of this application, determining the first garbage information in the current area in response to either the roadside or vehicle-side sensing results includes: prioritizing the use of the roadside sensing result when both roadside and vehicle-side sensing results exist; using the existing sensing result when only one of them exists; determining garbage attribute information in each grid cell based on the sensing result as the first garbage information in the current sensing area, wherein the garbage attribute information includes at least the quantity, type, and location of garbage; if the current sensing area differs between the vehicle-side and roadside sensing results, and the roadside sensing result is prioritized, the non-overlapping portion of the vehicle-side sensing area is supplemented by the vehicle-side sensing result, and the overlapping portion is based on the roadside sensing result.

[0069] An arbitration mechanism combining roadside and vehicle-side data is employed. If roadside visual data is available, vehicle cleaning actions are prioritized based on this data; otherwise, actions are executed according to vehicle-side visual feedback. Alternatively, actions can be executed using the fusion of roadside and vehicle-side visual data. For instance, if roadside visual sensing equipment detects a large accumulation of fallen leaves around the main road, a sweeper is dispatched to the starting point of that area, activating sweeping and heavy-duty modes. The vehicle's front main camera determines the specific location of the fallen leaves, activating the corresponding left and right sweeping discs. After the sweeping operation, the road cleanliness rate is assessed using the vehicle's rear main camera and roadside visual data. Furthermore, during continuous operation, the vehicle's direction, mode, and intensity are adjusted in real-time based on the fusion of roadside and front camera visual data, and the vehicle speed is controlled according to the visual results to achieve energy efficiency and high performance.

[0070] It is understandable that the grid, as a unified data carrier, can quickly integrate the perception results of the roadside (global perspective) and the vehicle side (local perspective). That is, overlapping areas are covered according to priority and non-overlapping areas are supplemented. There is no need to process data format differences. It directly supports the efficient merging of first garbage information into second garbage information, and provides a real-time data foundation for the upper structure decision (operation mode, vehicle speed, etc.).

[0071] Considering that the roadside sensing results fall within a fixed area, these results can be communicated to the vehicle in advance. When the sweeper is about to reach the fixed location, the sweeping mode is activated beforehand; therefore, roadside data is prioritized. Furthermore, the vehicle's sensing results can be updated to the roadside sensing results in real time. However, the vehicle's sensing range is shorter than that of the roadside sensing results, and it is significantly affected by the sweeper's speed.

[0072] Preferably, the visual grid area also needs to be filtered. It is known that the width of each lane on urban roads is 3.5 m, and the width of each lane at intersections is 2.3-2.5 m; the width of each lane on trunk roads, including expressways, is 3.75 m, and the shoulder emergency stopping lane on expressways is 1.5-2.5 m; the width of each lane at expressway toll stations is 2.5 m, and oversized toll lanes are over 3.5 m wide. For example... Figure 4 As shown, the sweeper truck's camera identifies lane debris and filters it using a grid system based on the widest lane width of 3.75m. With both sweeping discs fully extended, the overall width of the sweeper truck is 3.15m. A 2.5m wide (5 grids) area is reserved on the left side and a 2m wide (4 grids) area on the right side, totaling 4.5m wide and 28m long, comprising 180 grids. Figure 4 As shown, the grid width is 0.5m, the grid length is 1m for the 12-21m (nearest) area, 2m for the 22-31m area, and 3m for the 32-40m (farthest) area.

[0073] like Figure 5 As shown, the grid information is integrated to switch operating modes. 162 grid information are integrated into one grid, outputting information on waste type and waste quantity. More preferably, it can also identify the operating direction and vehicle speed. The 162 grids are integrated into two horizontal areas, and the waste type, waste quantity, and waste location information are output.

[0074] In one embodiment of this application, the roadside includes a roadside camera, and the vehicle-side includes a front-end camera and a rear-end camera. Image information is acquired through the roadside camera, the front-end camera, and the rear-end camera. The grid is obtained in the following manner: grid information is acquired based on the BEV in either the vehicle-side coordinate system or the roadside coordinate system. The grid information is uniform in local areas and non-uniform in global areas. The image information is used to assist in calibrating the positional accuracy of the BEV grid to ensure that the grid can accurately carry the garbage attribute information in the first garbage information.

[0075] This paper presents a grid partitioning scheme for vehicle-mounted waste identification and labeling. Specifically, the network distribution is generally uniform in the image. Furthermore, when using a vehicle-mounted electric vehicle (BEV), the grid becomes uniform in local areas within the vehicle coordinate system, but non-uniform globally, with a step-like variation in grid size. Using images facilitates labeling and recognition. It can be understood that a BEV converts sensor data into a unified top-down view, providing more comprehensive environmental perception information.

[0076] It is understandable that the grid design based on local uniformity and global non-uniformity from the perspective of BEV can not only meet the local fine-grained needs of sweeper operation (such as uniform recognition within a single lane), but also reduce invalid calculations through global non-uniform division (such as enlarging the grid in open areas and densifying the grid in complex road sections). Combined with image information calibration, it can ensure that attributes such as the location and quantity of garbage are accurately bound to the grid, avoiding confusion of multi-source perception data.

[0077] In one embodiment of this application, the garbage attribute information specifically includes: garbage type: assigning corresponding garbage serial numbers according to category as the basis for switching operation modes; garbage quantity: 0 indicates empty, 1 indicates a small amount, and 2 indicates a large amount; garbage location: determining whether the garbage is located to the left or right of the vehicle's centerline based on the unified converted vehicle coordinate system; the conversion rule between the vehicle coordinate system and the roadside coordinate system is: using the real-time positioning data of the sweeper as a reference, mapping the garbage location coordinates in the roadside coordinate system to the vehicle coordinate system.

[0078] (1) Waste categories are collected, as exemplarily shown in Table 1:

[0079]

[0080] It is understood that the waste categories are merely examples and are not intended to limit the scope of protection in the embodiments of this application.

[0081] (2) Dynamic operation switching corresponding to the scene and waste category

[0082] When the vehicle's battery level is below 30%, the upper structure cannot be opened.

[0083] The sweeper's sweeping and washing modes can be used for soil, white garbage (plastic bags, etc.), stones, bricks and tiles, fruit peels / shells, packaging shells, and roads with sand, thick dust, and attached garbage.

[0084] The sweeper's pure sweeping mode: suitable for cleaning leaves, cigarette butts, and scraps of paper on surfaces free of sand and dust, only dry and non-sticky debris.

[0085] The sweeper's pure suction mode can be used when there is sewage, no sand or dust on the road, only a small amount of small pieces of garbage; or when there is standing water on the road but no garbage.

[0086] The sweeper's pure wash mode: can be used when there is only a small amount of dust on the road surface and no visible floating garbage.

[0087] It should be noted that when the outdoor temperature is below 0℃, the sweeper should use the pure sweeping and pure vacuuming modes.

[0088] It should be noted that when the weather is rainy: if it is light rain and there is no standing water on the road, the sweeping mode will be activated by default, regardless of the type of garbage. If it is moderate to heavy rain and there is standing water on the road, the sweeping mode will be activated by default, regardless of the type of garbage.

[0089] It should be noted that when working at night: the default mode is pure scanning, and the camera is heavily reliant on light sources such as vehicle headlights and streetlights, with a visibility distance of at least 20m.

[0090] It should be noted that in autumn, when there are many leaves on forest paths, the default is the pure sweep mode.

[0091] (3) Cleaning modes corresponding to different types of waste:

[0092] 0: No junk files; clean — pure scan

[0093] 1: Leaf; leaf — pure sweeping

[0094] 2: Soil; earth — to wash and sweep

[0095] 3: Dust; dust — pure washing

[0096] 4: Sewage; sewage — pure aspiration

[0097] 5: Paper scraps; paper — pure sweeping

[0098] 6: Cigarette butt; snipe — pure sweep

[0099] 7: Plastic bags; bags — for washing and cleaning

[0100] 8: Fruit peel, shell; peel —to wash, sweep

[0101] 9: Packaging boxes; — Pure scan

[0102] 10: Pebbles, bricks; cobblestone — pure sweeping

[0103] (4) Define a cell where the area of ​​garbage is less than 10% as a small amount and more than 10% as a large amount. Then the amount of garbage is: 0: empty; 1: little; 2: large.

[0104] (5) Determine the location of the garbage based on the vehicle coordinate system: it is located to the left or right of the vehicle's centerline. Similarly, the location of the garbage can also be determined using the roadside coordinate system.

[0105] In one embodiment of this application, the step of generating upper structure decision information to control the sweeper in response to the second garbage information includes: generating a corresponding operation mode based on the garbage type and the number of grid cells occupied by the garbage in the second garbage information; determining the corresponding operation intensity based on the number of grid cells occupied by the garbage and the garbage type; executing the operation according to the default operation direction or a custom operation direction; determining the vehicle speed based on the amount of garbage: 8-12 km / h for a small amount of garbage and 12-15 km / h for a large amount of garbage; using the operation mode, operation intensity, operation direction, and vehicle speed as basic upper structure decision information; configuring the operation mode switching interval and the operation direction switching interval to generate complete upper structure decision information.

[0106] Determine the operation mode based on the type of waste. For example, if this type of waste exists in a grid and there are at least two grids containing this type of waste, then this type of waste is considered to exist.

[0107] If the waste type is "soil 2" and / or "plastic bags 7" and / or "fruit peels and shells 8", then the operation mode is washing and sweeping mode.

[0108] If the waste type is "No Waste 0", "Leaves 1" and / or, "Paper Scraps 5" and / or, "Cigarette Butts 6" and / or, "Packaging Shells 9" and / or, "Pebble, Brick and Tile 10", then the operation mode is pure sweeping mode.

[0109] If the waste type is "sewage 4", then the operating mode is pure suction mode.

[0110] If the waste type is "Dust 3", then the operation mode is pure washing mode.

[0111] To determine the workload, you can usually use the amount of garbage as a guideline: use accurate information on at least three grid cells. The default workload for sweepers is "cleaning".

[0112] If the amount of garbage is 1 and occupies more than 3 grid cells, or if the amount of garbage is 2 and occupies less than 5 grid cells, the sweeper's operating intensity is the standard.

[0113] If the amount of garbage is 2 and occupies more than 5 grid cells, the sweeper's operating intensity is high.

[0114] Determine the direction of the operation: you can default to both sides; or you can use the left or right side.

[0115] Determine vehicle speed control: (based on the amount of garbage) 0: empty, 1: small amount, 2: large amount;

[0116] If the amount of garbage is 0, the vehicle speed shall not be less than 15km / h;

[0117] If the amount of garbage is 1, the vehicle speed should not exceed 10km / h;

[0118] If the amount of garbage is 2, the vehicle speed should not exceed 8 km / h.

[0119] In addition, switching restrictions need to be considered, such as a 60-second frequency for switching work intensity. The sweeper's work mode / direction switching modes include: changing the work mode or direction when the sweeper needs to stop. Furthermore, once the above instructions are issued, the mode cannot be changed again within a certain timeframe.

[0120] In one embodiment of this application, the method further includes: configuring the sweeping disc speed according to a default mode, wherein the default mode is associated with the matching relationship between the work intensity, the work mode and the sweeping disc speed; when the sweeper turns around, controlling the sweeping disc speed to be reduced to the minimum working condition value, and the vehicle speed is not lower than 8km / h; when the sweeper is waiting at a red light, uniformly adjusting the work intensity to the default intensity and maintaining the current work mode; when the sweeper is working along the edge, determining the side of the edge based on the location of the garbage: when working along the left edge, turning off the right sweeping disc and water spray bar, and when working along the right edge, turning off the left sweeping disc and water spray bar.

[0121] In addition to controlling the speed of the sweeper, it is also necessary to control the rotation speed of the sweeping disc according to the different scenarios in which the sweeper is located.

[0122] When the vehicle is making a U-turn, reduce the sweeping disc speed to the minimum (e.g., 40% of the speed).

[0123] When a vehicle is waiting at a red light, regardless of the current operation level (cleaning | standard | heavy), the operation intensity will be adjusted to cleaning.

[0124] Set default parameters to identify a large amount of garbage and switch to a higher intensity or mode:

[0125] Upper body operating intensity: Cleaning. Upper body operating mode: Sweeping only. Upper body sweeping disc speed: 80%.

[0126] When selecting the direction for edge-sweeping operations, and the upper garment's selected operation mode is: pure sweeping or washing sweeping. Left edge-sweeping operation: Turn off the right-side sweeping disc and water spray bar. Right edge-sweeping operation: Turn off the left-side sweeping disc and water spray bar.

[0127] In one embodiment of this application, the step of integrating and processing the first garbage information to obtain the merged second garbage information includes: in response to the switching results of the sweeper's operation mode, operation direction, and operation speed, integrating the first garbage information of multiple grids, merging the garbage category, garbage quantity, and garbage location information of overlapping or related grids into the second garbage information of the same grid; in response to the second garbage information, generating and issuing switching instructions for operation mode, operation intensity, operation direction, and speed, wherein the switching instructions conform to the preset configuration rules.

[0128] like Figure 3 As shown, the superstructure decision module responds to waste amounts a, b, and c (normal or small amount of waste) and adjusts the sweeper's operating mode, operating direction, operating intensity, and sweeping disc speed according to the corresponding mapping conditions to achieve superstructure control of the sweeper. When responding to waste amount d (large amount of waste), the superstructure decision module first controls the vehicle to reduce its speed, and then implements superstructure control. It can be understood that when there is a large amount of waste, the vehicle speed is appropriately reduced to ensure cleaning efficiency.

[0129] like Figure 5 The diagram illustrates a method for integrating grid information. The merged image grid information obtained from the vehicle's front-view camera includes grids A, B, and C, while the merged image grid information obtained from the vehicle's rear-view camera includes grids D, E, and F. Each merged image grid (A, B, C, D, E, F) contains a different number of grids; for example, A contains 378 grids, B contains 162 grids, etc. By switching operating modes, the 162 grid information is integrated into one grid, outputting waste category and waste quantity information. Preferably, the operating direction and vehicle speed can also be identified, integrating the 162 grids into two horizontal regions, outputting waste category, waste quantity, and waste location information.

[0130] This application embodiment also provides a cleaning operation device 600, such as... Figure 6 The diagram shows a structural schematic of a cleaning device 600 according to an embodiment of this application. The cleaning device 600 includes at least: a first processing module 610, a second processing module 620, and a third processing module 630, wherein:

[0131] In one embodiment of this application, the first processing module 610 is specifically used to: determine the first garbage information in the current area in response to either the roadside or vehicle-side perception results.

[0132] Based on roadside and vehicle-mounted visual sensors, roadside and vehicle-mounted perception results can be acquired, and the garbage information in the current area can be determined. This "first garbage information" can be understood as information on all garbage types, quantities, and locations in each grid cell of the visual image grid within the perception results. This "first garbage information" needs to be as comprehensive as possible.

[0133] In one embodiment of this application, the second processing module 620 is specifically used to: integrate and process the first garbage information to obtain the merged second garbage information.

[0134] By integrating the first type of waste information, a second type of waste information can be obtained. This second type of waste information is the result of grid information integration and also includes information such as the type, quantity, and location of the waste. It is important to note that the second type of waste information, as the result of identifying the location, type, and quantity of road waste, can be used to determine the timing, mode, and intensity of the sweeper's sweeping operation, thereby significantly improving the sweeper's intelligent, accurate, energy-saving, and environmentally friendly efficiency.

[0135] In one embodiment of this application, the third processing module 630 is specifically used to: generate upper-mount decision information to control the sweeper in response to the second garbage information.

[0136] In one embodiment of this application, upper structure decision information is generated based on single information or a combination of multiple sets of information such as garbage type, garbage quantity and garbage location in the second garbage information to control the sweeper.

[0137] It is understandable that the decision information of autonomous driving refers to the set of instructions generated by the autonomous driving system after perceiving the environment, based on real-time data and prediction results, to guide the vehicle's behavior, including core elements such as path planning, action planning, and behavior decision-making.

[0138] In one embodiment of this application, the first processing module 610 is further configured to:

[0139] When both roadside perception results and vehicle-side perception results exist, the roadside perception results are used first; when only one type of perception result exists, the only existing perception result is used.

[0140] Based on the perception results, the garbage attribute information in each grid cell of the current area is determined as the first garbage information in the current perception area. The garbage attribute information includes at least the garbage quantity, garbage type, and garbage location.

[0141] Wherein, the current sensing area is different in the vehicle-side sensing result and the road-side sensing result. If the road-side sensing result is used first, the non-overlapping part of the vehicle-side sensing area is supplemented by the vehicle-side sensing result, and the overlapping part is based on the road-side sensing result.

[0142] In one embodiment of this application, the roadside includes a roadside camera, and the vehicle side includes a front-end camera and a rear-end camera. Image information is acquired through the roadside camera, the front-end camera, and the rear-end camera. The grid in the first processing module 610 is obtained in the following manner:

[0143] Based on BEV, grid information is obtained in the vehicle-end coordinate system or the road-end coordinate system, and the grid information is uniform in the local area and non-uniform in the global area;

[0144] The image information is used to assist in calibrating the positional accuracy of the BEV grid, ensuring that the grid can accurately carry the garbage attribute information in the first garbage information.

[0145] In one embodiment of this application, the garbage attribute information in the first processing module 610 specifically includes:

[0146] Waste type: Assign corresponding waste serial numbers according to category, which serve as the basis for switching operation modes;

[0147] Garbage quantity: 0 indicates empty, 1 indicates a small amount, 2 indicates a large amount;

[0148] Waste location: Based on the unified and transformed vehicle coordinate system, determine whether the waste is located to the left or right of the vehicle's centerline;

[0149] The conversion rule between the vehicle-side coordinate system and the roadside coordinate system is as follows: based on the real-time positioning data of the sweeper, the coordinates of the garbage location in the roadside coordinate system are mapped to the vehicle-side coordinate system.

[0150] In one embodiment of this application, the third processing module 630 is further configured to:

[0151] Based on the type of waste and the number of grid cells occupied by the waste in the second waste information, a corresponding operation mode is generated;

[0152] The corresponding workload is determined based on the number of grid cells occupied by the waste and the type of waste.

[0153] Execute the job according to the default job direction or a custom job direction;

[0154] Determine the vehicle speed based on the amount of garbage;

[0155] The aforementioned work mode, work intensity, work direction, and vehicle speed are used as basic equipment decision information;

[0156] Configure the work mode switching interval and work direction switching interval to generate complete upper equipment decision information.

[0157] In one embodiment of this application, the third processing module 630 is further configured to:

[0158] Configure the upper sweeping speed according to the default mode, which is associated with the matching relationship between the work intensity, work mode and sweeping speed;

[0159] When the sweeper turns around, the sweeping disc speed should be reduced to the lowest operating value, and the vehicle speed should not be lower than 8km / h;

[0160] When the sweeper is waiting at a red light, the work intensity will be uniformly adjusted to the default intensity to maintain the current work mode;

[0161] When the sweeper is working along the edge, the side to be swept is determined according to the location of the garbage: when sweeping along the left edge, the right sweeping disc and water spray bar are turned off; when sweeping along the right edge, the left sweeping disc and water spray bar are turned off.

[0162] In one embodiment of this application, the second processing module 620 is further configured to:

[0163] In response to the switching results of the sweeper's operating mode, operating direction and operating speed, the first garbage information of multiple grids is integrated, and the garbage category, garbage quantity and garbage location information of overlapping or related grids are merged into the second garbage information of the same grid.

[0164] In response to the second garbage information, a switching instruction for the operation mode, operation intensity, operation direction, and vehicle speed is generated and issued, and the switching instruction conforms to the preset configuration rules.

[0165] It is understood that the above-mentioned cleaning device can realize each step of the cleaning method provided in the foregoing embodiments. The relevant explanations of the cleaning method are applicable to the cleaning device and will not be repeated here.

[0166] Figure 7 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 7 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0167] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0168] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0169] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming a cleaning operation at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0170] In response to either the roadside or vehicle-side perception results, determine the first piece of garbage information in the current area;

[0171] The first garbage information is integrated and processed to obtain the merged second garbage information; and

[0172] In response to the second garbage information, the upper structure decision information is generated to control the sweeper.

[0173] The above is as stated in this application. Figure 2The cleaning operation device disclosed in the illustrated embodiment can be applied to a processor, or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0174] The electronic device can also perform Figure 2 The method of the sweeping operation device, and the realization of the sweeping operation device in Figure 1 The functions of the embodiments shown are not described in detail here.

[0175] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 2 The method executed by the cleaning device in the illustrated embodiment is specifically used to perform the following:

[0176] In response to either the roadside or vehicle-side perception results, determine the first piece of garbage information in the current area;

[0177] The first garbage information is integrated and processed to obtain the merged second garbage information; and

[0178] In response to the second garbage information, the upper structure decision information is generated to control the sweeper.

[0179] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0180] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0181] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0182] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes ​ The steps of the function specified in one or more boxes.

[0183] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0184] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0185] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0186] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0187] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0188] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A cleaning work method, wherein, The method comprises: determining first garbage information in a current area in response to any one of road end and vehicle end perception results; integrating processing the first garbage information to obtain second garbage information after merging processing; and generating upper loading decision information to control the sweeper in response to the second garbage information.

2. The method of claim 1, wherein, The response to any one of road end and vehicle end perception results to determine the first garbage information in the current area comprises: in the case that both road end and vehicle end perception results exist, the road end perception result is used preferentially; in the case that only one kind of perception result exists, the only existing perception result is used; determining garbage attribute information in each grid in the current area according to the perception result as the first garbage information in the current perception area, the garbage attribute information at least comprising garbage quantity, garbage type and garbage position; wherein the current perception area is not the same in the vehicle end perception result and the road end perception result, if the road end perception result is used preferentially, the non-overlapping part of the vehicle end perception area is supplemented by the vehicle end perception result, and the overlapping part is subject to the road end perception result.

3. The method of claim 2, wherein, The road end comprises a roadside camera, the vehicle end comprises a front end camera and a rear end camera, and image information is acquired through the roadside camera, the front end camera and the rear end camera; the grid is obtained by the following way: based on BEV, grid information is acquired in the vehicle end coordinate system or the road end coordinate system, the grid information is uniform in the local area and non-uniform in the global area; the image information is used to assist in calibrating the position accuracy of the BEV grid, to ensure that the grid can accurately carry the garbage attribute information in the first garbage information.

4. The method of claim 3, wherein, The garbage attribute information specifically comprises: garbage type: assigning corresponding garbage serial number according to the category as the basis for switching the operation mode; garbage quantity: 0 represents empty, 1 represents small amount, and 2 represents large amount; garbage position: determining whether the garbage is located on the left or right side of the vehicle center line based on the unified converted vehicle body coordinate system; the conversion rule of the vehicle end coordinate system and the road end coordinate system is that, taking the real-time positioning data of the sweeper as the reference, the garbage position coordinates in the roadside coordinate system are mapped to the vehicle body coordinate system.

5. The method of claim 3, wherein, The response to the second garbage information to generate upper loading decision information to control the sweeper comprises: generating corresponding operation mode according to the garbage type and the number of grids occupied by the garbage in the second garbage information; determining corresponding operation intensity according to the number of grids occupied by the garbage and the garbage type; performing operation according to the default operation direction or the self-defined operation direction; determining the vehicle speed according to the garbage amount; taking the operation mode, operation intensity, operation direction and vehicle speed as the basic upper loading decision information; configuring operation mode switching interval and operation direction switching interval to generate complete upper loading decision information.

6. The method of claim 5, wherein, It also comprises: configuring the upper loading sweeping disc speed according to the default mode, the default mode being associated with the matching relationship of operation intensity, operation mode and sweeping disc speed; when the sweeper turns around, controlling the sweeping disc speed to reduce to the minimum working condition value, and the vehicle speed is not lower than 8km / h; when the sweeper stops at a red light, uniformly adjusting the operation intensity to the default intensity to maintain the current operation mode. When the sweeper is working in the edge cleaning mode, the right sweeping disc and the water spraying rod are closed when the left edge is cleaned, and the left sweeping disc and the water spraying rod are closed when the right edge is cleaned.

7. The method of claims 1, 2, 5, wherein, The first garbage information is integrated to obtain second garbage information after the integration processing, including: In response to the switching results of the working mode, the working direction and the working speed of the sweeper, the first garbage information of multiple grids is integrated, and the garbage category, the garbage amount and the garbage position information of the overlapping or associated grids are combined into the second garbage information of the same grid; In response to the second garbage information, a switching instruction of the working mode, the working intensity, the working direction and the vehicle speed is generated and issued, and the switching instruction conforms to the preset configuration rule.

8. A cleaning work device in which, The device comprises: A first processing module is configured to determine first garbage information in a current area in response to any one of the sensing results of the road end and the vehicle end; A second processing module is configured to integrate and process the first garbage information to obtain second garbage information after the integration processing; and A third processing module is configured to generate upper loading decision information to control the sweeper in response to the second garbage information. 9.An electronic device comprising: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method of any one of claims 1-7. 10.A computer readable storage medium storing one or more programs, which when executed by an electronic device comprising multiple applications, cause the electronic device to perform the method of any one of claims 1-7.

Images