Threshold area identification method and device, medium, and electronic device

Abstract

The present disclosure provides a threshold area identification method, a threshold area identification device, a computer-readable storage medium, and an electronic device. The method includes the steps of: determining a first trap-prone area based on escape information during the cleaning process of a cleaning robot; determining the first trap-prone area where a continuous obstacle of a predetermined height exists as a second trap-prone area; and determining whether the second trap-prone area is a threshold area based on the second trap-prone area and room map information where the second trap-prone area is located. The method is capable of identifying a threshold area within a cleaning area.

Description

[Technical Field]

[0001] (Related Applications) This application claims priority to Chinese Patent Application No. 202211436872.3, filed on November 16, 2022, the entire contents of which are incorporated herein by reference.

[0002] The present disclosure relates to the field of smart homes, and in particular to a threshold area identification method, a threshold area identification device, a computer-readable storage medium, and an electronic device. [Background technology]

[0003] In recent years, with the rapid development of computer technology and artificial intelligence science, intelligent robot technology has gradually become a hot spot in the field of modern robot research. Cleaning robots are one of the most practical intelligent robots, and with a certain degree of artificial intelligence, they can automatically complete floor cleaning.

[0004] Currently, during the cleaning process of a cleaning robot, some threshold areas are prone to getting stuck, which results in a longer cleaning time and a reduced cleaning effect.

[0005] In order to give special treatment to the threshold area during the cleaning process, it is very important to first identify the threshold area. Summary of the Invention [Problem to be solved by the invention]

[0006] An object of the present disclosure is to provide a threshold area identification method, a threshold area identification device, a computer-readable storage medium, and an electronic device for identifying a threshold area in a cleaning area. [Means for solving the problem]

[0007] According to a specific embodiment of the present disclosure, a first aspect provides a threshold area identification method, the method including: determining a first trap-prone area based on escape information during a cleaning process of a cleaning robot; determining the first trap-prone area where a continuous obstacle of a predetermined height exists as a second trap-prone area; and determining whether the second trap-prone area is a threshold area based on room map information of the second trap-prone area and its location.

[0008] In an exemplary embodiment of the present disclosure, the step of determining a first area prone to getting caught based on escape information during the cleaning process of the cleaning robot includes obtaining a trigger position during the cleaning process of the cleaning robot that triggers the cleaning robot to perform a predetermined escape operation, and determining the first area prone to getting caught based on the trigger position.

[0009] In an exemplary embodiment of the present disclosure, determining the first snag-prone area based on the trigger position includes, if there is a single trigger position, determining a trigger area within a predetermined range in which the trigger position is located as the first snag-prone area, and, if there are multiple trigger positions, clustering the multiple trigger areas corresponding to the multiple trigger positions to obtain at least one first snag-prone area.

[0010] In an exemplary embodiment of the present disclosure, clustering the plurality of trigger regions corresponding to the plurality of trigger positions to obtain at least one of the first catch-prone regions includes clustering the plurality of trigger regions based on mutual distances between the plurality of trigger positions to obtain the first catch-prone region.

[0011] In an exemplary embodiment of the present disclosure, the predetermined range is within 50 cm of the trigger position.

[0012] In an exemplary embodiment of the present disclosure, the predetermined escape action is an escape action that is triggered after the cleaning robot slips.

[0013] In an exemplary embodiment of the present disclosure, the step of determining the first snagging-prone area in which consecutive obstacles of the predetermined height exist as a second snagging-prone area includes obtaining height information of obstacles in the first snagging-prone area, determining based on the obstacle height information whether consecutive obstacles that meet the predetermined height exist in the first snagging-prone area, and if so, determining the first snagging-prone area as the second snagging-prone area.

[0014] In an exemplary embodiment of the present disclosure, the predetermined height is between 1.5 cm and 2 cm.

[0015] In an exemplary embodiment of the present disclosure, the step of determining whether the second snag-prone area is a threshold area based on the second snag-prone area and room map information in which it is located includes selecting a predetermined number of sampling points from the second snag-prone area, obtaining nearest obstacle distance information on the room map of the sampling points based on the room map information, and determining whether the second snag-prone area is the threshold area based on the nearest obstacle distance information.

[0016] In an exemplary embodiment of the present disclosure, obtaining the closest obstacle distance information on the room map of the sampling point based on the room map information includes obtaining the closest obstacle distance in each direction of the sampling point on the room map, starting from the sampling point, and constituting the closest obstacle distance information.

[0017] In an exemplary embodiment of the present disclosure, determining whether the second prone to getting caught area is the threshold area based on the nearest obstacle distance information includes using a neural network classifier to identify the nearest obstacle distance information and determine whether the second prone to getting caught area is the threshold area, wherein the neural network classifier is trained with nearest obstacle distance training information.

[0018] In an exemplary embodiment of the present disclosure, the method further includes, in the process of determining whether the second snagging-prone area is the threshold area based on multiple pieces of nearest obstacle distance information obtained from a predetermined number of the sampling points, a step of determining the second snagging-prone area as the threshold area if the second snagging-prone area is determined to be the threshold area based on the nearest obstacle distance information corresponding to any one of the sampling points.

[0019] In an exemplary embodiment of the present disclosure, the predetermined number is 8 to 10.

[0020] In a second aspect, the present disclosure provides a threshold area identification device, comprising: a first snag-prone area determination module for determining a first snag-prone area based on escape information during the cleaning process of a cleaning robot; a second snag-prone area determination module for determining the first snag-prone area, where continuous obstacles of a predetermined height exist, as a second snag-prone area; and a threshold area determination module for determining whether the second snag-prone area is a threshold area based on the second snag-prone area and room map information in which it is located.

[0021] In a third aspect, the present disclosure provides a computer-readable storage medium having stored thereon a computer program that, when executed by a processor, performs the above threshold area identification method.

[0022] In a fourth aspect, the present disclosure provides an electronic device, comprising: a processor; and a memory for storing executable instructions for the processor, the processor configured to execute the executable instructions to implement the threshold area identification method described above.

[0023] A threshold area identification method provided by an exemplary embodiment of the present disclosure acquires escape information during the cleaning process of a cleaning robot, determines a first trap-prone area based on the escape information, and predetermines a possible threshold area in the cleaning area. Next, among the determined first trap-prone areas, an area where a continuous obstacle of a predetermined height exists is determined as a second trap-prone area, i.e., a possible threshold area of ​​a certain height is determined as an area to be further determined. Finally, based on the second trap-prone area and room map information in which it is located, it is determined whether the second trap-prone area is a threshold area. That is, during the threshold area identification process, combining the escape information with the continuous obstacle information can improve the accuracy of threshold area determination, and can identify threshold-like areas that are not located at doorways based on the room map information, thereby providing sufficient threshold area information to subsequently improve cleaning efficiency. [Brief explanation of the drawings]

[0024] The accompanying drawings herein are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the accompanying drawings in the following description are merely some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these accompanying drawings without creative work. [Figure 1] 1 shows a flowchart of a threshold area identification method provided by an exemplary embodiment of the present disclosure. [Figure 2] 1 shows a schematic diagram of trigger locations within a room map provided by an exemplary embodiment of the present disclosure; [Figure 3]10 illustrates a flowchart of a method for determining a threshold area based on nearest obstacle distance information provided by an exemplary embodiment of the present disclosure. [Figure 4] 10 shows a schematic diagram of determining the nearest obstacle distance around a sampling point in a room map provided by an exemplary embodiment of the present disclosure; [Figure 5A] 5 shows a schematic diagram of the nearest obstacle locations obtained from two different sampling points determined in the room map shown in FIG. 4. [Figure 5B] 5 shows a schematic diagram of the nearest obstacle locations obtained from two different sampling points determined in the room map shown in FIG. 4. [Figure 6] 1 shows a flowchart of the operation procedure of a threshold area identification method provided by an exemplary embodiment of the present disclosure. [Figure 7] 1 illustrates a block diagram of a threshold area identification device provided by an exemplary embodiment of the present disclosure; [Figure 8] 1 shows a schematic diagram of a module of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0025] In order to make the objectives, technical solutions and advantages of the present disclosure clearer, the present disclosure will be described in more detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present disclosure, but not all of the embodiments. Based on the embodiments of the present disclosure, other embodiments obtained by those skilled in the art without any creative work are all included in the protection scope of the present disclosure.

[0026] The terms used in the embodiments of the present disclosure are used only for the purpose of describing particular embodiments and are not intended to limit the present disclosure. As used in the embodiments of the present disclosure and the appended claims, the singular forms "a," "the," and "the" are also intended to encompass the plural, and "plurality" generally includes at least two, unless the context clearly dictates otherwise.

[0027] The term "and / or" used in this specification merely describes the relationship between related objects, and there are three relationships. For example, A and / or B means that A may exist alone, A and B may exist simultaneously, or B may exist alone. In addition, " / " in this specification generally indicates that the related objects before and after it are in an "or" relationship.

[0028] In the embodiments of the present disclosure, terms such as first, second, and third may be used to describe ..., but it should be understood that these terms should not be used to limit the scope of the present disclosure. These terms are used only to distinguish between .... For example, a first ... may also be called a second ..., and similarly, a second ... may also be called a first ..., without departing from the scope of the embodiments of the present disclosure.

[0029] Depending on the context, the terms "if" and "then" as used herein may be interpreted as "when" or "if" or "responsive to determining" or "responsive to detecting." Similarly, depending on the context, "(a described condition or event) is determined" or "(a described condition or event) is detected" may be interpreted as "when it is determined" or "responsive to determining" or "when (a described condition or event) is detected" or "responsive to (a described condition or event) being detected."

[0030] It should be noted that the terms "comprises," "has," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a product or device comprising a set of elements not only includes those elements, but also other elements explicitly listed or inherent in those products or devices. Unless further limited, an element defined with the phrase "comprises" does not exclude the presence of other identical elements in a product or device that includes said element.

[0031] A cleaning robot is a type of intelligent home appliance that can automatically clean the floor of a room using a certain type of artificial intelligence. Generally, it uses a brush to sweep and a vacuum to suck up the dirt on the floor, first sucking it into its own dirt storage box, and then completing the floor cleaning function.

[0032] If a cleaning robot collides with a threshold area during cleaning due to external interference or other reasons, it may not be able to clean thoroughly, resulting in missed spots, or it may have to go back and forth across the threshold area multiple times to clean, which will lengthen the cleaning time and ultimately affect the cleaning effect.

[0033] Therefore, by specially processing the threshold area during the cleaning process of the cleaning robot, for example, by reducing the number of passes or slowing down the speed when passing through, it is possible to prevent the above-mentioned situation from occurring. However, determining the threshold area before performing the above processing is also a very important step.

[0034] Based on this, an exemplary embodiment of the present disclosure provides a threshold area identification method applicable to a cleaning robot, which can be realized by the cleaning robot using hardware and / or software. Referring to Figure 1, a flowchart of the threshold area identification method provided by the exemplary embodiment of the present disclosure can include the following steps S110, S120, and S130.

[0035] Step S110: Determine a first trap-prone area based on the escape information of the cleaning robot during the cleaning process.

[0036] In step S120, the first trapping-prone area where a series of obstacles of a predetermined height exist is determined as the second trapping-prone area.

[0037] In step S130, it is determined whether the second trap-prone area is a threshold area based on the second trap-prone area and the room map information where the second trap-prone area is located.

[0038] A threshold area identification method provided by an exemplary embodiment of the present disclosure acquires escape information during the cleaning process of a cleaning robot, determines a first trap-prone area based on the escape information, and predetermines a possible threshold area in the cleaning area. Next, within the determined first trap-prone area, an area where a series of obstacles of a predetermined height exists is determined as a second trap-prone area, i.e., a possible threshold area of ​​a certain height is determined as an area to be further determined. Finally, based on the second trap-prone area and room map information in which it is located, it is determined whether the second trap-prone area is a threshold area. That is, during the threshold area identification process, combining the escape information with the series of obstacle information can improve the accuracy of threshold area determination, and can identify threshold-like areas that are not located at doorways based on the room map information, providing sufficient threshold area information for improving subsequent cleaning efficiency.

[0039] As can be seen from this, the threshold area identification method provided by the exemplary embodiment of the present disclosure can not only identify threshold areas located at entrance / exit positions, but also identify threshold-like areas that are not located at entrance / exit positions. Since threshold-like areas affect the cleaning effect in the same way as threshold areas, the cleaning robot can improve cleaning efficiency by performing specialized cleaning processes for both threshold areas and threshold-like areas according to actual needs.

[0040] Hereinafter, specific embodiments will be taken to describe in detail each step of the threshold area identification method provided by the exemplary embodiment of the present disclosure.

[0041] In step S110, a first trap-prone area is determined based on the escape information of the cleaning robot during the cleaning process.

[0042] Typically, when a cleaning robot encounters a stuck position during the course of performing an actual cleaning task, an escape operation is triggered to help the cleaning robot smoothly pass through the stuck position through the escape operation. In practice, the escape operation can take various forms, such as gearing up or deceleration.

[0043] In an exemplary embodiment of the present disclosure, a predetermined escape action is set in advance, and when the predetermined escape action is triggered during the cleaning process of the cleaning robot, a trigger position that triggers the predetermined escape action of the cleaning robot can be obtained, and a first area that is prone to getting caught can be determined based on the trigger position.

[0044] That is, an exemplary embodiment of the present disclosure sets a predetermined escape action to determine a threshold area, and collects and obtains the corresponding location only when the cleaning robot triggers such an escape action, and excludes escape situations that occur in other cases, such as escape actions triggered when encountering an obstacle, thereby excluding areas belonging to the obstacle from possible threshold areas.

[0045] In an exemplary embodiment of the present disclosure, the predetermined escape action may be an escape action triggered after a slip of the cleaning robot, specifically, an escape action triggered after a forward slip or a backward slip.

[0046] Here, the escape operation triggered after a front slip is mainly a phenomenon in which two wheels get stuck at the threshold area position and slip when the cleaning robot passes through a threshold area such as a door stone. Here, the slip state can be determined based on data such as Odom (odometer), Gyro (gyroscope), Laser (radar data), and SLAM (map), and the specific determination process will not be repeated here, and existing methods for determining the slip state can be used.

[0047] If the cleaning robot slips during its forward movement, a special escape action is triggered. The special escape action specifically includes controlling the cleaning robot to retreat a certain distance and detour around the slipped position along an arc path. After the slip state is released, the angle of the cleaning robot is adjusted to the angle before the special escape action was triggered. If the slip state is not released, the above-mentioned retreat detour action is repeated.

[0048] The above-mentioned circular arc path to bypass the slip position includes the following: controlling the cleaning robot to take a path that moves left forward and then right forward (in this case, a wall is located on the right side of the cleaning robot); if a wall is located on the left side of the cleaning robot, first move right forward and then move left forward; if there is no wall near the slip position, the order of the above two actions can be set randomly, i.e., move left forward and then move back and rightward, or move right forward and then move left forward.

[0049] If the slipping state cannot be released by the above-mentioned backward arc path detouring operation, the cleaning robot wheel PWM (Pulse Width Modulation) signal format can be directly controlled to move the cleaning robot backward, and then rotate around the left wheel and the right wheel in sequence, and after the rotation is completed, the cleaning robot can be controlled to move forward to escape from the slipping position.

[0050] If the cleaning robot does not escape from the slip state even after performing the special escape action, the slip position is marked and the cleaning robot is set not to clean the position in the subsequent cleaning process, thereby preventing the robot from being unable to escape.

[0051] The escape action triggered after a rearward slip is an escape action that is mainly performed when the cleaning robot slips while backing up from a threshold area such as a door stone. For example, as the front side of the cleaning robot becomes higher, the mop cloth pushes against the floor surface, causing the wheels to slip. At this time, the cleaning robot tries to back up or turn, triggering another special escape action.

[0052] This special escape operation may be to reverse the machine and then rotate forward or backward on the spot to release the slippage, or to directly control the wheel PWM to move the cleaning robot backward to the right and backward to the left, and repeat this operation until the slippage is released, or to directly control the wheel PWM to rotate the machine forward or backward to release the slippage.

[0053] If the slip state is not released even after the cleaning robot executes the special escape operation, the slip position is marked and the cleaning robot is set not to clean the position in the subsequent cleaning process, thereby preventing the escape from becoming difficult.

[0054] The exemplary embodiment of the present disclosure determines both the special escape operation triggered during a forward slip and the special escape operation triggered during a rearward slip as the predetermined escape operation.

[0055] In an exemplary embodiment of the present disclosure, after the cleaning robot triggers the above-mentioned predetermined escape operation, it needs to obtain a trigger position at which the cleaning robot will perform the predetermined escape operation. After obtaining the trigger position, the obtained trigger position is marked on a room map, and the black dot on the room map shown in FIG. 2 is the obtained trigger position 210.

[0056] During the actual cleaning process, there may be multiple positions that trigger the cleaning robot to perform the above-mentioned specified escape operation, i.e., there may be multiple acquired trigger positions, and these multiple trigger positions may be positions in the same threshold area or positions in multiple threshold areas.

[0057] Therefore, in an exemplary embodiment of the present disclosure, if multiple trigger positions are obtained, multiple trigger regions corresponding to the multiple trigger positions can be clustered to obtain at least one first catch-prone region.

[0058] Typically, the acquired trigger position is a single point, and the corresponding trigger area may be a small area centered on the trigger position, and the shape of the small area may be circular, square, etc., and is not particularly limited in the exemplary embodiment of the present disclosure.

[0059] In practical applications, there may be various different clustering methods in the process of clustering the multiple trigger regions corresponding to the multiple trigger positions. In the exemplary embodiment of the present disclosure, the multiple trigger regions are clustered mainly based on the mutual distances between the multiple trigger positions to obtain the first trap-prone region.

[0060] For example, as shown in Fig. 2, if there are a total of three black dots in the room map, each representing three different trigger positions 210, and the mutual distance between these three trigger positions 210 is within a predetermined range, the trigger regions corresponding to these three trigger positions 210 can be clustered into one first prone-to-get region 220. Alternatively, first, the trigger regions corresponding to two trigger positions 210 whose mutual distance is within a predetermined range are clustered to obtain a first clustering region, and then it is determined whether the distance from the third trigger position 210 to the first clustering region is within a predetermined range. If so, the trigger region corresponding to the third trigger position 210 is merged into the first clustering region to obtain a second clustering region. If there are other trigger positions, they are clustered one by one according to the above method until no more trigger positions remain, or if the trigger positions are not within the predetermined range, the first prone-to-get region 220 is obtained.

[0061] In practical applications, the above-mentioned predetermined range may be determined according to actual conditions, for example, the predetermined range may be within 50 cm from the trigger position, and the specific value of the predetermined range is not particularly limited in the exemplary embodiment of the present disclosure.

[0062] In actual applications, there may be only one trigger position, and in this case, the trigger region within a predetermined range where the trigger position is located may be determined as the first region likely to be caught.

[0063] In step S120, the first trapping prone area where a series of obstacles of a predetermined height exist is determined as the second trapping prone area.

[0064] In an exemplary embodiment of the present disclosure, after determining the first snag-prone area, it is necessary to further determine whether there are consecutive obstacles in the first snag-prone area that meet a predetermined height, thereby determining whether the first snag-prone area is a possible threshold area, i.e., a second snag-prone area.

[0065] Specifically, to determine whether there are consecutive obstacles in the first prone to getting caught area that meet a predetermined height, first, height information of the obstacles in the first prone to getting caught area is obtained, and then, based on the obstacle height information, it is determined whether there are consecutive obstacles in the first prone to getting caught area that meet a predetermined height, and if there are, the first prone to getting caught area is determined to be a second prone to getting caught area, and if there are no consecutive obstacles in the first prone to getting caught area, the first prone to getting caught area is ignored.

[0066] In practical applications, the threshold area is usually an area with a certain height relative to the floor, so when acquiring the height information of the obstacle, the height information of all positions within the first trap-prone area is acquired, and this height information is statistically analyzed to determine whether there are any consecutive positions whose height is higher than a certain height, and then the consecutive positions are determined to be consecutive obstacles, where the length of the consecutive obstacles must be greater than a certain length, for example, 50 cm.

[0067] Furthermore, the predetermined height may be set according to the actual situation, for example, the predetermined height may be between 1.5 cm and 2 cm, and in the exemplary embodiment of the present disclosure, the predetermined height is not particularly limited.

[0068] In step S130, it is determined whether the second area prone to getting caught is a threshold area based on the second area prone to getting caught and the room map information in which it is located.

[0069] In an exemplary embodiment of the present disclosure, after determining the second snag-prone area, it is necessary to determine whether the second snag-prone area is a threshold area.

[0070] In practical applications, there are various methods for determining whether the second prone to getting caught area is a threshold area. For example, the determination can be made directly based on the position of the second prone to getting caught area on the room map. However, such a determination method involves a relatively large amount of information and therefore requires a relatively large amount of calculations.

[0071] Based on this, the exemplary embodiment of the present disclosure proposes a method for determining a threshold area based on nearest obstacle distance information, which, referring to FIG. 3, specifically includes the following steps S310, S320 and S330.

[0072] In step S310, a predetermined number of sampling points are selected from the second trap-prone area.

[0073] In practical application, a sampling point is selected at an arbitrary position in the second prone-to-get-trapped area. In an exemplary embodiment of the present disclosure, in order to improve the accuracy of the determination, a sampling point is selected whose distance from the nearest obstacle is greater than a predetermined length, where the predetermined length may be 5 cm or other values, and is not particularly limited herein.

[0074] The number of sampling points, i.e., the predetermined number, may be any number, and in the exemplary embodiment of the present disclosure, the predetermined number may be 8 to 10.

[0075] Step S320: Based on the room map information, obtain distance information of the nearest obstacle on the room map of the sampling point.

[0076] In an exemplary embodiment of the present disclosure, after determining the sampling point, the nearest obstacle distance in each direction of the sampling point is obtained from the sampling point on the room map where the second trap-prone area is located, and nearest obstacle distance information is formed. Referring to Figure 4, a schematic diagram of determining the nearest obstacle distance centered on the sampling point 410 on the room map is shown.

[0077] In practical applications, a laser radar is simulated at the sampling point, and a laser is emitted in directions from 0° (directly to the right) to 359° (sampling directions are drawn at 5° intervals in Figure 4 for ease of display) to obtain geospatial information for the area around the sampling point. If the laser is blocked by an obstacle, the length of the laser from the sampling point to the obstacle is obtained as the nearest obstacle distance, and therefore, each direction in the 360° direction has a nearest obstacle distance. If the laser does not encounter an obstacle in a certain direction, the nearest obstacle distance in that direction is determined to be none or a predetermined farthest distance.

[0078] 5A and 5B show schematic diagrams of the nearest obstacle locations obtained from two different sampling points determined on the room map shown in FIG. 4, where the nearest obstacle is identified by a point, and the distance from the point to the sampling point is the nearest obstacle distance. Sampling point 510 in FIG. 5A and sampling point 520 in FIG. 5B are different sampling points in the second prone-to-trapping area, where sampling point 520 in FIG. 5B is closer to the actual threshold. Different determination results may be obtained based on the nearest obstacle distance information corresponding to different sampling points.

[0079] In step S330, it is determined whether the second trap-prone area is a threshold area based on the nearest obstacle distance information.

[0080] In an exemplary embodiment of the present disclosure, after acquiring nearest obstacle distance information, a threshold area can be determined based on that information. The laser information acquired from a sampling point is a 360-dimensional feature vector representing the nearest obstacle distance in one direction. This distance information includes spatial information (including room shape, obstacle location, etc.) around the sampling point, which contains the information necessary to determine whether the point is on a threshold. However, this information is often hidden, making it difficult to intuitively narrow down and determine the location. Deep learning technology observes countless threshold and non-threshold feature vectors, automatically applies information narrowing rules through hidden layers (usually multiple layers), and finally outputs a number (0 to 1) from the output layer indicating the probability that the point is on a threshold.

[0081] Therefore, in practical application, a neural network classifier can be used to identify the nearest obstacle distance information and determine whether the second trap-prone area is a threshold area, where the neural network classifier needs to be obtained by data training, specifically, by training the nearest obstacle distance training information. In the exemplary embodiment of the present disclosure, the specific training process is not described in detail.

[0082] After obtaining a trained neural network classifier, the nearest obstacle distance information obtained from different sampling points can be identified. Specifically, the nearest obstacle distance information corresponding to the sampling points is input to the neural network classifier. For example, the nearest obstacle location map obtained from Figures 5A and 5B is input to the neural network classifier for identification. Note that the information input to the classifier must be consistent with the information during training. Finally, the neural network classifier outputs a result indicating whether the second trap-prone area where the sampling point is located is a threshold area.

[0083] In practical applications, the determination results based on the nearest obstacle distance information obtained from different sampling points within the same second trap-prone area may vary, and a certain percentage may be used to determine whether the second trap-prone area is a threshold area. For example, if the determination results corresponding to 60% or more of the sampling points are "yes," the second trap-prone area is determined to be a threshold area. As long as the nearest obstacle distance information corresponding to one sampling point determines the second trap-prone area to be a threshold area, the second trap-prone area is determined to be a threshold area. In the exemplary embodiment of the present disclosure, the specific determination percentage is not limited.

[0084] The threshold area identification method provided by the exemplary embodiment of the present disclosure, on the one hand, can improve the accuracy of determining the threshold area by combining continuous obstacle information based on escape information during the threshold area identification process, can identify threshold-like areas that are not located at entrances and exits, and can provide sufficient threshold area information to improve subsequent cleaning efficiency; on the other hand, during the process of determining whether the second prone to getting caught area is a threshold area, can reduce the amount of information in the identification process by using the nearest obstacle distance information, can reduce the amount of calculation in the identification process, and improve calculation efficiency.

[0085] Finally, after the threshold area is determined, the threshold area is sent to the APP on the user terminal, and the threshold area is displayed on the room map, so that the user can be reminded that there is a threshold area in that area, and the subsequent cleaning strategy can be optimized to improve cleaning efficiency.

[0086] Referring to FIG. 6, a flowchart of the operation steps of the threshold area identification method provided by an exemplary embodiment of the present disclosure is shown. In FIG. 6, in step S601, when the cleaning robot is triggered to perform a predetermined escape operation, the trigger position is obtained, then the process proceeds to step S602, where the trigger position is clustered to determine a first snagging area, the process proceeds to step S603, where height information of obstacles in the first snagging area is obtained, the process proceeds to step S604, where condition 1 is judged, and whether there are consecutive obstacles that meet the predetermined height, if there are, the process proceeds to step S605, where the first snagging area is determined as a second snagging area, and if there are no consecutive obstacles, the process terminates.

[0087] After step S605, proceed to step S606, select a predetermined number of sampling points (abbreviated as sampling point selection) from the second prone to getting stuck area, proceed to step S607, obtain the nearest obstacle distance information corresponding to the sampling points, step S608, determine condition 2, and determine whether the second prone to getting stuck area is a threshold area based on the nearest obstacle distance information, if yes, proceed to step S609, upload the threshold area to the APP, if not, end.

[0088] It should be noted that although the accompanying figures depict the steps of the disclosed methods in a particular order, this does not require or imply that the steps must be performed in a particular order, or that all steps shown must be performed to achieve a desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined and performed as a single step, and / or a single step may be broken down into multiple steps and performed.

[0089] In an exemplary embodiment of the present disclosure, a threshold area identification device is further provided, and as shown in FIG. 7, the threshold area identification device 700 includes a first trap-prone area determination module 710, a second trap-prone area determination module 720, and a threshold area determination module 730.

[0090] The first trap-prone area determining module 710 is used to determine a first trap-prone area based on escape information during the cleaning process of the cleaning robot.

[0091] The second trapping area determining module 720 is used to determine the first trapping area where a series of obstacles of a predetermined height exist as the second trapping area.

[0092] The threshold area determination module 730 is used to determine whether the second trap-prone area is a threshold area based on the second trap-prone area and the room map information where it is located.

[0093] In an exemplary embodiment of the present disclosure, the first snag-prone area determination module 710 is used to obtain a trigger position that triggers a predetermined escape operation of the cleaning robot during the cleaning process of the cleaning robot, and determine the first snag-prone area based on the trigger position.

[0094] In an exemplary embodiment of the present disclosure, the first snag-prone area determination module 710 is used to determine, when there is one trigger position, a trigger area within a predetermined range in which the trigger position is located as the first snag-prone area; when there are multiple trigger positions, to cluster multiple trigger areas corresponding to the multiple trigger positions to obtain at least one first snag-prone area.

[0095] In an exemplary embodiment of the present disclosure, the first snag-prone region determination module 710 clusters the multiple trigger regions to obtain the first snag-prone region based on the mutual distances between the multiple trigger positions.

[0096] In an exemplary embodiment of the present disclosure, the predetermined range is within 50 cm of the trigger position.

[0097] In an exemplary embodiment of the present disclosure, the predetermined escape action is an escape action that is triggered after the cleaning robot slips.

[0098] In an exemplary embodiment of the present disclosure, the second snag-prone area determination module 720 obtains height information of obstacles in the first snag-prone area, and based on the obstacle height information, determines whether there are consecutive obstacles that meet a predetermined height in the first snag-prone area, and if so, is used to determine the first snag-prone area as the second snag-prone area.

[0099] In an exemplary embodiment of the present disclosure, the predetermined height is between 1.5 cm and 2 cm.

[0100] In an exemplary embodiment of the present disclosure, the threshold area determination module 730 is used to select a predetermined number of sampling points from the second snag-prone area, obtain the nearest obstacle distance information on the room map of the sampling points based on the room map information, and determine whether the second snag-prone area is a threshold area based on the nearest obstacle distance information.

[0101] In an exemplary embodiment of the present disclosure, the threshold area determination module 730 is used to obtain the nearest obstacle distance in each direction of the sampling point starting from the sampling point in the room map, and to construct the nearest obstacle distance information.

[0102] In an exemplary embodiment of the present disclosure, the threshold area determination module 730 is used to identify the nearest obstacle distance information using a neural network classifier and determine whether the second trap-prone area is a threshold area, where the neural network classifier is trained with the nearest obstacle distance training information.

[0103] In an exemplary embodiment of the present disclosure, the threshold area determination module 730 is used to determine whether the second snag-prone area is a threshold area based on multiple nearest obstacle distance information obtained from a predetermined number of sampling points, and if the nearest obstacle distance information corresponding to one sampling point determines that the second snag-prone area is a threshold area, the threshold area determination module 730 is used to determine that the second snag-prone area is a threshold area.

[0104] In an exemplary embodiment of the present disclosure, the predetermined number is 8-10.

[0105] The specific details of each of the above threshold area identification device modules have already been described in detail in the corresponding threshold area identification method, so they will not be repeated here.

[0106] It should be noted that although the above detailed description refers to multiple modules or units of an apparatus for execution, such division is not required. In fact, according to embodiments of the present disclosure, the features and functions of two or more of the modules or units described above may be embodied in a single module or unit. Conversely, the features and functions of one module or unit described above may be further divided so as to be embodied by multiple modules or units.

[0107] An exemplary embodiment of the present disclosure further provides an electronic device capable of implementing the above method, and the electronic device may be, for example, a cleaning robot capable of implementing the above method.

[0108] Those skilled in the art will appreciate that each aspect of the present disclosure may be realized as a system, a method, or a program product. Accordingly, each aspect of the present disclosure may be specifically realized in the form of an entirely hardware implementation, an entirely software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, which may be collectively referred to herein as a "circuit," "module," or "system."

[0109] An electronic device 800 according to such an embodiment of the present disclosure will now be described with reference to Fig. 8. The electronic device 800 shown in Fig. 8 is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present disclosure.

[0110] 8, the electronic device 800 is represented in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to, the at least one processing unit 810, the at least one storage unit 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), and a display unit 840.

[0111] The storage unit 820 stores program code that, when executed by the processing unit 810, can cause the processing unit 810 to perform steps according to the exemplary embodiments of the present disclosure described in the "Exemplary Method" section herein. For example, the processing unit 810 can perform the steps shown in FIGS. 1 and 3.

[0112] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 8201 and / or a cache storage unit 8202, and may further include a read-only storage unit (ROM) 8203.

[0113] The storage unit 820 may further include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, and may also include a network environment implementation in each of these examples or in some combination.

[0114] Bus 830 may be one or more of several bus structures, including a storage unit bus or storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local area bus using any bus structure in multiple bus structures.

[0115] The electronic device 800 may communicate with one or more external devices 870 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that allow a user to interact with the electronic device 800, and / or any device (e.g., a router, a modem, etc.) that allows the electronic device 800 to communicate with one or more other computing devices. Such communication may occur via an input / output (I / O) interface 850. The electronic device 800 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown, other hardware and / or software modules (including, but not limited to, microcode, device drives, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems) may be used in conjunction with the electronic device 800.

[0116] From the above description of the embodiments, it is easily understood by those skilled in the art that the exemplary embodiments described herein may be realized by software or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a removable hard disk, etc.) or a network, and includes a number of instructions for causing a computing device (such as a personal computer, a server, a terminal device, or a network device) to execute the method of the embodiments of the present disclosure.

[0117] An exemplary embodiment of the present disclosure further provides a computer-readable storage medium having stored thereon a program product capable of implementing the methods described herein. In some possible embodiments, aspects of the present disclosure may be implemented in the form of a program product including program code, which, when executed on a terminal device, is used to cause the terminal device to perform steps according to the exemplary embodiments of the present disclosure described in the "Exemplary Methods" section of this specification.

[0118] A program product for implementing the above method according to an embodiment of the present disclosure may be a portable compact disc read-only memory (CD-ROM), containing program code, and may be executed on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this specification, a readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in combination with an instruction execution system, apparatus, or device.

[0119] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0120] A computer-readable signal medium may comprise a propagated data signal in baseband or as part of a carrier carrying readable program code. Such a propagated data signal may take various forms, including, but not limited to, an electromagnetic signal, an optical signal, or any suitable combination of the above. A readable signal medium may be any readable medium, other than a readable storage medium, that transmits, propagates, or transports a program for use by or in connection with an instruction execution system, apparatus, or device.

[0121] The program code contained in the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, fiber optic cable, RF, etc., or any suitable combination of the above.

[0122] Program code for carrying out the operations of the present disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may execute entirely on the user computing device, partially on the user device, as a standalone software package, partially on the user computing device, partially on a remote computing device, or entirely on a remote computing device or server. In situations involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by using an Internet service provider to connect via the Internet).

[0123] Furthermore, the above-mentioned attached drawings are merely schematic illustrations of the processes involved in the method according to the exemplary embodiments of the present disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above-mentioned attached drawings do not indicate or limit the chronological order of these processes. It is also readily understood that the processes may be performed synchronously or asynchronously in multiple modules, for example.

[0124] Other embodiments of the present disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure in accordance with the general principles of the present disclosure, including technical means known or customary in the art but not disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0125] It should be understood that the present disclosure is not limited to the exact construction described above and illustrated in the accompanying drawings, and that various modifications and changes may be made thereto without departing from the scope thereof, which is intended to be limited only by the appended claims.

Claims

1. A threshold area identification method, comprising: determining a first trap-prone area based on escape information during the cleaning process of the cleaning robot; determining the first trapping-prone area in which a continuous obstacle of a predetermined height exists as a second trapping-prone area; and determining whether the second prone to getting caught area is a threshold area based on the second prone to getting caught area and room map information in which the second prone to getting caught area is located.

2. The step of determining a first trap-prone area based on escape information during the cleaning process of the cleaning robot includes: acquiring a trigger position for triggering the cleaning robot to perform a predetermined escape action during a cleaning process of the cleaning robot; The method of claim 1 , further comprising determining the first snag prone area based on the trigger position.

3. determining the first prone-to-get-trapped area based on the trigger position, If the trigger position is single, a trigger area within a predetermined range where the trigger position is located is determined as the first easy-to-catch area; The method of claim 2 , further comprising: if there are a plurality of trigger locations, clustering a plurality of the trigger regions corresponding to the plurality of trigger locations to obtain at least one of the first snag-prone regions.

4. Clustering the plurality of trigger regions corresponding to the plurality of trigger positions to obtain at least one first catch-prone region includes: The method of claim 3 , further comprising: clustering the plurality of trigger regions based on mutual distances between the plurality of trigger positions to obtain the first snag-prone region.

5. The method according to claim 3 or 4, wherein the predetermined range is within 50 cm from the trigger position.

6. The method according to any one of claims 2 to 5, wherein the predetermined escape action is an escape action triggered after the cleaning robot slips.

7. The step of determining the first trapping-prone area where a continuous obstacle of a predetermined height exists as a second trapping-prone area includes: obtaining height information of obstacles in the first prone-to-trapping region; determining whether or not a continuous obstacle having the predetermined height is present in the first trap-prone area based on the height information of the obstacle; The method of any one of claims 1 to 6, comprising determining the first snag prone area as the second snag prone area if present.

8. The method according to any one of claims 1 to 7, wherein the predetermined height is between 1.5 cm and 2 cm.

9. The step of determining whether the second trap-prone area is a threshold area based on the second trap-prone area and room map information in which the second trap-prone area is located includes: selecting a predetermined number of sampling points from the second prone area; acquiring distance information of the nearest obstacle on the room map of the sampling point based on the room map information; The method according to any one of claims 1 to 8, further comprising: determining whether the second prone-to-trap area is the threshold area based on the nearest obstacle distance information.

10. Obtaining distance information of the nearest obstacle on the room map of the sampling point based on the room map information The method of claim 9 , further comprising: obtaining, on the room map, the nearest obstacle distance in each direction from the sampling point as a starting point, and configuring the nearest obstacle distance information.

11. Determining whether the second trap-prone area is the threshold area based on the nearest obstacle distance information includes: identifying the nearest obstacle distance information using a neural network classifier and determining whether the second trapping prone area is the threshold area; The method of claim 9 or 10, wherein the neural network classifier is trained with nearest obstacle distance training information.

12. A method according to any one of claims 9 to 11, further comprising, in the process of determining whether the second area prone to getting caught is the threshold area based on a plurality of pieces of nearest obstacle distance information obtained from a predetermined number of the sampling points, a step of determining that the second area prone to getting caught is the threshold area if the second area prone to getting caught is determined to be the threshold area based on the nearest obstacle distance information corresponding to any one of the sampling points.

13. The method according to any one of claims 9 to 12, wherein the predetermined number is between 8 and 10.

14. a first trap-prone area determination module configured to determine a first trap-prone area based on escape information during a cleaning process of the cleaning robot; a second trapping-prone area determination module configured to determine the first trapping-prone area where a continuous obstacle of a predetermined height exists as a second trapping-prone area; and a threshold area determination module configured to determine whether the second prone to getting caught area is a threshold area based on the second prone to getting caught area and room map information in which it is located.

15. A computer-readable storage medium having a computer program stored therein, the computer program implementing the threshold area identification method according to any one of claims 1 to 13 when executed by a processor.

16. a processor; a memory for storing executable instructions for said processor; wherein the processor is configured to implement the threshold area identification method according to any one of claims 1 to 13 by executing the executable instructions.

Images