WO2023019873A1 - 清扫路径的规划 - Google Patents

清扫路径的规划 Download PDF

Info

Publication number
WO2023019873A1
WO2023019873A1 PCT/CN2022/070536 CN2022070536W WO2023019873A1 WO 2023019873 A1 WO2023019873 A1 WO 2023019873A1 CN 2022070536 W CN2022070536 W CN 2022070536W WO 2023019873 A1 WO2023019873 A1 WO 2023019873A1
Authority
WO
WIPO (PCT)
Prior art keywords
cleaning
area
areas
target area
path
Prior art date
Application number
PCT/CN2022/070536
Other languages
English (en)
French (fr)
Inventor
黄超
盛文威
Original Assignee
上海仙途智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海仙途智能科技有限公司 filed Critical 上海仙途智能科技有限公司
Publication of WO2023019873A1 publication Critical patent/WO2023019873A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30—Map- or contour-matching
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes

Definitions

  • One or more embodiments of this specification relate to the field of computer technology, and in particular to a method and device for planning a cleaning path.
  • one or more embodiments of this specification provide a cleaning path planning method and device.
  • a cleaning path planning method is proposed, which is applied to any cleaning task
  • the method includes: acquiring several areas to be cleaned, and performing obstacle scanning on the several areas to be cleaned; when there is an obstacle in any area to be cleaned, based on the position information of the obstacle, the The area to be cleaned is divided into a plurality of sub-areas to obtain a target area set, which includes divided sub-areas and areas to be cleaned without obstacles; for each target area in the target area set , carry out cleaning path planning inside the area, and obtain the internal cleaning path of the target area; based on the internal cleaning path of each target area, perform cleaning path planning between areas, and determine the external cleaning path between each target area; The internal cleaning path and the external cleaning path are used to generate a global cleaning path.
  • a cleaning path planning device which is applied to any electronic device that performs cleaning tasks, and the device includes an obstacle scanning unit, an area division unit, and an intra-area planning unit , an inter-domain planning unit and a path generation unit: the obstacle scanning unit is used to acquire several areas to be cleaned, and scan the obstacles on the several areas to be cleaned; the area division unit is used to When there is an obstacle in the area, based on the position information of the obstacle, the area to be cleaned is divided into a plurality of sub-areas to obtain a set of target areas, the set of target areas includes sub-areas obtained after division and no obstacles The area to be cleaned of objects; the intra-area planning unit is used to plan the cleaning path inside the area for each target area in the target area set, and obtain the internal cleaning path of the target area; the inter-domain planning A unit, configured to plan cleaning paths between regions based on the internal cleaning paths of each target area, and determine an external cleaning path between each target area; the path generation unit
  • an electronic device including a processor, and a memory for storing processor-executable instructions; wherein, the processor executes the executable instructions
  • a computer-readable storage medium on which computer instructions are stored, and when the computer instructions are executed by a processor, the method described in the above-mentioned first aspect is implemented. step.
  • the electronic device performing the cleaning task can obtain several areas to be cleaned and scan for obstacles.
  • the area to be cleaned can be divided into Multiple sub-areas, the area to be cleaned without obstacles, and the sub-areas divided by the area to be cleaned with obstacles constitute the target area set; for each target area in the target area set, the path planning within the area is performed , get the internal cleaning path of each target area, further plan the cleaning path between the target areas based on the internal cleaning path of each target area, and obtain the external cleaning path between each target area, based on the internal cleaning path and external cleaning path paths, concatenated to generate a global sweeping path.
  • the electronic device performing the cleaning task can obtain and scan the area to be cleaned, divide sub-areas according to obstacles, and then combine the sub-areas for path planning within and between areas to dynamically generate a global cleaning path. There is no need to build and maintain fixed lanes, which can avoid equipment damage and effectively reduce costs.
  • Fig. 1 is a flow chart of a method for planning a cleaning path provided by an exemplary embodiment of the present specification.
  • Fig. 2 is a schematic diagram of a preset map including several areas to be cleaned according to an exemplary embodiment of the present specification.
  • Fig. 3 is a schematic diagram of dividing an area to be cleaned into multiple sub-areas according to an exemplary embodiment of the present specification.
  • Fig. 4 is a schematic diagram of a generated global cleaning path according to an exemplary embodiment of the present specification.
  • Fig. 5 is a flowchart of a method for obtaining internal cleaning paths of each target area according to an exemplary embodiment of the present specification.
  • Fig. 6 is a schematic diagram of internal cleaning paths of each target area shown in an exemplary embodiment of the present specification.
  • Fig. 7 is a flow chart of a method for determining external cleaning routes between target areas according to an exemplary embodiment of the present specification.
  • Fig. 8 is a flow chart of a method for determining the cleaning cost between any two target areas according to an exemplary embodiment of the present specification.
  • Fig. 9 is a schematic diagram showing a corresponding weighted directed graph generated from a target area and cleaning costs between the target areas according to an exemplary embodiment of the present specification.
  • Fig. 10 is a schematic diagram of multiple internal cleaning paths with different cleaning start points and cleaning end points obtained in the same target area according to an exemplary embodiment of the present specification.
  • Fig. 11 is a flow chart of a method for determining a cleaning cost for a target area with multiple groups of cleaning start points and cleaning end points according to an exemplary embodiment of the present specification.
  • Fig. 12 is a schematic diagram of determining cleaning costs between multiple virtual areas generated in the same target area according to an exemplary embodiment of the present specification.
  • Fig. 13 is a schematic structural diagram of an electronic device where an apparatus for planning a cleaning path is located according to an exemplary embodiment.
  • Fig. 14 is a block diagram of an apparatus for planning a cleaning path provided by an exemplary embodiment.
  • the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification.
  • the method may include more or less steps than those described in this specification.
  • a single step described in this specification may be decomposed into multiple steps for description in other embodiments; multiple steps described in this specification may also be combined into a single step in other embodiments describe.
  • this specification proposes a cleaning path planning method, which can be applied to any electronic device that performs cleaning tasks, including but not limited to unmanned cleaning vehicles.
  • the method is suitable for the above-mentioned urban sanitation applications under the scene.
  • FIG. 1 is a flow chart of a method for planning a cleaning path provided in an exemplary embodiment of the present specification.
  • the cleaning path planning method may include the following specific steps: Step 102, the electronic device performing the cleaning task acquires several areas to be cleaned, and scans for obstacles in the several areas to be cleaned.
  • the cleaning task performed by the electronic device is a cleaning task for several areas to be cleaned.
  • a map with a predetermined range can be preset in the electronic device, and there are several cleaning tasks in the map that need to be cleaned Areas to be cleaned by overlay cleaning. These areas to be cleaned can actually be parking spaces, open spaces, and roads.
  • the electronic device needs to perform a cleaning task, and in order to complete this cleaning task, the electronic device will plan a cleaning path. It can be understood that a number of areas to be cleaned may also be preset in the electronic device in a form other than a map, which is not specifically limited.
  • FIG. 2 is a schematic diagram of a map including several areas to be cleaned that is preset in an electronic device according to an exemplary embodiment of the present specification.
  • area 1 to be cleaned is an open space
  • Areas 2 and 3 to be cleaned are parking spaces
  • area 4 to be cleaned is a road.
  • the area to be cleaned shown in FIG. 2 is only used for illustration and does not constitute a specific limitation.
  • the electronic device Before performing the cleaning task, the electronic device will first obtain several areas to be cleaned, specifically, the electronic device can obtain position information of several areas to be cleaned, and the position information includes coordinates that can locate the area to be cleaned information etc. Taking the area to be cleaned 1 in the map shown in FIG. 2 as an example, the electronic device will acquire the coordinate information of the four vertices of the area to be cleaned 1 in the map.
  • the electronic device After obtaining several areas to be cleaned, in order to dynamically generate a safer and more efficient cleaning path in combination with specific environmental conditions, the electronic device will scan the several areas to be cleaned for obstacles to determine whether each area to be cleaned is currently There is an obstacle.
  • the electronic device can scan obstacles in each area to be cleaned with the help of sensors such as radar installed in itself, and can also receive monitoring
  • the camera takes images from a bird's-eye view and performs obstacle scanning on each area to be cleaned based on the images. This embodiment does not limit the specific implementation of the electronic device's obstacle scanning.
  • the electronic device may drive based on a preset reference route, and scan the obstacles in the several areas to be cleaned through sensors and cameras equipped on itself during driving.
  • the preset reference path is only a driving path preset in the driving system of the electronic device, and does not need to establish a physical lane.
  • the preset reference path should satisfy, based on the reference path After complete driving, the location information of all obstacles in the area to be cleaned can be obtained. Taking the reference path shown in FIG. 2 as an example, the reference path is a circular path. Based on the complete reference path, the location information of all obstacles in the area to be cleaned can be obtained, that is, as shown in FIG. 2, the The above-mentioned electronic equipment can scan and obtain the obstacles 1-1 and 1-2 in the area to be cleaned 1, the obstacles 3-1 and 3-2 in the area 3 to be cleaned, and the obstacle 4-2 in the area 4 to be cleaned. 1 location information.
  • Step 104 when there is an obstacle in any area to be cleaned, the electronic device divides the area to be cleaned into a plurality of sub-areas based on the location information of the obstacle, and obtains a set of target areas, the set of target areas Include the divided sub-area and the area to be cleaned without obstacles.
  • the electronic device After obtaining the area to be cleaned and scanning it for obstacles, the electronic device will divide the sub-area based on whether there are obstacles in the area, and obtain the undivided area to be cleaned and the sub-area after dividing the area to be cleaned. A set of target areas, and then plan and generate a cleaning path based on each target area in the set of target areas, so as to avoid damage to electronic equipment caused by the existence of obstacles in the planned and generated cleaning paths without considering obstacles. Corruption problem.
  • the electronic device may not perform area division, and an original area to be cleaned is a target area. For example, if there is no obstacle in the area to be cleaned 2 in the map shown in FIG. 2 , the area to be cleaned 2 is a target area.
  • the area For scanning the area to be cleaned with obstacles, the area is divided, and the electronic device will divide the area to be cleaned into multiple sub-areas based on the position information of the area to be cleaned and the position information of the internal obstacles.
  • the area to be cleaned is no longer included in the target area set, and multiple sub-areas obtained by dividing the area to be cleaned are included in the target area set instead of the area to be cleaned, and a divided sub-area is a target area.
  • the electronic device may use a greedy algorithm to divide the area to be cleaned into multiple sub-areas based on the position information of obstacles, and the greedy algorithm will make each time when dividing the area to be cleaned The area of the obtained sub-region is as large as possible, and the number of finally obtained sub-regions is as small as possible, which is conducive to improving the efficiency of subsequent path planning and generation. Taking the area 1 to be cleaned in the map shown in Figure 2 as an example, the electronic device will divide the area 1 to be cleaned into sub-areas 1-1, sub-areas 1-2, and sub-areas 1-3 shown in Figure 3 and subregions 1-4.
  • Step 106 the electronic device performs cleaning path planning inside the area for each target area in the set of target areas, and obtains the internal cleaning path of the target area.
  • the electronic device After obtaining the set of target areas, the electronic device will plan the internal cleaning path for each target area in the set of target areas, the undivided original area to be cleaned in the set of target areas, and The sub-area divided by the original area to be cleaned is an equivalent target area, and it is not necessary to distinguish when planning the cleaning path inside the area.
  • the electronic device can plan the internal cleaning path for each target area based on the preset cleaning path planning rules to obtain the internal cleaning path of the target area, wherein different target areas can all adopt the same cleaning path planning
  • the rules may also use different cleaning path planning rules respectively. This embodiment does not limit the specific implementation manner of obtaining the internal cleaning paths of each target area based on the cleaning path planning rules.
  • the internal cleaning path obtained after planning the cleaning path inside the area should cover the entire area, so that the electronic device is based on the internal cleaning path.
  • the sweeping path can complete a blanket sweep of the entire area.
  • Step 108 the electronic device performs cleaning path planning between areas based on the internal cleaning paths of each target area, and determines an external cleaning path between each target area.
  • the internal cleaning path of the target area obtained after the cleaning path planning inside the area is a path with two endpoints.
  • the path can be a straight line or a curve.
  • the two endpoints are usually located at the apex or On the boundary, the electronic device can determine the cleaning start point and the cleaning end point of the target area based on the two end points of the internal cleaning path, wherein the same end point of the internal cleaning path can be used as the cleaning start point of the target area, or can be As the cleaning end point of the target area.
  • end point A is used as the cleaning start point of the target area
  • end point B is the cleaning end point of the target area
  • end point A is used as the cleaning end point of the target area
  • end point B is the starting point of cleaning in the target area
  • the electronic device After the electronic device determines the cleaning start point and cleaning end point of each target area, it will determine the external cleaning path between each target area based on the cleaning start point and cleaning end point.
  • the cleaning starting point of this target area is used to carry out the covering cleaning inside the target area. Starting from the cleaning end point of this target area, it can reach the cleaning starting point of other target areas for covering cleaning inside other target areas.
  • the electronic device will Determine the cleaning sequence of each target area and the cleaning path between two adjacent target areas.
  • the global cleaning starting point and the global cleaning end point can be preset in the electronic device, and the external cleaning path should start from the global cleaning starting point, clean all target areas, and reach the global cleaning end point, so that all The electronic device can move between areas and clean all target areas based on the external cleaning path.
  • the global cleaning start point and the global cleaning end point may not be preset in the electronic device, combined with the current location of the electronic device and the cleaning start points of the target areas located at the first and last positions in the cleaning sequence in the planned external cleaning path And cleaning end point also can finish above-mentioned cleaning task.
  • Step 110 the electronic device generates a global cleaning path based on the internal cleaning path and the external cleaning path.
  • the electronic device determines the cleaning sequence of all target areas and the cleaning paths between adjacent target areas in the cleaning sequence based on the external cleaning path, and based on the cleaning sequence, the corresponding The cleaning paths between adjacent target areas and the internal cleaning paths inside the target areas are concatenated to generate a global cleaning path.
  • the electronic device performing the cleaning task can obtain several areas to be cleaned and scan for obstacles.
  • the area to be cleaned can be divided into Multiple sub-areas, the area to be cleaned without obstacles, and the sub-areas divided by the area to be cleaned with obstacles constitute the target area set; for each target area in the target area set, the path planning within the area is performed , get the internal cleaning path of each target area, further plan the cleaning path between the target areas based on the internal cleaning path of each target area, and obtain the external cleaning path between each target area, based on the internal cleaning path and external cleaning path paths, concatenated to generate a global sweeping path.
  • the electronic device performing the cleaning task can obtain and scan the area to be cleaned, divide sub-areas according to obstacles, and then combine the sub-areas for path planning within and between areas to dynamically generate a global cleaning path. There is no need to build and maintain fixed lanes, which can avoid equipment damage and effectively reduce costs.
  • this embodiment may further include, after the global cleaning path is generated, the electronic device executes cleaning tasks for the plurality of areas to be cleaned based on the global cleaning path.
  • the electronic device moves between different target areas and performs covering cleaning in each target area.
  • the internal cleaning path of the target area in step 106 may be obtained after path planning based on preset cleaning path planning rules.
  • the area type of the area to be cleaned and the mapping relationship between the area type and the cleaning path planning rules are preset in the electronic device for performing the cleaning task.
  • the area type of the area to be cleaned may be preset based on the shape and size of the area to be cleaned, and/or the actual use of the area to be cleaned. Taking the map shown in Fig. 2 as an example, based on actual use, the area type of the area to be cleaned 1 is preset as an open space, the area types of the areas to be cleaned 2 and 3 are preset as parking spaces, and the area to be cleaned 4
  • the area type for is pre-set to road; the area types described here are for illustration purposes only and are not intended to be specific limitations.
  • cleaning path planning rules can be specified based on the shape and size of the target area under the area type, and/or the actual use.
  • the cleaning path planning rules indicate the specific way of path planning within the area . Taking the map shown in Figure 2 as an example, for the three types of areas it includes, the cleaning path planning rules corresponding to the open space plan the cleaning path in a serpentine manner, and the cleaning path planning rules corresponding to the parking spaces are based on the number of consecutive parking spaces in U
  • the cleaning path is planned in a font, N or L shape, while the cleaning path planning rules corresponding to the road plan the cleaning path in a straight line based on the length of the road; the cleaning path planning rules corresponding to the area types described here are only for example description, without specific limitation.
  • mapping relationship between the area type and the cleaning path planning rules is preset in the electronic device for easy query.
  • the electronic device performs cleaning path planning inside the area for each target area in the target area set, and obtains the internal cleaning path of the target area, including: Step 1062, For each target area, the electronic device acquires the area type of the target area.
  • Step 1064 the electronic device searches the mapping relationship for cleaning path planning rules corresponding to the area type.
  • Step 1066 the electronic device plans the cleaning path inside the target area based on the cleaning path planning rules, and obtains the internal cleaning path of the target area.
  • the electronic device may acquire the area type of the area to be cleaned, and for the subareas in the target area set divided by the original area to be cleaned, the electronic device may acquire the area type of the area to be cleaned to which the subarea belongs. Query the mapping relationship based on the obtained area type, obtain the cleaning path planning rules corresponding to each target area, and then perform internal cleaning path planning for each target area based on the queried cleaning path planning rules, and obtain The internal cleaning path of the target area.
  • the path planning is carried out in a serpentine manner parallel to its longer boundary, and the internal cleaning path of each target area in the area to be cleaned 1 is obtained.
  • path planning is performed based on the number of consecutive parking spaces included in the target area.
  • the path planning is performed in a U-shaped manner.
  • path planning is performed in an N-shaped manner; when the number of continuous parking spaces is less than or equal to the second number threshold.
  • path planning is performed based on the length of the road in the target area.
  • path planning is performed in a straight line.
  • the length of the road is less than the length threshold
  • the area type and cleaning path planning rules are pre-set based on the shape and/or actual use of the area to be cleaned, and the electronic device performing the cleaning task can query the corresponding cleaning path planning rules based on the area type of the target area for cleaning.
  • the planning of the internal cleaning path improves the efficiency of path planning while ensuring the accuracy and effectiveness of the planned internal cleaning path.
  • the electronic device performs cleaning path planning between areas based on the internal cleaning paths of each target area, and determines the external cleaning path between each target area.
  • the cleaning path includes: step 1082, the electronic device determines the cleaning start point and the cleaning end point of the target area based on the internal cleaning path of each target area.
  • Step 1084 the electronic device determines the cleaning cost between any two target areas based on the cleaning start point and the cleaning end point of each target area.
  • the internal cleaning path of the target area obtained after the cleaning path planning inside the area is a path with predetermined two ends, and based on the two end points, the electronic device can determine the cleaning start point and cleaning end point of the target area.
  • the cleaning cost between any two target areas can be determined.
  • the cleaning cost between any two target areas is bidirectional. Taking the cleaning cost between the first target area and the second target area as an example, the cleaning cost between the first target area and the second target area , including not only the cleaning cost determined based on the cleaning end point of the first target area and the cleaning start point of the second target area, that is, the cleaning cost of cleaning the first target area first and then cleaning the second target area, and It includes a cleaning cost determined based on the cleaning end point of the second target area and the cleaning start point of the first target area, that is, the cleaning cost of cleaning the first target area after cleaning the second target area.
  • the specific cost value of the cleaning cost may be determined based on the specific distance between the cleaning start point and the cleaning end point, and the collision penalty caused by obstacles in the cleaning path, which is not limited in this embodiment.
  • the electronic device determines the cleaning cost between any two target areas based on the cleaning start point and cleaning end point of each target area, including: step 1084a, the electronic device The device first determines whether the area distance between any two target areas exceeds a preset distance threshold.
  • the electronic device may determine the area distance between the two target areas based on the position information of the center point of the target area, or determine the area distance between the two target areas based on the cleaning start point and the cleaning end point of the target area. For example, when determining the cleaning cost between the first target area and the second target area, if the cleaning cost for cleaning the first target area and then cleaning the second target area is determined, it may be based on the The distance between the cleaning end point of the first target area and the cleaning start point of the second target area determines the area distance; if the cleaning cost of cleaning the first target area after cleaning the second target area is determined , the area distance may be determined based on the distance between the cleaning start point of the first target area and the cleaning end point of the second target area.
  • Step 1084b when the distance of the area does not exceed the distance threshold, the electronic device determines the cleaning cost for the cleaning start point and cleaning end point of the target area based on a preset cost estimation algorithm; step 1084c, when When the area distance exceeds the distance threshold, the electronic device determines the starting distance between the cleaning start point of the target area and a preset reference path, and the distance between the cleaning end point of the target area and the reference path. The distance to the end point, and based on the distance from the start point and the distance to the end point, determine the cleaning cost.
  • the distance between the areas does not exceed the distance threshold, it means that the distance between the two target areas is relatively close. Describe the cost of cleaning.
  • Hybrid A Star Hybrid A Star
  • the Hybrid A Star algorithm can be used to further combine collision penalties through the dubin and reeds-sheep curves that conform to vehicle kinematics, and determine based on the cleaning end point of the first target area and the cleaning start point of the second target area First clean the first target area and then clean the cleaning cost of the second target area, determine the cleaning cost of cleaning the second target area first and then clean the first target area based on the cleaning starting point of the first target area and the cleaning end point of the second target area, so that A bidirectional cleaning cost between the first target area and the second target area is determined.
  • the electronic device can first determine the starting distance between the preset reference path and the starting point of cleaning in the target area, and the distance between the reference path and the target area. The end distance between the cleaning end points of the area, and then the cleaning cost is determined based on the starting point distance and the end point distance.
  • the electronic device can select a first reference point close to the cleaning end point of the first target area on the preset reference path, and use a cost estimation algorithm such as the Hybrid A Star (hybrid A star) algorithm to determine the The end distance between the cleaning end point of the first target area and the first reference point, and select a second reference point on the reference path that is close to the cleaning start point of the second target area, and use the cost estimation method to determine The starting distance between the cleaning starting point of the second target area and the second reference point is determined based on the starting distance, the end point distance, and the distance between the first and second reference points on the reference path, and the cleaning of the second reference point is determined first.
  • a cost estimation algorithm such as the Hybrid A Star (hybrid A star) algorithm
  • the cleaning cost of cleaning the second target area after the first target area similarly, determine the cleaning cost of cleaning the first target area after cleaning the second target area, and then determine the distance between the first target area and the second target area Two-way cleaning cost.
  • the electronic device can also select a plurality of first reference points on the reference path to respectively determine the terminal distance between them and the cleaning end point of the first target area, and the first reference point corresponding to the minimum terminal distance The cleaning cost is determined, and other situations are the same.
  • Step 1086 the electronic device determines the external cleaning path between all target areas with the goal of cleaning all target areas starting from the preset global cleaning starting point and reaching the preset global cleaning end point with the minimum total cleaning cost.
  • a weighted directed graph can be constructed, each target area is used as a node, and the cleaning cost between any two target areas is used as a directed weight between nodes.
  • the global cleaning path is preset with a global cleaning starting point and a global cleaning end point
  • the global cleaning starting point and the global cleaning end point are also used as nodes in the graph
  • the global cleaning starting point is the starting point node
  • the end point of the global cleaning is the end node; wherein, the directional weight between the starting node and the corresponding node of the target area, and the directional weight between the corresponding node of the target area and the end node are unidirectional.
  • the cleaning cost of cleaning the first target area first and then cleaning the second target area that is, the directed weight w12 of the first node corresponding to the first target area pointing to the second node corresponding to the second target area
  • the cleaning cost of cleaning the first target area after cleaning the second target area that is, the directed weight w21 of the second node pointing to the first node
  • the starting node points to the directional weight w01 of the first node, starting from the starting point of the global cleaning, the cleaning cost of cleaning the second target area first, that is, the directional weight w02 of the starting node pointing to the second node, each target area corresponds to The node cannot point to the starting node; after cleaning the first target area, it finally reaches the cleaning cost of the global cleaning end point, that is, the directed weight w1n of the end node corresponding to the first node pointing to the global cleaning end point, and finally reaches the global cleaning cost after cleaning the second target area
  • the cleaning cost of cleaning the end point that is
  • the electronic device determines the external cleaning path with the smallest total cleaning cost, that is, in the weighted directed graph, solves the optimal path with the smallest total weight for traversing all nodes, when there is
  • the global cleaning start point and the global cleaning end point are used to solve the optimal path starting from the start node and ending at the end node, traversing all nodes with the smallest total weight.
  • There are many alternative algorithms for solving the optimal path including but not limited to the LKH (Lin-Kernighan-Helsgaun) algorithm under the TSP (Traveling Salesman) problem.
  • the global cleaning path generated under this implementation method when the internal cleaning path of each target area is fixed, based on the connection of the external cleaning path with the smallest total cleaning cost, the optimal cleaning sequence is selected, which effectively reduces the electronic cost of cleaning tasks.
  • the total distance that the equipment transfers between different target areas improves the cleaning efficiency of the equipment.
  • a target area can actually have multiple sets of different cleaning start points and the cleaning end point, for example, as shown in Figure 10, for a rectangular open space target area, two internal cleaning paths can be generated, and the two sets of diagonal vertices on the two diagonals of the regular quadrilateral can form the Four sets of cleaning start points and cleaning end points for the target area.
  • the global cleaning path generated by using different cleaning start points and cleaning end points in the same target area may be very different in the cleaning order and external cleaning paths.
  • an optimal set of cleaning start point and cleaning end point is determined.
  • the electronic device may use different groups of cleaning start points and cleaning end points as the cleaning start points and cleaning end points of the target area respectively, and plan external cleaning paths respectively, and obtain multiple external cleaning paths. After comparing the cleaning paths, determine the best one to generate the global cleaning path.
  • this method is equivalent to solving multiple external cleaning paths for the same multiple target areas, which increases the amount of calculation and affects the efficiency of the equipment. .
  • the electronic device determines the cleaning cost between any two target areas based on the cleaning start point and cleaning end point of each target area, including: 1084A.
  • the electronic device When the target area has multiple sets of cleaning start points and cleaning end points, the electronic device generates a corresponding virtual area for the target area based on each set of cleaning start points and cleaning end points, and obtains multiple virtual areas corresponding to the target area. area.
  • two groups of cleaning starting points and cleaning end points can be determined, which are cleaning starting point A and cleaning end point B, and cleaning Starting point B and cleaning end point A
  • the direction of the internal cleaning path when using cleaning starting point A and cleaning end point B is the same line segment as when using cleaning starting point B and cleaning end point A, but the direction is opposite.
  • another two groups of cleaning start points and cleaning end points may also be determined, which will not be repeated here.
  • Each of the virtual areas is consistent with the target area in shape and size, but their respective cleaning start points and cleaning end points, internal cleaning paths and directions thereof may be different.
  • Step 1084B the electronic device replaces the target area with the plurality of virtual areas to determine the cleaning cost between any two target areas, and obtains a cleaning cost set between any two target areas, where any two The cleaning cost among the virtual areas is determined based on preset virtual area planning rules.
  • the target area that has generated multiple virtual areas no longer participates in the determination of the cleaning cost, and the electronic device will use the multiple virtual areas corresponding to the target area to replace all virtual areas.
  • the target area is used to determine the cleaning cost between areas.
  • each virtual area and the target area that has not generated a virtual area are equivalent to each other, and the electronic device will determine the cleaning cost between any two virtual areas, any virtual area and any other target area that has not generated a virtual area
  • the cleaning cost between, and the cleaning cost between any two target areas that do not generate virtual areas and then get the cleaning cost set.
  • the cleaning cost between the virtual area and other target areas can be determined based on the manner described above.
  • the cleaning cost between virtual areas can be determined based on preset virtual area planning rules.
  • the virtual area planning rule indicates how to determine the cleaning cost between multiple virtual areas generated in the same target area. Specifically, based on the virtual area planning rules, various virtual cleaning sequences among the plurality of virtual areas can be determined first, and then based on the virtual cleaning sequences, the relationship between the virtual areas can be determined with a preset cleaning cost value. The cleaning cost, the virtual cleaning sequence and the preset cleaning cost value can make the multiple virtual areas be cleaned according to one of the multiple virtual cleaning sequences and the multiple virtual areas are cleaned in the subsequently generated external cleaning path. No additional cleaning cost will be added when creating a virtual area.
  • the virtual cleaning sequence first randomly arrange the virtual areas 1, 2, 3, 4 to obtain the first virtual cleaning sequence, which is assumed to be virtual area 1-virtual area 2-virtual area 3-virtual area 4 (hereinafter abbreviated as 1-2-3-4), then the remaining three virtual cleaning sequences can be obtained based on the first virtual cleaning sequence 1-2-3-4, starting from any bit in the first virtual cleaning sequence, When it reaches the last position, it will return to the first position until the four virtual areas are traversed in turn, and the remaining three virtual cleaning sequences are obtained: 2-3-4-1, 3-4-1-2, 4-1-2-3 . Multiple virtual cleaning sequences can also be obtained by generating more virtual areas in the same target area.
  • the cleaning cost from the previous virtual area to the next virtual area is 0, by The cleaning cost from the next virtual area to the previous virtual area is positive infinity; for the two virtual areas at the first and last in the virtual cleaning order, the cleaning cost from the last virtual area to the first virtual area is 0, the cleaning cost from the first virtual area to the last virtual area is positive infinity; for the two virtual areas that are not adjacent in the virtual cleaning sequence and are not at the first and last, the two-way The cleaning costs of are all set to positive infinity; thus, the cleaning costs between virtual regions 1, 2, 3, and 4 shown in Table 3 can be obtained.
  • the planning method of the cleaning path can also be Including: based on preset virtual area planning rules, determining various virtual cleaning sequences among multiple virtual areas; The cleaning cost between the other target areas is replaced by the cleaning cost between the first virtual area in the cleaning order and the same target area, and the corresponding replacement under all virtual cleaning orders is completed to obtain an updated cleaning cost set; the external The cleaning path is determined based on the updated cleaning cost set.
  • Virtual cleaning sequence 1-2-3-4, 2-3-4-1, 3-4-1-2, 4-1-2-3.
  • the replacement of cleaning costs between different virtual areas should be the corresponding replacement for the same target area.
  • the cleaning cost from the virtual area 4 to the second target area should be replaced by the cleaning cost from the virtual area 1 to the second target area.
  • an updated cleaning cost set can be obtained, among which, the cleaning costs from other target areas that have not generated virtual areas to virtual areas, the cleaning costs between virtual areas, and other target areas The cleaning costs between each other do not need to be updated and remain unchanged.
  • the external cleaning path will be determined based on the updated cleaning cost set.
  • Figure 12 shows four kinds of virtual cleaning sequences. Since there are cleaning costs of 0 between the virtual areas, the virtual areas 1, 2, 3, and 4 in the external cleaning path determined with the goal of minimizing the total cleaning cost The cleaning sequence in between must be one of the four virtual cleaning sequences.
  • a target area will reach the first virtual area in any virtual cleaning order, and then arrive at each virtual area in turn based on the virtual cleaning order, and finally the The last virtual area in the virtual cleaning sequence reaches another target area, since the cleaning cost of the last virtual area to other target areas has been replaced by the cleaning cost of the first virtual area to other target areas, the determined external What is actually calculated in the cleaning path is the cleaning cost between the first virtual area and other target areas.
  • the electronic device generates a global cleaning path based on the internal cleaning path and the external cleaning path, including: for a target area with multiple sets of cleaning starting points and cleaning end points, the electronic device generates a global cleaning path based on For the external cleaning path, the virtual area with the first cleaning order among the multiple virtual areas corresponding to the target area is determined as the target virtual area; the internal cleaning path of the target virtual area is used as the internal cleaning path of the target area.
  • the electronic device will use the virtual area that is first in the cleaning order among the multiple virtual areas generated by the target area as the target virtual area to replace the target area to generate a global cleaning path .
  • the first target area generates corresponding virtual areas 1, 2, 3, and 4.
  • the cleaning order starts from the starting point of the global cleaning, and then cleans virtual areas 1, 2, 3, 4 and the first If the second target area finally reaches the end point of the global cleaning, the electronic device may use the virtual area 1 as the target virtual area to replace the first target area to generate a global cleaning path.
  • the global cleaning path generated by the electronic device includes the cleaning path from the global cleaning starting point to the cleaning starting point A of the virtual area 1, the internal cleaning path between the cleaning starting point A and the cleaning end point B of the virtual area 1, and the cleaning path of the virtual area 1.
  • the cleaning path between the cleaning end point B and the cleaning start point of the second target area, the internal cleaning path between the cleaning start point and the cleaning end point of the second target area, and the cleaning between the cleaning end point of the second target area and the global cleaning end point The paths are concatenated.
  • this implementation reduces the amount of calculation for solving the optimal path, and improves the efficiency of the electronic device in planning the global cleaning path.
  • Fig. 13 is a schematic structural diagram of an electronic device provided by an exemplary embodiment.
  • the device includes a processor 1302 , an internal bus 1304 , a network interface 1306 , a memory 1308 and a non-volatile memory 1310 , and of course it may also include hardware required by other services.
  • the processor 1302 reads a corresponding computer program from the non-volatile memory 1310 into the memory 1308 and executes it.
  • one or more embodiments of this specification do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each A logic unit, which can also be a hardware or logic device.
  • the cleaning path planning device can be applied to the electronic device as shown in FIG. 13 to realize the technical solution of this specification.
  • the cleaning path planning device includes an obstacle scanning unit 1410, an area division unit 1420, an intra-area planning unit 1430, an inter-area planning unit 1440, and a path generation unit 1450:
  • the obstacle scanning unit 1410 is used to obtain several areas to be cleaned, and perform obstacle scanning on the several areas to be cleaned;
  • the area division unit 1420 is configured to divide the area to be cleaned based on the position information of the obstacle when there is an obstacle in any area to be cleaned
  • a target area set is obtained for a plurality of sub-areas, and the target area set includes divided sub-areas and areas to be cleaned without obstacles;
  • the intra-area planning unit 1430 is configured to For each target area, perform cleaning path planning inside the area to obtain the internal cleaning path of the target area;
  • the inter-area planning unit 1440 is configured to perform cleaning path planning between areas based on the internal cleaning paths of each target area , to determine an external cleaning
  • the electronic device is preset with the area type of the area to be cleaned, and the mapping relationship between the area type and the cleaning path planning rules; the intra-area planning unit 1430, for each target in the set of target areas Area, planning the cleaning path inside the area to obtain the internal cleaning path of the target area, including: for each target area, obtaining the area type of the target area; searching for the corresponding area type in the mapping relationship Cleaning path planning rules: perform cleaning path planning inside the target area based on the cleaning path planning rules, and obtain internal cleaning paths in the target area.
  • the inter-domain planning unit 1440 performs cleaning route planning between areas based on the internal cleaning route of each target area, and determines the external cleaning route between each target area, including: based on the internal cleaning route of each target area Path, determine the cleaning start point and cleaning end point of the target area; determine the cleaning cost between any two target areas based on the cleaning start point and cleaning end point of each target area; start from the preset global cleaning starting point, clean all For the target area, the minimum total cleaning cost to reach the preset global cleaning end point is the goal, and the external cleaning path between each target area is determined.
  • the inter-domain planning unit 1440 determines the cleaning cost between any two target areas, including: determining whether the area distance between any two target areas exceeds A preset distance threshold; when the distance of the area does not exceed the distance threshold, according to a preset cost estimation method, the cleaning cost is determined based on the cleaning start point and the cleaning end point of the target area; when the area distance When the distance threshold is exceeded, determine the starting distance between the cleaning start point of the target area and the preset reference path, and the end distance between the cleaning end point of the target area and the reference path, and based on the The starting distance and the ending distance determine the cleaning cost.
  • the inter-domain planning unit 1440 determines the cleaning cost between any two target areas based on the cleaning start points and cleaning end points of each target area, including: when the target area has multiple sets of cleaning start points and cleaning end points , generate a corresponding virtual area for the target area based on each group of cleaning start points and cleaning end points, and obtain multiple virtual areas corresponding to the target area; use the multiple virtual areas to replace the target area for any two target areas
  • the determination of the cleaning cost between areas obtains the cleaning cost set between any two target areas, wherein the cleaning cost between any two virtual areas is determined based on preset virtual area planning rules;
  • the inter-domain The planning unit 1440 is further configured to: determine various virtual cleaning sequences between the virtual regions based on preset virtual region planning rules; for each virtual cleaning sequence, place the cleaning cost set in the virtual cleaning
  • the cleaning cost between the virtual area at the end of the order and other target areas is replaced by the cleaning cost between the virtual area at the top of the cleaning order and the same target area, and the corresponding replacements under all virtual cleaning orders are
  • the obstacle scanning unit 1410 performing obstacle scanning on the several areas to be cleaned includes: driving based on a preset reference route, and performing obstacle scanning on the several areas to be cleaned during driving.
  • the device further includes: a task execution unit 1460, configured to execute cleaning tasks for the several areas to be cleaned based on the global cleaning path.
  • a task execution unit 1460 configured to execute cleaning tasks for the several areas to be cleaned based on the global cleaning path.
  • a typical implementing device is a computer, which may take the form of a personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media player, navigation device, e-mail device, game control device, etc. desktops, tablets, wearables, or any combination of these.
  • a computer includes one or more processors (CPUs), input/output interfaces, network interfaces and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • Memory may include non-permanent storage in computer-readable media, in the form of random access memory (RAM) and/or nonvolatile memory such as read-only memory (ROM) or flash RAM. Memory is an example of computer readable media.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash random access memory
  • Computer-readable media including both permanent and non-permanent, removable and non-removable media, can be implemented by any method or technology for storage of information.
  • Information may be computer readable instructions, data structures, modules of a program, 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 technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by computing devices.
  • computer-readable media excludes transitory computer-readable media, such as modulated data signals and carrier waves.
  • first, second, third, etc. may be used in one or more embodiments of the present specification to describe various information, the information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of one or more embodiments of this specification, first information may also be called second information, and similarly, second information may also be called first information. Depending on the context, the word “if” as used herein may be interpreted as “at” or "when” or "in response to a determination.”

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种清扫路径的规划方法、装置、电子设备及计算机可读存储介质，该方法包括：获取若干待清扫区域并对其进行障碍物扫描（102）；当任一待清扫区域内存在障碍物时，基于障碍物的位置信息，将其划分为多个子区域，得到由划分后的子区域以及不存在障碍物的待清扫区域组成的目标区域集合（104）；针对目标区域集合中的每个目标区域，进行区域内部的清扫路径规划，得到目标区域的内部清扫路径（106）；基于各个目标区域的内部清扫路径，进行区域之间的清扫路径规划，确定各个目标区域之间的外部清扫路径（108）；基于内部清扫路径和外部清扫路径生成全局清扫路径（110）。该方法根据扫描到的障碍物划分子区域，动态地生成全局清扫路径，无需构建和维护车道，既能避免设备损坏，且能有效降低成本。

Description

清扫路径的规划 技术领域
本说明书一个或多个实施例涉及计算机技术领域，尤其涉及一种清扫路径的规划方法及装置。
背景技术
随着机器人及相关技术领域的发展，在城市环卫等应用场景下，正在逐步实现由机器代替人工完成清扫。由于城市环卫等应用场景下需要覆盖式清扫的环境复杂、清扫车运动不够灵活，相关技术中，一般采用预先建立固定车道的方式使清扫车基于车道完成清扫，不过该方式中固定车道的构建和维护成本都很高，且一旦环境变动在新环境中就难再适用。
发明内容
有鉴于此，本说明书一个或多个实施例提供一种清扫路径的规划方法及装置。
为实现上述目的，本说明书一个或多个实施例提供如下技术方案：根据本说明书一个或多个实施例的第一方面，提出了一种清扫路径的规划方法，应用于任一执行清扫任务的电子设备，所述方法包括：获取若干待清扫区域，并对所述若干待清扫区域进行障碍物扫描；当任一待清扫区域内存在障碍物时，基于所述障碍物的位置信息，将所述待清扫区域划分为多个子区域，得到目标区域集合，所述目标区域集合中包括划分后得到的子区域以及不存在障碍物的待清扫区域；针对所述目标区域集合中的每个目标区域，进行区域内部的清扫路径规划，得到所述目标区域的内部清扫路径；基于各个目标区域的内部清扫路径，进行区域之间的清扫路径规划，确定各个目标区域之间的外部清扫路径；基于所述内部清扫路径和所述外部清扫路径，生成全局清扫路径。
根据本说明书一个或多个实施例的第二方面，提出了一种清扫路径的规划装置，应用于任一执行清扫任务的电子设备，所述装置包括障碍扫描单元、区域划分单元、域内规划单元、域间规划单元和路径生成单元：所述障碍扫描单元，用于获取若干待清扫区域，并对所述若干待清扫区域进行障碍物扫描；所述区域划分单元，用于当任一待清扫区域内存在障碍物时，基于所述障碍物的位置信息，将所述待清扫区域划分为多个子区域，得到目标区域集合，所述目标区域集合中包括划分后得到的子区域以及不存在障碍物的待清扫区域；所述域内规划单元，用于针对所述目标区域集合中的每个目标区域，进行区域内部的清扫路径规划，得到所述目标区域的内部清扫路径；所述域间规划单元，用于基于各个目标区域的内部清扫路径，进行区域之间的清扫路径规划，确定各个目标区域之间的外部清扫路径；所述路径生成单元，用于基于所述内部清扫路径和所述外部清扫路径，生成全局清扫路径。
根据本说明书一个或多个实施例的第三方面，提出了一种电子设备，包括处理器，和用于存储处理器可执行指令的存储器；其中，所述处理器通过运行所述可执行指令实现上述第一方面所述方法中的步骤。
根据本说明书一个或多个实施例的第四方面，提出了一种计算机可读存储介质，其上存储有计算机指令，所述计算机指令被处理器执行时实现上述第一方面所述方法中的步骤。
由以上描述可以看出，本说明书中，执行清扫任务的电子设备可以获取若干待清扫区域并进行障碍物扫描，当待清扫区域中存在障碍物时，可以基于障碍物的位置信息将其划分为多个子区域，不存在障碍物的待清扫区域、以及由存在障碍物的待清扫区域划分而得的子区域组成了目标区域集合；针对目标区域集合中的每个目标区域进行区域内部的路径规划，得到各个目标区域的内部清扫路径，基于各个目标区域的内部清扫路径 进一步对目标区域彼此间的清扫路径进行规划，得到各个目标区域之间的外部清扫路径，基于所述内部清扫路径和外部清扫路径，串联生成全局清扫路径。该方案中，执行清扫任务的电子设备可以在获取待清扫区域并进行扫描后，根据障碍物划分子区域，进而结合子区域进行区域内部和区域之间的路径规划以动态地生成全局清扫路径，无需构建和维护固定车道，既能避免设备损坏，且能有效降低成本。
附图说明
图1是本说明书一示例性实施例提供的一种清扫路径的规划方法的流程图。
图2是本说明书一示例性实施例示出的预先设置的包括若干待清扫区域的地图的示意图。
图3是本说明书一示例性实施例示出的将待清扫区域划分为多个子区域的示意图。
图4是本说明书一示例性实施例示出的生成的全局清扫路径的示意图。
图5是本说明书一示例性实施例示出的得到各个目标区域的内部清扫路径的方法流程图。
图6是本说明书一示例性实施例示出的各个目标区域的内部清扫路径的示意图。
图7是本说明书一示例性实施例示出的确定各个目标区域之间的外部清扫路径的方法流程图。
图8是本说明书一示例性实施例示出的确定任意两个目标区域之间的清扫代价的方法流程图。
图9是本说明书一示例性实施例示出的由目标区域和目标区域之间的清扫代价生成对应的加权有向图的示意图。
图10是本说明书一示例性实施例示出的同一目标区域得到的多条清扫起点和清扫终点不同的内部清扫路径的示意图。
图11是本说明书一示例性实施例示出的针对具有多组清扫起点和清扫终点的目标区域确定清扫代价的方法流程图。
图12是本说明书一示例性实施例示出的确定同一目标区域生成的多个虚拟区域之间的清扫代价的示意图。
图13是一示例性实施例提供的一种清扫路径的规划装置所在电子设备的结构示意图。
图14是一示例性实施例提供的一种清扫路径的规划装置的框图。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本说明书一个或多个实施例相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本说明书一个或多个实施例的一些方面相一致的装置和方法的例子。
需要说明的是：在其他实施例中并不一定按照本说明书示出和描述的顺序来执行相应方法的步骤。在一些其他实施例中，其方法所包括的步骤可以比本说明书所描述的更多或更少。此外，本说明书中所描述的单个步骤，在其他实施例中可能被分解为多个步骤进行描述；而本说明书中所描述的多个步骤，在其他实施例中也可能被合并为单个步骤进行描述。
随着机器人及相关技术领域的发展，城市环卫的应用场景下，正逐步采用无人清扫车等设备代替人工执行清扫任务。不同于小型家用扫地机执行家庭清扫任务，城市环卫场景下需要覆盖式清扫的环境复杂，极易受到往来车辆和行人的干扰，且无人清扫车也不具备小型家用扫地机耐碰撞、移动灵活的特性，因而小型家用扫地机执行家庭清扫任 务时采用的较为激进的路径规划方法在此类场景中并不适用。相关技术中鲜有在城市环卫等应用场景下进行清扫路径规划的方法，一般都是通过预先建立固定车道的方式使清扫车基于车道完成清扫，不过建立和维护固定车道的耗费很高，一旦环境变动，原有车道又难以在新环境中使用，造成了很大的浪费。
有鉴于此，本说明书提出一种清扫路径的规划方法，可以应用在任一执行清扫任务的电子设备中，所述电子设备包括但不限于无人清扫车，所述方法适用于上述城市环卫的应用场景下。
请参考图1，图1为本说明书一示例性实施例提供的一种清扫路径的规划方法的方法流程图。
所述清扫路径的规划方法可以包括如下具体步骤：步骤102，执行清扫任务的电子设备获取若干待清扫区域，并对所述若干待清扫区域进行障碍物扫描。
在本实施例中，所述电子设备执行的清扫任务是针对若干待清扫区域的清扫任务，具体地，所述电子设备中可以预先设置有一范围既定的地图，所述地图中存在着若干需要进行覆盖式清扫的待清扫区域，这些待清扫区域实际上可以是停车位、空地和道路等，它们的大小和形状并没有具体的限制，完成所述地图中所有待清扫区域的覆盖式清扫即所述电子设备需要执行的清扫任务，为完成这一清扫任务，所述电子设备将进行清扫路径的规划。可以理解的是，所述电子设备中也可以采用地图之外的其他形式预先设置若干待清扫区域，具体不做限制。
请参考图2，图2为本说明书一示例性实施例示出的预先设置于电子设备中的包括若干待清扫区域的地图的示意图。
所述地图中存在着4个以矩形框标出的待清扫区域，分别标记为待清扫区域1、待清扫区域2、待清扫区域3和待清扫区域4，其中，待清扫区域1为空地，待清扫区域2、3为停车位，待清扫区域4为道路。图2所示的待清扫区域仅用以示例说明，不构成具体限制。
在执行清扫任务前，所述电子设备首先将获取若干待清扫区域，具体地，所述电子设备可以获取若干待清扫区域的位置信息，所述位置信息包括可以定位出所述待清扫区域的坐标信息等。以图2所示地图中的待清扫区域1为例，所述电子设备将获取到所述待清扫区域1的四个顶点在地图中的坐标信息。
在获取到若干待清扫区域后，为了结合具体环境状况动态生成更安全、高效的清扫路径，所述电子设备将对所述若干待清扫区域进行障碍物扫描，以确定各个待清扫区域内当前是否存在障碍物。所述电子设备对若干待清扫区域进行障碍物扫描存在多种可选择的实现方式，所述电子设备可以借助装配于自身的诸如雷达等传感器对各个待清扫区域进行障碍物扫描，也可以接收监控相机以鸟瞰视角拍摄的图像并基于所述图像对各个待清扫区域进行障碍物扫描，本实施例对于电子设备进行障碍物扫描的具体实现方式不做限制。
在一种可选择的实现方式下，所述电子设备可以基于预设的基准路径行驶，在行驶过程中通过装配于自身的传感器、相机等完成对所述若干待清扫区域的障碍物扫描。
要说明的是，所述预设的基准路径只是预先设置于电子设备驾驶系统中的一条行驶路径，并不需要建立物理车道，另外，预先设置的所述基准路径应当满足，基于所述基准路径完整行驶后能够得到所有待清扫区域内全部障碍物的位置信息。以图2所示的基准路径为例，所述基准路径为环形路径，基于完整的基准路径行驶一周，可以得到所有待清扫区域内全部障碍物的位置信息，即，如图2所示，所述电子设备可以扫描得到待清扫区域1内障碍物1-1和障碍物1-2、待清扫区域3内障碍物3-1和障碍物3-2、以及待清扫区域4内障碍物4-1的位置信息。
步骤104，当任一待清扫区域内存在障碍物时，所述电子设备基于所述障碍物的位 置信息，将所述待清扫区域划分为多个子区域，得到目标区域集合，所述目标区域集合中包括划分后得到的子区域以及不存在障碍物的待清扫区域。
在获取待清扫区域并对其进行障碍物扫描后，所述电子设备将基于区域内是否存在障碍物进行子区域划分，得到由未划分的待清扫区域以及待清扫区域划分后的子区域组成的目标区域集合，进而基于所述目标区域集合中的各个目标区域进行清扫路径的规划和生成，避免在不考虑障碍物的情况下所规划和生成的清扫路径因障碍物的存在而对电子设备造成损坏的问题。
其中，针对扫描不存在障碍物的待清扫区域，所述电子设备可以不进行区域划分，一个原始的待清扫区域即一个目标区域。举例来说，图2所示地图中的待清扫区域2中不存在障碍物，则待清扫区域2即一个目标区域。
而针对扫描存在障碍物的待清扫区域，则进行区域划分，所述电子设备将基于待清扫区域的位置信息以及其内部障碍物的位置信息，划分所述待清扫区域为多个子区域，原始的待清扫区域不再计入目标区域集合，由所述待清扫区域划分后得到的多个子区域代替所述待清扫区域计入目标区域集合，一个划分而得的子区域即一个目标区域。
所述电子设备基于所述位置信息划分一个待清扫区域为多个子区域存在多种可选择的实现方式，本实施例对此不做具体限制。在一种可选择的实现方式下，所述电子设备可以采用贪心算法，基于障碍物的位置信息，将待清扫区域划分为多个子区域，所述贪心算法在划分待清扫区域时将使每次得到的子区域面积尽可能大、使最终得到的子区域数量尽可能少，因而有利于提升后续路径规划和生成的效率。以图2所示地图中的待清扫区域1为例，所述电子设备将划分所述待清扫区域1为图3所示的子区域1-1、子区域1-2、子区域1-3和子区域1-4。
步骤106，所述电子设备针对所述目标区域集合中的每个目标区域，进行区域内部的清扫路径规划，得到所述目标区域的内部清扫路径。
在得到所述目标区域集合后，所述电子设备将针对所述目标区域集合中的每一个目标区域进行区域内部的清扫路径规划，所述目标区域集合中未划分的原始的待清扫区域、以及由原始的待清扫区域划分而得的子区域为等价的目标区域，进行区域内部的清扫路径规划时可以不进行区分。
所述电子设备可以基于预设的清扫路径规划规则对每个目标区域进行区域内部的清扫路径规划，得到所述目标区域的内部清扫路径，其中，不同的目标区域可以均采用相同的清扫路径规划规则，也可以分别采用不同的清扫路径规划规则，本实施例对基于清扫路径规划规则得到各个目标区域的内部清扫路径的具体实现方式不做限制。
要说明的是，由于本实施例中对若干待清扫区域执行的是覆盖式清扫，进行区域内部的清扫路径规划后得到的内部清扫路径应当覆盖整个区域，以使所述电子设备基于所述内部清扫路径可以完成整个区域的覆盖式清扫。
步骤108，所述电子设备基于各个目标区域的内部清扫路径，进行区域之间的清扫路径规划，确定各个目标区域之间的外部清扫路径。
进行区域内部的清扫路径规划后得到的目标区域的内部清扫路径为一条两端端点已定的路径，所述路径可以是直线，也可以是曲线，所述两端端点通常位于目标区域的顶点或边界上，所述电子设备基于所述内部清扫路径的两端端点可以确定所述目标区域的清扫起点和清扫终点，其中，内部清扫路径的同一端点既可以作为该目标区域的清扫起点，也可以作为该目标区域的清扫终点。举例来说，假设一内部清扫路径的两端端点分别标记为端点A和端点B，以端点A作为目标区域的清扫起点则端点B为目标区域的清扫终点，以端点A作为目标区域的清扫终点则端点B为目标区域的清扫起点。
所述电子设备在确定各个目标区域的清扫起点和清扫终点后，将基于所述清扫起点和清扫终点确定各个目标区域之间的外部清扫路径，其中，由其他目标区域的清扫终点 出发可以到的本目标区域的清扫起点，以进行本目标区域内部的覆盖式清扫，由本目标区域的清扫终点出发可以到达其他目标区域的清扫起点，以进行其他目标区域内部的覆盖式清扫，所述电子设备将确定各个目标区域的清扫顺序以及相邻两个目标区域之间的清扫路径。
要说明的是，所述电子设备中可以预先设置全局清扫起点和全局清扫终点，所述外部清扫路径应当自所述全局清扫起点出发，清扫所有目标区域，到达所述全局清扫终点，以使所述电子设备基于所述外部清扫路径可以完成区域之间的移动并清扫所有目标区域。当然，所述电子设备中也可以不预先设置全局清扫起点和全局清扫终点，结合所述电子设备当前所在位置，以及所规划的外部清扫路径中位于清扫顺序首位和末位的目标区域的清扫起点和清扫终点也可以完成上述清扫任务。
步骤110，所述电子设备基于所述内部清扫路径和所述外部清扫路径，生成全局清扫路径。
请参考图4，所述电子设备基于所述外部清扫路径，确定所有目标区域的清扫顺序以及所述清扫顺序下相邻目标区域之间的清扫路径，并基于所述清扫顺序，将所述相邻目标区域之间的清扫路径以及目标区域内部的内部清扫路径串联生成全局清扫路径。
由以上描述可以看出，本说明书中，执行清扫任务的电子设备可以获取若干待清扫区域并进行障碍物扫描，当待清扫区域中存在障碍物时，可以基于障碍物的位置信息将其划分为多个子区域，不存在障碍物的待清扫区域、以及由存在障碍物的待清扫区域划分而得的子区域组成了目标区域集合；针对目标区域集合中的每个目标区域进行区域内部的路径规划，得到各个目标区域的内部清扫路径，基于各个目标区域的内部清扫路径进一步对目标区域彼此间的清扫路径进行规划，得到各个目标区域之间的外部清扫路径，基于所述内部清扫路径和外部清扫路径，串联生成全局清扫路径。
该方案中，执行清扫任务的电子设备可以在获取待清扫区域并进行扫描后，根据障碍物划分子区域，进而结合子区域进行区域内部和区域之间的路径规划以动态地生成全局清扫路径，无需构建和维护固定车道，既能够避免设备损坏，且能有效降低成本。
进一步地，本实施例还可以包括，在生成全局清扫路径后，所述电子设备基于所述全局清扫路径，执行针对所述若干待清扫区域的清扫任务。
所述电子设备基于生成的全局清扫路径，在不同目标区域之间移动并在各个目标区域内部执行覆盖式清扫。
在一种可选择的实现方式下，步骤106中所述目标区域的内部清扫路径可以是基于预先设置的清扫路径规划规则进行路径规划后得到。
执行清扫任务的电子设备中预先设置有待清扫区域的区域类型，以及区域类型和清扫路径规划规则之间的映射关系。
其中，待清扫区域的区域类型可以基于待清扫区域的形状大小，和/或，待清扫区域的实际用途进行预先设置。以图2所示地图为例，基于实际用途，所述待清扫区域1的区域类型预先设置为空地，所述待清扫区域2、3的区域类型预先设置为停车位，所述待清扫区域4的区域类型则预先设置为道路；此处所述的区域类型仅用以示例说明，不构成具体限制。
针对不同的区域类型，可以基于所述区域类型下目标区域的形状大小，和/或实际用途，分别指定对应的清扫路径规划规则，所述清扫路径规划规则指示了区域内部进行路径规划的具体方式。以图2所示地图为例，针对其所包括的3种区域类型，空地对应的清扫路径规划规则以蛇形方式规划清扫路径，停车位对应的清扫路径规划规则基于连续停车位数量分别以U字型、N字型或L字型方式规划清扫路径，而道路对应的清扫路径规划规则基于道路长度以直线方式规划清扫路径；此处所述的区域类型对应的清扫路径规划规则仅用以示例说明，不构成具体限制。
所述区域类型和清扫路径规划规则之间的映射关系预先设置在电子设备之中，便于进行查询。
请参考图5，上述步骤106中，所述电子设备针对所述目标区域集合中的每个目标区域，进行区域内部的清扫路径规划，得到所述目标区域的内部清扫路径，包括：步骤1062，针对每个目标区域，所述电子设备获取所述目标区域的区域类型。
步骤1064，所述电子设备在所述映射关系中查找所述区域类型对应的清扫路径规划规则。
步骤1066，所述电子设备基于所述清扫路径规划规则进行所述目标区域内部的清扫路径规划，得到所述目标区域的内部清扫路径。
具体地，所述电子设备中预先设置的是原始的待清扫区域的区域类型，以及所述区域类型和清扫路径规划规则之间的映射关系，针对目标区域集合中原始的待清扫区域，所述电子设备可以获取所述待清扫区域的区域类型，而针对目标区域集合中由原始的待清扫区域划分而得的子区域，所述电子设备可以获取所述子区域所属待清扫区域的区域类型。基于获取到的所述区域类型查询所述映射关系，得到每个目标区域对应的清扫路径规划规则，进而基于查询到的清扫路径规划规则，对每个目标区域进行区域内部的清扫路径规划，得到所述目标区域的内部清扫路径。
请参考图6，以图2所示地图中的3种区域类型为例，分别基于对应的清扫路径规划规则进行清扫路径规划，得到各个目标区域的内部清扫路径的示意图。
针对区域类型为空地的目标区域，平行于其更长边界以蛇形方式进行路径规划，得到待清扫区域1中各个目标区域的内部清扫路径。
针对区域类型为停车位的目标区域，基于目标区域中包括的连续停车位数量进行路径规划，当所述连续停车位数量大于预设的第一数量阈值时以U字型方式进行路径规划，当所述连续停车位数量小于等于所述第一数量阈值且大于预设的第二数量阈值时以N字型方式进行路径规划，当所述连续停车位小于等于所述第二数量阈值时以L字型进行路径规划，得到待清扫区域2、3中各个目标区域的内部清扫路径。
针对区域类型为道路的目标区域，基于目标区域中的道路长度进行路径规划，当所述道路长度大于等于预设的长度阈值时以直线方式进行路径规划，当所述道路长度小于所述长度阈值时不进行路径规划和清扫，得到待清扫区域4中目标区域的内部清扫路径。
该实现方式下，基于待清扫区域的形状大小和/或实际用途预先设置了区域类型和清扫路径规划规则，执行清扫任务的电子设备可以基于目标区域的区域类型查询对应的清扫路径规划规则以进行内部清扫路径的规划，从而在保障所规划的内部清扫路径准确有效的同时，提高了路径规划效率。
请参考图7，在一种可选择的实现方式下，上述步骤108中，所述电子设备基于各个目标区域的内部清扫路径，进行区域之间的清扫路径规划，确定各个目标区域之间的外部清扫路径，包括：步骤1082，所述电子设备基于各个目标区域的内部清扫路径，确定所述目标区域的清扫起点和清扫终点。
步骤1084，所述电子设备基于各个目标区域的清扫起点和清扫终点，确定任意两个目标区域之间的清扫代价。
进行区域内部的清扫路径规划后得到的目标区域的内部清扫路径为一条两端端点既定的路径，基于所述两端端点，所述电子设备可以确定目标区域的清扫起点和清扫终点。
在确定各个目标区域的清扫起点和清扫终点后，可以确定任意两个目标区域之间的清扫代价。所述任意两个目标区域之间的清扫代价是双向的，以第一目标区域和第二目标区域之间的清扫代价为例，所述第一目标区域和第二目标区域之间的清扫代价，既包括基于所述第一目标区域的清扫终点和所述第二目标区域的清扫起点确定的清扫代价，即先清扫所述第一目标区域后清扫所述第二目标区域的清扫代价，又包括基于所述第二 目标区域的清扫终点和所述第一目标区域的清扫起点确定的清扫代价，即先清扫所述第二目标区域后清扫所述第一目标区域的清扫代价。所述清扫代价的具体代价值可以基于所述清扫起点和清扫终点之间的具体距离，以及由清扫路径中的障碍物造成的碰撞惩罚确定，本实施例对此不做限制。
请参考图8，在一个例子中，上述步骤1084中，所述电子设备基于各个目标区域的清扫起点和清扫终点，确定任意两个目标区域之间的清扫代价，包括：步骤1084a，所述电子设备首先确定任意两个目标区域之间的区域距离是否超出预设的距离阈值。
具体地，所述电子设备可以基于目标区域的中心点的位置信息确定两个目标区域之间的区域距离，也可以基于目标区域的清扫起点和清扫终点确定两个目标区域之间的区域距离。举例来说，当确定第一目标区域和第二目标区域之间的清扫代价时，若确定的是先清扫所述第一目标区域后清扫所述第二目标区域的清扫代价，可以基于所述第一目标区域的清扫终点和所述第二目标区域的清扫起点之间的距离确定所述区域距离；若确定的是先清扫所述第二目标区域后清扫所述第一目标区域的清扫代价，可以基于所述第一目标区域的清扫起点和所述第二目标区域的清扫终点之间的距离确定所述区域距离。
步骤1084b，当所述区域距离未超出所述距离阈值时，所述电子设备基于预设的代价预估算法，针对所述目标区域的清扫起点和清扫终点确定所述清扫代价；步骤1084c，当所述区域距离超出所述距离阈值时，所述电子设备确定所述目标区域的清扫起点和预设的基准路径之间的起点距离，以及所述目标区域的清扫终点和所述基准路径之间的终点距离，并基于所述起点距离和终点距离，确定所述清扫代价。
具体地，当所述区域距离未超出所述距离阈值时，说明两个目标区域距离较近，所述电子设备可以基于目标区域的清扫起点和清扫终点，采用预设的代价预估算法确定所述清扫代价。
举例来说，可以采用Hybird A Star(混合A星)算法，通过符合车辆运动学的dubin和reeds-sheep曲线进一步结合碰撞惩罚，基于第一目标区域的清扫终点与第二目标区域的清扫起点确定先清扫第一目标区域后清扫第二目标区域的清扫代价，基于第一目标区域的清扫起点与第二目标区域的清扫终点确定先清扫第二目标区域后清扫第一目标区域的清扫代价，从而确定了所述第一目标区域和所述第二目标区域之间双向的清扫代价。
当所述区域距离超出所述距离阈值时，说明两个目标区域距离较远，所述电子设备可以先确定预设的基准路径与目标区域的清扫起点之间的起点距离，以及基准路径与目标区域的清扫终点之间的终点距离，进而基于所述起点距离和终点距离确定所述清扫代价。
举例来说，所述电子设备可以在预设的基准路径上选取与第一目标区域的清扫终点相近的第一基准点，采用诸如Hybird A Star(混合A星)算法的代价预估算法确定所述第一目标区域的清扫终点与所述第一基准点之间的终点距离，并在所述基准路径上选取与第二目标区域的清扫起点相近的第二基准点，采用代价预估算法确定所述第二目标区域的清扫起点与所述第二基准点之间的起点距离，基于所述起点距离、终点距离以及所述第一、二基准点在基准路径上的距离，确定先清扫第一目标区域后清扫第二目标区域的清扫代价，同理，确定先清扫第二目标区域后清扫第一目标区域的清扫代价，进而确定了所述第一目标区域和所述第二目标区域之间双向的清扫代价。可以理解的是，所述电子设备也可以在所述基准路径上选取多个第一基准点分别确定其与第一目标区域清扫终点之间的终点距离，以最小终点距离对应的第一基准点确定所述清扫代价，其他情况同理。
步骤1086，所述电子设备以起始自预设的全局清扫起点，清扫所有目标区域，到达预设的全局清扫终点的总清扫代价最小为目标，确定所有目标区域之间的外部清扫路径。
为确定自全局清扫起点出发，清扫所有目标区域，到达全局清扫终点的总清扫代价 最小的外部清扫路径，可以通过加权有向图进行求解。
首先，可以进行加权有向图的构建，将各个目标区域作为节点，任意两个目标区域之间的清扫代价作为节点之间的有向权值。
如果全局清扫路径预设有全局清扫起点和全局清扫终点，构建加权有向图时，除目标区域对应节点外，全局清扫起点和全局清扫终点也作为图中节点，所述全局清扫起点为起始节点，所述全局清扫终点为结束节点；其中，起始节点和目标区域对应节点之间的有向权值、目标区域对应节点和结束节点之间的有向权值是单向的。
如图9所示，先清扫第一目标区域后清扫第二目标区域的清扫代价，即第一目标区域对应的第一节点指向第二目区域对应的第二节点的有向权值w12，先清扫第二目标区域后清扫第一目标区域的清扫代价，即第二节点指向第一节点的有向权值w21；由全局清扫起点出发首先清扫第一目标区域的清扫代价，即全局清扫起点对应的起始节点指向第一节点的有向权值w01，由全局清扫起点出发首先清扫第二目标区域的清扫代价，即起始节点指向第二节点的有向权值w02，各目标区域对应的节点不能指向起始节点；清扫第一目标区域后最终达到全局清扫终点的清扫代价，即第一节点指向全局清扫终点对应的结束节点的有向权值w1n，清扫第二目标区域后最终到达全局清扫终点的清扫代价，即第二节点指向结束节点的有向权值w2n，结束节点不能指向各目标区域对应的节点。
在加权有向图的构建完毕后，所述电子设备确定总清扫代价最小的外部清扫路径，即在所述加权有向图中，求解遍历所有节点的总权值最小的最优路径，当存在全局清扫起点和全局清扫终点，求解自起始节点出发，到达结束节点终止，遍历所有节点的总权值最小的最优路径。求解所述最优路径存在多种可选择的算法，包括但不限于TSP(旅行商)问题下的LKH(Lin-Kernighan-Helsgaun)算法。
该实现方式下生成的全局清扫路径，在各个目标区域的内部清扫路径既定的情况下，基于总清扫代价最小的外部清扫路径串联，选取了最优的清扫顺序，有效降低了执行清扫任务的电子设备在不同的目标区域间转移的总距离，提高了设备的清扫效率。
考虑到目标区域内部的一条内部清扫路径的两端端点实际可以确定两组清扫起点和清扫终点，且同一目标区域可以生成多条内部清扫路径，一个目标区域实际上可以存在多组不同的清扫起点和清扫终点，举例来说，如图10所示，针对形状为长方形的空地类型的目标区域，可以生成两条内部清扫路径，正四边形两条对角线上的两组对角顶点可以构成所述目标区域的四组清扫起点和清扫终点。同一目标区域采用不同的清扫起点和清扫终点生成的全局清扫路径在清扫顺序和外部清扫路径上皆可能有很大不同，为了生成更高效的全局清扫路径，需要在目标区域的多组清扫起点和清扫终点中确定最优的一组清扫起点和清扫终点。
在一种常规的实现方式下，所述电子设备可以使用不同组的清扫起点和清扫终点分别作为所述目标区域的清扫起点和清扫终点，各自进行外部清扫路径的规划，将得到的多条外部清扫路径进行比较后确定其中最优的一条进行全局清扫路径的生成，但该方式相当于针对同样的多个目标区域进行了多次外部清扫路径的求解，增大了运算量，影响了设备效率。
请参考图11，在一种更优的实现方式下，上述步骤1084中，所述电子设备基于各个目标区域的清扫起点和清扫终点，确定任意两个目标区域之间的清扫代价，包括：步骤1084A，当所述目标区域具有多组清扫起点和清扫终点时，所述电子设备基于每组清扫起点和清扫终点为所述目标区域生成对应的虚拟区域，得到所述目标区域对应的多个虚拟区域。
举例来说，如表1所示，针对目标区域内部的一条内部清扫路径的两端端点A、B，可以确定两组清扫起点和清扫终点，它们分别为清扫起点A和清扫终点B、以及清扫起点B和清扫终点A，采用清扫起点A和清扫终点B时所述内部清扫路径的方向与采用 清扫起点B和清扫终点A时所述内部清扫路径虽为同一线段，但方向相反。类推地，针对目标区域内部的另一条内部清扫路径的两端端点C、D，也可以确定另外两组清扫起点和清扫终点，此处不再赘述。
Figure PCTCN2022070536-appb-000001
表1
基于同一目标区域的多组清扫起点和清扫终点，分别生成对应的虚拟区域，得到所述目标区域对应的多个虚拟区域。每个所述虚拟区域在形状大小上与所述目标区域一致，但各自的清扫起点和清扫终点、内部清扫路径及其方向可以不同。
如表1所示，同一目标区域内的每条内部清扫路径，以不同方向分别得到两组清扫起点和清扫终点，每组清扫起点和清扫终点分别生成一个虚拟区域，因而得到了所述目标区域对应的4个虚拟区域，分别标记为虚拟区域1、虚拟区域2、虚拟区域3和虚拟区域4。
步骤1084B，所述电子设备采用所述多个虚拟区域替换所述目标区域进行任意两个目标区域之间的清扫代价的确定，得到任意两个目标区域之间的清扫代价集合，其中，任意两个所述虚拟区域之间的清扫代价基于预设的虚拟区域规划规则确定。
具体地，在确定区域之间的清扫代价时，已生成多个虚拟区域的目标区域不再参与所述清扫代价的确定，所述电子设备将采用所述目标区域对应的多个虚拟区域替换所述目标区域进行区域之间清扫代价的确定。替换后，各个虚拟区域和未生成虚拟区域的目标区域彼此等价，所述电子设备将确定任意两个虚拟区域之间的清扫代价，任一虚拟区域与任一未生成虚拟区域的其他目标区域之间的清扫代价，以及任意两个未生成虚拟区域的目标区域之间的清扫代价，继而得到清扫代价集合。
其中，虚拟区域与其他目标区域之间的清扫代价可以基于前文所述的方式进行确定。
举例来说，假设由第一目标区域生成了对应的虚拟区域1、2、3、4，替换所述第一目标区域，将基于前文所述的诸如Hybird A Star(混合A星)算法的代价预估算法确定虚拟区域1与其他目标区域之间的清扫代价、虚拟区域2与其他目标区域之间的清扫代价、虚拟区域3与其他目标区域之间的清扫代价，以及虚拟区域4与其他目标区域之间的清扫代价，而不再确定第一目标区域与其他目标区域之间的清扫代价，由此可以得到表2所示的虚拟区域与目标区域之间的清扫代价。
Figure PCTCN2022070536-appb-000002
表2
而虚拟区域彼此间的清扫代价，则可以基于预设的虚拟区域规划规则进行确定。
所述虚拟区域规划规则，指示了同一目标区域生成的多个虚拟区域彼此间清扫代价的确定方式。具体地，基于所述虚拟区域规划规则，首先可以确定所述多个虚拟区域之间的多种虚拟清扫顺序，然后基于所述虚拟清扫顺序，以预设的清扫代价值确定虚拟区域彼此间的清扫代价，所述虚拟清扫顺序和预设的清扫代价值可以使得后续生成的外部 清扫路径中，所述多个虚拟区域按照所述多种虚拟清扫顺序中的一种被清扫且清扫所述多个虚拟区域时不会增加额外的清扫代价。
举例来说，针对第一目标区域生成的多个虚拟区域1、2、3、4，基于预设的虚拟区域规划规则，可以确定所述虚拟区域1、2、3、4之间的4种虚拟清扫顺序，首先将所述虚拟区域1、2、3、4随机排列得到第一种虚拟清扫顺序，此处假设其为虚拟区域1-虚拟区域2-虚拟区域3-虚拟区域4(后文简写为1-2-3-4)，则剩余的3种虚拟清扫顺序可以基于第一种虚拟清扫顺序1-2-3-4得到，从第一种虚拟清扫顺序中的任一位出发，达到末位则返回首位，直至4个虚拟区域依次遍历完毕，得到剩余的3种虚拟清扫顺序分别为：2-3-4-1、3-4-1-2、4-1-2-3。同一目标区域生成更多虚拟区域亦可以同理得到多种虚拟清扫顺序。
基于任一所述虚拟清扫顺序，确定虚拟区域彼此间的清扫代价，针对所述虚拟清扫顺序中相邻的两个虚拟区域，由前一虚拟区域到达后一虚拟区域的清扫代价为0，由后一虚拟区域到达前一虚拟区域的清扫代价为正无穷；针对所述虚拟清扫顺序中位于首位和末位的两个虚拟区域，由位于末位的虚拟区域到达位于首位的虚拟区域的清扫代价为0，由位于首位的虚拟区域到达位于末位的虚拟区域的清扫代价为正无穷；针对所述虚拟清扫顺序中不相邻且不是位于首位和末位的两个虚拟区域，二者间双向的清扫代价均设置为正无穷；由此可以得到表3所示的虚拟区域1、2、3、4彼此间的清扫代价。
虚拟区域 1 2 3 4
1 —— 0 正无穷 正无穷
2 正无穷 —— 0 正无穷
3 正无穷 正无穷 —— 0
4 0 正无穷 正无穷 ——
表3
进一步地，为消除进行外部路径规划时因使用多个虚拟区域替换原目标区域因虚拟区域造成的规划误差，在得到清扫代价集合后，确定外部清扫路径前，所述清扫路径的规划方法还可以包括：基于预设的虚拟区域规划规则，确定多个虚拟区域之间的多种虚拟清扫顺序；针对每种虚拟清扫顺序，将所述清扫代价集合中位于所述虚拟清扫顺序末位的虚拟区域至其他目标区域之间的清扫代价替换为所述清扫顺序首位的虚拟区域至相同目标区域之间的清扫代价，完成所有虚拟清扫顺序下的对应替换，得到更新后的清扫代价集合；所述外部清扫路径基于所述更新后的清扫代价集合确定。
举例来说，针对第一目标区域生成的多个虚拟区域1、2、3、4，基于预设的虚拟区域规划规则，可以确定所述虚拟区域1、2、3、4之间的4种虚拟清扫顺序：1-2-3-4、2-3-4-1、3-4-1-2、4-1-2-3。
针对虚拟清扫顺序1-2-3-4，将清扫代价集合中位于所述虚拟清扫顺序末位的虚拟区域4至其他目标区域的清扫代价4out替换为位于所述虚拟清扫顺序首位的虚拟区域1至其他目标的清扫代价1out。同理，针对虚拟清扫顺序2-3-4-1，将虚拟区域1至其他目标区域的清扫代价1out替换为虚拟区域2至其他目标区域的清扫代价2out；针对虚拟清扫顺序3-4-1-2，将虚拟区域2至其他目标区域的清扫代价2out替换为虚拟区域3至其他目标区域的清扫代价3out；针对虚拟清扫顺序4-1-2-3，将虚拟区域3至其他目标区域的清扫代价3out替换为虚拟区域4至其他目标区域的清扫代价4out；由此可以得到表4所示的更新后虚拟区域与目标区域之间的清扫代价。
要说明的是，不同虚拟区域之间清扫代价的替换应当是针对相同目标区域的对应替换。例如，虚拟区域4至第二目标区域的清扫代价应当替换为虚拟区域1至第二目标区域的清扫代价。
Figure PCTCN2022070536-appb-000003
表4
完成所有虚拟清扫顺序下清扫代价的对应替换后，可以得到更新后的清扫代价集合，其中，未生成虚拟区域的其他目标区域至虚拟区域的清扫代价、虚拟区域彼此间的清扫代价以及其他目标区域彼此间的清扫代价无需更新，保持不变。
所述外部清扫路径将基于更新后的清扫代价集合确定。
如图12所示，同一目标区域生成对应的多个虚拟区域1、2、3、4，虚拟区域彼此间的清扫代价如表3所示，虚拟区域至其他目标区域间替换后的清扫代价如表4所示。
图12中示出了4种虚拟清扫顺序，由于虚拟区域彼此间存在的值为0的清扫代价，以总清扫代价最小为目标确定的外部清扫路径中所述虚拟区域1、2、3、4之间的清扫顺序必为所述4种虚拟清扫顺序中的一种。
同时，基于更新后的清扫代价集合确定的外部清扫路径中，将由一目标区域到达任一虚拟清扫顺序中位于首位的虚拟区域，再基于所述虚拟清扫顺序依次到达各个虚拟区域，最终由所述虚拟清扫顺序中位于末位的虚拟区域到达另一目标区域，由于位于末位的虚拟区域到达其他目标区域的清扫代价已替换为位于首位的虚拟区域到达其他目标区域的清扫代价，因而确定的外部清扫路径中实际计算的是位于首位的虚拟区域与其他目标区域之间的清扫代价。以虚拟清扫顺序1-2-3-4为例，如果外部清扫路径中最终采用了1-2-3-4的清扫顺序，由于已将虚拟区域4到达其他目标区域的清扫代价4out替换为虚拟区域1到达其他目标区域的清扫代价1out，因而实际计算的仍然是目标区域到达虚拟区域1的清扫代价以及虚拟区域1到达另一目标区域的清扫代价，未引入因虚拟区域1和虚拟区域4的清扫起点、清扫终点不同而造成的误差。
相应地，上述步骤110中，所述电子设备基于所述内部清扫路径和所述外部清扫路径，生成全局清扫路径，包括：针对具有多组清扫起点和清扫终点的目标区域，所述电子设备基于所述外部清扫路径，将所述目标区域对应的多个虚拟区域中清扫顺序位于首位虚拟区域确定为目标虚拟区域；采用所述目标虚拟区域的内部清扫路径作为所述目标区域的内部清扫路径。
具体地，所述全局清扫路径中无需代入同一目标区域生成的多个虚拟区域，以外部清扫路径的总清扫代价最小为目标得到所述外部清扫路径中，同一目标区域生成的多个虚拟区域在清扫顺序中总是相邻的，所述电子设备将采用所述目标区域生成的多个虚拟区域中在所述清扫顺序中位于首位的作为目标虚拟区域替换所述目标区域进行全局清扫路径的生成。
基于前例，第一目标区域生成对应的虚拟区域1、2、3、4，假设得到的外部清扫路径中，清扫顺序为由全局清扫起点出发，先后清扫虚拟区域1、2、3、4以及第二目标区域，最终到达全局清扫终点，则所述电子设备可以将虚拟区域1作为目标虚拟区域，替换所述第一目标区域进行全局清扫路径的生成。
所述电子设备生成的全局清扫路径，将由全局清扫起点到虚拟区域1的清扫起点A之间的清扫路径，虚拟区域1的清扫起点A与清扫终点B之间的内部清扫路径，虚拟区域1的清扫终点B与第二目标区域的清扫起点之间的清扫路径，第二目标区域的清扫起点与清扫终点之间的内部清扫路径，以及第二目标区域的清扫终点与全局清扫终点之间的清扫路径串联而成。
该实现方式相较于常规的实现方式，减小了求解最优路径的计算量，提高了电子设备规划全局清扫路径的效率。
图13是一示例性实施例提供的一种电子设备的示意结构图。请参考图13，在硬件层面，该设备包括处理器1302、内部总线1304、网络接口1306、内存1308以及非易失性存储器1310，当然还可能包括其他业务所需要的硬件。本说明书一个或多个实施例可以基于软件方式来实现，比如由处理器1302从非易失性存储器1310中读取对应的计算机程序到内存1308中然后运行。当然，除了软件实现方式之外，本说明书一个或多个实施例并不排除其他实现方式，比如逻辑器件抑或软硬件结合的方式等等，也就是说以下处理流程的执行主体并不限定于各个逻辑单元，也可以是硬件或逻辑器件。
请参考图14，清扫路径的规划装置可以应用于如图13所示的电子设备中，以实现本说明书的技术方案。其中，该清扫路径的规划装置包括障碍扫描单元1410、区域划分单元1420、域内规划单元1430、域间规划单元1440和路径生成单元1450：所述障碍扫描单元1410，用于获取若干待清扫区域，并对所述若干待清扫区域进行障碍物扫描；所述区域划分单元1420，用于当任一待清扫区域内存在障碍物时，基于所述障碍物的位置信息，将所述待清扫区域划分为多个子区域，得到目标区域集合，所述目标区域集合中包括划分后得到的子区域以及不存在障碍物的待清扫区域；所述域内规划单元1430，用于针对所述目标区域集合中的每个目标区域，进行区域内部的清扫路径规划，得到所述目标区域的内部清扫路径；所述域间规划单元1440，用于基于各个目标区域的内部清扫路径，进行区域之间的清扫路径规划，确定各个目标区域之间的外部清扫路径；所述路径生成单元1450，用于基于所述内部清扫路径和所述外部清扫路径，生成全局清扫路径。
可选地，所述电子设备中预先设置有待清扫区域的区域类型，以及区域类型和清扫路径规划规则之间的映射关系；所述域内规划单元1430，针对所述目标区域集合中的每个目标区域，进行区域内部的清扫路径规划，得到所述目标区域的内部清扫路径，包括：针对每个目标区域，获取所述目标区域的区域类型；在所述映射关系中查找所述区域类型对应的清扫路径规划规则；基于所述清扫路径规划规则进行所述目标区域内部的清扫路径规划，得到所述目标区域的内部清扫路径。
可选地，所述域间规划单元1440，基于各个目标区域的内部清扫路径，进行区域之间的清扫路径规划，确定各个目标区域之间的外部清扫路径，包括：基于各个目标区域的内部清扫路径，确定所述目标区域的清扫起点和清扫终点；基于各个目标区域的清扫起点和清扫终点，确定任意两个目标区域之间的清扫代价；以起始自预设的全局清扫起点，清扫所有目标区域，到达预设的全局清扫终点的总清扫代价最小为目标，确定各个目标区域之间的外部清扫路径。
可选地，所述域间规划单元1440，基于各个目标区域的清扫起点和清扫终点，确定任意两个目标区域之间的清扫代价，包括：确定任意两个目标区域之间的区域距离是否超出预设的距离阈值；当所述区域距离未超出所述距离阈值时，根据预设的代价预估算法，基于所述目标区域的清扫起点和清扫终点确定所述清扫代价；当所述区域距离超出所述距离阈值时，确定所述目标区域的清扫起点和预设的基准路径之间的起点距离，以及所述目标区域的清扫终点和所述基准路径之间的终点距离，并基于所述起点距离和终点距离，确定所述清扫代价。
可选地，所述域间规划单元1440，基于各个目标区域的清扫起点和清扫终点，确定任意两个目标区域之间的清扫代价，包括：当所述目标区域具有多组清扫起点和清扫终点时，基于每组清扫起点和清扫终点为所述目标区域生成对应的虚拟区域，得到所述目标区域对应的多个虚拟区域；采用所述多个虚拟区域替换所述目标区域进行任意两个目标区域之间的清扫代价的确定，得到任意两个目标区域之间的清扫代价集合，其中，任意两个所述虚拟区域之间的清扫代价基于预设的虚拟区域规划规则确定；所述域间规 划单元1440，还用于：基于预设的虚拟区域规划规则，确定所述虚拟区域之间的多种虚拟清扫顺序；针对每种虚拟清扫顺序，将所述清扫代价集合中位于所述虚拟清扫顺序末位的虚拟区域至其他目标区域之间的清扫代价替换为所述清扫顺序首位的虚拟区域至相同目标区域之间的清扫代价，完成所有虚拟清扫顺序下的对应替换，得到更新后的清扫代价集合；所述外部清扫路径基于所述更新后的清扫代价集合确定；所述路径生成单元1450，基于所述内部清扫路径和所述外部清扫路径，生成全局清扫路径，包括：针对具有多组清扫起点和清扫终点的目标区域，基于所述外部清扫路径，将所述目标区域对应的多个虚拟区域中清扫顺序位于首位虚拟区域确定为目标虚拟区域；采用所述目标虚拟区域的内部清扫路径作为所述目标区域的内部清扫路径。
可选地，所述障碍物扫描单元1410，对所述若干待清扫区域进行障碍物扫描，包括：基于预设的基准路径行驶，在行驶过程中对所述若干待清扫区域进行障碍物扫描。
可选地，所述装置还包括：任务执行单元1460，基于所述全局清扫路径，执行针对所述若干待清扫区域的清扫任务。
上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机，计算机的具体形式可以是个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件收发设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任意几种设备的组合。
在一个典型的配置中，计算机包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带、磁盘存储、量子存储器、基于石墨烯的存储介质或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
上述对本说明书特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中，多任务处理和并行处理也是可以的或者可能是有利的。
在本说明书一个或多个实施例使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本说明书一个或多个实施例。在本说明书一个或多个实施例和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下 文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解，尽管在本说明书一个或多个实施例可能采用术语第一、第二、第三等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本说明书一个或多个实施例范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”。
以上所述仅为本说明书一个或多个实施例的较佳实施例而已，并不用以限制本说明书一个或多个实施例，凡在本说明书一个或多个实施例的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本说明书一个或多个实施例保护的范围之内。

Claims (12)

  1. 一种清扫路径的规划方法，应用于任一执行清扫任务的电子设备，所述方法包括：
    获取若干待清扫区域；
    对所述若干待清扫区域进行障碍物扫描；
    当任一待清扫区域内存在障碍物时，基于所述障碍物的位置信息，将所述待清扫区域划分为多个子区域，得到目标区域集合，所述目标区域集合中包括划分后得到的子区域以及不存在障碍物的待清扫区域；
    针对所述目标区域集合中的每个目标区域，进行区域内部的清扫路径规划，得到所述目标区域的内部清扫路径；
    基于各个目标区域的内部清扫路径，进行区域之间的清扫路径规划，确定各个目标区域之间的外部清扫路径；
    基于所述内部清扫路径和所述外部清扫路径，生成全局清扫路径。
  2. 根据权利要求1所述的方法，所述电子设备中预先设置有待清扫区域的区域类型，以及区域类型和清扫路径规划规则之间的映射关系；
    所述针对所述目标区域集合中的每个目标区域，进行区域内部的清扫路径规划，得到所述目标区域的内部清扫路径，包括：
    针对每个目标区域，获取所述目标区域的区域类型；
    在所述映射关系中查找所述区域类型对应的清扫路径规划规则；
    基于所述清扫路径规划规则进行所述目标区域内部的清扫路径规划，得到所述目标区域的内部清扫路径。
  3. 根据权利要求1所述的方法，所述基于各个目标区域的内部清扫路径，进行区域之间的清扫路径规划，确定各个目标区域之间的外部清扫路径，包括：
    基于各个目标区域的内部清扫路径，确定所述目标区域的清扫起点和清扫终点；
    基于各个目标区域的清扫起点和清扫终点，确定任意两个目标区域之间的清扫代价；
    以起始自预设的全局清扫起点，清扫所有目标区域，到达预设的全局清扫终点的总清扫代价最小为目标，确定各个目标区域之间的外部清扫路径。
  4. 根据权利要求3所述的方法，所述基于各个目标区域的清扫起点和清扫终点，确定任意两个目标区域之间的清扫代价，包括：
    确定任意两个目标区域之间的区域距离是否超出预设的距离阈值；
    当所述区域距离未超出所述距离阈值时，
    根据预设的代价预估算法，基于所述目标区域的清扫起点和清扫终点确定所述清扫代价；
    当所述区域距离超出所述距离阈值时，
    确定所述目标区域的清扫起点和预设的基准路径之间的起点距离，以及所述目标区域的清扫终点和所述基准路径之间的终点距离，并
    基于所述起点距离和终点距离，确定所述清扫代价。
  5. 根据权利要求3所述的方法，所述基于各个目标区域的清扫起点和清扫终点，确定任意两个目标区域之间的清扫代价，包括：
    当所述目标区域具有多组清扫起点和清扫终点时，基于每组清扫起点和清扫终点为所述目标区域生成对应的虚拟区域，得到所述目标区域对应的多个虚拟区域；
    采用所述多个虚拟区域替换所述目标区域进行任意两个目标区域之间的清扫代价的确定，得到任意两个目标区域之间的清扫代价集合，其中，任意两个所述虚拟区域之间的清扫代价基于预设的虚拟区域规划规则确定。
  6. 根据权利要求5所述的方法，所述方法还包括：
    基于预设的虚拟区域规划规则，确定所述虚拟区域之间的多种虚拟清扫顺序；
    针对每种虚拟清扫顺序，
    将所述清扫代价集合中位于所述虚拟清扫顺序末位的虚拟区域至其他目标区域之间的清扫代价替换为所述清扫顺序首位的虚拟区域至相同目标区域之间的清扫代价，完成所有虚拟清扫顺序下的对应替换，得到更新后的清扫代价集合；
    所述外部清扫路径基于所述更新后的清扫代价集合确定。
  7. 根据权利要求5所述的方法，所述基于所述内部清扫路径和所述外部清扫路径，生成全局清扫路径，包括：
    针对具有多组清扫起点和清扫终点的目标区域，基于所述外部清扫路径，将所述目标区域对应的多个虚拟区域中清扫顺序位于首位的虚拟区域确定为目标虚拟区域；
    采用所述目标虚拟区域的内部清扫路径作为所述目标区域的内部清扫路径。
  8. 根据权利要求1所述的方法，所述对所述若干待清扫区域进行障碍物扫描，包括：
    基于预设的基准路径行驶，
    在行驶过程中对所述若干待清扫区域进行障碍物扫描。
  9. 根据权利要求1所述的方法，所述方法还包括：
    基于所述全局清扫路径，执行针对所述若干待清扫区域的清扫任务。
  10. 一种清扫路径的规划装置，应用于任一执行清扫任务的电子设备，所述装置包括障碍扫描单元、区域划分单元、域内规划单元、域间规划单元和路径生成单元：
    所述障碍扫描单元，用于获取若干待清扫区域，并对所述若干待清扫区域进行障碍物扫描；
    所述区域划分单元，用于当任一待清扫区域内存在障碍物时，基于所述障碍物的位置信息，将所述待清扫区域划分为多个子区域，得到目标区域集合，所述目标区域集合中包括划分后得到的子区域以及不存在障碍物的待清扫区域；
    所述域内规划单元，用于针对所述目标区域集合中的每个目标区域，进行区域内部的清扫路径规划，得到所述目标区域的内部清扫路径；
    所述域间规划单元，用于基于各个目标区域的内部清扫路径，进行区域之间的清扫路径规划，确定各个目标区域之间的外部清扫路径；
    所述路径生成单元，用于基于所述内部清扫路径和所述外部清扫路径，生成全局清扫路径。
  11. 一种电子设备，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器通过运行所述可执行指令实现如权利要求1-7中任一项所述方法中的步骤。
  12. 一种计算机可读存储介质，其上存储有计算机指令，所述计算机指令被处理器执行时实现如权利要求1-9中任一项所述方法的步骤。
PCT/CN2022/070536 2021-08-18 2022-01-06 清扫路径的规划 WO2023019873A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110951193.9 2021-08-18
CN202110951193.9A CN115248042A (zh) 2021-08-18 2021-08-18 一种清扫路径的规划方法及装置

Publications (1)

Publication Number Publication Date
WO2023019873A1 true WO2023019873A1 (zh) 2023-02-23

Family

ID=83697638

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/070536 WO2023019873A1 (zh) 2021-08-18 2022-01-06 清扫路径的规划

Country Status (2)

Country Link
CN (1) CN115248042A (zh)
WO (1) WO2023019873A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117173415A (zh) * 2023-11-03 2023-12-05 南京特沃斯清洁设备有限公司 用于大型洗地机的视觉分析方法及系统
CN117934245A (zh) * 2024-03-20 2024-04-26 南京信息工程大学 城乡规划数据处理方法及系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050171644A1 (en) * 2004-01-30 2005-08-04 Funai Electric Co., Ltd. Autonomous mobile robot cleaner
CN108120441A (zh) * 2016-11-28 2018-06-05 沈阳新松机器人自动化股份有限公司 全覆盖路径规划方法及系统
CN108592923A (zh) * 2018-06-05 2018-09-28 北京智行者科技有限公司 一种作业路径规划方法
CN109508002A (zh) * 2018-11-09 2019-03-22 深圳乐动机器人有限公司 一种机器人清扫地面的方法、装置及机器人
CN112068557A (zh) * 2020-08-27 2020-12-11 珠海市一微半导体有限公司 移动机器人全覆盖路径规划方法、芯片和机器人
CN112799398A (zh) * 2020-12-25 2021-05-14 珠海市一微半导体有限公司 基于寻径代价的清洁路径规划方法、芯片及清洁机器人
CN113064407A (zh) * 2019-12-13 2021-07-02 深圳拓邦股份有限公司 全区域覆盖的清扫方法、装置、清扫机器人及存储装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050171644A1 (en) * 2004-01-30 2005-08-04 Funai Electric Co., Ltd. Autonomous mobile robot cleaner
CN108120441A (zh) * 2016-11-28 2018-06-05 沈阳新松机器人自动化股份有限公司 全覆盖路径规划方法及系统
CN108592923A (zh) * 2018-06-05 2018-09-28 北京智行者科技有限公司 一种作业路径规划方法
CN109508002A (zh) * 2018-11-09 2019-03-22 深圳乐动机器人有限公司 一种机器人清扫地面的方法、装置及机器人
CN113064407A (zh) * 2019-12-13 2021-07-02 深圳拓邦股份有限公司 全区域覆盖的清扫方法、装置、清扫机器人及存储装置
CN112068557A (zh) * 2020-08-27 2020-12-11 珠海市一微半导体有限公司 移动机器人全覆盖路径规划方法、芯片和机器人
CN112799398A (zh) * 2020-12-25 2021-05-14 珠海市一微半导体有限公司 基于寻径代价的清洁路径规划方法、芯片及清洁机器人

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117173415A (zh) * 2023-11-03 2023-12-05 南京特沃斯清洁设备有限公司 用于大型洗地机的视觉分析方法及系统
CN117173415B (zh) * 2023-11-03 2024-01-26 南京特沃斯清洁设备有限公司 用于大型洗地机的视觉分析方法及系统
CN117934245A (zh) * 2024-03-20 2024-04-26 南京信息工程大学 城乡规划数据处理方法及系统
CN117934245B (zh) * 2024-03-20 2024-05-24 南京信息工程大学 城乡规划数据处理方法及系统

Also Published As

Publication number Publication date
CN115248042A (zh) 2022-10-28

Similar Documents

Publication Publication Date Title
WO2023019873A1 (zh) 清扫路径的规划
JP7181092B2 (ja) 自律型車両用動作計画及び再構成可能な動作計画プロセッサ
Lau et al. Improved updating of Euclidean distance maps and Voronoi diagrams
US8849559B2 (en) Apparatus and method for generating and using a grid map path
TWI718612B (zh) 操作路線產生器之方法及計算系統
WO2019062649A1 (zh) 一种自适应区域划分的方法及系统
WO2023125512A1 (zh) 导航路径的规划方法、装置及存储介质
CN114440916B (zh) 一种导航方法、装置、设备及存储介质
CN111066064A (zh) 使用误差范围分布的网格占用建图
US20200125115A1 (en) Methods and systems of distributing task regions for a plurality of cleaning devices
Chen et al. Research on Ship Meteorological Route Based on A‐Star Algorithm
KR102006925B1 (ko) 선박 항로 및 속도 결정 장치, 선박 항로 및 속도 결정 방법, 기록 매체
CN116105742B (zh) 复合场景巡检导航方法、系统及相关设备
Bose et al. Online routing in convex subdivisions
Sujit et al. Route planning for angle constrained terrain mapping using an unmanned aerial vehicle
CN114705196B (zh) 一种用于机器人的自适应启发式全局路径规划方法与系统
CN113442908B (zh) 自动泊车路径规划方法及系统、泊车控制设备
Wang et al. Coordination-free multi-robot path planning for congestion reduction using topological reasoning
CN116952251B (zh) 路径规划的方法、装置、终端设备及可读存储介质
Arney An efficient solution to autonomous path planning by approximate cell decomposition
CN117389305A (zh) 一种无人机巡检路径规划方法、系统、设备及介质
JP2021076593A (ja) 構築及び位置特定技術分野に焦点を当てた動的マップ生成
CN113561962A (zh) 一种自动泊车路径规划方法及系统、泊车控制设备
CN115402323A (zh) 换道决策方法和电子设备
CN112489131B (zh) 基于路面检测构建代价地图的方法、装置、介质和机器人

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22857197

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE