Parking lot cleaning method, device, equipment and storage medium

Abstract

The present disclosure provides a parking lot cleaning method, apparatus, device, and storage medium. The parking lot cleaning method includes: determining at least one first parking space area based on the original key points of each original parking space area on a passage in a parking lot map, and determining a global path to each first parking space area based on the first key points corresponding to each first parking space area. After a sanitation vehicle arrives at the first parking space area according to the global path, the method determines the parking space area to be cleaned and the local path for cleaning each parking space area to be cleaned by obtaining a real-time map of the first parking space area. This method allows the cleaning path to be determined based on the status of the parking spaces in the parking lot, thereby improving the cleaning efficiency of the sanitation vehicle.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent driving technology, and in particular to a parking lot cleaning method, device, equipment, and storage medium. Background Art

[0002] Existing intelligent driving sanitation technology is typically used on urban roads. Due to traffic regulations and oncoming traffic, sanitation vehicles typically plan cleaning routes based on fixed lanes. When applying this intelligent driving sanitation technology used on urban roads to parking lots, unmanned sanitation vehicles will clean along fixed routes. However, parking space status updates frequently, and fixed routes can cause sanitation vehicles to waste time in spaces they don't need to clean. Summary of the Invention

[0003] To overcome the problems existing in the related art, the present disclosure provides a parking lot cleaning method, device, equipment and storage medium.

[0004] According to a first aspect of the present disclosure, a parking lot cleaning method is provided, which is applied to a sanitation vehicle, and the method comprises:

[0005] Determining at least one first parking space area based on an original key point of each original parking space area on the passage in the parking lot map, wherein the first parking space area includes at least one original parking space area, and the original key point is determined based on a center position of the original parking space area;

[0006] determining a global path to each first parking space area based on first key points corresponding to each first parking space area, wherein the first key points are determined based on original key points of all original parking space areas in the first parking space area;

[0007] For the first parking area reached by the sanitation vehicle according to the global path, obtaining a real-time map of the first parking area, and determining a parking area to be cleaned according to the real-time map, wherein the parking area to be cleaned includes one or more consecutive vacant parking spaces;

[0008] A local path to each parking area to be cleaned is determined according to a second key point corresponding to each parking area to be cleaned, wherein the second key point is determined according to a starting position of the parking area to be cleaned.

[0009] In some embodiments, determining at least one first parking space area based on the original key points of each original parking space area on the passage in the parking lot map includes:

[0010] The original parking areas whose distances between the original key points are less than the distance threshold are divided into the same group;

[0011] The original parking space area in the same group is determined as the first parking space area.

[0012] In some embodiments, determining a global path to each first parking space area based on the first key point corresponding to each first parking space area includes:

[0013] Obtaining the starting position and the ending position of the passage, and the first key points of all first parking spaces on the passage;

[0014] Determine a first cleaning order with the goal of taking the shortest path from the starting position, passing through all first key points, and reaching the end position;

[0015] A global path to each first parking space area is determined according to the first cleaning sequence.

[0016] In some embodiments, determining a local path to each parking area to be cleaned based on the second key point corresponding to each parking area to be cleaned includes:

[0017] Obtain the second key point corresponding to each parking area to be cleaned;

[0018] Determine a second cleaning order for each parking area to be cleaned, with the goal of minimizing the total path cost from the location of the sanitation vehicle, passing through all second key points, and the starting and ending locations of each parking area to be cleaned, to the end location of the first parking area;

[0019] According to the second cleaning sequence and the cleaning mode for cleaning each parking area to be cleaned, a local path to each parking area to be cleaned is determined.

[0020] In some embodiments, obtaining the second key point corresponding to each parking area to be cleaned includes:

[0021] Obtaining a channel closest to the parking area to be cleaned, a center line of the channel, and a plurality of sampling points located on the center line;

[0022] For each sampling point, obtaining the connection cost from the sampling point to the starting position of the parking area to be cleaned;

[0023] The sampling point with the smallest connection cost is determined as the second key point of the parking area to be cleaned.

[0024] In some embodiments, the method further comprises:

[0025] Dividing each parking space area to be cleaned into a first continuous parking space area, a second continuous parking space area, or a single parking space area based on the number of vacant parking spaces in each parking space area to be cleaned, wherein the number of consecutive vacant parking spaces in the first continuous parking space area is greater than or equal to a number threshold, and the number of consecutive vacant parking spaces in the second continuous parking space area is less than the number threshold;

[0026] In response to detecting that the parking space area to be cleaned belongs to the first continuous parking space area, setting the cleaning mode of the sanitation vehicle to a C-mode;

[0027] In response to detecting that the parking space area to be cleaned belongs to the second continuous parking space area, setting the cleaning mode of the sanitation vehicle to a zigzag mode;

[0028] In response to detecting that the parking area to be cleaned belongs to a single parking area, the cleaning mode of the sanitation vehicle is set to an L-shaped mode.

[0029] In some embodiments, the method further includes: obtaining a cleaning width of the parking area to be cleaned; and adjusting a cleaning distance between cleaning brushes on both sides of the sanitation vehicle according to the cleaning width.

[0030] In some embodiments, the method further comprises:

[0031] In response to monitoring that a vacant parking space in the parking area to be cleaned is occupied during the cleaning process, or a parking space adjacent to the parking area to be cleaned becomes vacant, causing the state of the parking area to be cleaned to change, the local path is re-determined based on the changed parking area to be cleaned and the current location of the sanitation vehicle.

[0032] In some embodiments, the method further comprises:

[0033] After cleaning is completed along the global path, if the number of parking areas to be cleaned is greater than a quantity threshold, a local path is generated according to the parking areas to be cleaned and cleaning is performed along the local path.

[0034] According to a second aspect of the present disclosure, a parking lot cleaning device is provided, which is applied to a sanitation vehicle, and the device comprises:

[0035] a first parking space area determining unit, configured to determine at least one first parking space area based on an original key point of each original parking space area on the passage in the parking lot map, wherein the first parking space area includes at least one original parking space area, and the original key point is determined based on a center position of the original parking space area;

[0036] a global path determining unit, configured to determine a global path to each first parking area based on a first key point corresponding to each first parking area, wherein the first key point is determined based on original key points of all original parking areas in the first parking area;

[0037] a parking space area to be cleaned determining unit, configured to obtain a real-time map of the first parking space area reached by the sanitation vehicle according to the global path, and determine a parking space area to be cleaned based on the real-time map, wherein the parking space area to be cleaned includes one or more consecutive vacant parking spaces;

[0038] The local path determination unit is used to determine a local path to each parking area to be cleaned according to a second key point corresponding to each parking area to be cleaned, where the second key point is determined according to a starting position of the parking area to be cleaned.

[0039] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor to execute the method described in any embodiment of the present disclosure.

[0040] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described in any embodiment of the present disclosure is implemented.

[0041] The technical solution provided by the present disclosure may include the following beneficial effects: the present disclosure determines at least one first parking space area based on the original key points of each original parking space area on the channel in the parking lot map, and determines the global path to each first parking space area based on the first key points corresponding to each first parking space area. After the sanitation vehicle arrives at the first parking space area according to the global path, the parking space area to be cleaned and the local path for cleaning each parking space area to be cleaned are determined by obtaining a real-time map in the first parking space area, so that the cleaning path can be determined according to the status of the parking spaces in the parking lot, thereby improving the cleaning efficiency of the sanitation vehicle.

[0042] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description, are used to explain the technical solutions of the present disclosure.

[0044] Figure 1 The figure is a flowchart of a parking lot cleaning method according to an exemplary embodiment of the present disclosure.

[0045] Figure 2 It is a schematic diagram of a scene of a parking lot according to an exemplary embodiment of the present disclosure.

[0046] Figure 3 2 is a schematic diagram of a second cleaning sequence in a first parking space area A according to an exemplary embodiment of the present disclosure.

[0047] Figure 4A 2 is a schematic diagram showing that the cleaning mode is set to C mode according to an exemplary embodiment of the present disclosure.

[0048] Figure 4B 2 is a schematic diagram showing that the cleaning mode is set to a Z-shaped mode according to an exemplary embodiment of the present disclosure.

[0049] Figure 4C 2 is a schematic diagram showing that the cleaning mode is set to an L-shaped mode according to an exemplary embodiment of the present disclosure.

[0050] Figure 5 It is an overall flow chart of a parking lot cleaning path planning method according to an exemplary embodiment of the present disclosure.

[0051] Figure 6 The figure is a schematic structural diagram of a parking lot cleaning device according to an exemplary embodiment of the present disclosure.

[0052] Figure 7 A schematic diagram of the structure of an electronic device for executing a parking lot cleaning method provided in at least one embodiment of the present disclosure. DETAILED DESCRIPTION

[0053] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0054] The terms used in this disclosure are for the purpose of describing specific embodiments only and are not intended to limit the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0055] It should be understood that although the terms first, second, third, etc. may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining."

[0056] This disclosure provides a parking lot cleaning method based on the cleaning needs of intelligent sanitation vehicles. The method can be applied to the planning module of the sanitation vehicle. The planning module can receive a high-precision map of the parking lot and the real-time perception of the environmental status, and transmit trajectory information to the downstream through this disclosure. The high-precision map of the parking lot is a high-precision map that can be used for autonomous driving. It contains map elements such as the shape of the parking lot's aisles, the area where the parking spaces are located, traffic signs, and obstacles. The accuracy of the high-precision map can reach the centimeter level.

[0057] The method provided in the present disclosure can be divided into global planning and local planning. The global planning may include a whole continuous task from the current position to the target position, and the local planning may include a feasible trajectory under the current state.

[0058] The following embodiments will illustrate the method provided by the present disclosure in conjunction with the accompanying drawings.

[0059] Figure 1 is a flow chart of a parking lot cleaning method according to an exemplary embodiment of the present disclosure, as shown in FIG. Figure 1 As shown, the method may include the following steps 101 to 104.

[0060] In step 101 , at least one first parking space area is determined based on original key points of each original parking space area on a passage in a parking lot map, where the first parking space area includes at least one original parking space area.

[0061] The original key point can be determined based on the center position of the original parking area. The parking map is a high-precision map, and the original parking area can include one or more parking spaces, such as two consecutive adjacent parking spaces or five consecutive adjacent parking spaces.

[0062] In this embodiment, the passage in the parking lot and each original parking space area in the parking lot can be obtained based on the parking lot map, the original key point of the original parking space area on the passage is determined based on the center position of the original parking space area, and the original parking space areas are grouped based on the original key points of each original parking space area to obtain multiple first parking space areas, each of which includes at least one original parking space area.

[0063] In step 102 , a global path to each first parking area is determined based on the first key point corresponding to each first parking area.

[0064] If the first parking area includes one original parking area, the first key point of the first parking area is the original key point of the original parking area. If the first parking area includes two or more original parking areas, the first key point of the first parking area is determined based on the original key points of all the original parking areas in the first parking area. In one example, the center point of all the original key points of the original parking areas can be determined as the first key point of the first parking area. For example, if the first parking area A includes original parking area 1 and original parking area 2, the center point between original key point 1 and original key point 2 can be determined as the first key point of the first parking area. In another example, the original key point of any original parking area in the first parking area can be determined as the first key point. For example, if the first parking area A includes original parking area 1 and original parking area 2, the original key point of original parking area 1 can be determined as the first key point of the first parking area A, and the original key point of original parking area 2 can also be determined as the first key point of the first parking area A.

[0065] In step 103, for the first parking area reached by the sanitation vehicle according to the global path, a real-time map of the first parking area is obtained, and a parking area to be cleaned is determined according to the real-time map.

[0066] Considering that the status of parking spaces in a parking lot changes frequently, after the sanitation vehicle arrives at the first parking space area according to the global path, a real-time map of the first parking space area can be obtained. The real-time map can be used to determine the parking space area to be cleaned in the first parking space area. The parking space area to be cleaned refers to the area where the vacant parking spaces are located.

[0067] When the sanitation vehicle arrives at the first parking area, it can build a real-time map of the parking area based on the point cloud and the camera's perception results, and compare the real-time map with the pre-saved parking map to obtain the vacant parking spaces in the first parking area.

[0068] A parking space area to be cleaned may include one or more consecutive vacant parking spaces. In this embodiment, a plurality of consecutive adjacent vacant parking spaces may be determined as a parking space area to be cleaned.

[0069] In step 104, a local path to each parking area to be cleaned is determined based on the second key point corresponding to each parking area to be cleaned.

[0070] The second key point can be determined based on the starting point of the parking area to be cleaned. If the first parking area includes multiple parking areas to be cleaned, a local path to each parking area to be cleaned can be determined based on the second key point corresponding to each parking area to be cleaned, with the goal of minimizing the cleaning cost (also called the connection cost).

[0071] The present invention determines at least one first parking space area based on the original key points of each original parking space area on the channel in the parking lot map, and determines the global path to each first parking space area based on the first key points corresponding to each first parking space area. After the sanitation vehicle arrives at the first parking space area according to the global path, the parking space area to be cleaned and the local path for cleaning each parking space area to be cleaned are determined by obtaining a real-time map in the first parking space area, so that the cleaning path can be determined according to the status of the parking spaces in the parking lot, thereby improving the cleaning efficiency of the sanitation vehicle.

[0072] In some embodiments, determining at least one first parking space area based on the original key points of each original parking space area on the channel in the parking lot map may include: dividing the original parking spaces whose distances between the original key points are less than a distance threshold into the same group; and determining the original parking spaces within the same group as the first parking space area.

[0073] The purpose of grouping multiple original parking areas is to reduce the cleaning cost of sanitation vehicles. In other words, original parking areas in the same group can be cleaned during the same task. Therefore, this embodiment groups original parking areas corresponding to original key points located in the same channel and close to each other into the same group.

[0074] Figure 2 is a schematic diagram of a parking lot according to an exemplary embodiment of the present disclosure. Figure 2 As shown, the darker grey lane 201 in the middle represents the passage of the parking lot, and the area 202 represents each original parking space area. Figure 2In the parking lot shown, the original parking space area includes 13 blocks, namely {1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}, each of which can include multiple parking spaces. In this embodiment, the parking lot's access information and original parking space areas can be obtained from a pre-collected high-precision map.

[0075] The original key point of the original parking area on the channel is determined according to the center position of each original parking area. Taking original parking area 1 as an example, the original key point 203 of original parking area 1 on the channel is determined according to the center position of original parking area 1. A similar method is used to determine the original key points of original parking areas 2 to 13 respectively.

[0076] Original parking areas located in the same passageway and with a distance between original key points less than a distance threshold are grouped together. The original parking areas within the same group are identified as the first parking area. For example, if the original key points of original parking area 1 and original parking area 2 are located in the same passageway and the distance between the original key points of original parking area 1 and original parking area 2 is less than the distance threshold, original parking area 1 and original parking area 2 can be identified as the first parking area.

[0077] After the above operations, you can Figure 2 The 13 original parking spaces are grouped into 9 first parking spaces. For ease of representation, A to I are used to identify the first parking spaces, i.e., A:{1,2}, B:{7}, C:{3,4}, D:{8}, E:{9}, F:{12}, G:{5,6}, H:{10,11}, I:{13}.

[0078] In some embodiments, determining the global path to each first parking area based on the first key points corresponding to each first parking area may include: obtaining the starting position and the end position of the channel, and the first key points of all first parking areas on the channel; determining a first cleaning order with the goal of shortening the path from the starting position, passing through all the first key points and reaching the end position; and determining the global path to each first parking area based on the first cleaning order.

[0079] In this embodiment, the process of the sanitation vehicle starting from the starting position of the passage, passing through the first key points of all the first parking spaces on the passage, and reaching the end position is called a whole continuous task, that is, global planning. Figure 2For clarity, consider A through I as the first key points (also called nodes) in each first parking area. Node 204 represents the starting and ending points of the sanitation vehicle, respectively. The edges between nodes represent the connection cost. Based on the directed graph, we obtain the cleaning order from A to I, which is the shortest path from the starting point to the ending point through all intermediate nodes.

[0080] Those skilled in the art should understand that the above Figure 2 The coincidence of the starting point and the end point in is an example. Figure 2 In addition to the case shown, the starting position and the end position of the channel may not overlap, and this disclosure does not limit this. In order to distinguish it from the sweeping order mentioned later, the sweeping order used to determine the global path is called the first sweeping order in this embodiment.

[0081] Through the above analysis, the entire process of determining the global path can be regarded as a traveling salesman problem (TSP). Therefore, genetic algorithms, simulated annealing, ant colony algorithms, tabu search algorithms, greedy algorithms and neural networks can be used to solve the TSP problem to obtain the first sweeping order.

[0082] In one embodiment, the LKH (Lin-Kernighan heuristic) algorithm can be used to solve the TSP problem to obtain a first sweeping order (start, A, B, E, D, C, G, H, I, F, end), where Start represents the starting position of the channel and end represents the end position of the channel.

[0083] In some embodiments, determining the local path to each parking area to be cleaned based on the second key point corresponding to each parking area to be cleaned may include the following steps 1041 to 1043.

[0084] In step 1041, the second key point corresponding to each parking area to be cleaned is obtained.

[0085] In one embodiment, the channel closest to the parking area to be cleaned, as well as the center line of the channel and multiple sampling points located on the center line can be obtained; for each sampling point, the connection cost from the sampling point to the starting position of the parking area to be cleaned is obtained; and the sampling point with the smallest connection cost is determined as the second key point of the parking area to be cleaned.

[0086] The sampling interval between each sampling point is a set distance. A heuristic function curve algorithm can be used to calculate the connection cost between each sampling point and the starting point of the parking area to be cleaned. The sampling point with the minimum connection cost is used as the second key point of the parking area to be cleaned. Such heuristic function curve algorithms include the Reeds-Sheep curve and the Dubins curve.

[0087] In another embodiment, a sampling point located in the middle of the parking area to be cleaned can be selected from multiple sampling points on the centerline of the channel as the second key point of the parking area to be cleaned. Compared to selecting the sampling point with the lowest connection cost as the second key point of the parking area to be cleaned, the second key point determined in this embodiment will result in a higher connection cost.

[0088] In step 1042, the second cleaning order for cleaning each parking area to be cleaned is determined with the goal of minimizing the total path cost from the position of the sanitation vehicle, passing through all second key points, and the starting and ending positions of each parking area to be cleaned, to the end position of the first parking area.

[0089] When determining the second cleaning order, not only the connection cost from the second key point of one parking area to be cleaned to the second key point of another parking area to be cleaned should be considered, but also the connection cost from the second key point of one parking area to be cleaned to the starting position of the parking area to be cleaned, and after cleaning the parking area to be cleaned, the connection cost from the end position of the parking area to be cleaned to the second key point of the next parking area to be cleaned should be considered.

[0090] In step 1043, a local path to each parking area to be cleaned is determined according to the second cleaning sequence and the cleaning mode for cleaning each parking area to be cleaned.

[0091] Figure 3 : is a schematic diagram of the second cleaning sequence in the first parking area A according to an exemplary embodiment of the present disclosure. Figure 3As shown, it is assumed that the parking area to be cleaned obtained after arriving at the first parking area A is {a, b, c, d, e, f}. Taking the parking area a to be cleaned and the parking area b to be cleaned as examples, first find the channel closest to the parking area a to be cleaned, and obtain the center line of the channel and multiple sampling points located on the center line, the sampling points are 301, 302, 303 and 304 respectively. For each sampling point, the reeds-sheep curve is used to calculate its connection cost, and the sampling point 301 with the smallest cost is found as the second key point, denoted as Pa. Similarly, the second key point Pb of the parking area b to be cleaned is obtained. For the two second key points Pa and the second key points Pb in the channel, the obstacle avoidance algorithm can be used to calculate their connection costs. The obstacle avoidance algorithm can select the A* algorithm, the Voronoi diagram algorithm and the artificial potential field algorithm. In this embodiment, a hybrid A* algorithm can be used for local path planning, and the reeds-sheeps curve is used as the heuristic function in the hybrid A* algorithm.

[0092] exist Figure 3 In the example, a1 represents the starting point of parking area a to be cleaned, and a2 represents the ending point of parking area a to be cleaned. start represents the location of the sanitation vehicle, which can also be called the starting point of the first parking area A, and end represents the ending point of the first parking area A. For a parking area to be cleaned that includes one parking area, the starting point and ending point of the parking area to be cleaned are the same. For example, the starting point and ending point of parking area b to be cleaned are the same.

[0093] In this way, the connection cost between the parking area a to be cleaned and the parking area b to be cleaned can be obtained: Cost(ab)=rs(a1→Pa)+astar(Pa→Pb)+rs(Pb→b), where rs(a1→Pa) represents the connection cost from the starting position of the parking area a to be cleaned to the second key point Pa; astar(Pa→Pb) represents the connection cost from the second key point Pa to the second key point Pb; rs(Pb→b) represents the connection cost from the second key point Pb to the parking area b to be cleaned.

[0094] Similarly, based on the starting and ending positions of each parking area to be cleaned, each second key point, the position start of the sanitation vehicle, and the end position end of the first parking area A, the connection cost between each two parking areas to be cleaned in {a, b, c, d, e, f} can be calculated, and a cost matrix can be constructed. The TSP problem is then solved using the LKH algorithm to obtain the optimal second cleaning order (start, d, a, e, b, f, c, end).

[0095] Since a parking area to be cleaned may include one vacant parking space or multiple consecutive vacant parking spaces, in this embodiment, the parking area to be cleaned can be divided into a first consecutive parking area, a second consecutive parking area or a single parking area according to the number of vacant parking spaces in each parking area to be cleaned, the number of consecutive vacant parking spaces in the first consecutive parking area is greater than or equal to a number threshold, and the number of consecutive vacant parking spaces in the second consecutive parking area is less than the number threshold.

[0096] For example, assuming that the number threshold is 6, the parking space area to be cleaned with the number of consecutive vacant parking spaces greater than or equal to 6 is called the first consecutive parking space area, and the parking space area to be cleaned with the number of consecutive vacant parking spaces between 2 and 5 is called the second consecutive parking space area.

[0097] See also Figure 3 , parking space areas a and d to be cleaned belong to the second continuous parking space area; parking space areas b, c and e to be cleaned belong to a single parking space area; parking space area f to be cleaned belongs to the first continuous parking space area.

[0098] In this embodiment, different cleaning modes can be set for different types of parking areas to be cleaned. The cleaning modes are respectively called C-mode, Z-mode and L-mode according to the trajectory of the sanitation vehicle when working in the cleaning mode. Figure 4A is a schematic diagram showing that the cleaning mode is set to C mode according to an exemplary embodiment of the present disclosure. Figure 4B is a schematic diagram showing that the cleaning mode is set to a Z-shaped mode according to an exemplary embodiment of the present disclosure. Figure 4C 2 is a schematic diagram showing that the cleaning mode is set to an L-shaped mode according to an exemplary embodiment of the present disclosure.

[0099] In response to detecting that the parking area to be cleaned belongs to the first continuous parking area, the cleaning mode of the sanitation vehicle is set to the C-mode. For example, when cleaning the parking area to be cleaned f, the cleaning mode of the sanitation vehicle is set to the C-mode.

[0100] In response to detecting that the parking area to be cleaned belongs to the second continuous parking area, the cleaning mode of the sanitation vehicle is set to a Z-shaped mode. For example, in the case of parking areas a and d to be cleaned, the cleaning mode of the sanitation vehicle is set to a Z-shaped mode.

[0101] In response to detecting that the parking area to be cleaned belongs to a single parking area, the cleaning mode of the sanitation vehicle is set to an L-shaped mode. For example, when parking areas b, c, and e are to be cleaned, the cleaning mode of the sanitation vehicle is set to an L-shaped mode.

[0102] Choosing different cleaning patterns for different parking areas to be cleaned can improve the cleaning efficiency of sanitation vehicles. In actual applications, the efficiency of using a C-shaped pattern to clean the first continuous parking area with a large number of vacant parking spaces is higher than that of using an L-shaped pattern.

[0103] During the cleaning process, the cleaning width of the parking area to be cleaned can be obtained; and the cleaning distance between the cleaning brushes on both sides of the sanitation vehicle can be adjusted according to the cleaning width.

[0104] Since the garbage on the parking space is often located around the vehicle and close to the edge area of ​​the parking space frame, in order to clean the edge of the parking area, the cleaning intervals of the three modes can be adjusted according to the cleaning width of the parking area to be cleaned, so as to achieve better cleaning effect.

[0105] like Figure 4A As shown, in the C-shaped mode, the length of the parking space in the parking area to be cleaned can be determined as the cleaning width. Generally, the length of a parking space is usually greater than 5m and the width is 2.5m. Assuming that the body of the sanitation vehicle is 2m wide, for a parking area to be cleaned with a cleaning width of 5m, the cleaning spacing between the cleaning brushes on both sides of the sanitation vehicle can be set to 1.8m. That is to say, the sanitation vehicle repeats the cleaning three times in the C-shaped mode, and the overlapping area between the cleaning tracks each time is 0.2m. The cleaning work of the parking area to be cleaned can be completed in three times. Not only is the cleaning efficiency high, but the cleaning effect can also meet expectations.

[0106] The cleaning spacing of the Z-shaped mode and the L-shaped mode is set in the same way. The width of the parking space in the parking area to be cleaned can be determined as the cleaning width. Assuming it is 2.5m, for a sanitation vehicle with a body width of 2m, the cleaning spacing between the cleaning brushes on both sides of the sanitation vehicle can be set to 1.6m.

[0107] In one embodiment, considering that the size of the parking space and the size of the sanitation vehicle are determinable, possible sweeping widths are determined based on the size of the parking space, and a cleaning interval is pre-set for each sweeping width. The sweeping widths and cleaning intervals are associated and stored. When a sweeping width is obtained, the cleaning interval corresponding to the sweeping width is obtained from the corresponding association.

[0108] When sanitation vehicles use C-shaped and Z-shaped patterns for cleaning, they may encounter situations where a vehicle occupies some of the unoccupied parking spaces, causing the current continuous parking area to be split, or new parking spaces become available and merge with the current continuous parking area. These two situations will cause the status of the parking area to be cleaned to change. If the status of the parking area to be cleaned changes, the area to be cleaned can be regenerated and replanned based on the current position of the vehicle. If the original parking area to be cleaned is split, the new split area can be found based on the current position of the vehicle, and the cleaning path can be replanned based on the new split area.

[0109] That is, in response to monitoring that during the cleaning process, a vacant parking space in the parking area to be cleaned is occupied, or a parking space adjacent to the parking area to be cleaned becomes vacant, causing the state of the parking area to be cleaned to change, the local path is re-determined according to the changed parking area to be cleaned and the current position of the sanitation vehicle.

[0110] In some embodiments, after the sanitation vehicle completes cleaning along the global path, if the number of parking areas to be cleaned is greater than a quantity threshold, a local path is generated according to the parking areas to be cleaned and cleaning is performed along the local path.

[0111] When the sanitation vehicle is traveling along the global path, it will store the parking spaces to be cleaned according to the real-time map collected. When determining the local path, if the connection cost required to clean the parking spaces to be cleaned is greater than the cost threshold, the parking spaces to be cleaned will be cached in a temporary area. After the sanitation vehicle completes cleaning along the global path, if the number of parking spaces to be cleaned in the temporary area is greater than the number threshold, a local path will be generated according to the parking spaces to be cleaned in the temporary area and cleaning will be carried out along the local path.

[0112] Still Figure 2 For example, assuming that the sanitation vehicle is currently cleaning the parking area to be cleaned in the first parking space area B, which is far away from the first parking space area A, if it is determined according to the real-time map that there is a parking area x to be cleaned in the first parking space area A, since the connection cost required to clean the parking area x to be cleaned is greater than the cost threshold, the parking area x to be cleaned can be cached in the temporary area. When the sanitation vehicle completes a cleaning along the global path, or when it goes to the next first parking space area along the global path, it passes through the cleaned first parking space area, and the parking area to be cleaned in the temporary area can be cleaned.

[0113] Figure 5 This is an overall flow chart of a parking lot cleaning path planning method according to an exemplary embodiment of the present disclosure. Figure 5 As shown, the method includes the following steps 501 to 506.

[0114] In step 501 , a global path to each first parking space area is determined according to a parking lot map.

[0115] At least one first parking area is determined based on the original key points of each original parking area on the passage in the parking lot map, and a global path to each first parking area is determined based on the first key points corresponding to each first parking area.

[0116] In step 502, the parking area to be cleaned is obtained according to the real-time map.

[0117] When each first parking space area is reached according to the global path, a real-time map of the parking space area is constructed based on the point cloud and the camera's perception results. By comparing it with the pre-saved parking space map, the vacant parking spaces, i.e., the parking spaces to be cleaned areas, are obtained, and the parking spaces to be cleaned areas are added to the parking spaces to be cleaned set, and the parking spaces to be cleaned set is updated in real time.

[0118] In step 503, a local path to each parking area to be cleaned is determined.

[0119] The minimum cost required to move between any two parking areas to be cleaned is calculated based on the starting and ending locations of each area to be cleaned. The second cleaning order is determined based on the sanitation vehicle's current location, the ending location of the first parking area, and the cost of moving between each area to be cleaned.

[0120] The difference between step 501 and step 503 is that step 501 is to obtain a global path that reaches the first key point corresponding to each first parking area in sequence, while step 503 is to determine the parking areas to be cleaned in the first parking area based on the results of real-time perception and online mapping after the sanitation vehicle arrives at each first parking area, and generate a path to clean them in sequence.

[0121] In step 504, the parking area to be cleaned is classified and a cleaning mode is determined.

[0122] The parking areas to be cleaned are classified according to the number of consecutive vacant parking spaces: first consecutive parking area, second consecutive parking area, and single parking area. The cleaning mode is determined based on the classification results.

[0123] In step 505, a path to reach the starting position of the parking area to be cleaned and a path for cleaning the parking area to be cleaned are generated.

[0124] The next parking area to be cleaned is selected along the local path, a path to the starting position of the parking area to be cleaned and a path to clean the parking area to be cleaned are generated, and after cleaning is completed, the parking area to be cleaned is added to the set of cleaned parking spaces.

[0125] In step 506, after cleaning is completed along the global path, if the number of parking space areas to be cleaned in the set of parking spaces to be cleaned is greater than the quantity threshold, steps 503-505 are repeated for the parking space areas to be cleaned in the current set of parking spaces to be cleaned until the number of parking space areas to be cleaned in the set of parking spaces to be cleaned is less than the quantity threshold, indicating that the cleaning task is completed.

[0126] This embodiment can automatically generate a global path based on the parking lot map, dynamically update the parking space status in each first parking space area, generate a local path for the parking space area to be cleaned in real time, and adjust the cleaning mode according to the continuity of the idle parking spaces to achieve better cleaning effect and efficiency.

[0127] It should be noted that when the same sanitation vehicle cleans the same parking lot, the global path can be determined according to the parking space map, and the process of determining the local path can be repeated subsequently.

[0128] Corresponding to the aforementioned method embodiments, the present disclosure also provides an embodiment of a parking lot cleaning device.

[0129] Figure 6 A schematic diagram of a parking lot cleaning device provided by at least one embodiment of the present disclosure, such as Figure 6 As shown, the parking lot cleaning device includes:

[0130] A first parking space area determining unit 601 is configured to determine at least one first parking space area based on an original key point of each original parking space area on a passage in a parking lot map, wherein the first parking space area includes at least one original parking space area, and the original key point is determined based on a center position of the original parking space area;

[0131] a global path determining unit 602 for determining a global path to each first parking area based on a first key point corresponding to each first parking area, wherein the first key point is determined based on original key points of all original parking areas in the first parking area;

[0132] a parking space area to be cleaned determining unit 603, configured to obtain a real-time map of the first parking space area reached by the sanitation vehicle according to the global path, and determine a parking space area to be cleaned based on the real-time map, wherein the parking space area to be cleaned includes one or more consecutive vacant parking spaces;

[0133] The local path determining unit 604 is configured to determine a local path to each parking area to be cleaned according to a second key point corresponding to each parking area to be cleaned, wherein the second key point is determined according to a starting position of the parking area to be cleaned.

[0134] In some embodiments, the first parking space area determination unit 601 is specifically configured to:

[0135] The original parking areas whose distances between the original key points are less than the distance threshold are divided into the same group;

[0136] The original parking space area in the same group is determined as the first parking space area.

[0137] In some embodiments, the global path determination unit 602 is specifically configured to:

[0138] Obtaining the starting position and the ending position of the passage, and the first key points of all first parking spaces on the passage;

[0139] Determine a first cleaning order with the goal of taking the shortest path from the starting position, passing through all first key points, and reaching the end position;

[0140] A global path to each first parking space area is determined according to the first cleaning sequence.

[0141] In some embodiments, the local path determination unit 604 is specifically configured to:

[0142] Obtain the second key point corresponding to each parking area to be cleaned;

[0143] Determine a second cleaning order for each parking area to be cleaned, with the goal of minimizing the total path cost from the location of the sanitation vehicle, passing through all second key points, and the starting and ending locations of each parking area to be cleaned, to the end location of the first parking area;

[0144] According to the second cleaning sequence and the cleaning mode for cleaning each parking area to be cleaned, a local path to each parking area to be cleaned is determined.

[0145] In some embodiments, the local path determination unit 604 is specifically configured to:

[0146] Obtaining a channel closest to the parking area to be cleaned, a center line of the channel, and a plurality of sampling points located on the center line;

[0147] For each sampling point, obtaining the connection cost from the sampling point to the starting position of the parking area to be cleaned;

[0148] The sampling point with the smallest connection cost is determined as the second key point of the parking area to be cleaned.

[0149] In some embodiments, the apparatus further includes a cleaning mode setting unit configured to divide the parking space area to be cleaned into a first continuous parking space area, a second continuous parking space area, or a single parking space area based on the number of vacant parking spaces in each parking space area to be cleaned, wherein the number of continuous vacant parking spaces in the first continuous parking space area is greater than or equal to a number threshold, and the number of continuous vacant parking spaces in the second continuous parking space area is less than the number threshold;

[0150] In response to detecting that the parking space area to be cleaned belongs to the first continuous parking space area, setting the cleaning mode of the sanitation vehicle to a C-mode;

[0151] In response to detecting that the parking space area to be cleaned belongs to the second continuous parking space area, setting the cleaning mode of the sanitation vehicle to a zigzag mode;

[0152] In response to detecting that the parking area to be cleaned belongs to a single parking area, the cleaning mode of the sanitation vehicle is set to an L-shaped mode.

[0153] In some embodiments, the device further includes a cleaning spacing unit for obtaining a cleaning width of the parking area to be cleaned; and adjusting the cleaning spacing between the cleaning brushes on both sides of the sanitation vehicle according to the cleaning width.

[0154] In some embodiments, the device also includes an updating unit for redetermining the local path according to the changed parking area to be cleaned and the current location of the sanitation vehicle in response to monitoring that a vacant parking space in the parking area to be cleaned is occupied during the cleaning process, or a parking space adjacent to the parking area to be cleaned becomes vacant, resulting in a change in the state of the parking area to be cleaned.

[0155] In some embodiments, the device further includes a judgment unit for generating a local path according to the parking areas to be cleaned and performing cleaning along the local path if the number of parking areas to be cleaned is greater than a quantity threshold after completing cleaning along the global path.

[0156] Figure 7 A schematic diagram of the electronic device structure for executing a parking lot cleaning method according to at least one embodiment of the present disclosure. Figure 7 As shown, the electronic device includes a memory and a processor, the memory is used to store computer instructions that can be executed on the processor, and the processor is used to implement the parking lot cleaning method described in any embodiment of the present disclosure when executing the computer instructions.

[0157] At least one embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any parking lot cleaning method described in the present disclosure.

[0158] It will be understood by those skilled in the art that one or more embodiments of the present disclosure may be provided as a method, system, or computer program product. Therefore, one or more embodiments of the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present disclosure may take the form of a computer program product implemented 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.

[0159] In the present disclosure, “and / or” means at least one of the two. For example, “A and / or B” includes three solutions: A, B, and “A and B”.

[0160] The various embodiments of this disclosure are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the data processing device embodiment is generally similar to the method embodiment, so its description is relatively simple. For relevant portions, refer to the description of the method embodiment.

[0161] The foregoing description describes specific embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0162] Embodiments of the subject matter and functional operations described in this disclosure may be implemented in the following: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this disclosure and their structural equivalents, or a combination of one or more thereof. Embodiments of the subject matter described in this disclosure may be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier to be executed by a data processing device or to control the operation of a data processing device. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagation signal, such as a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode information and transmit it to a suitable receiver device for execution by a data processing device. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more thereof.

[0163] The processes and logic flows described in this disclosure can be performed by one or more programmable computers executing one or more computer programs to perform the corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can be implemented as, special purpose logic circuitry, such as an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).

[0164] Computers suitable for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, or the computer will be operably coupled to such mass storage devices to receive data from them or to transmit data to them, or both. However, a computer does not necessarily have such devices. In addition, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0165] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and storage devices, including, for example, semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0166] Although the present disclosure includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of the claimed protection, but are primarily used to describe the features of the specific embodiments of a particular invention. Certain features described in multiple embodiments within the present disclosure may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may function in certain combinations as described above and even initially claimed as such, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of the sub-combination.

[0167] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into multiple software products.

[0168] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the particular order shown or sequential sequence to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.

[0169] The above description is merely a preferred embodiment of one or more embodiments of the present disclosure and is not intended to limit one or more embodiments of the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present disclosure shall be included in the scope of protection of one or more embodiments of the present disclosure.

Claims

1. A parking lot cleaning method, characterized in that: Applied to sanitation vehicles, the method includes: Determining at least one first parking space area based on an original key point of each original parking space area on the passage in the parking lot map, wherein the first parking space area includes at least one original parking space area, and the original key point is determined based on a center position of the original parking space area; determining a global path to each first parking space area based on first key points corresponding to each first parking space area, wherein the first key points are determined based on original key points of all original parking space areas in the first parking space area; For the first parking area reached by the sanitation vehicle according to the global path, obtaining a real-time map of the first parking area, and determining a parking area to be cleaned according to the real-time map, wherein the parking area to be cleaned includes one or more consecutive vacant parking spaces; Determine a local path to each parking area to be cleaned based on the second key point corresponding to each parking area to be cleaned, including: Obtaining a second key point corresponding to each parking area to be cleaned, where the second key point is determined according to a starting position of the parking area to be cleaned; Determine a second cleaning order for each parking area to be cleaned, with the goal of minimizing the total path cost from the location of the sanitation vehicle, passing through all second key points, and the starting and ending locations of each parking area to be cleaned, to the end location of the first parking area; According to the second cleaning sequence and the cleaning mode for cleaning each parking area to be cleaned, a local path to each parking area to be cleaned is determined.

2. The method according to claim 1, characterized in that The step of determining at least one first parking space area according to the original key point of each original parking space area on the passage in the parking lot map includes: The original parking areas whose distances between the original key points are less than the distance threshold are divided into the same group; The original parking space area in the same group is determined as the first parking space area.

3. The method according to claim 1, characterized in that The determining of a global path to each first parking space area according to the first key point corresponding to each first parking space area includes: Obtaining the starting position and the ending position of the passage, and the first key points of all first parking spaces on the passage; Determine a first cleaning order with the goal of taking the shortest path from the starting position, passing through all first key points, and reaching the end position; A global path to each first parking space area is determined according to the first cleaning sequence.

4. The method according to claim 1, wherein The step of obtaining the second key point corresponding to each parking area to be cleaned includes: Obtaining a channel closest to the parking area to be cleaned, a center line of the channel, and a plurality of sampling points located on the center line; For each sampling point, obtaining the connection cost from the sampling point to the starting position of the parking area to be cleaned; The sampling point with the smallest connection cost is determined as the second key point of the parking area to be cleaned.

5. The method according to claim 1, wherein The method further comprises: Dividing each parking space area to be cleaned into a first continuous parking space area, a second continuous parking space area, or a single parking space area based on the number of vacant parking spaces in each parking space area to be cleaned, wherein the number of consecutive vacant parking spaces in the first continuous parking space area is greater than or equal to a number threshold, and the number of consecutive vacant parking spaces in the second continuous parking space area is less than the number threshold; In response to detecting that the parking space area to be cleaned belongs to the first continuous parking space area, setting the cleaning mode of the sanitation vehicle to a C-mode; In response to detecting that the parking space area to be cleaned belongs to the second continuous parking space area, setting the cleaning mode of the sanitation vehicle to a zigzag mode; In response to detecting that the parking area to be cleaned belongs to a single parking area, the cleaning mode of the sanitation vehicle is set to an L-shaped mode.

6. The method according to claim 5, characterized in that The method further comprises: Get the cleaning width of the parking area to be cleaned; The cleaning distance between the cleaning brushes on both sides of the sanitation vehicle is adjusted according to the cleaning width.

7. The method according to claim 5, characterized in that The method further comprises: In response to monitoring that a vacant parking space in the parking area to be cleaned is occupied during the cleaning process, or a parking space adjacent to the parking area to be cleaned becomes vacant, causing the state of the parking area to be cleaned to change, the local path is re-determined based on the changed parking area to be cleaned and the current location of the sanitation vehicle.

8. The method according to claim 1, characterized in that The method further comprises: After cleaning is completed along the global path, if the number of parking areas to be cleaned is greater than a quantity threshold, a local path is generated according to the parking areas to be cleaned and cleaning is performed along the local path.

9. A parking lot cleaning device, characterized in that: Applied to sanitation vehicles, the device includes: a first parking space area determining unit, configured to determine at least one first parking space area based on an original key point of each original parking space area on the passage in the parking lot map, wherein the first parking space area includes at least one original parking space area, and the original key point is determined based on a center position of the original parking space area; a global path determining unit, configured to determine a global path to each first parking area based on a first key point corresponding to each first parking area, wherein the first key point is determined based on original key points of all original parking areas in the first parking area; a parking space area to be cleaned determining unit, configured to obtain a real-time map of the first parking space area reached by the sanitation vehicle according to the global path, and determine a parking space area to be cleaned based on the real-time map, wherein the parking space area to be cleaned includes one or more consecutive vacant parking spaces; The local path determination unit is used to determine the local path to each parking area to be cleaned according to the second key point corresponding to each parking area to be cleaned, including: Obtaining a second key point corresponding to each parking area to be cleaned, where the second key point is determined according to a starting position of the parking area to be cleaned; Determine a second cleaning order for each parking area to be cleaned, with the goal of minimizing the total path cost from the location of the sanitation vehicle, passing through all second key points, and the starting and ending locations of each parking area to be cleaned, to the end location of the first parking area; According to the second cleaning sequence and the cleaning mode for cleaning each parking area to be cleaned, a local path to each parking area to be cleaned is determined.

10. An electronic device, characterized in that: The device comprises: processor; A memory for storing processor-executable instructions for executing the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images