Robot control method, robot and storage medium
By detecting the gate video information and controlling the interaction between the robot arm and the gate, the problem of low flexibility of the robot is solved, and the autonomous identification and adaptation of gates of different models and locations is achieved, thereby improving traffic efficiency and safety.
Patent Information
- Application Number
- CN202411116782.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-12-06
AI Technical Summary
The robot lacks the ability to automatically identify and adapt when facing gates of different models or locations, resulting in low flexibility and inability to perform pass actions autonomously and accurately.
By detecting the video information of the gate, the position and the type of traffic control of the target gate are determined, the end effector of the control robot arm interacts with the gate, and responds to the pass command to pass through the gate.
It improves the flexibility and traffic efficiency of the robot, can independently complete complex gate operations, reduces manual intervention, and enhances the flexibility and safety of task execution.
Smart Images

Figure CN119077727A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of robotics technology, and in particular to a robot control method, a robot, and a storage medium. Background Art
[0002] With the continuous development of automation and robotics technology, robots are increasingly used in many fields, including but not limited to manufacturing, logistics, service industry, and security monitoring. In these applications, robots need to pass through various types of gates, such as revolving doors, sliding doors, security doors, etc., to achieve automatic access and monitoring of specific areas.
[0003] However, when facing gates of different models or locations, the robot lacks the ability to autonomously identify and adapt, and often cannot autonomously and accurately perform the passing action. Therefore, the current robot has the defect of low flexibility.
[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention
[0005] The main purpose of this application is to provide a robot control method, a robot and a storage medium, aiming to solve the technical problem of low flexibility of the robot.
[0006] To achieve the above objectives, the present application proposes a robot control method, the method comprising:
[0007] When detecting that the gate exists on the travel path, obtaining video information of the gate;
[0008] Determine the location of the target gate according to the video information;
[0009] When the robot moves to the passageway of the target gate, controlling the end effector of the robot arm to interact with the target gate;
[0010] In response to the passage instruction of the target gate, the robot is controlled to pass through the passage of the target gate.
[0011] In one embodiment, determining the location of the target gate according to the video information includes:
[0012] If there is a gate on the travel path, the gate in the video information is used as the target gate;
[0013] If there are multiple gates on the travel path, determine the current passage information and usage status of the multiple gates according to the video information;
[0014] According to the current traffic information and the usage status, among the multiple gates, a gate with the least number of passers-by is used as the target gate.
[0015] In one embodiment, when the robot moves to the passageway of the target gate, controlling the end effector of the robot arm to interact with the target gate includes:
[0016] When the robot moves to the passageway of the target gate, determining the access control type and access control area of the target gate according to the video information;
[0017] Determining a moving path of the robot arm according to the access control area, and determining an operation sequence of the robot arm according to the access control type;
[0018] The robot arm is controlled to move to the access control area according to the movement path, and a target end effector is selected based on the access control type to interact with the access control area.
[0019] In one embodiment, determining the access control type and access control area of the target gate according to the video information includes:
[0020] The video information is input into a pre-trained machine learning model to obtain the access control type and the access control area of the target gate.
[0021] In one embodiment, when detecting that the gate exists on the travel path, obtaining video information of the gate includes:
[0022] When the gate is detected on the travel path, the visual system of the robot is activated;
[0023] When the gate is in the detection field of view of the visual system, the gate is scanned and processed based on the visual system to obtain the video information.
[0024] In one embodiment, after responding to the passage instruction of the target gate and controlling the robot to pass through the passage of the target gate, the method further includes:
[0025] Generating passage operation data of the robot;
[0026] The passage operation data is updated to the machine learning model to optimize the processing action of the robot when a gate is detected.
[0027] In one embodiment, when the robot moves to the passageway of the target gate, after controlling the end effector of the robot arm to interact with the target gate, the method further includes:
[0028] Within a preset time period, when the target gate is in a closed state and / or the robot does not receive the passage instruction, negative sample training is performed on the machine learning model based on the passage operation data of the interaction between the end effector and the target gate;
[0029] Execute the step of obtaining the video information of the gate and subsequent steps.
[0030] In one embodiment, when the robot moves to the passageway of the target gate, after controlling the end effector of the robot arm to interact with the target gate, the method further includes:
[0031] Determine the opening and closing state of the target gate according to the communication sensor of the robot;
[0032] When it is detected that the target gate is in an open state, controlling the robot to pass through the target gate;
[0033] The operation result data of the robotic arm is fed back to the control system of the robot so that the control system optimizes the control logic and decision-making algorithm of the robotic arm.
[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a robot, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the robot control method as described above.
[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the robot control method described above are implemented.
[0036] One or more technical solutions proposed in this application have at least the following technical effects:
[0037] Since an end effector capable of interacting with gates is added to the robot's mechanical arm, when a gate is detected on the road, the real-time video data stream is used to accurately identify the gate's switch status, usage status, and operation interface, and the target gate that needs to be passed is selected from it. Then, according to the type of the target gate, the end effector is controlled to interact with it and pass through the gate. Based on this, the optimal control strategy of the robot is obtained by analyzing the image data of the gate, which improves the flexibility of the robot. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0040] Figure 1 A schematic flow chart of a first embodiment of a control method for a robot of the present application;
[0041] Figure 2 A schematic flow chart of a second embodiment of the robot control method provided in the present application;
[0042] Figure 3 A schematic flow chart of a third embodiment of the robot control method provided in the present application;
[0043] Figure 4 Schematic diagram of the device structure of the hardware operating environment involved in the robot control method in the embodiment of the present application.
[0044] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0045] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0046] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0047] The main solution of the embodiment of the present application is: when a gate is detected on the robot's path of travel, the best target gate is selected for entry based on the video information of the gate, and when reaching the channel entrance, a control strategy is selected based on the gate information in the video information, and the end effector is controlled to interact with the target gate. Based on this, the robot's response method after encountering a gate when performing a task is improved, thereby improving the robot's flexibility.
[0048] In this embodiment, for ease of description, the following description is made with a robot as the execution subject.
[0049] In the prior art, when robots are performing tasks, if there are gates of different models on their route, they lack autonomous recognition and adaptability and cannot accurately perform the passing action autonomously, resulting in low flexibility and low efficiency in task execution.
[0050] The present application provides a solution, which is that when the robot detects the existence of a gate on its path, it obtains video information of the gate, and then selects the gate that needs to be passed through and the method of interacting with it through the video information. Then, after reaching the passage entrance of the gate, the end interactor of the robotic arm is controlled to interact with it, and then responds to the passage instruction of the gate and passes through the gate channel to carry out subsequent tasks, thereby improving the flexibility of the robot when performing tasks or traveling.
[0051] Based on this, an embodiment of the present application provides a method for controlling a robot, wherein the robot includes a robotic arm for operating a gate, and the robotic arm includes an end effector for exchanging with the gate. The end effector is a device or tool installed at the end of the robotic arm for interacting with the outside world. In this embodiment, the end effector is a highly complex and multifunctional device that can perform a variety of operations, such as pressing buttons, sliding touch screens, card scanning, etc., that is, the end effector includes at least a piston or lever arm for pressing the pass button of the gate, a smooth touch head for sliding the touch screen, and a storage bin for storing pass cards.
[0052] Reference Figure 1 , Figure 1 This is a flow chart of the first embodiment of the robot control method of the present application.
[0053] In this embodiment, the robot control method includes steps S10 to S40:
[0054] Step S10, when it is detected that the gate exists on the travel path, the video information of the gate is obtained.
[0055] It should be noted that a gate usually refers to a device used to control the flow of people or vehicles. It can limit or allow passage through lifting rails, revolving doors or other forms. In different occasions, the structure and function of the gate may be different, but its main purpose is to ensure orderly and safe traffic management. The gate is mainly set up to achieve the control and management of the flow of people or vehicles, for safety control, flow management, order maintenance, data collection and optimization of space utilization. Video information refers to a series of continuous images of the area where the gate is located collected by the robot, usually including the gate's passage type, passage area, detection method and detection area, etc.
[0056] In this embodiment, when the robot performs a task such as a distribution task, a leading task, an inspection task, a cargo transportation task in a large warehouse, or other robot navigation and control tasks, the robot needs to move from the starting point to the destination, and there are usually gates blocking the way on the route. Therefore, the robot can detect whether there are gates on the path of travel by means of magnetic field induction, radio frequency identification (RFID), infrared sensor recognition, or video recognition. Among them, in order to reduce the energy consumption of the robot, the detection range can be set according to actual needs, such as detecting whether there are gates within 30 meters around the robot. It is understandable that before the robot is put into use, the training of the deep learning model is completed, that is, the robot performing navigation and control tasks can identify gates of different brands and models. Based on the deep learning model, the accuracy and effectiveness of gate recognition are improved.
[0057] The video information of the gate can be obtained by the robot's visual system. When a gate is detected on the path, the robot's visual system needs to be activated. Then, when the robot gradually approaches the gate, that is, when the gate is in the detection field of view of the visual system, the gate is scanned and processed based on the visual system to obtain video information. By obtaining the video information of the gate, the robot can determine the type of gate and the best operation strategy for passing the gate based on the image information, thereby improving the flexibility of the robot. It is understandable that the video information can include information about one gate or multiple gates.
[0058] For example, when the robot performs a navigation task, it detects the gates on its path through radio frequency recognition and infrared sensor recognition. During the movement, it detects a gate 30 meters ahead. At this time, the robot activates the visual system and captures video information of the gate when it is 15 meters close to the gate.
[0059] It should be noted that the above parameters are only used for explanation and are not intended to limit the present application.
[0060] Step S20, determining the location of the target gate according to the video information.
[0061] It should be noted that the target gate is a gate that the robot needs to pass through. Among them, the number of gates is usually set according to the flow of the current place. In high-flow places, the number of gates is at least 2, and in low-flow places, the number of gates is 1. Furthermore, in some places, the passage areas of different gates correspond to different elevator floors, and the waiting time for passage corresponding to different gates is also different. Therefore, after obtaining the video information of the gate, it is necessary to determine the target gate for passage based on the real-time video information to avoid going to the wrong gate or queuing at the gate with higher flow, which will extend the task time and reduce the efficiency of task execution. Therefore, after obtaining the video information of the gate, it is necessary to determine the location of the target gate that needs to be passed based on the video information, so as to control the robot to move to the channel corresponding to the target gate in advance and improve the robot's passage efficiency.
[0062] In this embodiment, the real-time decision engine in the robot's control system can automatically select a target gate that meets the requirements based on environmental variables in the video information, such as traffic flow and gate status, to avoid selecting gates with a large number of users during peak hours. Specifically, when there is a gate on the path, the gate in the video information is used as the target gate. If there are multiple gates on the path, the current traffic information and usage status of the multiple gates can be determined based on the video information. The current traffic information refers to the traffic flow, and the usage status refers to whether the gate is passable. Then, based on the current traffic information and usage status, the passable gate with the least number of people passing through is used as the target gate among the multiple gates.
[0063] In addition, when there are multiple gates on the path, the gate can also be selected according to the task performed by the robot and the set path. For example, if the gate set to pass in the set path is gate No. 1, the robot determines the location of gate No. 1 through video information and uses it as the target gate for passing. Or the robot has performed a task with a high degree of repetition at the current location, such as the current task is to transport item A to No. 1 on the 15th floor, and the previous task was to transport item B to No. 3 on the 15th floor. At this time, the historical passage data shows that the target gate for passing was gate No. 2 when the previous task was performed. At this time, gate No. 2 in the video information can be used as the target gate. By determining the location of the target gate, the robot can avoid low task execution efficiency due to selecting a gate that cannot be passed, a gate with a long waiting time, or a gate whose target area is irrelevant to the task location. Based on this, the robot's passage flexibility is improved when there are multiple gates on the current path.
[0064] Step S30, when the robot moves to the passageway of the target gate, controlling the end effector of the robot arm to interact with the target gate.
[0065] In this embodiment, after the robot selects the target gate and moves to the channel of the target gate, based on the information of the target gate in the video information, the robot's control system can dynamically plan the motion path of the robot arm and the corresponding operation sequence, so as to move the robot arm so that the end effector performs the relevant interactive actions in the verification interaction area of the target gate. Among them, the motion path is the position where the robot controls the movement of the robot arm through the servo motor, and the operation sequence is the selected operation mode, such as selecting touch screen operation or using a card scanner, and the end effector is the corresponding execution state.
[0066] For example, the target gate's access verification type is card scanning, and the end effector contains an electronic card for authorization information verification. The robot controls the mechanical arm through a high-precision servo motor to place the end effector in the card scanning position to perform the card scanning action, thereby completing the access verification of the target gate. In addition, if the target gate only requires pressing a pass button to pass, the robot can control the mechanical arm to press the button based on the lever device of the end effector, or when the touch screen needs to be slid, the smooth touch head of the end effector can be used to slide the touch screen.
[0067] The precise control information of the robot is generated through video information, so that when the robot passes through the gate, it can independently complete complex gate operations, and at the same time can adapt to various operating environments and reduce manual intervention. In the control process, the movement of the robot arm can be precisely controlled, and the operation accuracy and equipment friendliness are ensured based on the intelligent decision-making system, which improves the safety of the robot when passing through the gate.
[0068] Step S40, responding to the passage instruction of the target gate, controlling the robot to pass through the channel of the target gate.
[0069] As an optional implementation, the passage instruction of the target gate can be a voice prompt instruction for opening the gate of the target gate, a passable instruction in the status display area of the gate, or an RFID (Radio Frequency Identification) door opening instruction broadcast by the gate to the robot. Among them, after the end effector of the robot-controlled mechanical arm interacts with the target gate, it can capture the state of the target gate in real time through the visual system, and detect the passage parameters of the target gate in real time through the sensor. The robot then confirms the gate response through the sensor, and after receiving the gate opening signal, it passes through the channel of the target gate. Among them, the robot can further confirm the opening state of the gate through the captured video information.
[0070] In another optional embodiment, in addition to responding to the target gate's instruction and then passing through the target gate, the robot's communication sensor can also be used to determine the opening and closing state of the target gate, for example, by using an infrared sensor to detect whether there is an obstacle (i.e., a gate) in front, and when the target gate is detected to be in an open state, the robot is controlled to pass through the target gate. After passing through the target gate, the operation result data of the robot arm can be fed back to the robot's control system, so that the control system optimizes the control effect and decision algorithm of the robot arm.
[0071] In addition, the robot is also equipped with a machine learning model, which optimizes and adjusts the robot's operation through the robot learning model. According to the response results of the target gate corresponding to the interactive operation between the robot and the target gate, the robot's current operation is evaluated to optimize the accuracy and efficiency of subsequent operations. For example, when the robot controls the mechanical arm to move to the target gate and perform interactive actions, the interaction time of the entire process is greater than 20 seconds, while the normal interaction time is usually around 5 to 10 seconds. At this time, the machine learning model can be used to optimize the movement path or control strategy of the mechanical arm, thereby improving the subsequent decision-making algorithm and mechanical arm control logic. By continuously optimizing the control logic of the robot, the flexibility of the robot is improved.
[0072] The present embodiment provides a control method for a robot. When a sensor detects the presence of a gate on a navigation path, the visual system is started and video information of the gate is obtained. A target gate that needs to be passed is selected from a single or multiple gates based on the video information to improve the passing efficiency. At the same time, based on a flexible control strategy, the robot arm and the end effector are controlled to interact with the target gate to improve the accuracy of the interaction. After the interaction is completed, the state of the target gate is detected in real time, the passing instruction of the target gate is responded to, and the channel of the target gate is passed. Finally, the control strategy of the robot is optimized based on the state of the target gate to further improve the flexibility of the robot when it needs to pass the gate.
[0073] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can refer to the above introduction, and will not be repeated in the following. Figure 2 , step S30 also includes steps S31 to S33:
[0074] Step S31, when the robot moves to the passage entrance of the target gate, the access control type and access control area of the target gate are determined according to the video information.
[0075] In this embodiment, the access control type refers to the control type required to control the target gate to open the gate, such as pressing the gate opening command, sliding the touch screen, scanning the ID card, verifying the RFID tag or voice interaction, etc. The access control area refers to the control area corresponding to when the robot performs an interactive action. For example, if the access control type of the target gate is the ID card verification type, the corresponding access control area is the card reader area of the target gate. If the access control type is the button switch control type, the corresponding access control area is the touch button area.
[0076] As an optional implementation, the video information can be analyzed and processed by a machine learning model, that is, the video information is input into a pre-trained machine learning model, and the video information is analyzed and processed by the machine learning model to obtain the type and model parameters of the target gate, so as to determine the corresponding access control type and access control area based on the specific type and model parameters of the target gate. Among them, the robot's information storage module will regularly update the information of the gates that have been put into use on the market, including the height, size, etc. of the access control area. Therefore, after the robot moves to the channel entrance, the control type and access control area required by the target gate are analyzed through the video information, so that the robot can generate the corresponding path to control the movement of the mechanical arm and select the corresponding operation sequence for access verification, thereby improving the flexibility of the robot to autonomously pass through the gate.
[0077] Step S32, determining the moving path of the robot arm according to the access control area, and determining the operation sequence of the robot arm according to the access control type.
[0078] In this embodiment, after obtaining the access control area, the moving path of the robot arm is determined based on the height, size, etc. of the area, so that the end effector of the robot arm interacts with the target gate. At the same time, after obtaining the access control type, the verification method can also be determined based on the type, that is, the operation sequence performed by the robot arm, such as selecting a press lever to perform an operation sequence of pressing a pass button in the access control area.
[0079] Step S33: controlling the robot arm to move to the access control area according to the moving path, and selecting a target end effector to interact with the access control area based on the access control type.
[0080] In this embodiment, after the moving path is obtained, the movement of the robot arm is controlled based on the moving path, and a suitable end effector is selected for interaction based on the control type, thereby improving the interaction efficiency between the robot and the target gate.
[0081] This embodiment provides a robot control method, which can reduce the possibility of manual intervention and misoperation by obtaining the access control type and access control area through video information. At the same time, the movement path and operation sequence of the robot arm are determined according to the access control type and access control area, so that the robot can adapt to different access control needs more flexibly. By selecting the target end effector to interact with the access control area, the adaptability and versatility of the robot can be improved, so that it can cope with various types of access control equipment. Based on this, the efficiency and accuracy of the robot in the process of interacting with the target gate are improved, the need for manual intervention is reduced, and the degree of automation of the system and the flexibility of operation are improved.
[0082] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can refer to the above introduction, and will not be repeated later. Figure 3 , step S40 also includes steps S50 to S60:
[0083] Step S50, generating the passage operation data of the robot;
[0084] Step S60, updating the passage operation data to the machine learning model to optimize the processing action of the robot when detecting the gate.
[0085] In this embodiment, after the robot passes through the target gate, it means that the robot has currently passed through the gate autonomously. At this time, the robot's passing operation data during the entire passing process can be generated, and the passing operation data includes the data of the robot's control arm movement, the data of the selected operation sequence, the time data spent in the process, etc. Then, these data are updated to the machine learning model, and through feedback learning, the robot's operating efficiency and success rate are improved, and the possibility of failure is reduced.
[0086] Furthermore, in addition to the positive feedback optimization process, negative sample learning can also be performed based on the operation data of failed traffic to improve the effectiveness and efficiency of subsequent operations. Based on this, in another optional implementation, after step S30, it also includes:
[0087] During a preset period of time, when the target gate is in a closed state and / or the robot has not received the passage instruction, the machine learning model is trained with negative samples based on the passage operation data of the interaction between the end effector and the target gate, and then the step of obtaining the video information of the gate and subsequent steps are performed to enable the robot to re-interact with the target gate or select a new target gate for interaction. It is understandable that when passage fails, it means that the action currently performed by the robot to interact with the target gate is an invalid action, or when identifying the target gate, the gate that cannot pass is identified as the target gate. Based on this, it is necessary to learn the passage operation data of the interaction process as a negative sample training set to avoid performing incorrect processing actions when the same scenario occurs later, thereby improving the flexibility of the robot.
[0088] This embodiment provides a robot control method, which collects the actual operation data of the robot after successfully passing through the target gate, or the operation data when the passage fails, and uses these positive sample data or negative sample data to train a machine learning model to improve the robot's response and operation when encountering the gate, thereby improving the robot's flexibility and the effectiveness of the control process and the accuracy of decision-making when passing the gate.
[0089] The present application provides a robot, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the control method of the robot in any of the above-mentioned embodiments.
[0090] Reference below Figure 4 , which shows a schematic structural diagram of a robot suitable for implementing an embodiment of the present application. Figure 4 The robot shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0091] like Figure 4As shown, the robot may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the robot are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the robot to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a robot with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.
[0092] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0093] The robot provided by the present application adopts the control method of the robot in the above embodiment, which can solve the technical problem of low flexibility of the robot. Compared with the prior art, the beneficial effects of the robot provided by the present application are the same as the beneficial effects of the control method of the robot provided by the above embodiment, and the other technical features of the robot are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0094] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0095] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0096] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the robot control method in the above-mentioned embodiment.
[0097] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0098] The computer-readable storage medium may be included in the robot; or may exist independently without being assembled into the robot.
[0099] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by a robot, the robot:
[0100] When detecting that the gate exists on the travel path, obtaining video information of the gate;
[0101] Determine the location of the target gate according to the video information;
[0102] When the robot moves to the passageway of the target gate, controlling the end effector of the robot arm to interact with the target gate;
[0103] In response to the passage instruction of the target gate, the robot is controlled to pass through the passage of the target gate.
[0104] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0106] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0107] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the control method of the above-mentioned robot, and can solve the technical problem of low flexibility of the robot. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the control method of the robot provided by the above-mentioned embodiment, and will not be repeated here.
[0108] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A robot control method, characterized in that: The robot comprises a mechanical arm for operating a gate, the mechanical arm comprises an end effector for interacting with the gate, and the method comprises: When detecting that the gate exists on the travel path, obtaining video information of the gate; Determine the location of the target gate according to the video information; When the robot moves to the passageway of the target gate, controlling the end effector of the robot arm to interact with the target gate; In response to the passage instruction of the target gate, the robot is controlled to pass through the passage of the target gate.
2. The method according to claim 1, characterized in that Determining the position of the target gate according to the video information includes: If there is a gate on the travel path, the gate in the video information is used as the target gate; If there are multiple gates on the travel path, determine the current passage information and usage status of the multiple gates according to the video information; According to the current traffic information and the usage status, among the multiple gates, a gate with the least number of passers-by is used as the target gate.
3. The method according to claim 1, characterized in that When the robot moves to the passageway of the target gate, controlling the end effector of the robot arm to interact with the target gate includes: When the robot moves to the passageway of the target gate, determining the access control type and access control area of the target gate according to the video information; Determining a moving path of the robot arm according to the access control area, and determining an operation sequence of the robot arm according to the access control type; The robot arm is controlled to move to the access control area according to the movement path, and a target end effector is selected based on the access control type to interact with the access control area.
4. The method according to claim 3, characterized in that The determining the access control type and access control area of the target gate according to the video information includes: The video information is input into a pre-trained machine learning model to obtain the access control type and the access control area of the target gate.
5. The method according to claim 1, characterized in that When the gate is detected to be present on the travel path, obtaining video information of the gate includes: When the gate is detected on the travel path, the visual system of the robot is activated; When the gate is in the detection field of view of the visual system, the gate is scanned and processed based on the visual system to obtain the video information.
6. The method according to claim 1, characterized in that After responding to the passage instruction of the target gate and controlling the robot to pass through the passage of the target gate, the method further includes: Generating passage operation data of the robot; The passage operation data is updated to the machine learning model to optimize the processing action of the robot when a gate is detected.
7. The method according to claim 6, characterized in that When the robot moves to the passageway of the target gate, after controlling the end effector of the robot arm to interact with the target gate, the method further includes: Within a preset time period, when the target gate is in a closed state and / or the robot does not receive the passage instruction, negative sample training is performed on the machine learning model based on the passage operation data of the interaction between the end effector and the target gate; Execute the step of obtaining the video information of the gate and subsequent steps.
8. The method according to claim 1, characterized in that When the robot moves to the passageway of the target gate, after controlling the end effector of the robot arm to interact with the target gate, the method further includes: Determine the opening and closing state of the target gate according to the communication sensor of the robot; When it is detected that the target gate is in an open state, controlling the robot to pass through the target gate; The operation result data of the robotic arm is fed back to the control system of the robot so that the control system optimizes the control logic and decision-making algorithm of the robotic arm.
9. A robot, characterized in that: The robot comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the robot control method according to any one of claims 1 to 8.
10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the robot control method according to any one of claims 1 to 8 are implemented.
Citation Information
Patent Citations
Crowd queue control method and device based on robot
CN110363695A
Control method and system for robot to go through gate machine
CN111360802A
Sample collecting method of robot and device thereof
CN113128545A
Method and device for robot to automatically select elevator based on reinforcement learning
CN115330276A
Multi-tool-end control system of electric execution robot
CN116237964A
