CN111283679A - A multi-connected voice control automatic guided transportation system and its control method - Google Patents

Abstract

The invention relates to a multi-connected voice control automatic guide transportation system and a control method thereof, and the control method is characterized in that: the method comprises the following steps: the software part comprises an instruction database arranged on the cloud server; the instruction database comprises object list data, object image identification data, object relative position data and instruction input position data; the hardware part comprises an instruction input device for inputting voice instructions and a robot for completing corresponding work according to the voice instructions; the instruction input device comprises a fixed input device and/or a mobile input device; the robot comprises a transplanting mechanism, a mechanical arm, a camera module and a control mainboard; the control main board controls the transplanting mechanism, the mechanical arm and/or the camera module; the robot is provided with an instruction input module and a communication module, and the instruction input module and/or the communication module are in communication connection with the control mainboard. The system can take voice as an instruction, and control the robot to complete related work after voice recognition.

Description

A multi-connected voice control automatic guided transportation system and its control method

technical field

The invention relates to a robot control system, in particular to a multi-connected voice-controlled automatic guided transportation system and a control method thereof.

Background technique

In today's society, robots have been inseparable from human society, and robots are definitely human's right-hand assistants; in industry, robotic arms have been widely used, no matter in light or heavy industry, robotic arms can be seen everywhere; in life, there have been It has become more and more common in the form of hospitality robots for hospitality and transport robots for serving dishes. Recently, some logistics companies have developed robotic arms for handling and trolley-guided transportation systems for logistics classification, which greatly increases the classification efficiency of goods; however, these robotic arms and trolley-guided transportation systems can only perform Some single and repeated instructions, that is, the entire link from receiving human instructions to completing related work is very simple, because the instructions issued by humans generally require temporary programming or pre-programming, so the degree of intelligence is low and cannot meet different requirements. Requirements.

Therefore, further improvements are required.

SUMMARY OF THE INVENTION

The purpose of the present invention is to overcome the deficiencies of the above-mentioned prior art, and provide a multi-connected voice control automatic guided transportation system and a control method thereof.

The object of the present invention is achieved in this way:

A multi-connected voice-controlled automatic guided transportation system is characterized in that: comprising:

The software part includes an instruction database set on the cloud server; the instruction database includes object list data that records information about more than one target object, object image identification data used to identify the target object, and object image identification data used to identify the location of the target object. The relative position data of the object, and the position data of the command input party used to feedback the operator's position;

The hardware part includes a command input device for inputting voice commands, and a robot that completes corresponding work according to the voice commands; the command input device includes a fixed input device fixed at a preset position and used for inputting voice commands and/or with operation A mobile input device for moving the operator and for inputting voice commands; the robot includes a transplanting mechanism for moving and walking, a robotic arm for grasping target objects, a camera module for acquiring surrounding image information, and a voice module for executing voice commands. The control board of the instruction; the control board controls the transplanting mechanism, the mechanical arm and/or the camera module; the robot is provided with an instruction input module for receiving voice instructions from the operator, and for communicating with the cloud server. The communication module, the command input module and/or the communication module are communicatively connected to the control board.

The object list data includes keyword information corresponding to the name, color, shape and/or size of the target object.

The image identification data includes picture information corresponding to the color, shape and/or size of the target object.

The object relative position data includes three-dimensional coordinate information corresponding to the position of the target object.

The position data of the command input party is fixed position information of the fixed input device and/or mobile position information of the mobile input device.

The control board is loaded with a voice mode and a manual mode, and the switching between the voice mode and the manual mode is performed through physical keys and/or virtual keys.

In the manual mode, the operator inputs control commands through the remote control, and the camera module transmits live images of the scene to the operator.

The control method of the above-mentioned multi-connected voice control automatic guided transportation system is characterized in that: comprising the following steps

Step A, the operator inputs a voice command, and the control system analyzes the input voice command to determine whether the target object mentioned in the voice command exists in the object list data, so as to execute the next step;

In step B, the control system extracts the image identification information corresponding to the target object from the image identification data, extracts the three-dimensional coordinate information corresponding to the target object from the object relative position data, and confirms the operator position information through the command input side position data; then the control system Send image identification information, three-dimensional coordinate information and operator position information to the robot to perform the next step;

Step C, control the main board to plan the required walking route of the transplanting mechanism to the position of the target object according to the received three-dimensional coordinate information; control the main board to find the target object through the camera module according to the received image identification information and/or the three-dimensional coordinate information, and perform the next step;

Step D, control the main board to confirm the real-time posture of the found target object through the camera module, and plan the action trajectory required for the robot arm to grasp the target object, and control the robot arm to smoothly grasp the target object according to the action trajectory; or, control the main board After confirming that the target object is found through the camera module, the operator controls the robot arm to grab the target object through the remote control according to the image sent back by the camera module;

Step E, the control board plans the required walking route of the transplanting mechanism to the operator's location according to the location of the target object and the operator's location information, and controls the transplanting mechanism to move to the operator's location according to the walking route.

The transplanting mechanism is provided with a laser sensor, an ultrasonic sensor, a photoelectric sensor, a magnetic sensor, a camera device, an infrared sensor and/or a GPS positioning module and the like.

In step E, the robot waits for the next voice command within the set time after delivering the target object to the operator. If the next voice command is not received within the set time, the control board plans the transplanting mechanism to return to The walking trajectory of the initial position, so that the robot can return to the initial position for waiting.

The beneficial effects of the present invention are as follows:

This multi-joint voice control automatic guided transportation system integrates five major technologies: voice recognition command technology, automatic guided vehicle technology, image recognition technology, wireless communication technology and mechanical action programming technology, so that the system can complete the operation according to the voice command issued by the operator. corresponding work. Specifically, the operator connects to the system through voice control, a robotic arm with an automatic guided vehicle, and a wireless network, and can remotely issue voice commands to control the robotic arm to complete related operations. The entire control process is simple, convenient, and can At the same time, voice commands are issued to multiple different robotic arms to assist the operator to complete the work, eliminating the need for traditional control robots to control complex control processes such as programming or controllers, making the robot control more intelligent and convenient; the voice control method of this system It can really shorten the distance between humans and robots, so that robots can better become the real assistants of human beings, and improve work efficiency and living standards.

Description of drawings

FIG. 1 is a schematic structural diagram of a robot in an embodiment of the present invention.

FIG. 2 is a working flowchart of a system in an embodiment of the present invention.

FIG. 3 is a working flowchart of a robot in an embodiment of the present invention.

Detailed ways

The present invention will be further described below with reference to the accompanying drawings and embodiments.

Referring to Figures 1-3, this multi-joint voice-controlled automatic guided transportation system includes

The software part includes the instruction database set on the cloud server. The instruction database is set on the cloud server to facilitate the updating of the control system, and it is also convenient to connect with robots M in different places anytime, anywhere; the instruction database includes records of more than one target object Object list data of relevant information, object image identification data used to identify the target object, relative position data of the object used to identify the location of the target object, and position data of the command input party used to feedback the operator's location;

The hardware part includes a command input device for inputting voice commands, and a robot M that completes corresponding work according to the voice commands; the command input device includes a fixed input device fixed at a preset position and used for inputting voice commands and/or a follow-up input device. The operator moves and is used to input voice commands, and the operator can freely choose the command input device to the UK according to usage habits or convenience; the robot M includes a transplanting mechanism 3 for moving and walking, and is used to grasp the target The robotic arm 1 of the object, the camera module 2 for acquiring surrounding image information, the control board for executing voice commands; the control board controls the transplanting mechanism 3, the robotic arm 1 and/or the camera module 2 to achieve the purpose of unified control; The robot M is provided with an instruction input module for receiving voice instructions from the operator, and a communication module for communicating with the cloud server, and the instruction input module and/or the communication module are communicatively connected to the control board; the communication mode of the communication module is: WIFI, 4G and/or 5G, etc., so that the robot M can connect to the cloud server effectively, stably and at high speed to exchange information and receive commands.

The system effectively associates the voice command data in the command database, the transplanting mechanism 3 that can walk to the destination through the walking route, the camera module 2 that can recognize the target object, and the robotic arm 1 that can grasp the target object, etc. The robot M with the transplanting mechanism 3 can recognize the relevant instructions from the voice input by the operator, and walk to the designated position to perform corresponding actions.

Further, the object list data includes keyword information that matches the name, color, shape and/or size of the target object, so as to be paired as a voice command; wherein, the name of the target object is not unique, and other names that may be called are all Can be recorded in the inventory data.

Further, the image identification data includes image information that is consistent with the color, shape and/or size of the target object; the control system needs more than one image (the more the better) that is consistent with the target object, and then uses an algorithm according to the image. The image data of the target object is obtained for identifying the target object to be found.

Further, the object relative position data includes three-dimensional coordinate information consistent with the location of the target object, and the three-dimensional coordinate information consists of a horizontal position, a vertical position and a height position, so that the control system can confirm the specific position of the target object.

Further, the position data of the instruction input party includes fixed position information of the fixed input device and/or mobile position information of the mobile input device. Among them, the mobile input device includes electronic accessories that have been connected to the control system through a wireless network; electronic accessories include smart phones, PC computers, remote controls, etc.

Further, a voice mode and a manual mode are loaded on the control main board, and the switching between the voice mode and the manual mode is performed through physical keys and/or virtual keys.

Further, in the manual mode, the operator inputs control commands through the remote controller, and the camera module 2 transmits the live real-time image to the operator. Specifically, in addition to the control through voice commands, the operator can switch to the manual mode; when the transplanting mechanism 3 is switched to the manual mode, the operator can use a designated remote controller to control the actions of the robot M, and the remote controller can It is hardware or software; in manual mode, the operator can manually control the robot M to perform some difficult tasks anytime and anywhere through the network. Real-time manipulation of distance; the camera module 2 is preferably a CCD camera.

Referring to Fig. 2-Fig. 3, the control method of the above-mentioned multi-connected voice-controlled automatic guided transportation system includes the following steps

In step A, the operator inputs a voice command, and the control system analyzes the input voice command to first determine whether the target object mentioned in the voice command exists in the object list data; when the target object exists in the object list data, the control system will The data related to the target object will be extracted from the instruction database, and the next step will be executed; when the target object does not exist in the object list data, the control system will send feedback to the operator through the communication medium, so that the operator can confirm the input target object Whether the basic information is correct, and notify it to re-enter;

In step B, the control system extracts the image identification information corresponding to the target object from the image identification data, extracts the three-dimensional coordinate information corresponding to the target object from the object relative position data, and confirms the operator position information through the command input side position data; then the control system Send image identification information, three-dimensional coordinate information and operator position information to the robot M to perform the next step;

Step C, the control board plans the required walking route of the transplanting mechanism 3 to the target object position according to the received three-dimensional coordinate information; when the robot M goes to the position where the target object is placed, the image around the robot M is obtained through the camera module 2 , the control board searches for the target object through the camera module 2 according to the received image identification information and/or three-dimensional coordinate information; when the target object is found, the control system executes the next step; when the target object cannot be found, the control system will Feedback to the operator, so that the operator can confirm whether the input target object position information is correct, and notify him to re-enter;

In step D, the control board confirms the real-time posture of the found target object through the camera module 2, and plans out the movement trajectory required by the robot arm 1 to grasp the target object, and controls the robot arm 1 to smoothly grasp the target object according to the movement trajectory; or , after the control board confirms that the target object is found through the camera module 2, the operator controls the robot arm 1 to grasp the target object through the remote control according to the image sent back by the camera module 2. This manual operation mode can not grasp the target in the automatic operation mode. In order to complete the tasks that cannot be completed by the automatic operation mode, and further ensure the reliability of the system;

Step E, the control board plans the required walking route of the transplanting mechanism 3 to the operator's location according to the location of the target object and the operator's location information, and controls the transplanting mechanism 3 to move to the operator's location according to the walking route.

Further, the transplanting mechanism 3 is provided with a laser sensor, an ultrasonic sensor, a photoelectric sensor, a magnetic sensor, a camera device, an infrared sensor and a GPS positioning module, etc., and the transplanting mechanism 3 can cooperate with each sensor to have an automatic driving function, and simultaneously have automatic avoidance. barrier function.

Further, in step E, the robot M waits for the next voice command within the set time after delivering the target object to the operator, if the next voice command is not received within the set time, the control motherboard plans the transplanting mechanism. 3. The walking track of returning to the original position, so that the robot M can return to the original position for waiting.

Further, in step A, the voice input by the operator includes the name of the target object, the features of the target object (features include color, shape, size, etc.), and the placement position of the target object.

Further, the control system can also identify some specific voice commands, such as "pause", "re-enter the command", "turn to manual mode", etc.; the control system will issue a corresponding command to the transplanting mechanism 3 after identifying the specific voice command. , let the transplanting mechanism 3 complete the corresponding action.

The above are preferred embodiments of the present invention, showing and describing the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above-mentioned embodiments. The above-mentioned embodiments and descriptions only illustrate the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various Variations and improvements are intended to fall within the scope of the claimed invention. The claimed scope of the present invention is defined by the appended claims and their equivalents.

Claims (10)

1. a multi-connected voice control automatic guided transport system, is characterized in that: comprising: The software part includes an instruction database set on the cloud server; the instruction database includes object list data that records information about more than one target object, object image identification data used to identify the target object, and object image identification data used to identify the location of the target object. The relative position data of the object, and the position data of the command input party used to feedback the operator's position; The hardware part includes a command input device for inputting voice commands, and a robot (M) that completes corresponding work according to the voice commands; the command input device includes a fixed input device fixed at a preset position and used for inputting voice commands and/or Or a mobile input device that moves with the operator and is used for inputting voice commands; the robot (M) includes a transplanting mechanism (3) for moving and walking, a robotic arm (1) for grasping the target object, a camera module (2) for acquiring surrounding image information, and a control board for executing voice commands; the control board controls the transplanting mechanism (3), the robotic arm (1) and/or the camera module (2); the robot ( M) is provided with an instruction input module for receiving voice commands from the operator, and a communication module for communication and interconnection with the cloud server, and the instruction input module and/or the communication module are communicatively connected to the control board. 2 . The multi-line voice-controlled automatic guided transportation system according to claim 1 , wherein the item list data includes keyword information that matches the name, color, shape and/or size of the target item. 3 . 3 . The automatic guided transportation system for multi-line voice control according to claim 1 , wherein the image identification data includes picture information that is consistent with the color, shape and/or size of the target object. 4 . 4 . The multi-connected voice-controlled automatic guided transportation system according to claim 1 , wherein the relative position data of the object includes three-dimensional coordinate information that is consistent with the position of the target object. 5 . 5 . The multi-line voice-controlled automatic guided transportation system according to claim 1 , wherein the position data of the command input party includes fixed position information of the fixed input device and/or moving position information of the mobile input device. 6 . 6. according to the described multi-connection voice control automatic guided transportation system of claim 1, it is characterized in that: described control main board is loaded with voice mode and manual mode, and the switching between voice mode and manual mode is by physical key and/or virtual keys. 7 . The multi-joint voice-controlled automatic guided transportation system according to claim 6 , wherein in the manual mode, the operator inputs control commands through the remote control, and the camera module ( 2 ) transmits on-site real-time images to the operator. 8 . 8. the control method of multi-connected voice control automatic guided transportation system as claimed in claim 1, is characterized in that: comprises the following steps Step A, the operator inputs a voice command, and the control system analyzes the input voice command to determine whether the target object mentioned in the voice command exists in the object list data, so as to execute the next step; In step B, the control system extracts the image identification information corresponding to the target object from the image identification data, extracts the three-dimensional coordinate information corresponding to the target object from the object relative position data, and confirms the operator position information through the command input side position data; then the control system Send image identification information, three-dimensional coordinate information and operator position information to the robot (M) to perform the next step; Step C, control the main board to plan the required walking route of the transplanting mechanism (3) to the position of the target object according to the received three-dimensional coordinate information; control the main board to pass the camera module (2) according to the received image identification information and/or the three-dimensional coordinate information. ) to find the target object and perform the next step; Step D, the control board confirms the real-time posture of the found target object through the camera module (2), and plans the motion trajectory required by the robotic arm (1) to grasp the target object, and controls the robotic arm (1) to follow the motion trajectory smoothly. Grab the target object; or, after the control board confirms that the target object is found through the camera module (2), the operator controls the robotic arm (1) to grasp the target object through the remote control according to the image sent back by the camera module (2); In step E, the control board plans the required walking route of the transplanting mechanism (3) to the operator's location according to the location of the target object and the operator's location information, and controls the transplanting mechanism (3) to move to the operator's location according to the walking route. . 9 . The multi-connection voice-controlled automatic guided transportation system according to claim 8 , wherein the transplanting mechanism ( 3 ) is provided with a laser sensor, an ultrasonic sensor, a photoelectric sensor, a magnetic sensor, a camera device, and an infrared sensor. 10 . and/or GPS positioning module. 10. The multi-joint voice-controlled automatic guided transportation system according to claim 8, characterized in that: in step E, the robot (M) waits for the next time within a set time after delivering the target object to the operator. Voice command, if the next voice command is not received within the set time, the control board will plan the walking trajectory of the transplanting mechanism (3) returning to the initial position, so that the robot (M) can return to the initial position for waiting.

Images