WO2023000679A1

WO2023000679A1 - Robot recharging control method and apparatus, and storage medium

Info

Publication number: WO2023000679A1
Application number: PCT/CN2022/079253
Authority: WO
Inventors: 鞠汶奇
Original assignee: 美智纵横科技有限责任公司
Priority date: 2021-07-19
Filing date: 2022-03-04
Publication date: 2023-01-26
Also published as: CN113534805A

Abstract

A robot recharging control method and apparatus, and a storage medium. The method comprises: controlling a plurality of sensors of a robot to collect signals around the robot (S201); acquiring, according to each sensor signal, a first relative position and a first confidence level of a charging base (S202); selecting a first relative position, the first confidence level of which exceeds a first threshold value, from among a plurality of first relative positions (S203); and planning a recharging route on the basis of the selected first relative position, and controlling, according to the recharging route, the robot to travel to be connected to the charging base (S204). Various sensors on a robot perform signal collection from different angles, such that if signals of one or more sensors are incomplete or the sensors fail due to a charging base being blocked or in a strong light environment, the position of the charging base, which has a high confidence level, can still be obtained by means of sensor signals from other angles, and thus a recharging route is planned according to the sensor signals from the other angles, thereby ensuring that the position of the charging base can be stably detected even in a scenario where one or more of the sensors fail.

Description

Robot recharging control method, device and storage medium

This application claims the priority of the Chinese patent application with the application number 202110815732.6 and the application name "robot recharging control method, device and storage medium" submitted to the China Patent Office on July 19, 2021, the entire contents of which are incorporated by reference in In this application.

technical field

The present invention relates to the technical field of robot control, in particular to a robot recharge control method, device and storage medium.

Background technique

With the development of science and technology, robots are used more and more in people's daily life, such as common sweeping robots, mopping robots, and more advanced robot housekeepers, etc. The application of these robots in the home makes people's lives It becomes more comfortable and convenient, but since it is the use of robots, it must involve the charging of robots. The existing charging of robots is divided into manual charging and automatic recharging of robots. Automatic recharging is more convenient and intelligent than manual charging.

In the existing automatic recharging method of the robot, by pasting a reflective code on the charging stand, the lidar on the robot scans and recognizes the reflective code to determine the location of the recharging station and achieve the purpose of recharging.

Since the principle of the reflective code is to provide identification features by means of highly reflective and scattered laser signals, with long-term use, the reflective code will lose its strong reflection and strong scattering capabilities after being stained with dust, resulting in the failure of lidar recognition, and when there is occlusion Or in a scene with strong light, because the lidar cannot receive the signal, the lidar recognition will also fail.

Contents of the invention

The purpose of the present invention is to propose a robot recharging control method, device and storage medium aiming at the shortcomings of the above-mentioned prior art, and the purpose is achieved through the following technical solutions.

The first aspect of the present invention proposes a robot recharging control method, the method comprising:

Controlling the existing multiple sensors on the robot to collect signals from the surrounding environment of the robot;

For each sensor signal, acquiring a first relative position and a first reliability of the charging stand according to the sensor signal;

From the plurality of first relative positions, selecting a first relative position whose first degree of confidence exceeds a first threshold;

A recharging route is planned based on the selected first relative position, and the robot is controlled to travel according to the recharging route so as to dock with the charging stand.

In some embodiments of the present application, the acquiring the first relative position and the first reliability of the charging stand according to the sensor signal includes:

The sensor signal is input into its corresponding trained first model, and the input sensor signal is processed by the first model to output a first relative position and a first reliability of the charging stand.

In some embodiments of the present application, the planning of the recharging route based on the selected first relative position includes:

When the number of selected first relative positions is 1, use the selected first relative positions to plan the recharging route;

When there are multiple selected first relative positions, an integrated relative position of the charging stand is obtained according to the multiple first relative positions, and a recharging route is planned using the integrated relative position.

In some embodiments of the present application, the obtaining the integrated relative position of the charging stand according to the plurality of first relative positions includes:

For each selected first relative position, determine its corresponding weight according to the first reliability corresponding to the first relative position;

The integrated relative position of the charging stand is obtained by using each first relative position and the corresponding weight.

In some embodiments of the present application, the method also includes:

When the first reliability corresponding to each sensor signal does not exceed the first threshold, continue to perform the step of controlling multiple sensors on the robot to collect signals of the robot's surrounding environment;

When the first reliability corresponding to each sensor signal has not exceeded the first threshold after the preset period of time, select the sensor signal whose first reliability exceeds the second threshold from the latest collected sensor signals;

Input the selected sensor signal into the trained second model, and the second model comprehensively processes the input sensor signal and outputs the second relative position and the second reliability of the charging stand;

According to the second reliability exceeding the third threshold, use the second relative position to plan a recharging route, and control the robot to travel according to the recharging route, so as to dock with the charging stand for charging;

According to the fact that the second reliability does not exceed the third threshold, an alarm prompt that the charging stand cannot be found is output.

In some embodiments of the present application, after selecting a first relative position whose first reliability exceeds a first threshold from the plurality of first relative positions, the method further includes: storing the selected first relative position and its corresponding first reliability;

The method also includes:

In the process of controlling the robot to move according to the recharging route, continue to control a plurality of sensors to collect signals of the surrounding environment of the robot, and for each sensor signal, obtain the first relative position and the first possible position of the charging base according to the sensor signal. Reliability;

When there is a first degree of confidence in the first degree of confidence of each sensor signal that is higher than the stored first degree of confidence, updating the first relative position based on the higher first degree of confidence Recharging route, and control the robot to travel according to the updated recharging route;

Utilizing the higher first degree of confidence and its corresponding first relative position, the stored first degree of confidence and its corresponding first relative position are updated.

In some embodiments of the present application, the method further includes a training process of the first model corresponding to the sensor:

Obtain the sensor signals of multiple distances and angles of the sensor relative to the charging stand, and label the relative position and reliability of the charging stand for each sensor signal;

Constructing a network model, and using the labeled sensor signals to train the constructed network model until the network model converges to obtain the first model.

In some embodiments of the present application, the method also includes the training process of the second model:

In scenes with occluders or strong light, collect sensor signals at multiple distances and angles from each sensor relative to the charging stand, and mark the relative position and reliability of the charging stand for each sensor signal collected at the same distance and at the same angle degree label;

A network model is constructed, and the constructed network model is trained by using the labeled sensor signals until the network model converges to obtain a second model.

The second aspect of the present invention provides a robot recharging control device, the device includes a memory, a processor and a computer program stored in the memory and operable on the processor, the processor executes the The computer program implements the steps of the method described in the first aspect above.

A third aspect of the present invention provides a robot, comprising:

The robot recharging control device as described in the second aspect above;

A variety of sensors are used to collect signals of the surrounding environment of the robot.

A fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in the above-mentioned first aspect are implemented.

Based on the robot recharging control method described in the first aspect above, the technical solution of the present invention has the following beneficial effects or benefits:

When the robot needs to be recharged, the sensor signals collected by the existing sensors on the robot are obtained, and the position and reliability of the charging stand are obtained according to each sensor signal, and the position of the charging stand that meets the reliability standard is selected for recharging. Route planning, since the various sensors on the robot collect signals from different angles, if one or more sensors have incomplete or invalid signal due to the charging stand being blocked or in a strong light scene, there will be other The position of the charging stand is obtained with high reliability by the angle sensor signal, and then the recharging route planning is carried out based on the position of the charging stand obtained by other angle sensor signals, so as to ensure that the charging stand can still be stably detected in the scene where one or more sensors fail. position, and stably complete the recharging task.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the application. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

Fig. 1 is the structural representation of a kind of robot shown in the present invention;

Fig. 2 is a schematic flowchart of an embodiment of a robot recharging control method according to an exemplary embodiment of the present invention;

Fig. 3 is a schematic diagram of a recharging route according to an exemplary embodiment of the present invention;

Fig. 4 is a schematic diagram showing a robot docking with a charging stand according to an exemplary embodiment of the present invention;

Fig. 5 is a schematic flowchart of another robot recharging control method according to an exemplary embodiment of the present invention;

Fig. 6 is a schematic structural diagram of a robot recharging control device according to an exemplary embodiment of the present invention;

Fig. 7 is a schematic structural diagram of a storage medium according to an exemplary embodiment of the present invention.

The realization of the purpose of the present invention, functional characteristics and advantages will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts all belong to the protection scope of the present invention.

It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relationship between the components in a certain posture (as shown in the accompanying drawings). Relative positional relationship, movement conditions, etc., if the specific posture changes, the directional indication will also change accordingly.

In addition, in the present invention, descriptions such as "first", "second" and so on are used for description purposes only, and should not be understood as indicating or implying their relative importance or implicitly indicating the quantity of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of these features. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

In the present invention, unless otherwise specified and limited, the terms "connection" and "fixation" should be understood in a broad sense, for example, "fixation" can be a fixed connection, a detachable connection, or an integral body; It may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediary, and it may be an internal communication between two elements or an interaction relationship between two elements, unless otherwise clearly defined. Those of ordinary skill in the art can understand the specific meanings of the above terms in the present invention according to specific situations.

In addition, the technical solutions of the various embodiments of the present invention can be combined with each other, but it must be based on the realization of those skilled in the art. When the combination of technical solutions is contradictory or cannot be realized, it should be considered as a combination of technical solutions. Does not exist, nor is it within the scope of protection required by the present invention.

At present, the automatic recharging of the robot mainly adopts the following two implementations:

1. Infrared sensor automatic recharging, the robot realizes the automatic recharging of the robot through the docking of the infrared receiver set by itself and the infrared emitter set on the charging stand. , stability, and installation consistency are difficult to guarantee, and infrared signals are prone to interference, reflection and other abnormalities. Infrared sensors need to be received and sent one by one, which is costly and has the risk of device damage.

2. The laser radar is automatically recharged, and the robot uses its own laser radar to automatically dock the charging stand.

However, none of the above methods takes into account that in some scenarios, such as when the charging stand is covered or in a strong light environment, some sensor signals may be incomplete or invalid, resulting in the inability to complete the automatic recharging of the charging stand.

In order to solve the above-mentioned technical problems, the present invention proposes a robot, referring to the schematic structural diagram of the robot shown in Figure 1, including a robot body 10, a robot recharging control device 20 and various sensors arranged on the robot body 10 (not specifically shown in Figure 1 out).

Wherein, the robot body 10 is used for moving, and is electrically connected with the robot recharging control device 20 . A variety of sensors on the robot are used to collect the surrounding environment signals during the movement of the robot to build an environmental map and plan travel routes, such as lidar sensors, ultrasonic radar sensors, camera sensors, etc. Direction, during the movement of the robot, scan the environment around the robot in real time to realize obstacle avoidance and path planning.

Optionally, the robot recharging control device 20 may be independent from the robot body 10, or may be integrated in the robot body 10, which is not specifically limited in this application.

It should be noted that the robot body 10 is provided with structures such as a motion module and a control module for realizing the construction of the robot's environment map and path planning.

Based on the functional descriptions of the above structures, the control principle of the robot recharging control device 20 is as follows:

When the robot needs to be docked with the charging stand, control the existing multiple sensors on the robot to collect the signals of the surrounding environment of the robot, and for each sensor signal, obtain the first relative position and first reliability of the charging stand according to the sensor signal , and then select the first relative position whose first reliability exceeds the first threshold from the plurality of first relative positions, and then plan the recharging route based on the selected first relative position, and control the robot to travel according to the recharging route , to dock with the charging stand.

The technical effects that can be achieved based on the above description are:

By obtaining the sensor signals collected by various sensors on the robot, and according to each sensor signal, the position and reliability of the charging stand are obtained, and the position of the charging stand that meets the standard of reliability is selected for recharging route planning. A variety of sensors collect signals from different angles, so when one or more sensors have incomplete or invalid sensor signals due to the occlusion or strong light scene of the charging stand, there will be sensor signals from other angles that are highly reliable. The position of the charging stand is reliable, and then the recharging route planning is carried out based on the position of the charging stand obtained from the signals of other angle sensors, so as to ensure that the position of the charging stand can still be stably detected in the scene where one or more sensors fail, and the recharging task can be completed stably .

In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

Embodiment one:

Fig. 2 is a schematic flow chart of an embodiment of a robot recharging control method according to an exemplary embodiment of the present invention. The robot recharging control method is applicable to the robot shown in Fig. 1 above, and the robot is a sweeping robot as the following Example for illustration, as shown in Figure 2, the robot recharging control method includes the following steps:

Step 201: controlling multiple sensors on the robot to collect signals of the surrounding environment of the robot.

In some embodiments, after the robot is started, it first constructs an environmental map based on the sensor signals of the surrounding environment collected by various sensors, and performs route planning through the constructed environmental map, and then proceeds according to the planned route, and during the travel process, The environment map is still constructed in real time based on the sensor signals collected by various sensors.

Optionally, when the robot needs to be recharged, the location of the charging stand located after the last recharging can be called, and the approximate orientation of the charging stand can be marked on the environment map according to the position of the charging stand, and then the robot can be controlled to move in the direction of the marked charging stand , while controlling multiple sensors on the robot to randomly collect signals from the surrounding environment of the robot from different angles.

Step 202: For each sensor signal, acquire a first relative position and a first reliability of the charging stand according to the sensor signal.

In an optional specific implementation, a model for processing sensor signals can be pre-trained for each sensor, and the output of the model is the relative position and reliability of the charging stand. By using the model to process sensor signals, the processing results can be improved Accuracy, thereby improving the efficiency of automatic recharging of the robot. Based on this, each sensor signal can be input into the corresponding pre-trained first model, so that the input sensor signal can be processed by the first model, and the first relative position and first reliability of the charging stand can be output .

Wherein, the first degree of reliability output by the first model is used to represent the degree of reliability of the outputted first relative position of the charging stand, and the higher the degree of first degree of reliability, the higher the degree of reliability.

It should be noted that before step 202 is performed, training is required to obtain the first model corresponding to each sensor, and the training process may include: collecting sensor signals at multiple distances and angles from the sensor relative to the charging stand, and for each sensor signal Label the relative position and reliability of the charging stand, which is used to calculate the loss value during the model training process, then build the network model, and use the labeled sensor signals to train the constructed network model until the network model converges to obtain the first model.

Taking the lidar sensor as an example, after fixing the charging stand at a certain position, control the robot to reach a position 1 meter away from the center point of the docking slot of the charging stand and 45 degrees away from the vertical line in the docking slot to obtain multi-frame lidar sensor signals, and then Control the robot to reach a position 1 meter away from the center point of the docking slot of the charging stand, and 46 degrees away from the vertical line in the docking slot, and obtain multi-frame lidar sensor signals, and so on, to obtain sensor signals in various situations, and then repeat multiple times Change the distance between the robot and the center point of the docking slot of the charging stand, and at this distance, constantly change the angle to obtain the sensor signal. It can be seen that by continuously changing the position of the robot, many sensor signals can be collected as training samples.

Optionally, in order to improve the accuracy of the model, it is possible to obtain sensor signals from multiple distances and multiple angles in different scenarios. For example, abnormal scenes with occluders, normal scenes without occluders, scenes with different lighting, etc.

During specific implementation, the relative position of the charging stand may include information such as relative distance, angle, center point coordinates of the docking slot on the charging stand, and such information can guide the robot how to enter the docking slot to achieve docking.

Step 203: From the plurality of first relative positions, select a first relative position whose first reliability exceeds a first threshold.

Wherein, the first threshold is used to indicate the condition of reaching the standard of credibility, so the first threshold will be relatively higher. Assuming that the value range of the credibility is 0 to 1, then the first threshold may be set above 0.8.

It should be noted that in practical applications, when screening the first relative positions whose reliability meets the standard, one or more first relative positions may be screened out, and of course zero first relative positions may be screened out, that is, no There is a first relative position at which the confidence level is met.

Wherein, if one or more first relative positions are screened out, the following step 204 is performed, and if the first relative position with the reliability up to the standard is not screened out, the sensor signal can be re-acquired for screening. If the first relative position that reaches the standard of reliability has not been found, the second model can be used to jointly judge multiple sensor signals. For the specific implementation process, please refer to the description of the following embodiments, and the present invention will not be described in detail here.

It should be noted that, after selecting the first relative position whose first reliability exceeds the first threshold from the plurality of first relative positions, the selected first relative position and its corresponding first reliability may also be stored. , to be replaced with higher confidence and relative position for subsequent robot travel.

Step 204: Planning a recharging route based on the selected first relative position, and controlling the robot to travel according to the recharging route so as to dock with the charging stand.

Based on the description of step 203 above, optionally, if the number of selected first relative positions is 1, the recharging route can be planned directly using the selected first relative positions; if the number of selected first relative positions If there are more than one, then the comprehensive relative position of the charging stand can be obtained according to the selected multiple first relative positions, and then the comprehensive relative position can be used to plan the recharging route.

In an optional specific implementation, for the process of obtaining the comprehensive relative position, for each selected first relative position, its corresponding weight can be determined according to the first reliability corresponding to the first relative position, and then use Each first relative position and corresponding weight obtains an integrated relative position of the charging stand.

Wherein, the higher the first reliability corresponding to the first relative position, the greater the determined weight.

Optionally, the quotient of the first credibility level corresponding to one of the first relative positions and the sum of all first credibility levels up to the standard can be used as the weight of this first relative position, so as to achieve the higher credibility , the purpose of greater weight.

For example, as shown in Figure 3, it is assumed that the relative position used for planning the route includes the distance L between the robot and the charging stand, and the angle θ relative to the vertical line in the docking slot. Using the distance L and angle θ to calculate and obtain L1 and L2, also That is to say, the planned recharging route is that after traveling southward to L1, the robot reaches the vertical line of the docking slot, and then the robot is facing the charging stand, and then travels westward to L2 to dock with the docking slot of the charging stand. The docking effect is shown in the figure 4.

It should be noted that when the robot is traveling along the recharging route, it can continue to control multiple sensors in real time to collect signals from the surrounding environment of the robot, and for each sensor signal, obtain the first relative position and the second relative position of the charging stand according to the sensor signal. A credibility, and compare the newly obtained first credibility with the stored first credibility, when there is a first credibility higher than the stored first credibility, you can use The newly obtained first relative position of the first degree of reliability is used to update the recharging route, so that the robot can dock with the charging stand more accurately. The stored first reliability and its corresponding first relative position.

That is to say, when the robot is traveling along the recharging route, it will continue to calculate the reliability of the newly collected sensor signal and the relative position of the charging stand in real time. If there is a relative position with higher reliability, it will use this reliability Higher relative positions update recharge routes.

Further, when updating the recharging route with the newly obtained first relative position of the first reliability, the newly obtained first relative position can also be used in combination with the route traveled by the robot on the recharging route and the stored to update the recharging route.

So far, the recharging process shown in Figure 2 above is completed. When the robot needs to be recharged, the sensor signals collected by the various sensors already on the robot are obtained, and the position and reliability of the charging stand are obtained according to each sensor signal. Select the position of the charging stand with the reliability standard to plan the recharging route. Since the various sensors on the robot collect signals from different angles, when one or more sensors are blocked by the charging stand or in the scene of strong light, the sensor will be damaged. When the signal is incomplete or invalid, there will be sensor signals from other angles to obtain the position of the charging stand with high reliability, and then the position of the charging stand obtained from the signals of other angle sensors will be used to plan the recharging route to ensure that one or more In the scene where the sensor fails, the position of the charging stand can still be detected stably, and the recharging task can be completed stably.

Embodiment two:

Fig. 5 is a schematic flowchart of another robot recharging control method according to an exemplary embodiment of the present invention. Based on the embodiment shown in Fig. 2 above, the robot recharging control method includes the following steps:

Step 501: Controlling multiple sensors on the robot to collect signals of the surrounding environment of the robot.

Step 502: For each sensor signal, acquire a first relative position and a first reliability of the charging stand according to the sensor signal.

Step 503: Judging whether there is a first confidence level exceeding the first threshold, if yes, execute step 504, if not, execute step 505.

Step 504: Planning a recharging route based on the first relative position whose first reliability exceeds the first threshold, and controlling the robot to travel according to the recharging route so as to dock with the charging stand.

For the specific implementation of the above step 501 to step 504, reference may be made to the description of the above embodiment, and the present invention will not repeat them here.

Step 505: start timing, and compare the counted time with the preset duration, if the counted time is less than the preset duration, continue to execute step 501, and if the counted time is greater than the preset duration, execute step 506.

Step 506: From the latest collected sensor signals, select the sensor signals whose first reliability exceeds the second threshold.

Wherein, the second threshold is lower than the first threshold, and the sensor signal whose first reliability exceeds the second threshold is a signal whose reliability can be improved through comprehensive processing.

It should be noted that for the sensor signal whose first reliability exceeds the second threshold but is lower than the first threshold, it may be that the charging stand is blocked or the signal obtained by the charging stand in a strong light scene results in an incomplete signal, which may Reliability is not up to standard.

Step 507: Input the selected sensor signal into the trained second model, and the second model comprehensively processes the input sensor signal and outputs the second relative position and the second reliability of the charging stand.

Before performing step 507, it is necessary to train to obtain a second model for comprehensive processing of various sensor signals. The training process may include: in a scene with an occluder or a strong light, collecting data of multiple distances and multiple angles of each sensor relative to the charging stand Sensor signals, and label the relative position and reliability of the charging stand for each sensor signal collected under the same distance and the same angle, and then build a network model, and use the labeled sensor signals to construct the network model. Train until the network model converges to obtain the second model.

It should be noted that, after the second model comprehensively processes each sensor signal, the outputted second relative position and second reliability are the positions and reliability obtained by integrating multiple sensor signals.

Step 508: If the second reliability exceeds the third threshold, use the second relative position to plan a recharging route, and control the robot to travel according to the recharging route, so as to dock with the charging stand for charging.

Wherein, the type of information contained in the second relative position is the same as that contained in the first relative position, so the principle of planning the recharging route by using the second relative position is consistent with the principle of planning the recharging route by using the first relative position.

It should be noted that the third threshold is greater than the second threshold, but the third threshold may be the same as or different from the first threshold, which is not specifically limited in the present invention.

Step 509: If the second reliability does not exceed the third threshold, output an alarm prompt that the charging stand cannot be found.

So far, the recharging process shown in Figure 5 above is completed. In the event that the reliability of various sensor signals continues to fall short of the standard and the recharging route cannot be planned, and after the situation lasts for a certain period of time, the data collected from the latest Among the sensor signals, the sensor signal whose first reliability exceeds the second threshold is selected as the input of the second model, and the second model makes a comprehensive judgment and outputs a comprehensive second relative position and second reliability of the charging stand , and use the second relative position to plan the recharging route, so as to ensure that the position of the charging stand can still be stably detected in the scene where one or more sensors fail, and the recharging task can be completed stably.

Embodiments of the present invention also provide a robot recharging control device corresponding to the robot recharging control method provided in the foregoing embodiments, so as to implement the above robot recharging control method.

Fig. 6 is a hardware structure diagram of a robot recharging control device according to an exemplary embodiment of the present invention. The robot recharging control device includes: a communication interface 701, a processor 702, a memory 703 and a bus 704; The interface 701 , the processor 702 and the memory 703 communicate with each other through the bus 704 . The processor 702 can execute the robot recharging control method described above by reading and executing the machine-executable instructions corresponding to the control logic of the robot recharging control method in the memory 703. For details of the method, refer to the above-mentioned embodiments. I won't repeat it here.

The memory 703 mentioned in the present invention can be any electronic, magnetic, optical or other physical storage device, which can contain stored information, such as executable instructions, data and so on. Specifically, memory 703 can be RAM (Random Access Memory, random access memory), flash memory, storage drive (such as hard drive), any type of storage disk (such as optical disc, DVD, etc.), or similar storage media, or their The combination. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 701 (which may be wired or wireless), and the Internet, wide area network, local network, metropolitan area network, etc. can be used.

The bus 704 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into address bus, data bus, control bus and so on. Wherein, the memory 703 is used to store a program, and the processor 702 executes the program after receiving an execution instruction.

The processor 702 may be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware in the processor 702 or instructions in the form of software. The above-mentioned processor 702 can be a general-purpose processor, including a central processing unit (Central Processing Unit, referred to as CPU), a network processor (Network Processor, referred to as NP) etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. Various methods, steps, and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor.

The robot recharging control device provided in the embodiment of the present application is based on the same inventive concept as the robot recharging control method provided in the embodiment of the present application, and has the same beneficial effect as the method adopted, operated or implemented.

The embodiment of the present application also provides a computer-readable storage medium corresponding to the robot recharging control method provided in the foregoing embodiment, please refer to FIG. A computer program (that is, a program product) is stored, and when the computer program is run by the processor, it will execute the robot recharging control method provided in any of the foregoing implementation manners.

It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random Access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other optical and magnetic storage media will not be repeated here.

The computer-readable storage medium provided by the above-mentioned embodiments of the present application is based on the same inventive concept as the robot recharging control method provided by the embodiments of the present application, and has the same beneficial effects as the method adopted, run or implemented by its stored application program .

Other embodiments of the invention will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. The present invention is intended to cover any modification, use or adaptation of the present invention. These modifications, uses or adaptations follow the general principles of the present invention and include common knowledge or conventional technical means in the technical field not disclosed in the present invention . The specification and examples are to be considered exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the present invention. within the scope of protection.

Claims

A method for controlling recharging of a robot, characterized in that the method comprises:

controlling a plurality of sensors on the robot to collect signals of the surrounding environment of the robot;

For each sensor signal, acquiring a first relative position and a first reliability of the charging stand according to the sensor signal;

From the plurality of first relative positions, selecting a first relative position with a first confidence level exceeding a first threshold;

A recharging route is planned based on the selected first relative position, and the robot is controlled to travel according to the recharging route so as to dock with the charging stand.
The method according to claim 1, wherein said obtaining the first relative position and the first reliability of the charging stand according to the sensor signal comprises:

The sensor signal is input into its corresponding trained first model, and the input sensor signal is processed by the first model to output a first relative position and a first reliability of the charging stand.
The method according to claim 1, wherein planning the recharging route based on the selected first relative position comprises:

When the number of selected first relative positions is 1, use the selected first relative positions to plan the recharging route;

When there are multiple selected first relative positions, an integrated relative position of the charging stand is obtained according to the multiple first relative positions, and a recharging route is planned using the integrated relative position.
The method according to claim 3, wherein said obtaining the comprehensive relative position of the charging stand according to the plurality of first relative positions comprises:

For each selected first relative position, determine its corresponding weight according to the first reliability corresponding to the first relative position;

The integrated relative position of the charging stand is obtained by using each first relative position and the corresponding weight.
The method of claim 1, further comprising:

When the first reliability corresponding to each sensor signal does not exceed the first threshold, continue to perform the step of controlling multiple sensors on the robot to collect signals of the robot's surrounding environment;

When the first reliability corresponding to each sensor signal has not exceeded the first threshold after the preset period of time, select the sensor signal whose first reliability exceeds the second threshold from the latest collected sensor signals;

Input the selected sensor signal into the trained second model, and the second model comprehensively processes the input sensor signal and outputs the second relative position and the second reliability of the charging stand;

According to the second reliability exceeding the third threshold, use the second relative position to plan a recharging route, and control the robot to travel according to the recharging route, so as to dock with the charging stand for charging;

According to the fact that the second reliability does not exceed the third threshold, an alarm prompt that the charging stand cannot be found is output.
The method according to claim 1, wherein after selecting a first relative position whose first reliability exceeds a first threshold from the plurality of first relative positions, the method further comprises: storing the selected The first relative position of and its corresponding first reliability;

The method also includes:

In the process of controlling the robot to move according to the recharging route, continue to control a plurality of sensors to collect signals of the surrounding environment of the robot, and for each sensor signal, obtain the first relative position and the first possible position of the charging base according to the sensor signal. Reliability;

When there is a higher first reliability in the first reliability of each sensor signal than the stored first reliability, the first relative position corresponding to the higher first reliability is updated based on the first relative position. Describe the recharging route, and control the robot to move according to the updated recharging route;

Utilizing the higher first degree of confidence and its corresponding first relative position, the stored first degree of confidence and its corresponding first relative position are updated.
The method according to claim 2, wherein the method further comprises a training process of the first model corresponding to the sensor:

Obtain the sensor signals of multiple distances and angles of the sensor relative to the charging stand, and label the relative position and reliability of the charging stand for each sensor signal;

Constructing a network model, and using the labeled sensor signals to train the constructed network model until the network model converges to obtain the first model.
The method according to claim 5, wherein the method further comprises a training process of the second model:

In scenes with occluders or strong light, collect sensor signals at multiple distances and angles from each sensor on the robot relative to the charging stand, and mark the relative position and location of the charging stand for each sensor signal collected at the same distance and at the same angle. credibility label;

A network model is constructed, and the constructed network model is trained by using the labeled sensor signals until the network model converges to obtain a second model.
A robot recharging control device, the device includes a memory, a processor and a computer program stored on the memory and operable on the processor, characterized in that, when the processor executes the computer program Implementing the steps of the method according to any one of claims 1-8.
A robot, characterized in that it comprises:

The robot recharging control device according to the above claim 9;

A variety of sensors are used to collect signals of the surrounding environment of the robot.
A computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, the steps of the method according to any one of claims 1-8 are realized.