CN117047760A

CN117047760A - Robot control method

Info

Publication number: CN117047760A
Application number: CN202311041067.5A
Authority: CN
Inventors: 张石磊
Original assignee: Xingmai Innovation Technology Suzhou Co ltd
Current assignee: Xingmai Innovation Technology Suzhou Co ltd
Priority date: 2023-08-17
Filing date: 2023-08-17
Publication date: 2023-11-14

Abstract

The embodiment of the invention provides a control method of a robot, which comprises the following steps: acquiring first identification information acquired by a target robot in a pool, wherein the first identification information represents characteristic information obtained by carrying out image identification on a target obstacle, and the target obstacle is an obstacle detected by the target robot in the pool; determining the type of the target obstacle according to the first identification information, wherein different types of obstacles which are allowed to be detected in the pool are preset, and different control modes which are used by the target robot to detect the different types of obstacles are allowed to be used; and under the condition that the category of the target obstacle is the target category, controlling the target robot to execute a preset task in the pool based on a target control mode corresponding to the target category. The invention solves the problem of lower working efficiency of the pool robot, thereby achieving the effect of improving the working efficiency of the robot.

Description

Robot control method

Technical Field

The embodiment of the invention relates to the field of robots, in particular to a control method of a robot.

Background

In the related art, various obstacles are generally encountered when a pool robot works in a pool, and the pool robot is controlled in such a way that the obstacle is avoided after collision or kept at a fixed distance from the obstacle.

If the obstacle is avoided after collision, the obstacle can be involved in an execution part of the pool robot to cause the execution part to be blocked; if the obstacle is kept away from the obstacle at a fixed distance, the cleaning of the specific obstacle and other treatments may be omitted; resulting in the technical problem of lower manual efficiency of the pool robot.

There is currently no effective solution to the above problems.

Disclosure of Invention

The embodiment of the invention provides a control method of a robot, which at least solves the technical problem of lower manual work efficiency of a pool robot in the related art.

According to an embodiment of the present invention, there is provided a control method of a robot including: acquiring first identification information acquired by a target robot in a pool, wherein the first identification information represents characteristic information obtained by carrying out image identification on a target obstacle, and the target obstacle is an obstacle detected by the target robot in the pool; determining the category of the target obstacle according to the first identification information, wherein different categories are preset for the obstacles allowed to be detected in the pool, and the control mode adopted by the target robot for detecting the obstacles of different categories is allowed to be different; and under the condition that the category of the target obstacle is a target category, controlling the target robot to execute a preset task in the pool based on a target control mode corresponding to the target category.

According to another embodiment of the present invention, there is provided a control device of a robot including: the acquisition module is used for acquiring first identification information acquired by the target robot in the pool, wherein the first identification information represents characteristic information obtained by carrying out image identification on a target obstacle, and the target obstacle is an obstacle detected by the target robot in the pool; the determining module is used for determining the category of the target obstacle according to the first identification information, wherein different categories are preset for the obstacles allowed to be detected in the pool, and the control mode adopted by the target robot for detecting the obstacles of different categories is allowed to be different; and the control module is used for controlling the target robot to execute a preset task in the pool based on a target control mode corresponding to the target category under the condition that the category of the target obstacle is the target category.

In an exemplary embodiment, the device is configured to obtain the first identification information collected by the target robot in the pool by: responding to the target robot to start executing the preset task, and acquiring an image of the target obstacle in the pool through a target image acquisition device to obtain target image data, wherein the target image acquisition device is arranged on the target robot; and identifying the target image data and determining the first identification information.

In an exemplary embodiment, the apparatus is configured to respond to the target robot beginning to perform the preset task by performing image acquisition on the target obstacle in the pool by using a target image acquisition device to obtain target image data: responding to the target robot to start executing the preset task, and detecting the depth of the water body where the target robot is located; and determining acquisition parameters of the target image acquisition equipment according to the water depth, and carrying out image acquisition on the target obstacle based on the acquisition parameters to obtain target image data.

In an exemplary embodiment, the apparatus is configured to respond to the target robot beginning to perform the preset task by performing image acquisition on the target obstacle in the pool by using a target image acquisition device to obtain target image data: detecting the water body cleanliness of the water tank, and determining the target water body cleanliness; and determining acquisition parameters of the target image acquisition equipment according to the target water body cleanliness, and carrying out image acquisition on the target obstacle based on the acquisition parameters to obtain target image data.

In an exemplary embodiment, the apparatus is configured to identify the target image data and determine the first identification information by: extracting features of the target image data, and determining target feature information of the target obstacle; preprocessing the target characteristic information, inputting the preprocessed target characteristic information into an identification model of the target robot, and determining the first identification information, wherein the preprocessing is used for adding a weight value corresponding to characteristic information used for determining the category of the target obstacle in the target characteristic information.

In an exemplary embodiment, the apparatus is configured to determine the category of the target obstacle according to the first identification information by at least one of: determining the category of the target obstacle as a first category according to the first identification information, wherein the target category comprises the first category, and the first category indicates that the target obstacle is an obstacle which needs the target robot to be far away; determining the category of the target obstacle as a second category according to the first identification information, wherein the target category comprises the second category, and the second category represents that the target obstacle is a fixed obstacle; determining the category of the target obstacle as a third category according to the first identification information, wherein the target category comprises the third category, and the third category indicates that the target obstacle is an obstacle needing to send out a reminding message; and determining the category of the target obstacle as a fourth category according to the first identification information, wherein the target category comprises the fourth category, and the fourth category indicates that the target obstacle is an obstacle which needs to be moved by the target robot.

In an exemplary embodiment, the device is configured to control the target robot to perform a preset task in the pool based on a target control mode corresponding to the target category when the category of the target obstacle is the target category by at least one of: setting a first obstacle avoidance distance under the condition that the category of the target obstacle is the first category, wherein the first obstacle avoidance distance is larger than an initial obstacle avoidance distance preset by the target robot; controlling the target robot to execute the preset task in the pool according to the first obstacle avoidance distance under the condition that the target robot moves to a distance from the target obstacle to meet the first obstacle avoidance distance; setting a second obstacle avoidance distance under the condition that the category of the target obstacle is the second category, wherein the second obstacle avoidance distance is smaller than an initial obstacle avoidance distance preset by the target robot; controlling the target robot to execute the preset task in the pool according to the second obstacle avoidance distance under the condition that the target robot moves to a distance from the target obstacle to meet the second obstacle avoidance distance; marking the position of the target obstacle under the condition that the category of the target obstacle is the third category; sending a target reminding message to a target terminal to indicate the position of the target obstacle in the pool, and executing the preset task in the pool according to the initial obstacle avoidance distance preset by the target robot; and under the condition that the category of the target obstacle is the fourth category, controlling a mechanical control part of the target robot to move the target obstacle, and cleaning the position of the target obstacle before moving so as to control the target robot to execute the preset task in the pool.

In an exemplary embodiment, the apparatus is further configured to: acquiring an original map of the pool and position information of the target obstacle, wherein the target robot is set to execute the preset task in the pool according to the original map; and marking and updating the original map according to the position information to obtain a target map so as to control the target robot to execute the preset task in the pool according to the target map.

In an exemplary embodiment, the apparatus is further configured to: when the target robot reaches a preset distance from a target position, controlling the target robot to decelerate, and acquiring second identification information acquired by the target robot in the pool, wherein the second identification information represents characteristic information obtained by carrying out image identification on the target obstacle in the process of cleaning the pool according to the target map, and the target position represents a marked position of the target obstacle in the target map; and determining the category of the target obstacle according to the second identification information, and controlling the target robot to execute the preset task in the pool according to the target obstacle avoidance distance corresponding to the target control mode under the condition that the category of the target obstacle is the target category.

According to still another embodiment of the present invention, there is also provided a pool robot, which is applied to the control method of the robot, including: the image acquisition equipment is used for acquiring first identification information; and the processor is used for determining the target control mode according to the first identification information and controlling the target robot to execute the preset task in the pool according to the target control mode.

According to a further embodiment of the invention, there is also provided a computer readable storage medium having stored therein a computer program, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.

According to a further embodiment of the invention, there is also provided an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.

According to the invention, the first identification information acquired by the target robot in the pool is acquired, wherein the first identification information represents the characteristic information obtained by carrying out image identification on the target obstacle, and the target obstacle is the obstacle detected by the target robot in the pool; determining the type of the target obstacle according to the first identification information, wherein different types of obstacles which are allowed to be detected in the pool are preset, and different control modes which are used by the target robot to detect the different types of obstacles are allowed to be used; and under the condition that the category of the target obstacle is the target category, controlling the target robot to execute a preset task in the pool based on a target control mode corresponding to the target category. By identifying the types of the obstacles and determining the related processing modes of the obstacles according to different types, the preset tasks can be executed more efficiently, the problem that when the underwater robot actually works to meet different obstacles, the machine executing parts are blocked or are not cleaned due to the fact that the effective processing modes cannot be adopted can be solved, and the working efficiency of the target robot can be improved. Therefore, the problem of lower working efficiency of the pool robot can be solved.

Drawings

Fig. 1 is a hardware block diagram of a mobile terminal of a control method of a robot according to an embodiment of the present application;

fig. 2 is a flowchart of a control method of a robot according to an embodiment of the present application;

fig. 3 is a detailed flowchart of a control method of a robot according to an embodiment of the present application;

fig. 4 is a block diagram of a control device of a robot according to an embodiment of the present application.

Detailed Description

Embodiments of the present application will be described in detail below with reference to the accompanying drawings in conjunction with the embodiments.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.

The method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, which may be a mobile robot, for example. Taking the operation on a mobile terminal as an example, fig. 1 is a block diagram of a hardware structure of a mobile terminal of a control method of a robot according to an embodiment of the present application. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.

The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a control method of a robot in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, to implement the above-described method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission arrangement 106 may be a Radio Frequency (RF) module for communicating wirelessly with the internet.

In this embodiment, a control method for the robot is provided, and the positioning method can be applied to a scene that the robot cleans a water body environment such as a swimming pool, a pool and the like, for example, the pool robot cleans in the swimming pool, and when an obstacle needs to be avoided, the control method for the robot can be adopted.

Fig. 2 is a flowchart of a control method of a robot according to an embodiment of the present invention, as shown in fig. 2, the flowchart including the steps of:

s202, acquiring first identification information acquired by a target robot in a pool, wherein the first identification information represents characteristic information obtained by carrying out image identification on a target obstacle, and the target obstacle is an obstacle detected by the target robot in the pool;

optionally, in this embodiment, the control method of the robot may include, but is not limited to, application scenarios that require cleaning of a water environment, such as a swimming pool cleaning scenario, a pool cleaning scenario, and a fish tank cleaning scenario.

It should be noted that, in this application scenario, there is an obstacle in the water body, and this obstacle may affect the cleaning process of the robot, so the determination of the type of the obstacle needs to be completed by using the control method of the robot, and a suitable control mode of the robot is selected according to the determined type of the obstacle to achieve cleaning of the water body environment.

Alternatively, in this embodiment, the target robot includes, but is not limited to, an underwater robot, which may be understood as a robot operating in a water environment, and may be a device for cleaning a water environment such as a swimming pool, such as a cabled submersible, a cableless submersible, or the like. The pool can be understood as a water environment in which a predetermined task is to be performed by a robot, and the target robot is controlled to perform the predetermined task in the pool by being placed in the pool.

It should be noted that the preset tasks may include, but are not limited to, a pool cleaning task, a pool detection task, and the like.

In an exemplary embodiment, the first identification information is used to represent feature information obtained by performing image recognition on the target obstacle, where the feature information may be feature information extracted based on an underwater target recognition algorithm.

It should be noted that the underwater target recognition algorithm may be, but not limited to, an artificial intelligence implementation-based target recognition algorithm.

Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision.

The artificial intelligence technology is a comprehensive subject, and relates to the technology with wide fields, namely the technology with a hardware level and the technology with a software level. Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

Computer Vision (CV) is a science of studying how to "look" a machine, and more specifically, to replace a human eye with a camera and a Computer to perform machine Vision such as recognition and measurement on a target, and further perform graphic processing to make the Computer process an image more suitable for human eye observation or transmission to an instrument for detection. As a scientific discipline, computer vision research-related theory and technology has attempted to build artificial intelligence systems that can acquire information from images or multidimensional data. Computer vision techniques typically include image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content/behavior recognition, three-dimensional object reconstruction, 3D techniques, virtual reality, augmented reality, synchronous positioning, and map construction, among others, as well as common biometric recognition techniques such as face recognition, fingerprint recognition, and others.

In an exemplary embodiment, the first identification information may be determined by an Object Detection (Object Detection) algorithm, where the Object is identified from the image/video, and the position and the category of the Object are fed back. The above-mentioned object recognition algorithm includes, but is not limited to, R-CNN, YOLO, SSD, etc., taking R-CNN as an example, its main principle is to build a large number (2 thousand or more) of candidate regions (regions) for one image, then perform object recognition calculation on these regions, and classify them by using SVM. On the basis of R-CNN, fast R-CNN and the like, taking a YOLO algorithm as an example, YOLO (You Only Look Once) is mainly applied to rapid target detection, and particularly in some edge devices, such as automatic driving, unmanned vehicles and the like, the obtained images and videos need to be rapidly identified and fed back for a control system to make rapid response. Compared with R-CNN adopting a proposal of a large number of detection areas, YOLO adopts a one-step in-place mode, namely, the input is the whole image, and the output is the area and the target type which are directly identified by the target. The key idea of YOLO is to take the whole graph as input and directly obtain the region and type of the target at the output layer. The whole image is used as input by the fast R-CNN, but the method of two steps is adopted by the fast R-CNN, the region for detecting the pro target is firstly detected, and then the image of each region is identified. Taking SSD as an example, SSD (Single Short multibox Detector) algorithm is a relatively excellent algorithm that appears for the characteristics of R-CNN and YOLO after they appear. The operating speed of YOLO is greatly improved compared with R-CNN, but the accuracy is inferior to that of R-CNN.

The above is merely an example, and the type of the identification algorithm for specifically acquiring the first identification information is not limited in this embodiment.

Alternatively, in the present embodiment, the above-described target obstacle may be understood as an obstacle that the target robot allows to detect in the pool, for example, an obstacle that affects the operation of the target robot, such as an escalator, a rag, leaves, clothes, or the like.

The classification of the target obstacle may be performed according to the influence on the target robot.

S204, determining the type of the target obstacle according to the first identification information, wherein different types of obstacles which are allowed to be detected in the pool are preset, and different control modes which are adopted by the target robot to detect the different types of obstacles are allowed to be used;

alternatively, in this embodiment, different types of obstacles allowed to be detected in the pool may be set in advance, and the recognition model may be trained based on the feature information extracted from the obstacles of the corresponding types, so as to obtain a recognition algorithm capable of classifying the recognized obstacles, and then, the type of the target obstacle may be determined according to the first recognition information by the target recognition algorithm.

It should be noted that, the different categories set for the obstacle may be set manually according to a priori knowledge, or may be implemented by a self-learning category generation algorithm.

For example, for the purpose of attaching clothes, rags, etc. to the hub of the target robot, which affects the normal operation of the robot, it is considered that the textiles such as clothes, rags, etc. are set in one category.

For example, the movement of the robot is blocked by the escalator, the stone pillar and the like, and the normal operation of the robot is affected, and at this time, the escalator, the stone pillar and the like can be considered to be set as one of the categories.

In an exemplary embodiment, taking the above object class as an example, when the object robot detects that an object a exists in front, image data is acquired by image acquisition equipment on the object a, and then feature extraction and object detection operations are performed on the image data, it can be determined that the object a belongs to the textile class, where the textile class is the above object class.

It should be noted that, the control manner adopted by the target robot to clear different types of obstacles allows the difference to be understood as adopting different clearing strategies for different obstacles, for example, if the obstacle is a textile, a relatively larger avoiding distance is set to avoid being entangled by the obstacle. Also for example, if the obstacle is a staircase, a relatively smaller avoidance distance is provided to avoid long-term non-cleaning of the staircase.

S206, controlling the target robot to execute a preset task in the pool based on a target control mode corresponding to the target type when the type of the target obstacle is the target type.

Optionally, in this embodiment, the target control manner and the target category have a mapping relationship.

Alternatively, in this embodiment, the preset tasks may include, but are not limited to, one or more of cleaning, disinfecting, water quality testing, etc. in the sink.

According to the embodiment of the invention, the first identification information acquired by the target robot in the pool is acquired, wherein the first identification information represents the characteristic information obtained by carrying out image identification on the target obstacle, the target obstacle is the obstacle detected by the target robot in the pool, the type of the target obstacle is determined to be the target type according to the first identification information, different types are preset for the obstacle allowed to be detected in the pool, the control modes adopted by the target robot for cleaning the different types of the obstacle are allowed to be different, and the target robot is controlled to clean the pool based on the target control mode corresponding to the target type. By identifying the type of the obstacle and processing the obstacle according to different types. The method aims at solving the problems that when the underwater robot actually works and encounters different obstacles, the effective treatment mode cannot be adopted, so that the machine executing component is blocked or cleaning is missed, and the working efficiency of the target robot can be improved. Therefore, the problem of lower working efficiency of the pool robot can be solved.

As an alternative, acquiring first identification information acquired by the target robot in the pool includes: responding to the target robot to start executing the preset task, and acquiring an image of the target obstacle in the pool through a target image acquisition device to obtain target image data, wherein the target image acquisition device is arranged on the target robot; and identifying the target image data and determining the first identification information.

Alternatively, in the present embodiment, the above-described target image capturing apparatus may be understood as an apparatus that allows communication with a target robot, which may be disposed above the target robot or may be disposed at a position where normal communication with the robot is possible, for example, a pool wall or the like.

As an alternative, acquiring first identification information acquired by the target robot in the pool includes: detecting the pool by the target sensor in response to the target robot entering the pool; under the condition that the existence of the target obstacle is detected, image acquisition is carried out on the target obstacle through target image acquisition equipment to obtain target image data; and identifying the target image data and determining first identification information.

Alternatively, in this embodiment, the above-mentioned target sensor may be, but not limited to, an ultrasonic sensor, and the sensor information collected by the sensor includes distance information and angle information, including, but not limited to, a distance between the obstacle and the target robot, and a direction angle of the obstacle relative to the target robot, that is, the sensor information includes distance information and angle information, where the distance information is used to represent a distance between the obstacle and the target robot, and the angle information is used to represent a direction angle between the obstacle and the target robot.

Alternatively, in the present embodiment, in the case where the target obstacle is detected by the above-described target sensor, image acquisition of the target obstacle by the target image acquisition apparatus, which may include, but is not limited to, an underwater camera or the like, is started.

In the process that the target robot moves along the edge of the pool or in the process that the target robot rotates, the sensing information collected by the sensor can obtain line segment data characteristics and angle characteristics of the obstacle, and the line segment data characteristics and the angle characteristics form part of characteristics of the pool, such as swimming pool angles, wall surfaces and other swimming pool characteristics of the pool.

In one exemplary embodiment, the sensed information is collected using an ultrasonic sensor, and includes some of the features in the pool, such as the outer right angle, inner right angle, outer circular arc, inner circular arc of the pool, and steps, escalators, etc. within the pool. Distance information of the vertical pool sides and corners in each pool can also be detected by ultrasonic sensors.

As an alternative, in response to the target robot starting to perform the preset task, image capturing, by a target image capturing device, the target obstacle in the pool to obtain target image data, including: responding to the target robot to start executing the preset task, and detecting the depth of the water body where the target robot is located; and determining acquisition parameters of the target image acquisition equipment according to the water depth, and carrying out image acquisition on the target obstacle based on the acquisition parameters to obtain target image data.

Alternatively, in this embodiment, the target robot may be configured with target image capturing devices that operate at different depths of the water body in advance, and the target image capturing devices that operate at different depths of the water body may have different energy consumption and/or computing power.

It should be noted that, the apparatus for detecting the depth of the water body may be a conventional physical apparatus, and after determining the depth of the water body where the target robot is located, a start instruction is sent to the target image acquisition device corresponding to the depth of the water body, and the corresponding target image acquisition device starts to work immediately.

As an alternative, determining an acquisition parameter of the target image acquisition device according to the depth of the water body, and performing image acquisition on the target obstacle based on the acquisition parameter to obtain target image data, including: determining a first target image acquisition device in response to the target robot being at a first water depth, wherein the first target image acquisition device is configured to detect an obstacle at the first water depth; and determining a second target image acquisition device in response to the target robot being at a second water depth, wherein the second target image acquisition device is used for detecting the obstacle at the second water depth, the second water depth is greater than the first water depth, and the power consumption of the second target image acquisition device is higher than the power consumption of the first target image acquisition device.

Optionally, in this embodiment, the second water depth may be understood as being greater than the first water depth, that is, when the target robot is at a different water depth, the target image capturing device used is different, when the target robot is at a deeper water depth, the working strength of the target image capturing device is relatively higher, the power consumption is relatively higher, when the target robot is at a shallower water depth, the working strength of the target image capturing device is relatively lower, and the power consumption is relatively lower.

According to the method and the device, the obstacle is detected by adopting different target image acquisition equipment under different water depths, so that the resource cost of the target robot can be reduced, and certain accuracy can be ensured.

As an alternative, in response to the target robot starting to perform the preset task, image capturing, by a target image capturing device, the target obstacle in the pool to obtain target image data, including: detecting the water body cleanliness of the water tank, and determining the target water body cleanliness; and determining acquisition parameters of the target image acquisition equipment according to the target water body cleanliness, and carrying out image acquisition on the target obstacle based on the acquisition parameters to obtain target image data.

Alternatively, in this embodiment, the above detection of the cleanliness of the water in the pool may be understood as that the acquisition parameters of the target image acquisition device are different when the water is cloudy or when the water is clear.

It should be noted that, the above-mentioned acquisition parameters can be understood as exposure degree, focal length, etc., so as to adapt to acquiring clearer target image data under different water body cleannesses by different acquisition parameters, so as to ensure the accuracy of subsequent identification.

As an alternative, determining an acquisition parameter of the target image acquisition device according to the cleanliness of the target water body, and performing image acquisition on the target obstacle based on the acquisition parameter to obtain target image data, including: configuring acquisition parameters of target image acquisition equipment as first acquisition parameters when the cleanliness of the target water body belongs to a first cleanliness interval, and carrying out image acquisition on a target obstacle based on the first acquisition parameters to obtain target image data, wherein the first acquisition parameters represent the acquisition parameters with a mapping relation with the first cleanliness interval; and configuring the acquisition parameters of the target image acquisition equipment as second acquisition parameters when the cleanliness of the target water body belongs to a second cleanliness interval, and carrying out image acquisition on the target obstacle based on the second acquisition parameters to obtain target image data, wherein the first cleanliness interval is different from the second cleanliness interval, the first acquisition parameters are different from the second acquisition parameters, and the second acquisition parameters represent the acquisition parameters with a mapping relation with the second cleanliness interval.

Optionally, in this embodiment, the first cleanliness interval and the second cleanliness interval may be preset by human beings according to priori knowledge, and different acquisition parameters are bound for different cleanliness intervals, so as to dynamically adjust the acquisition parameters to obtain clearer target image data in different cleanliness intervals.

As an alternative, identifying the target image data, and determining the first identification information includes: extracting features of the target image data, and determining target feature information of the target obstacle; preprocessing the target characteristic information, inputting the preprocessed target characteristic information into an identification model of the target robot, and determining the first identification information, wherein the preprocessing is used for adding a weight value corresponding to characteristic information used for determining the category of the target obstacle in the target characteristic information.

Optionally, in this embodiment, the preprocessing is used to represent weighting of the features in the target image data, so as to improve a weight value corresponding to the feature information used to determine the category to which the target obstacle belongs in the feature information, so that the accuracy of subsequent recognition corresponding to the preprocessed target feature information is higher.

Illustratively, the preprocessing operations described above may include, but are not limited to, image enhancement, image denoising, image sharpening, and the like.

As an alternative, determining the category of the target obstacle according to the first identification information includes at least one of:

Determining the category of the target obstacle as a first category according to the first identification information, wherein the target category comprises the first category, and the first category indicates that the target obstacle is an obstacle which needs the target robot to be far away; determining the category of the target obstacle as a second category according to the first identification information, wherein the target category comprises the second category, and the second category represents that the target obstacle is a fixed obstacle; determining the category of the target obstacle as a third category according to the first identification information, wherein the target category comprises the third category, and the third category indicates that the target obstacle is an obstacle needing to send out a reminding message; and determining the category of the target obstacle as a fourth category according to the first identification information, wherein the target category comprises the fourth category, and the fourth category indicates that the target obstacle is an obstacle which needs to be moved by the target robot.

Alternatively, in the present embodiment, the above-described first category may be understood as presetting an obstacle, such as a rag, clothing, or the like, that requires the target robot to avoid a greater distance.

Optionally, in this embodiment, the second category may be understood as an obstacle whose existing duration exceeds a preset duration, where the preset duration may be preset by a system or by an operator, and the existing duration may be recorded by identifying the obstacle each time, and the existing duration is the time from when the obstacle is identified earliest to when the obstacle is identified latest. Such as an escalator, a water pipe, etc. Because of the lengthy time, the target robot is required to more carefully clean its surroundings, requiring the target robot to avoid less distance.

In an exemplary embodiment, the specific kind of the obstacle may also be identified directly according to the image, for example, an underwater escalator or the like is identified as a fixed obstacle, in other words, the existence time of the obstacle is not required to be identified each time, but the obstacle is identified for the first time, that is, the type of the obstacle is determined through the existence time, and after the obstacle is identified again later, the obstacle is determined directly according to the image identification.

The fixed obstacle may be understood as an obstacle having a time period exceeding a preset time period, or the like.

Optionally, in this embodiment, the third category may be understood that the target robot needs to send a reminder message to the connected target terminal or play a reminder sound after identifying the target obstacle. For example, when a limb portion of a human is recognized, a warning message needs to be sent out and avoided.

Optionally, in this embodiment, the fourth category may be understood as an obstacle that needs to be moved by the target robot, where the target robot configures a corresponding mechanical control location, for example, a mechanical arm, and when it is identified that the obstacle belongs to the fourth category, the mechanical arm is controlled to move the obstacle, so as to achieve the effect of cleaning the area covered by the obstacle.

As an alternative, in the case that the category of the target obstacle is the target category, the target robot is controlled to perform a preset task in the pool based on a target control mode corresponding to the target category, including at least one of the following: setting a first obstacle avoidance distance under the condition that the category of the target obstacle is a first category, wherein the first obstacle avoidance distance is larger than an initial obstacle avoidance distance preset by the target robot; under the condition that the distance between the target robot and the target obstacle meets the first obstacle avoidance distance, controlling the target robot to execute a preset task in the pool according to the first obstacle avoidance distance; setting a second obstacle avoidance distance under the condition that the category of the target obstacle is a second category, wherein the second obstacle avoidance distance is smaller than an initial obstacle avoidance distance preset by the target robot; under the condition that the distance between the target robot and the target obstacle meets the second obstacle avoidance distance, controlling the target robot to execute a preset task in the pool according to the second obstacle avoidance distance; marking the position of the target obstacle under the condition that the category of the target obstacle is a third category; sending a target reminding message to a target terminal to indicate the position of a target obstacle in a pool, and executing a preset task in the pool according to an initial obstacle avoidance distance preset by a target robot; and under the condition that the category of the target obstacle is the fourth category, controlling the mechanical control part of the target robot to move the target obstacle, and cleaning the position of the target obstacle before moving so as to control the target robot to execute a preset task in the pool.

Optionally, in this embodiment, the first obstacle avoidance distance may be preset according to a priori knowledge, and may also be adaptively set according to the size of the identified target obstacle, that is, the first obstacle avoidance distance may be adaptively adjusted according to the size of the target obstacle.

It should be noted that, the second obstacle avoidance distance may be preset according to priori knowledge, and may also be adaptively set according to the size of the identified target obstacle, that is, the second obstacle avoidance distance may be adaptively adjusted according to the size of the target obstacle.

As an alternative, the method further includes: acquiring an original map of a pool and position information of a target obstacle, wherein the target robot is set to execute a preset task in the pool according to the original map; and marking and updating the original map according to the position information to obtain a target map so as to control the target robot to execute a preset task in the pool according to the target map.

Optionally, in this embodiment, the original map of the pool may be calibrated in advance by a map calibration algorithm, where the original map does not mark a position of a target obstacle, when the target obstacle is first identified, the position of the target obstacle needs to be marked, and when the original map is further located at a preset distance from the target position of the target robot, the target robot is controlled to slow down, and second identification information acquired by the target robot in the pool is acquired, where the second identification information represents feature information obtained by performing image identification on the target obstacle in a process of cleaning the pool according to the target map, and the target position represents a marked position of the target obstacle in the target map; and determining the category of the target obstacle according to the second identification information, and controlling the target robot to execute the preset task in the pool according to the target obstacle avoidance distance corresponding to the target control mode under the condition that the category of the target obstacle is the target category.

Alternatively, in this embodiment, the original map is a map of a pool constructed in advance, and the original map may be a map of a bottom surface of the pool, a map of a water surface, or a combination of the map of the bottom surface and the map of the water surface. The original map is a map created before the target robot performs position calibration on the target obstacle or a map created in the process of performing position calibration on the target obstacle by the target robot.

Specifically, an original map of the pool can be constructed as follows:

controlling the target robot to move along the edge of the water pool in the water pool; acquiring sensing information through a sensor arranged on the target robot in the moving process of the target robot to obtain original sensing information; and constructing an original map according to the original sensing information.

Or the target robot can be controlled to rotate for one circle at a preset position, and sensing information is acquired through a sensor arranged on the target robot.

In addition, for the acquisition of the sensing information by moving along the edge of the pool, the characteristics of the obstacle located on the side of the target robot may be acquired, or the characteristics of the obstacle located in front of the target robot may be acquired (the object detected by the sensor provided on the target robot is regarded as an obstacle, for example, a pool wall surface, a water surface, or the like).

For the acquisition of the sensing information by means of one rotation, the characteristics of the obstacle located at the side of the target robot may be acquired, the characteristics of the obstacle located in front of the target robot may be acquired, or the characteristics of the obstacle located at the side and in front of the target robot may be acquired at the same time.

The features of the barrier include a wall feature located on the floor of the pool or a feature located on the water surface of the pool.

The application is illustrated by the following embodiments:

taking the target robot as a pool robot as an example, an ultrasonic sensor and an image acquisition device are arranged on the pool robot, the ultrasonic sensor can detect the obstacle, and the image acquisition device can complete the image acquisition of the obstacle.

The pool robot can perform work in the pool, for example, cleaning, disinfecting, or water quality testing the pool, etc.

During operation of the pool robot in the swimming pool, sensing information (including but not limited to distance information of the obstacle and direction information of the obstacle on the pool robot) in the swimming pool is collected through the ultrasonic sensor to determine whether the obstacle is detected. After the obstacle is detected, the image acquisition equipment is controlled to acquire and identify the image of the obstacle, so that the target robot is controlled to clean the swimming pool in a corresponding control mode finally selected according to the type of the obstacle.

The application adopts AI recognition and machine real-time positioning technology to recognize the type of the obstacle and process the obstacle according to different types. The method aims at solving the problems that when the underwater robot actually works and encounters different obstacles, the machine executing component is blocked or cleaning is missed due to the fact that an effective processing mode cannot be adopted.

The present application mainly uses AI recognition technology to recognize and classify obstacles, and updates the positions of the obstacles to a map, so as to execute different obstacle avoidance strategies for different types of obstacles, and fig. 3 is a specific flow diagram of a control method of a robot according to an embodiment of the present application, as shown in fig. 3, including but not limited to the following steps:

s302, in the cleaning process of the pool robot, image information in a preset range is acquired through an image acquisition module of the pool robot, and then the acquired image information is matched and identified through an AI identification technology, so that the type of the front obstacle is identified.

S304, after the type of the obstacle is identified, obstacle avoidance processing is performed according to the type of the obstacle. For example, if the influence of the obstacle on the operation of the pool robot is relatively large, a large obstacle avoidance distance is set, and a large detour distance is reserved when detour. If the obstacle type is fixed for a long time, the pool robot can select a closer obstacle avoidance distance, so that dust accumulation around the obstacle is cleaned.

S306, after the obstacle is identified, the position information of the obstacle is marked according to the position information of the pool robot.

This function is advantageous in that, when the obstacle is secondarily cleaned, some processing operations are performed in advance. For example, when the obstacle marked last time is reached, the speed is reduced in advance, and the information of the obstacle is confirmed for the second time, so that the following obstacle avoidance process is facilitated.

Through this embodiment, utilize AI recognition technology to discern the classification to the barrier to mark in the map, thereby set up different obstacle avoidance strategies, compare conventional machine can more efficient clean swimming pool, reduce machine collision and stranded rate, more show intellectuality.

From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.

The embodiment also provides a control device for a robot, which is used for implementing the foregoing embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

Fig. 4 is a block diagram of a control apparatus of a robot according to an embodiment of the present invention, as shown in fig. 4, the apparatus including:

according to another embodiment of the present invention, there is provided a control device of a robot including:

an obtaining module 402, configured to obtain first identification information collected by a target robot in a pool, where the first identification information represents feature information obtained by performing image recognition on a target obstacle, where the target obstacle is an obstacle detected by the target robot in the pool;

a determining module 404, configured to determine a type of the target obstacle according to the first identification information, where different types of obstacles allowed to be detected in the pool are preset, and a control mode adopted by the target robot to detect the different types of obstacles is allowed to be different;

And the control module 406 is configured to control the target robot to perform a preset task in the pool based on a target control mode corresponding to the target category when the category of the target obstacle is the target category.

As an alternative, the device is used for acquiring the first identification information acquired by the target robot in the pool by the following modes: responding to the target robot to start executing the preset task, and acquiring an image of the target obstacle in the pool through a target image acquisition device to obtain target image data, wherein the target image acquisition device is arranged on the target robot; and identifying the target image data and determining the first identification information.

As an alternative, the device is configured to respond to the target robot to start executing the preset task by performing image acquisition on the target obstacle in the pool by using a target image acquisition device, so as to obtain target image data: responding to the target robot to start executing the preset task, and detecting the depth of the water body where the target robot is located; and determining acquisition parameters of the target image acquisition equipment according to the water depth, and carrying out image acquisition on the target obstacle based on the acquisition parameters to obtain target image data.

As an alternative, the device is configured to respond to the target robot to start executing the preset task by performing image acquisition on the target obstacle in the pool by using a target image acquisition device, so as to obtain target image data: detecting the water body cleanliness of the water tank, and determining the target water body cleanliness; and determining acquisition parameters of the target image acquisition equipment according to the target water body cleanliness, and carrying out image acquisition on the target obstacle based on the acquisition parameters to obtain target image data.

As an alternative, the device is configured to identify the target image data and determine the first identifying information by: extracting features of the target image data, and determining target feature information of the target obstacle; preprocessing the target characteristic information, inputting the preprocessed target characteristic information into an identification model of the target robot, and determining the first identification information, wherein the preprocessing is used for adding a weight value corresponding to characteristic information used for determining the category of the target obstacle in the target characteristic information.

As an alternative, the device is configured to determine the category of the target obstacle according to the first identification information by at least one of: determining the category of the target obstacle as a first category according to the first identification information, wherein the target category comprises the first category, and the first category indicates that the target obstacle is an obstacle which needs the target robot to be far away; determining the category of the target obstacle as a second category according to the first identification information, wherein the target category comprises the second category, and the second category represents that the target obstacle is a fixed obstacle; determining the category of the target obstacle as a third category according to the first identification information, wherein the target category comprises the third category, and the third category indicates that the target obstacle is an obstacle needing to send out a reminding message; and determining the category of the target obstacle as a fourth category according to the first identification information, wherein the target category comprises the fourth category, and the fourth category indicates that the target obstacle is an obstacle which needs to be moved by the target robot.

As an alternative, the device is configured to control the target robot to perform a preset task in the pool based on a target control mode corresponding to the target category when the category of the target obstacle is the target category by at least one of: setting a first obstacle avoidance distance under the condition that the category of the target obstacle is the first category, wherein the first obstacle avoidance distance is larger than an initial obstacle avoidance distance preset by the target robot; controlling the target robot to execute the preset task in the pool according to the first obstacle avoidance distance under the condition that the target robot moves to a distance from the target obstacle to meet the first obstacle avoidance distance; setting a second obstacle avoidance distance under the condition that the category of the target obstacle is the second category, wherein the second obstacle avoidance distance is smaller than an initial obstacle avoidance distance preset by the target robot; controlling the target robot to execute the preset task in the pool according to the second obstacle avoidance distance under the condition that the target robot moves to a distance from the target obstacle to meet the second obstacle avoidance distance; marking the position of the target obstacle under the condition that the category of the target obstacle is the third category; sending a target reminding message to a target terminal to indicate the position of the target obstacle in the pool, and executing the preset task in the pool according to the initial obstacle avoidance distance preset by the target robot; and under the condition that the category of the target obstacle is the fourth category, controlling a mechanical control part of the target robot to move the target obstacle, and cleaning the position of the target obstacle before moving so as to control the target robot to execute the preset task in the pool.

As an alternative, the device is further configured to: acquiring an original map of the pool and position information of the target obstacle, wherein the target robot is set to execute the preset task in the pool according to the original map; and marking and updating the original map according to the position information to obtain a target map so as to control the target robot to execute the preset task in the pool according to the target map.

As an alternative, the device is further configured to: when the target robot reaches a preset distance from a target position, controlling the target robot to decelerate, and acquiring second identification information acquired by the target robot in the pool, wherein the second identification information represents characteristic information obtained by carrying out image identification on the target obstacle in the process of cleaning the pool according to the target map, and the target position represents a marked position of the target obstacle in the target map; and determining the category of the target obstacle according to the second identification information, and controlling the target robot to execute the preset task in the pool according to the target obstacle avoidance distance corresponding to the target control mode under the condition that the category of the target obstacle is the target category.

It should be noted that each of the above modules may be implemented by software or hardware, and for the latter, it may be implemented by, but not limited to: the modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.

Embodiments of the present invention also provide a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.

In one exemplary embodiment, the computer readable storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.

An embodiment of the invention also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.

In an exemplary embodiment, the electronic apparatus may further include a transmission device connected to the processor, and an input/output device connected to the processor.

The embodiment of the invention also provides a pool robot, which is applied to the control method of the robot in the embodiment. The pool robot image acquisition equipment is used for acquiring first identification information; and the processor is used for determining the target control mode according to the first identification information and controlling the target robot to execute the preset task in the pool according to the target control mode.

Specific examples in this embodiment may refer to the examples described in the foregoing embodiments and the exemplary implementation, and this embodiment is not described herein.

It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

The above description is only a few embodiments of the present invention and is not intended to limit the present invention, and various modifications and variations will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A control method of a robot, comprising:

acquiring first identification information acquired by a target robot in a pool, wherein the first identification information represents characteristic information obtained by carrying out image identification on a target obstacle, and the target obstacle is an obstacle detected by the target robot in the pool;

determining the category of the target obstacle according to the first identification information, wherein different categories are preset for the obstacles allowed to be detected in the pool, and the control mode adopted by the target robot for detecting the obstacles of different categories is allowed to be different;

and under the condition that the category of the target obstacle is a target category, controlling the target robot to execute a preset task in the pool based on a target control mode corresponding to the target category.

2. The method of claim 1, wherein obtaining first identification information collected by the target robot within the pool comprises:

responding to the target robot to start executing the preset task, and acquiring an image of the target obstacle in the pool through a target image acquisition device to obtain target image data, wherein the target image acquisition device is arranged on the target robot;

and identifying the target image data and determining the first identification information.

3. The method of claim 2, wherein responsive to the target robot beginning to perform the preset task, image capturing the target obstacle in the pool by a target image capturing device to obtain target image data, comprising:

responding to the target robot to start executing the preset task, and detecting the depth of the water body where the target robot is located;

and determining acquisition parameters of the target image acquisition equipment according to the water depth, and carrying out image acquisition on the target obstacle based on the acquisition parameters to obtain target image data.

4. The method of claim 2, wherein responsive to the target robot beginning to perform the preset task, image capturing the target obstacle in the pool by a target image capturing device to obtain target image data, comprising:

Detecting the water body cleanliness of the water tank, and determining the target water body cleanliness;

and determining acquisition parameters of the target image acquisition equipment according to the target water body cleanliness, and carrying out image acquisition on the target obstacle based on the acquisition parameters to obtain target image data.

5. The method of claim 2, wherein identifying the target image data, determining the first identification information, comprises:

extracting features of the target image data, and determining target feature information of the target obstacle;

preprocessing the target characteristic information, inputting the preprocessed target characteristic information into an identification model of the target robot, and determining the first identification information, wherein the preprocessing is used for adding a weight value corresponding to characteristic information used for determining the category of the target obstacle in the target characteristic information.

6. The method of claim 1, wherein determining the category of the target obstacle based on the first identification information comprises at least one of:

determining the category of the target obstacle as a first category according to the first identification information, wherein the target category comprises the first category, and the first category indicates that the target obstacle is an obstacle which needs the target robot to be far away;

Determining the category of the target obstacle as a second category according to the first identification information, wherein the target category comprises the second category, and the second category represents that the target obstacle is a fixed obstacle;

determining the category of the target obstacle as a third category according to the first identification information, wherein the target category comprises the third category, and the third category indicates that the target obstacle is an obstacle needing to send out a reminding message;

and determining the category of the target obstacle as a fourth category according to the first identification information, wherein the target category comprises the fourth category, and the fourth category indicates that the target obstacle is an obstacle which needs to be moved by the target robot.

7. The method of claim 6, wherein, in the case where the category of the target obstacle is a target category, controlling the target robot to perform a preset task in the pool based on a target control manner corresponding to the target category, comprises at least one of:

setting a first obstacle avoidance distance under the condition that the category of the target obstacle is the first category, wherein the first obstacle avoidance distance is larger than an initial obstacle avoidance distance preset by the target robot; controlling the target robot to execute the preset task in the pool according to the first obstacle avoidance distance under the condition that the target robot moves to a distance from the target obstacle to meet the first obstacle avoidance distance;

Setting a second obstacle avoidance distance under the condition that the category of the target obstacle is the second category, wherein the second obstacle avoidance distance is smaller than an initial obstacle avoidance distance preset by the target robot; controlling the target robot to execute the preset task in the pool according to the second obstacle avoidance distance under the condition that the target robot moves to a distance from the target obstacle to meet the second obstacle avoidance distance;

marking the position of the target obstacle under the condition that the category of the target obstacle is the third category; sending a target reminding message to a target terminal to indicate the position of the target obstacle in the pool, and executing the preset task in the pool according to the initial obstacle avoidance distance preset by the target robot;

and under the condition that the category of the target obstacle is the fourth category, controlling a mechanical control part of the target robot to move the target obstacle, and cleaning the position of the target obstacle before moving so as to control the target robot to execute the preset task in the pool.

8. The method according to claim 1, wherein the method further comprises:

acquiring an original map of the pool and position information of the target obstacle, wherein the target robot is set to execute the preset task in the pool according to the original map;

and marking and updating the original map according to the position information to obtain a target map so as to control the target robot to execute the preset task in the pool according to the target map.

9. The method of claim 8, wherein the method further comprises:

when the target robot reaches a preset distance from a target position, controlling the target robot to decelerate, and acquiring second identification information acquired by the target robot in the pool, wherein the second identification information represents characteristic information obtained by carrying out image identification on the target obstacle in the process of cleaning the pool according to the target map, and the target position represents a marked position of the target obstacle in the target map;

and determining the category of the target obstacle according to the second identification information, and controlling the target robot to execute the preset task in the pool according to the target obstacle avoidance distance corresponding to the target control mode under the condition that the category of the target obstacle is the target category.

10. A pool robot, a control method applied to the robot of any one of the above claims 1 to 9, comprising:

the image acquisition equipment is used for acquiring first identification information;

and the processor is used for determining the target control mode according to the first identification information and controlling the target robot to execute the preset task in the pool according to the target control mode.

11. A computer readable storage medium, characterized in that a computer program is stored in the computer readable storage medium, wherein the computer program, when being executed by a processor, implements the steps of the method according to any of the claims 1 to 9.