Robot navigation method, robot and computer readable storage medium

Abstract

The invention relates to the technical field of robots, in particular to a navigation method of a robot, the robot and a computer readable storage medium. The navigation method comprises the following steps: acquiring a current position of a robot, an initial navigation map of a target navigation area and preset navigation configuration information, determining a target navigation subarea according to the current position and the preset navigation configuration information, and determining each closing door in the target navigation area according to the initial navigation map, and navigating the robot to the target closing door according to each closing door and the target navigation subarea, updating the initial navigation map at the target closing door to obtain a target navigation map, and navigating the robot to the target navigation subarea according to the target navigation map. When the robot is navigated to each target navigation subarea, the robot is navigated to the door which may affect navigation and is considered to be closed in the navigation map, and whether the door is really closed or not is verified, so that a navigation task which may be completed cannot be discarded when the navigation map is not accurate enough.

Description

Technical Field

[0001] The present invention relates to the field of robotics technology, and in particular to a robot navigation method, a robot, and a computer-readable storage medium. Background Art

[0002] As people's quality of life improves, more and more robots are entering our homes. Current robots typically navigate based on pre-stored navigation maps. When a robot needs to navigate to a target area, if the door to the target area is currently open but the navigation map shows it as closed, the robot will mistakenly believe the target area is unreachable and will not navigate to it, thus easily abandoning an otherwise complete navigation task. Summary of the Invention

[0003] One object of the present invention is to provide a robot navigation method, a robot and a computer-readable storage medium, aiming to improve the problem that existing navigation algorithms easily discard navigation tasks that could have been completed.

[0004] In a first aspect, an embodiment of the present invention provides a robot navigation method, comprising: Obtaining the current position of the robot, preset navigation configuration information, and an initial navigation map of a target navigation area, wherein the target navigation area includes a plurality of navigation partitions; Determine a target navigation partition according to the current location and the preset navigation configuration information; determining each closed door in the target navigation area according to the initial navigation map; Navigating the robot to a target closed door according to each closed door and the target navigation partition; updating the initial navigation map at the target closed door to obtain a target navigation map; The robot is navigated to the target navigation zone according to the target navigation map.

[0005] Optionally, navigating the robot to a target closed door according to each closed door and the target navigation zone includes: Determine a target navigation point of the target closed door according to each of the closed doors and the target navigation partition; The robot is navigated to the target closed door according to the target navigation point.

[0006] Optionally, determining a target navigation point of a target closed door according to each closed door and the target navigation partition includes: traversing each of the closed doors in the initial navigation image and taking the currently traversed closed door as the target closed door; Setting the target closed door as an open door in the initial navigation image to obtain a first navigation image; Acquire a partition outline of the target navigation partition and determine a designated navigation point of the target navigation partition using the partition outline; determining whether the robot can reach the designated navigation point according to the first navigation image, and obtaining a determination result; The target navigation point of the target closed door is determined according to the judgment result.

[0007] Optionally, determining the target navigation point of the target closed door according to the judgment result includes: If the judgment result is that the robot can reach the designated navigation point, generating a target navigation path according to the current position and the designated navigation point; A target navigation point of the target closed door is determined according to the target navigation path.

[0008] Optionally, determining the target navigation point of the target closed door according to the target navigation path includes: Determine the partitions to be passed and the partitions not to be passed according to the target navigation path; removing the unpartitioned regions from the initial navigation image to obtain a second navigation image; Extracting the outermost contour of the partition to be passed according to the second navigation image to obtain a target contour map; Determining a first area and a second area according to the target contour map, wherein the first area includes a navigation partition in the same area as the robot, and the second area includes a navigation partition in a different area from the robot; A target navigation point of the target closed door is determined from the target navigation path according to the first area and the second area.

[0009] Optionally, the target navigation path includes a plurality of path points, and determining the target navigation point of the target closed door from the target navigation path according to the first area and the second area includes: Acquire path points located in the first area and the second area respectively from a plurality of path points of the target navigation path to obtain a first path point set and a second path point set; Determine a candidate navigation point for a target closed door based on the first set of path points and the second set of path points, the candidate navigation point being a path point in the first set of path points; Determining whether the robot can reach the candidate path point; If the candidate path point is reachable, determining the candidate path point as the target navigation point; If the candidate path point cannot be reached, traverse the next closed door of the target closed door in the initial navigation image, take the next closed door as the target closed door and enter the initial navigation image to set the target closed door as an open door to obtain the first navigation image.

[0010] Optionally, the navigation method further includes: If the judgment result is that the robot cannot reach the designated navigation point, then traverse the next closed door of the target closed door in the initial navigation image, take the next closed door as the target closed door and enter the initial navigation image to set the target closed door as the open door, thereby obtaining the first navigation image.

[0011] Optionally, determining each closed door in the target navigation area according to the initial navigation map includes: extracting an initial navigation image according to the initial navigation map; Performing a closing operation on the initial navigation image according to a preset radius to obtain a third navigation image; Each closed door in the target navigation area is determined according to the third navigation image and the initial navigation image.

[0012] Optionally, the preset navigation configuration information includes navigation sequence information of each navigation partition, and determining the target navigation partition according to the current position and the preset navigation configuration information includes: determining an initial navigation partition according to the current position; The next navigation partition of the initial navigation partition is determined according to the navigation sequence information, and the next navigation partition is used as a target navigation partition.

[0013] Optionally, navigating the robot to the target navigation zone according to the target navigation map includes: determining whether the target closed door is in an open state according to the target navigation map; If the target closed door is in an open state, navigating the robot from the target navigation point to the target navigation partition; If the target closed door is in a closed state, the target navigation partition is skipped, the target navigation partition is re-determined according to the current position and the preset navigation configuration information, and the step of determining each closed door in the target navigation area according to the initial navigation map is entered.

[0014] In a second aspect, an embodiment of the present invention provides a robot, comprising a memory and a processor, wherein the memory is connected to the processor, and the processor is used to execute one or more computer programs stored in the memory. When the processor executes the one or more computer programs, the robot implements the robot navigation method described in the first aspect above.

[0015] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the robot navigation method described in the second aspect above.

[0016] Compared with the prior art, an embodiment of the present invention provides a robot navigation method, a robot, and a computer-readable storage medium. The robot navigation method includes: obtaining the current position of the robot, an initial navigation map of a target navigation area, and preset navigation configuration information, wherein the target navigation area includes multiple navigation partitions, determining the target navigation partition based on the current position and the preset navigation configuration information, determining each closed door in the target navigation area based on the initial navigation map, navigating the robot to the target closed door based on each closed door and the target navigation partition, updating the initial navigation map at the target closed door to obtain the target navigation map, and navigating the robot to the target navigation partition based on the target navigation map. When navigating the robot to each target navigation partition, the robot is navigated to a door that may affect navigation and is considered to be closed in the navigation map, and verifying whether the door is actually closed, so that the robot is navigated to the target navigation partition when the door is actually not closed. Therefore, even if the switch status of each closed door in the navigation map is not updated in a timely manner, it can be ensured that any navigation task that may be completed will not be discarded, thereby improving the navigation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 A schematic flow chart of a robot navigation method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a target navigation area provided by an embodiment of the present invention; Figure 3 A schematic diagram of a target navigation area provided by another embodiment of the present invention; Figure 4 A schematic diagram of a target navigation area provided by yet another embodiment of the present invention; Figure 5 A schematic diagram of an initial navigation image provided by an embodiment of the present invention; Figure 6 A schematic diagram of a third navigation image provided by an embodiment of the present invention; Figure 7 A schematic diagram of the flow of S14 in a robot navigation method provided by an embodiment of the present invention; Figure 8 A schematic diagram of the flow of S141 in a robot navigation method provided by an embodiment of the present invention; Figure 9 A schematic diagram of a first navigation image provided by an embodiment of the present invention; Figure 10 A schematic diagram of a target navigation path provided by an embodiment of the present invention; Figure 11 A schematic diagram of a second navigation image provided by an embodiment of the present invention; Figure 12 A schematic diagram of a target contour map provided by an embodiment of the present invention; Figure 13 A schematic diagram of a first area and a second area provided in an embodiment of the present invention; Figure 14 A schematic structural diagram of a robot navigation device provided by an embodiment of the present invention; Figure 15 A schematic structural diagram of a third determination module in a robot navigation device provided by an embodiment of the present invention; Figure 16 A schematic structural diagram of a first determination module in a robot navigation device provided by an embodiment of the present invention; Figure 17 A schematic structural diagram of a second determination module in a robot navigation device provided by an embodiment of the present invention; Figure 18 A schematic diagram of the hardware structure of a robot provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0020] It should be noted that, unless there is a conflict, the various features of the embodiments of the present invention may be combined with each other and are all within the scope of protection of the present invention. In addition, although the functional modules are divided in the device schematics and the logical order is shown in the flow charts, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flow charts. Furthermore, the terms "first," "second," "third," etc. used in the present invention do not limit the data or execution order, but only distinguish between identical or similar items with substantially the same functions and effects.

[0021] An embodiment of the present invention provides a robot including but not limited to a sweeping robot, a cleaning robot, a service robot, a remote monitoring robot, an unmanned vehicle, etc., wherein the sweeping robot may include a cleaning robot, a floor washing robot, a mopping robot, a sweeping and mopping robot, a vacuuming robot, etc.

[0022] See also Figure 1 In an embodiment of the present invention, a robot navigation method is provided. The navigation method is applied to the robot as described above. Figure 1 As shown, the navigation method includes: S11. Obtain the current position of the robot, an initial navigation map of a target navigation area, and preset navigation configuration information, wherein the target navigation area includes multiple navigation partitions.

[0023] In this step, the robot's current position is the starting position for navigation. The robot can use any positioning technology to obtain its current position, including but not limited to positioning technologies based on lidar, computer vision algorithms, multi-sensor fusion, and artificial intelligence (AI) vision combined with lidar.

[0024] The target navigation area is the area where the navigation task needs to be performed, and the navigation partition is the area obtained by dividing the target navigation partition. For example, see Figure 2 The target navigation area includes a first navigation partition 201, a second navigation partition 202, a third navigation partition 203, and a fourth navigation partition 204. The navigation task may be navigating from one of the navigation partitions in the target navigation area to one or more of the remaining navigation partitions, for example, Figure 2 As shown, the navigation task may be navigating from the first navigation partition 201 to the second navigation partition 202 , or from the first navigation partition 201 to the third navigation partition 203 , and then from the third navigation partition 203 to the second navigation partition 202 .

[0025] It is understandable that, in addition to performing navigation tasks in the target navigation area, the robot can also perform other tasks. For example, when the robot is a sweeping robot, as described above, the robot can perform a cleaning task in the first navigation partition 201, and then navigate from the first navigation partition 201 to the second navigation partition 202, and perform a cleaning task in the second navigation partition 202; for another example, when the robot is a mopping robot, as described above, the robot can perform a mopping task in the first navigation partition 201, and then navigate from the first navigation partition 201 to the third navigation partition 203, perform a mopping task in the third navigation partition 203, and then navigate from the third navigation partition 203 to the second navigation partition 202, and perform a mopping task in the second navigation partition 202.

[0026] The preset navigation configuration information is used to guide the robot to perform a preset navigation task in the target navigation area. In some embodiments, the preset navigation configuration information includes navigation sequence information, and the navigation sequence information is used to guide the robot to navigate to each navigation zone according to the preset navigation sequence.

[0027] In some embodiments, the navigation sequence information may include a partition identifier corresponding to each navigation partition and sequence configuration information, wherein the partition identifier may be a number, letter or other symbol, and the sequence configuration information is used to indicate the arrangement order of each partition identifier.

[0028] For example, when the partition identifier is a number, each navigation partition can correspond to a number, such as Figure 2 As shown, assuming that the first navigation partition 201 corresponds to number 1, the second navigation partition 202 corresponds to number 2, the third navigation partition 203 corresponds to number 3, and the fourth navigation partition 204 corresponds to number 4, the sequential configuration information can be set according to actual needs. For example, if the sequential configuration information is that the order of number 1, number 2, number 3 and number 4 is from first to last, the robot navigates in the order of the first navigation partition 201, the second navigation partition 202, the third navigation partition 203 and the fourth navigation partition 204; if the sequential configuration information is that the order of number 1, number 3, number 2 and number 4 is from first to last, the robot navigates in the order of the first navigation partition 201, the third navigation partition 203, the second navigation partition 202 and the fourth navigation partition 204.

[0029] The target navigation area may include multiple doors, and adjacent navigation partitions may be separated by doors or not. For example, Figure 2As shown, the first navigation partition 201 and the second navigation partition 202 are separated by a first door G1, the first navigation partition 201 and the fourth navigation partition 204 are separated by a wall, the second navigation partition 202 and the third navigation partition 203 are separated by a second door G2, and the third navigation partition 203 and the fourth navigation partition 204 are separated by a third door G3. Each door can be in an open state or a closed state. A door in an open state is an open door, and a door in a closed state is a closed door. For example, see Figure 3 , the first door G1 is in an open state, and the second door G2 and the third door G3 are in a closed state. Therefore, the first door G1 is an open door, and the second door G2 and the third door G3 are closed doors.

[0030] The initial navigation map is a map created by collecting environmental data of the target navigation area and based on the environmental data. It is understandable that the initial navigation map contains the switch status information of each door when the robot is navigating. For example, when the target navigation area is Figure 2 When the target navigation area is the area shown, the initial navigation map contains the switch status information of the first door G1, the second door G2 and the third door G3 in the closed state. Figure 3 When the area shown is shown, the initial navigation map includes switch status information that the first door G1 is in the open state, and the second door G2 and the third door G3 are in the closed state.

[0031] If the initial navigation map is not updated in time, the current opening and closing status of each door in the target navigation area may be different from the opening and closing status information of each door in the initial navigation map. For example, Figure 3 In the initial navigation map generated by the target navigation area shown, the second gate G2 is a closed gate. However, see Figure 4 , the second door G2 in the target navigation area is currently an open door. Assuming that the robot performs the navigation task of navigating from the first navigation partition 201 to the third navigation partition 203, when the traditional navigation algorithm navigates according to the initial navigation map, since the second door G2 is a closed door in the initial navigation map, the robot will mistakenly believe that the third navigation partition 203 is unreachable and will not navigate to the third navigation partition 203. In fact, the second door G2 is an open door, so the robot can navigate to the third navigation partition 203. This will cause the navigation task from the first navigation partition 201 to the third navigation partition 203 to be erroneously discarded.

[0032] S12. Determine the target navigation partition according to the current location and preset navigation configuration information.

[0033] In this step, the target navigation zone is the next navigation zone that the robot is about to navigate to. The robot can use the preset navigation configuration information and the current position of the robot to infer the next navigation zone to be navigated to, thereby determining the next navigation zone as the target navigation zone.

[0034] In some embodiments, the robot may determine an initial navigation partition according to the current position, determine a next navigation partition of the initial navigation partition according to the navigation sequence information, and use the next navigation partition as a target navigation partition.

[0035] In this step, the robot may determine the navigation area where the current position of the robot is located as the initial navigation partition, or may select a navigation partition from multiple navigation partitions as the initial navigation partition.

[0036] For example, if Figure 4 As shown, point A is the current position of the robot. Since the current position of the robot is located in the first navigation partition 201, the robot can determine that the first navigation partition 201 is the initial navigation partition.

[0037] For another example, if the robot's current position is not located in any navigation partition in the target navigation area, the robot can select a navigation partition from multiple navigation partitions as the initial navigation partition based on actual conditions, such as selecting the navigation partition closest to the current position as the initial navigation partition, or selecting the navigation partition that can be reached fastest from the current position as the initial navigation partition.

[0038] As mentioned above, the navigation sequence information includes the partition identifier and sequence configuration information corresponding to each navigation partition. The partition identifier is a number. The first navigation partition 201 corresponds to number 1, the second navigation partition 202 corresponds to number 2, the third navigation partition 203 corresponds to number 3, and the fourth navigation partition 204 corresponds to number 4. If the sequence configuration information is number 1, number 3, number 2 and number 4, the order is from first to last. Assuming that the initial navigation partition is the first navigation partition 201, since the next number of number 1 corresponding to the first navigation partition 201 is number 3, the robot can determine that the third navigation partition 203 corresponding to number 3 is the next navigation partition of the first navigation partition 201, and use the third navigation partition 203 as the target navigation partition.

[0039] S13. Determine each closed door in the target navigation area according to the initial navigation map.

[0040] In this step, the robot can process the initial navigation map using image processing algorithms such as morphology, feature extraction, and state classification to determine each closed door in the target navigation area.

[0041] In some embodiments, the robot can extract an initial navigation image based on the initial navigation map, perform a closing operation on the initial navigation image according to a preset radius to obtain a third navigation image, and determine each closed door in the target navigation area based on the third navigation image and the initial navigation image.

[0042] In this embodiment, the robot can extract the initial navigation image from the initial navigation map using an image extraction algorithm or an extraction tool (such as an image extraction function in the OpenCV library). The preset radius can be determined based on the actual door thickness of each door in the target navigation area. In some embodiments, the preset radius is smaller than the actual door thickness, for example, half or one-third of the actual door thickness.

[0043] In some embodiments, the preset radius is half the actual door thickness.

[0044] Closing operation is an image processing algorithm based on morphology. Generally, the expansion operation is performed first, followed by the erosion operation. The expansion operation refers to the expansion of the region with a circular structuring element of a specified radius to fill the small holes in the region. The erosion operation refers to the erosion of the expanded region with the same circular structuring element to restore the boundary shape of the region. The robot can use the preset radius as the radius of the closing operation to perform a closing operation on the initial navigation image, thereby converting a closed door into an open door in the initial navigation image. For example, the robot can perform a closing operation on the initial navigation image. Figure 5 After closing the initial navigation image shown, we can get Figure 6 The third navigation image shown. Figure 6 It can be seen that the closing operation only converts the closed doors in the initial navigation image into open doors, and has no effect on the open doors in the initial navigation image.

[0045] Since the actual thickness of each door is usually smaller than the thickness of the wall, using a preset radius smaller than the actual door thickness as the radius of the closing operation can ensure that the wall remains unchanged.

[0046] Since the difference between the initial navigation image and the third navigation image lies in the closed doors, the robot may subtract the third navigation image from the initial navigation image to determine each closed door in the target navigation area.

[0047] S14. Navigate the robot to the target closed door according to each closed door and the target navigation partition.

[0048] In this step, the target closed door is the closed door that prevents the robot from entering the target navigation zone during navigation to the target navigation zone in the initial navigation map. It is understood that there may be one or more closed doors that prevent the robot from entering the target navigation zone. When there are multiple closed doors that prevent the robot from entering the target navigation zone, the target closed door may be any one of them.

[0049] For example, see Figure 3 When the robot needs to navigate from the first navigation partition 201 to the third navigation partition 203, according to Figure 3 In the initial navigation map generated by the target navigation area shown, the robot cannot enter the third navigation partition 203 due to the obstruction of the second door G2, so the target closed door can be the second door G2.

[0050] S15. Update the initial navigation map at the target closed door to obtain the target navigation map.

[0051] In this step, the target navigation map is used to guide the robot to navigate to the target navigation zone. When the robot navigates to the target closed door, it can use information collection devices such as lidar and cameras to collect environmental information about the target closed door and update the initial navigation map based on the collected environmental information, thereby obtaining the target navigation map.

[0052] S16. Navigate the robot to the target navigation partition according to the target navigation map.

[0053] In this step, the robot can determine the switch status of the target closed door according to the target navigation map, and navigate the robot to the target navigation partition according to the switch status.

[0054] In general, when navigating the robot to each target navigation partition, this embodiment navigates the robot to a door that may affect the robot's entry into the target navigation partition and is considered to be closed in the initial navigation map, and verifies whether this door is actually closed, so that the robot can be navigated to the target navigation partition when this door is not actually closed. Therefore, even if the switch status of each closed door in the initial navigation map is not updated in time, it can ensure that the navigation task that may be completed will not be discarded, thereby improving the navigation effect.

[0055] In some embodiments, see Figure 7 , S14 includes: S141. Determine a target navigation point of a target closed door according to each closed door and the target navigation partition.

[0056] The target navigation point is used to navigate to the target closed door. The robot can traverse each closed door and adjust the switch status of each closed door. The target navigation point of the target closed door is determined based on the adjusted switch status and the target navigation zone.

[0057] In some embodiments, see Figure 8 , S14 includes: S1411. Traverse each closed door in the initial navigation image and use the currently traversed closed door as the target closed door.

[0058] S1412: Set the target closed door as an open door in the initial navigation image to obtain a first navigation image.

[0059] S1413: Acquire a partition outline of the target navigation partition and determine a designated navigation point of the target navigation partition according to the partition outline of the target navigation partition.

[0060] S1414. Determine whether the robot can reach the designated navigation point based on the first navigation image, and obtain a determination result.

[0061] S1415. Determine the target navigation point of the target closed door according to the judgment result.

[0062] In S1411, please continue to see Figure 5 ,exist Figure 5 In the initial navigation image shown, the second door G2 is a closed door, so the robot can traverse to the second door G2 in the initial navigation image. If the closed door currently traversed is the second door G2, the robot can use the second door G2 as the target closed door.

[0063] In S1412, as mentioned above, since the second door G2 is the target closed door, the robot can set the second door G2 as the open door in the initial navigation image, and obtain Figure 9 The first navigation image is shown.

[0064] In S1413, the robot can obtain the boundary of the target navigation area and then use a contour extraction algorithm or extraction tool (such as the contour extraction function in the OpenCV library) to obtain the partition outline of the target navigation partition. The designated navigation point is a point specified within the partition outline of the target navigation partition. The designated navigation point can be specified based on actual needs. For example, the designated navigation point can be located near the door within the partition outline or at a certain angle within the partition outline.

[0065] In S1414, the robot may use a preset navigation algorithm to determine whether the robot can reach the designated navigation point based on the first navigation image. The preset navigation algorithm includes, but is not limited to, a global path planning algorithm and a local path planning algorithm. The determination result may include a determination that the robot can reach the designated navigation point or a determination that the robot cannot reach the designated navigation point.

[0066] In S1415, if the judgment result is that the robot cannot reach the specified navigation point, it means that the specified navigation point cannot be reached even after the target closed door is opened, and the robot can only traverse other closed doors. Therefore, in some embodiments, when the judgment result is that the robot cannot reach the specified navigation point, the robot can traverse the next closed door of the target closed door in the initial navigation image, take the next closed door as the target closed door and enter S1412.

[0067] Since there may be multiple closed doors in the initial navigation map, the robot cannot determine whether the closed door currently traversed is the closed door that makes the robot inaccessible. By traversing each closed door in the initial navigation map and simulating whether it is possible to navigate to the target navigation partition when each closed door is open, if it is not possible to navigate to the target navigation partition, it will not navigate to the corresponding closed door for switch status verification. Therefore, this embodiment can improve the switch status verification efficiency of the target closed door.

[0068] S142: Navigate the robot to the target closed door according to the target navigation point.

[0069] In this step, the robot can store the target navigation point in a preset storage area so that the target navigation point can be retrieved from the preset storage area later, path planning can be performed according to the target navigation point, and the robot can be navigated to the target closed door according to the planned path.

[0070] In some embodiments, if the judgment result is that the robot can reach the designated navigation point, the robot can generate a target navigation path according to the current position and the designated navigation point, and determine the target navigation point of the target closing door according to the target navigation path.

[0071] For example, see Figure 10 , assuming the robot's current position is A and the specified navigation point is B, the robot can generate Figure 10 The target navigation path is shown.

[0072] In some embodiments, the robot can determine the partitions that need to be passed and the partitions that have not been passed based on the target navigation path, remove the partitions that have not been passed from the initial navigation image to obtain a second navigation image, extract the outermost contour of the partitions that need to be passed based on the second navigation image to obtain a target contour map, and determine the first area and the second area based on the target contour map, wherein the first area includes navigation partitions in the same area as the robot, and the second area includes navigation partitions in different areas from the robot, and determine the target navigation point of the target closed door from the target navigation path based on the first area and the second area. The partitions that need to be passed are the navigation partitions that the target navigation path passes through, and the partitions that have not been passed through are the navigation partitions that the target navigation path does not pass through.

[0073] For example, first, Figure 10 As shown, since the target navigation path passes through the first navigation partition 201, the second navigation partition 202 and the third navigation partition 203 respectively, and does not pass through the fourth navigation partition 204, the robot can determine that the first navigation partition 201, the second navigation partition 202 and the third navigation partition 203 are partitions that need to be passed through, and determine that the fourth navigation partition 204 is a partition that has not been passed through.

[0074] Then, as described above, the robot can move the fourth navigation zone 204 from Figure 5 Remove the initial navigation image shown in Figure 11 The second navigation image is shown.

[0075] Then, as mentioned above, the robot can use contour extraction algorithms or extraction tools (such as the contour extraction function in the OpenCV library) according to Figure 11 The second navigation image shown extracts the outermost contours of the first navigation partition 201, the second navigation partition 202 and the third navigation partition 203, and obtains Figure 12 Target outline shown.

[0076] Then, as mentioned above, the robot can Figure 12 The target profile shown is determined Figure 13 The first area and the second area shown, wherein the first area includes the first navigation partition 201 and the second navigation partition 202, and the first area includes the third navigation partition 203. It can be understood that, since the robot is in the first navigation partition 201, the first navigation partition 201 is connected to the second navigation partition 202, so the first navigation partition 201 and the second navigation partition 202 are navigation partitions in the same area as the robot, and the third navigation partition 203 is not connected to the first navigation partition 201 or the second navigation partition 202, so the third navigation partition 203 is a navigation partition in a different area from the robot.

[0077] Finally, the robot can determine the target navigation point of the target closed door from the first path segment according to the target navigation path being in the first path segment of the first area and the second path segment being in the second area.

[0078] Since in this embodiment, the target navigation point is located on the target navigation path of the robot to the target navigation partition, the robot does not need to perform wall-following operations to re-update the map when navigating to each target navigation partition. It only needs to quickly update the map on the target navigation path and verify whether the closed door that may affect the navigation to the target navigation partition is actually closed. If the closed door is in the open state, the target navigation partition can be entered directly. This can improve the map update efficiency and thus improve the navigation efficiency.

[0079] In some embodiments, the target navigation path includes multiple path points, where a path point is a point on the target navigation path. It is understandable that, as described above, the first path segment may include multiple path points, and the second path segment may also include multiple path points.

[0080] In some embodiments, the robot can obtain path points in the first area and the second area respectively from multiple path points of the target navigation path, obtain a first path point set and a second path point set, determine the candidate navigation points of the target closed door based on the first path point set and the second path point set, the candidate navigation points are path points in the first path point set, and judge whether the robot can reach the candidate path points. If the candidate path points can be reached, the candidate path points are determined as the target navigation points. If the candidate path points cannot be reached, the next closed door of the target closed door is traversed in the initial navigation image, the next closed door is used as the target closed door and enters S1412.

[0081] In this embodiment, as described above, the first path point set may include each path point of the first path segment, the second path point set may include each path point of the second path segment, and the candidate path points are potential target navigation points.

[0082] In some embodiments, the robot can find the nearest path point from the first path point set to each path point in the second path point set and determine the nearest path point as a candidate path point, or it can find the fastest path point from the first path point set to reach each path point in the second path point set and determine the fastest path point as a candidate path point.

[0083] In some embodiments, the robot can determine whether the robot can reach the candidate path point based on a preset navigation algorithm, wherein the preset navigation algorithm includes but is not limited to a global path planning algorithm, a local path planning algorithm, etc.

[0084] It is understood that if a candidate pathpoint is unreachable, it means that the robot has not found a path to the candidate pathpoint. Therefore, the robot can only abandon the candidate pathpoint for the current target door closing and try to find another candidate pathpoint for closing the door. If a candidate pathpoint is reachable, it means that the robot has found a path to the candidate pathpoint. Therefore, the robot can use the candidate pathpoint as the target navigation point.

[0085] Therefore, this embodiment can reliably select the target navigation point of the target closed door.

[0086] In some embodiments, the robot can determine whether the target closed door is in an open state based on the target navigation map. If the target closed door is in an open state, the robot is navigated from the target navigation point to the target navigation partition. If the target closed door is in a closed state, the target navigation partition is skipped, and the target navigation partition is re-determined based on the current position and preset navigation configuration information and enters S13.

[0087] In some embodiments, the robot can determine the switch status of the target closed door according to the target navigation map based on any suitable algorithm such as an image recognition algorithm and a map comparison algorithm.

[0088] It can be understood that if it is determined that the target closed door is in an open state, it means that the target closed door is actually an open door, not a closed door. At this time, the robot can enter the target navigation partition normally. If it is determined that the target closed door is in a closed state, it means that the target closed door is a real closed door. At this time, the robot cannot enter the target navigation partition and can only navigate to other navigation partitions. Therefore, the robot can skip the current target navigation partition, re-determine the target navigation partition according to the current position and preset navigation configuration information, and execute S14, so as to continue to execute subsequent navigation tasks.

[0089] For example, as mentioned above, assuming that the robot navigates in the order of the first navigation partition 201, the third navigation partition 203, the second navigation partition 202 and the fourth navigation partition 204, the current navigation task is to navigate from the first navigation partition 201 to the third navigation partition 203, please continue to refer to Figure 5 When the robot navigates to the target closed door G2, it determines that the target closed door G2 is still in a closed state. At this time, the robot cannot enter the third navigation partition 203. Therefore, the robot can skip the third navigation partition 203, re-determine the next navigation partition of the third navigation partition 203 (that is, the second navigation partition 202) as the target navigation partition and continue to execute the navigation task of navigating the robot to the second navigation partition 202.

[0090] It should be noted that, in each of the above-mentioned embodiments, there is not necessarily a certain order between the above-mentioned steps. A person of ordinary skill in the art can understand from the description of the embodiments of the present invention that, in different embodiments, the above-mentioned steps may have different execution orders, that is, they may be executed in parallel, may be executed interchangeably, and so on.

[0091] As another aspect of the present invention, an embodiment of the present invention provides a robot navigation device. The robot navigation device may be a software module comprising a plurality of instructions stored in a memory. A processor may access the memory and execute the instructions to implement the robot navigation method described in each of the above embodiments.

[0092] In some embodiments, the robot's navigation device can be constructed from hardware devices. For example, the robot's navigation device can be constructed from one or more chips, and the chips can work in coordination with each other to implement the robot navigation methods described in the above embodiments. For another example, the robot's navigation device can also be constructed from a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine), a programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination of these components.

[0093] In some embodiments, see Figure 14 The robot navigation device 1400 provided by the embodiment of the present invention includes an acquisition module 1401, a first determination module 1402, a second determination module 1403, a first navigation module 1404, an update module 1405 and a second navigation module 1406.

[0094] The acquisition module 1401 is used to obtain the current position of the robot, the initial navigation map of the target navigation area and the preset navigation configuration information, wherein the target navigation area includes multiple navigation partitions, the first determination module 1402 is used to determine the target navigation partition based on the current position and the preset navigation configuration information, the second determination module 1403 is used to determine each closed door in the target navigation area based on the initial navigation map, the first navigation module 1404 is used to navigate the robot to the target closed door based on each closed door and the target navigation partition, the update module 1405 is used to update the initial navigation map at the target closed door to obtain the target navigation map, and the second navigation module 1406 is used to navigate the robot to the target navigation partition based on the target navigation map.

[0095] In some embodiments, see Figure 15 The first navigation module 1404 includes a first determination unit 14041 and a navigation unit 14042 .

[0096] The first determining unit 14041 is used to determine a target navigation point of a target closed door according to each closed door and the target navigation partition, and the navigation unit 14042 is used to navigate the robot to the target closed door according to the target navigation point.

[0097] In some embodiments, the first determination unit 14041 is specifically used to: traverse each closed door in the initial navigation image and use the currently traversed closed door as the target closed door, set the target closed door as the open door in the initial navigation image, obtain the first navigation image, obtain the partition outline of the target navigation partition and determine the designated navigation point of the target navigation partition according to the partition outline of the target navigation partition, judge whether the robot can reach the designated navigation point according to the first navigation image, obtain a judgment result, and determine the target navigation point of the target closed door according to the judgment result.

[0098] In some embodiments, see Figure 16 The second determination module 1403 includes an extraction unit 14031 , a calculation unit 14032 and a second determination unit 14033 .

[0099] The extraction unit 14031 is used to extract the initial navigation image according to the initial navigation map, the operation unit 14032 is used to perform a closing operation on the initial navigation image according to a preset radius to obtain a third navigation image, and the second determination unit 14033 is used to determine each closed door in the target navigation area according to the third navigation image and the initial navigation image.

[0100] In some embodiments, see Figure 17 The first determining module 1402 includes a third determining unit 14021 and a fourth determining unit 14022 .

[0101] The third determining unit 14021 is used to determine an initial navigation partition according to the current position, and the fourth determining unit 14022 is used to determine a next navigation partition of the initial navigation partition according to the navigation sequence information, and use the next navigation partition as a target navigation partition.

[0102] It should be noted that the robot navigation device described above can execute the robot navigation method provided in the embodiments of the present invention and has the corresponding functional modules and beneficial effects of executing the method. For technical details not fully described in the embodiments of the robot navigation device, please refer to the robot navigation method provided in the embodiments of the present invention.

[0103] See also Figure 18 , Figure 18 The present invention provides a hardware structure diagram of a robot. Figure 18 As shown, the robot 1800 includes one or more processors 1801 and a memory 1802. Figure 18 A processor 1801 is taken as an example.

[0104] Processor 1801 is configured to support the computer device in executing the corresponding functions of the method in the above method embodiment. Processor 1801 can be a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof. The hardware chip can be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or any combination thereof. The PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0105] Memory 1802 is used to store program code. Memory 1802 may include volatile memory (VM), such as random access memory (RAM); non-volatile memory (NVM), such as read-only memory (ROM), flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); or a combination of these types of memory.

[0106] Memory 1802 can be used to store non-volatile software programs, non-volatile computer executable programs, and modules, such as the program instructions / modules corresponding to the robot navigation method in the embodiments of the present invention. Processor 1801 executes the non-volatile software programs, instructions, and modules stored in memory 1802 to execute the various functional applications and data processing of the robot navigation method and the robot navigation device, thereby implementing the functions of the robot navigation method and the various modules or units of the robot navigation device provided in the above-mentioned method embodiments.

[0107] Memory 1802 may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function. The data storage area may store data generated based on the use of the robot's navigation device. In some embodiments, memory 1802 may optionally include a remote memory device located relative to the processor. Such remote memory device may be connected to the robot's navigation device via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0108] The one or more modules are stored in the memory 1802. When executed by the one or more processors 1801, the navigation method of the robot in any of the above-mentioned method embodiments is executed, for example, the method steps described in the above-mentioned method embodiments are executed to realize the functions of the modules described in the above-mentioned device embodiments.

[0109] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the robot navigation method as described in the aforementioned embodiment.

[0110] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0111] Finally, it should be noted that the present invention can be implemented in many different forms and is not limited to the embodiments described in this specification. These embodiments are not intended to be additional limitations on the content of the present invention. The purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive. In addition, under the thinking of the present invention, the above-mentioned technical features continue to be combined with each other, and there are many other changes in different aspects of the present invention as described above, all of which are considered to be within the scope of the description of the present invention. Furthermore, it is clear to those skilled in the art that improvements or changes can be made based on the above description, and all such improvements and changes should fall within the scope of protection of the claims appended to the present invention.

Claims

1. A robot navigation method, characterized in that: include: Obtaining the current position of the robot, an initial navigation map of a target navigation area, and preset navigation configuration information, wherein the target navigation area includes a plurality of navigation partitions; Determine a target navigation partition according to the current location and the preset navigation configuration information; determining each closed door in the target navigation area according to the initial navigation map; Navigating the robot to a target closed door according to each closed door and the target navigation partition; updating the initial navigation map at the target closed door to obtain a target navigation map; The robot is navigated to the target navigation zone according to the target navigation map.

2. The navigation method according to claim 1, wherein: Said navigating the robot to the target closed door according to each closed door and the target navigation zone comprises: Determine a target navigation point of the target closed door according to each of the closed doors and the target navigation partition; The robot is navigated to the target closed door according to the target navigation point.

3. The navigation method according to claim 2, wherein: Determining the target navigation point of the target closed door according to each of the closed doors and the target navigation partition includes: traversing each of the closed doors in the initial navigation image and taking the currently traversed closed door as the target closed door; Setting the target closed door as an open door in the initial navigation image to obtain a first navigation image; Acquire a partition outline of the target navigation partition and determine a designated navigation point of the target navigation partition according to the partition outline; determining whether the robot can reach the designated navigation point according to the first navigation image, and obtaining a determination result; The target navigation point of the target closed door is determined according to the judgment result.

4. The navigation method according to claim 3, characterized in that: Determining the target navigation point of the target closed door according to the judgment result includes: If the judgment result is that the robot can reach the designated navigation point, generating a target navigation path according to the current position and the designated navigation point; A target navigation point of the target closed door is determined according to the target navigation path.

5. The navigation method according to claim 4, characterized in that: Determining the target navigation point of the target closed door according to the target navigation path includes: Determine the partitions to be passed and the partitions not to be passed according to the target navigation path; removing the unpartitioned regions from the initial navigation image to obtain a second navigation image; Extracting the outermost contour of the partition to be passed according to the second navigation image to obtain a target contour map; Determining a first area and a second area according to the target contour map, wherein the first area includes a navigation partition in the same area as the robot, and the second area includes a navigation partition in a different area from the robot; A target navigation point of the target closed door is determined from the target navigation path according to the first area and the second area.

6. The navigation method according to claim 5, characterized in that: The target navigation path includes a plurality of path points, and determining the target navigation point of the target closed door from the target navigation path according to the first area and the second area includes: Acquire path points located in the first area and the second area respectively from a plurality of path points of the target navigation path to obtain a first path point set and a second path point set; Determine a candidate navigation point of the target closed door according to the first path point set and the second path point set, the candidate navigation point being a path point in the first path point set; Determining whether the robot can reach the candidate path point; If the candidate path point is reachable, determining the candidate path point as the target navigation point; If the candidate path point cannot be reached, traverse the next closed door of the target closed door in the initial navigation image, take the next closed door as the target closed door and enter the initial navigation image to set the target closed door as an open door to obtain the first navigation image.

7. The navigation method according to claim 3, characterized in that: Also includes: If the judgment result is that the robot cannot reach the designated navigation point, then traverse the next closed door of the target closed door in the initial navigation image, take the next closed door as the target closed door and enter the initial navigation image to set the target closed door as the open door, thereby obtaining the first navigation image.

8. The navigation method according to claim 1, wherein: Determining each closed door in the target navigation area according to the initial navigation map includes: extracting an initial navigation image according to the initial navigation map; Performing a closing operation on the initial navigation image according to a preset radius to obtain a third navigation image; Each closed door in the target navigation area is determined according to the third navigation image and the initial navigation image.

9. The navigation method according to claim 1, wherein: The preset navigation configuration information includes navigation sequence information of each navigation partition, and determining the target navigation partition according to the current position and the preset navigation configuration information includes: determining an initial navigation partition according to the current position; The next navigation partition of the initial navigation partition is determined according to the navigation sequence information, and the next navigation partition is used as a target navigation partition.

10. The navigation method according to any one of claims 1 to 9, characterized in that: Said navigating the robot to the target navigation zone according to the target navigation map comprises: determining whether the target closed door is in an open state according to the target navigation map; If the target closed door is in an open state, navigating the robot from the target navigation point to the target navigation partition; If the target closed door is in a closed state, the target navigation partition is skipped, the target navigation partition is re-determined according to the current position and the preset navigation configuration information, and the step of determining each closed door in the target navigation area according to the initial navigation map is entered.

11. A robot, characterized in that: The robot includes a memory and a processor, the memory is connected to the processor, and the processor is used to execute one or more computer programs stored in the memory. When the processor executes the one or more computer programs, the robot implements the robot navigation method as described in any one of claims 1 to 10.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the navigation method of the robot according to any one of claims 1 to 10.

Images