WO2018077164A1

WO2018077164A1 - Method and system for enabling robot to automatically return for charging

Info

Publication number: WO2018077164A1
Application number: PCT/CN2017/107498
Authority: WO
Inventors: 乔涛; 薛林
Original assignee: 北京进化者机器人科技有限公司
Priority date: 2016-10-28
Filing date: 2017-10-24
Publication date: 2018-05-03
Also published as: CN106444777A; CN106444777B

Abstract

A method and system for enabling a robot (100) to automatically return for charging, relating to the technical field of automation. The method comprises: obtain current visual field information by means of a robot (100) (S110); accordingly determine whether a target system is within the range of the current visual field information (S120); if the target system is within the range of current visual field information, photograph the target system, so as to obtain a first image (S131); process the first image to obtain a black-white image (S140); establish a Cartesian coordinate system according to the black-white image, and control, according to the Cartesian coordinate system, the robot (100) to move to a preset correction point (S150); then the robot (100) sends a drive instruction to the target system, so that the target system feeds back a pulse signal to the robot (100) according to the drive instruction (S160); the robot (100) aligns with the target system; after the alignment ends, start charging the robot (100) (S190). In the present invention, the equipment costs of the obstacle avoidance and navigation of the robot (100) can be reduced, and the stability, accuracy and practicability of the walking state of the robot (100) can be improved.

Description

Robot automatic return charging method and system

Cross-reference to related applications

This application claims priority to Chinese Patent Application No. CN201610971722.0, entitled "Robot Automatic Return Charging Method and System", filed on October 28, 2016, the entire contents of which are incorporated herein by reference. In the application.

Technical field

The present invention relates to the field of automation technology, and in particular to a robot automatic return charging method and system.

Background technique

In recent years, as a high-tech technology, robotics has gradually penetrated into every aspect of our lives. From the production workshop to the hospital, the role played by robots is immeasurable. Traditional industrial robots are suitable for structured environments and perform repetitive tasks. Modern robots hope to work together with humans in the same unstructured space and environment to perform non-deterministic tasks online in real time. The field has emerged from the fixed-point operations in the structural environment, and has developed into autonomous operations in aerospace, interstellar exploration, military reconnaissance attacks, underwater underground pipelines, disease inspection and treatment, disaster relief and other non-structural environments; Input and single-ended output systems, while modern robots are multi-input and multi-end output systems; traditional robots are far less than in smart homework, online perception, understanding of human behavior and abstract commands, cognitive and decision-making capabilities, etc. People can't communicate and communicate effectively with people.

The charging of the robot is an important part to ensure that the robot is in a state of sufficient power for effective use and work. At present, the robot charging and returning technology mainly includes: infrared positioning, ultrasonic positioning and Bluetooth technology. However, infrared rays cannot penetrate objects, can only be positioned within the line of sight, and are easily interfered by indoor fluorescent lamps during transmission, so there is a case where the robot cannot find the charging base; ultrasonic ranging is affected by multipath and non-viewing. The distance propagation has a great influence; the Bluetooth positioning establishes a slow connection speed, low precision, and poor anti-interference ability.

Summary of the invention

In view of this, the object of the present invention is to provide a robot automatic return charging method and system, to save equipment cost of robot obstacle avoidance navigation, and to improve the stability, accuracy and practicability of the robot walking state.

In a first aspect, an embodiment of the present invention provides a robot automatic return charging method, which includes:

The robot acquires current view information;

Determining, according to the current view information, whether the target system is within the current view information range;

If the target system is within the current field of view information, taking a picture of the target system to obtain a first image;

Processing the first image to obtain a black and white image;

Establishing a Cartesian coordinate system according to the black and white image, and controlling the robot to move to a preset correction point according to the Cartesian coordinate system;

After the robot moves to the preset correction point, the robot sends a driving instruction to the target system, so that the target system feeds back a pulse signal to the robot according to the driving instruction;

The robot performs alignment with the target system and sends a sensor command to the target system to cause the target system to calculate a alignment time required by the robot;

Determining whether the alignment time is within a preset time threshold;

If the alignment time of the robot is within the preset time threshold, charging the robot to start;

If the alignment time of the robot is not within the preset time threshold, the robot re-aligns with the target system and re-sends sensor commands to the target system to make the target system Calculate the alignment time required for the robot.

With reference to the first aspect, the embodiment of the present invention provides the first possible implementation manner of the first aspect, wherein the determining, according to the current view information, whether the target system is within the current view information includes:

If the target system is not within the current view information range, the navigation obstacle avoidance is performed according to the A* algorithm until the target system is within the current view information range.

With reference to the first aspect, the embodiment of the present invention provides a second possible implementation manner of the first aspect, wherein the processing the first image to obtain a black and white image comprises:

Normalizing the first image to obtain a normalized image;

The normalized image is binarized to obtain a black and white image.

In conjunction with the second possible implementation of the first aspect, the embodiment of the present invention provides a third possible implementation manner of the first aspect, wherein the first image is normalized to obtain a normalization Image includes:

Performing channel separation on the first image to obtain a first channel, a second channel, and a third channel, respectively;

Obtaining a second image according to the value of the first channel, the value of the second channel, and the value of the third channel;

The second image is normalized to obtain the normalized image.

With reference to the second possible implementation manner of the first aspect, the embodiment of the present invention provides a fourth possible implementation manner of the first aspect, wherein the normalized image is binarized to obtain black and white. The image includes:

Determining whether a pixel value of any pixel in the normalized image is lower than a preset pixel threshold;

If it is lower, the pixel value is set to a first value;

If it is higher, the pixel value is set to a second value;

The black and white image is acquired by binarization processing.

With reference to the first aspect, the embodiment of the present invention provides a fifth possible implementation manner of the first aspect, wherein the establishing a Cartesian coordinate system according to the black and white image comprises:

Draw a minimum rectangle circumscribing the white area in the black and white image, so that the minimum rectangle frames the red light area in the first channel image;

Determining an optical center of the red light region, and obtaining a coordinate of the LED point light source in the camera coordinate system in the target system by using a binocular ranging principle;

Calling coordinates of the camera coordinate system to obtain coordinates of the LED point source in the robot coordinate system;

Obtaining a center point according to coordinates in the robot coordinate system;

The Cartesian coordinate system is established with the center point as an origin.

With reference to the first aspect, the embodiment of the present invention provides a sixth possible implementation manner of the first aspect, wherein the controlling the movement of the robot to a preset correction point according to the Cartesian coordinate system comprises:

Calculating the distance and angle of the robot relative to the first correction point, and controlling the movement of the robot to the first correction point;

Calculating a distance and an angle of the robot relative to the second correction point, and controlling the movement of the robot to the second correction point;

Calculate the distance and angle of the robot relative to the third correction point, control the robot movement to the third correction point, and end the visual alignment.

With reference to the first aspect, the embodiment of the present invention provides a seventh possible implementation manner of the first aspect, wherein the performing, by the robot, the alignment with the target object includes:

Using an infrared receiving tube for voltage detection;

Detecting a relationship between a voltage of the infrared receiving tube;

If the voltage of the infrared receiving tube on the right side is lower, the robot moves to the right;

If the voltage of the infrared receiving tube on the left side is low, the robot moves to the left;

If the voltages of the infrared receiving tubes on the left and right sides are the same, and the voltage of the receiving tube in the middle is large, the robot goes straight.

In a second aspect, an embodiment of the present invention further provides a robot automatic return charging system, including a robot (100) and a target system, wherein the robot (100) includes a central controller (120), a camera (110), and a motion unit ( 130), the target system includes a charging pile (200), the charging pile (200) is provided with an MCU (210) and a sensor (220);

The camera (110) is configured to acquire current view information by the robot (100), determine, according to the current view information, whether the target system is within the current view information range, if the target system is in the current view information Within the scope, the target system is photographed to obtain a first image;

The central controller (120) is configured to process the first image, acquire a black and white image, establish a Cartesian coordinate system according to the black and white image, and after the robot (100) moves to a preset correction point, The robot (100) Sending a drive command to the target system while controlling the robot (100) to perform alignment with the target system and transmitting a sensor command to the target system;

The motion unit (130) is configured to control the movement of the robot (100) to a preset correction point according to the Cartesian coordinate system;

The MCU (210) is configured to receive the driving instruction, and control the sensor (220) according to the driving instruction, receive the sensor instruction at the same time, and calculate a alignment time required by the robot (100) If the alignment time of the robot (100) is within a preset time threshold, charging the robot (100) begins;

The sensor (220) is configured to feed back a pulse signal to the robot (100) according to the driving instruction.

With reference to the second aspect, the embodiment of the present invention provides a first possible implementation manner of the second aspect, wherein the central controller (120) is further configured to draw a minimum of splicing a white area in the black and white image. Rectangularly, the minimum rectangle is framed in the red light region in the first channel image, and the optical center of the red light region is determined, and the LED point light source (230) in the target system is obtained in the camera coordinates by using the binocular ranging principle. The coordinates of the system are called, the coordinates of the camera coordinate system are called, the coordinates of the LED point light source (230) in the robot coordinate system are obtained, and the center point is obtained according to the coordinates in the robot coordinate system, and the center point is obtained. For the origin, the Cartesian coordinate system is established.

The invention provides a robot automatic return charging method and system, which acquires current field of view information by a robot, determines whether the target system is within the current field of view information according to current field of view information, and photographs the target system if the target system is within the current field of view information range. , thereby acquiring a first image, processing the first image, acquiring a black and white image, establishing a Cartesian coordinate system according to the black and white image, and controlling the robot motion to a preset correction point according to the Cartesian coordinate system, when the robot moves to a preset After the correction point, the driving command is sent to the target system, so that the target system feeds back the pulse signal to the robot according to the driving instruction, and the robot performs alignment with the target system, and sends a sensor instruction to the target system, so that the target system calculates the required operation of the robot. The alignment time, if the robot's alignment time is within a preset time threshold, the robot starts charging, and if the robot's alignment time is not within the preset time threshold, the robot re-aligns with the target system, Resend sensor finger to target system . The invention can save the equipment cost of the obstacle avoidance navigation of the robot, quickly and accurately identify the target system, improve the stability of the motion state, and has stronger practicability.

Other features and advantages of the invention will be set forth in the description which follows, and The objectives and other advantages of the invention are realized and attained by the invention particularly pointed in

The above described objects, features and advantages of the present invention will become more apparent from the aspects of the appended claims.

DRAWINGS

In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will be specifically implemented. BRIEF DESCRIPTION OF THE DRAWINGS The drawings, which are required to be used in the description of the prior art, are briefly described. It is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art will not be creatively labored. Further drawings can also be obtained from these drawings.

1 is a flowchart of a method for automatic return charging of a robot according to Embodiment 1 of the present invention;

2 is a flowchart of step S140 in the automatic return charging method of the robot according to the first embodiment of the present invention;

3 is a flowchart of a method for acquiring a normalized image according to Embodiment 1 of the present invention;

4 is a flowchart of a method for acquiring a black and white image according to Embodiment 1 of the present invention;

FIG. 5 is a flowchart of a method for establishing a Cartesian coordinate system according to a black and white image according to Embodiment 1 of the present invention; FIG.

6 is a flowchart of a method for controlling a robot to move to a preset correction point according to a Cartesian coordinate system according to Embodiment 1 of the present invention;

FIG. 7 is a flowchart of a method for correcting a robot according to Embodiment 1 of the present invention; FIG.

FIG. 8 is a schematic diagram of a robot automatic return charging system according to Embodiment 2 of the present invention.

icon:

100-robot; 110-camera; 120-central controller; 130-motion unit; 200-charging pile; 210-MCU; 220-sensor; 230-LED point source.

detailed description

The embodiments of the present invention will be clearly and completely described in detail with reference to the accompanying drawings. An embodiment. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

At present, as a high-tech technology, robot technology has gradually penetrated into all aspects of our life. The charging of robots is an important link to ensure that the robot is in a state of sufficient power to achieve effective use and work. At present, the robot charging and returning technology mainly includes: infrared positioning, ultrasonic positioning and Bluetooth technology. However, infrared rays cannot penetrate objects, can only be positioned within the line of sight, and are easily interfered by indoor fluorescent lamps during transmission, so there is a case where the robot cannot find the charging base; ultrasonic ranging is affected by multipath effects and non- The line-of-sight propagation has a great influence; the Bluetooth connection establishes a slow connection speed, low precision, and poor anti-interference ability. Based on this, the automatic returning charging method and system for the robot provided by the embodiment of the invention can save the equipment cost of the obstacle avoidance navigation of the robot, quickly and accurately identify the target system, improve the stability of the motion state, and have greater practicability.

In order to facilitate the understanding of the embodiment, the robot automatic return charging method disclosed in the embodiment of the present invention is first introduced in detail.

Embodiment 1:

FIG. 1 is a flowchart of a method for automatic return charging of a robot according to Embodiment 1 of the present invention.

Referring to Figure 1, the method includes the following steps:

Step S110, the robot acquires current view information;

Specifically, the robot enables binoculars, relies on the principle of visual measurement to detect an unknown environment, and effectively obtains current field of view information, and the current field of view information includes information of unknown obstacles, including the actual shape, size, size, and orientation of the obstacle. When the battery is insufficient, the charging pile is recognized and returned to the charging pile for charging, which greatly saves the equipment cost of the robot for obstacle avoidance navigation.

In step S120, it is determined whether the target system is within the current field of view information according to the current field of view information; if the target system is within the current field of view information, step S131 is performed; if the target system is not within the current field of view information, step S132 is performed;

Specifically, the target system is a charging pile. When the robot has insufficient power, the robot automatically recognizes the charging pile and returns to the charging pile to charge, which greatly saves the equipment cost of the robot obstacle avoidance navigation; the robot determines whether the binocular vision can be in the current field of view. The existence of the charging pile is directly seen in the information range. If the target system is within the current field of view information, step S131 is performed; if the target system is not within the current field of view information, step S132 is performed.

Step S131, taking a picture of the target system, thereby acquiring the first image;

Specifically, the robot enables binoculars, looks for four blue LED point sources provided on the head of the charging pile, and takes photos of the four blue LED point sources to obtain a first image.

Step S132, performing navigation avoidance according to the A* algorithm until the target system is within the current field of view information range;

Specifically, the A*(A-Star) algorithm is the most effective direct search method for solving the shortest path in a static road network. It is also an effective algorithm for solving many search problems. The closer the distance estimate is to the actual value, the final. The faster the search speed is; the obstacle avoidance is performed according to the A* algorithm until the position of the charging pile can be directly seen, and step S131 can be started.

Step S140, processing the first image to obtain a black and white image;

Specifically, the first image is subjected to normalization processing and binarization processing to obtain a black and white image.

Step S150, establishing a Cartesian coordinate system according to the black and white image, and controlling the robot to move to a preset correction point according to the Cartesian coordinate system;

Specifically, in the Cartesian coordinate system, that is, the XOY coordinate system, the visual measurement is more accurate, thereby ensuring the stability and accuracy of the walking state of the robot; the robot sets the starting point and the ending point of the movement in the XOY coordinate system, and sets Three correction points with different distances to the end point are used to adjust the moving angle and distance of the three correction points to accurately locate the charging pile, which is quite accurate and practical.

Step S160, after the robot moves to the preset correction point, the robot sends a driving instruction to the target system, so that the target system feeds back the pulse signal to the robot according to the driving instruction;

Specifically, after three times of correcting motion, after positioning the position of the charging pile, the robot goes to the MCU on the charging pile. (Microcontroller Unit, Micro Control Unit) sends a drive command to drive the sensor to work, sends a pulse with a fixed frequency of 5KHz, and sends a feedback pulse signal to the robot.

Step S170, the robot performs alignment with the target system, and sends a sensor instruction to the target system, so that the target system calculates the alignment time required by the robot;

Specifically, the robot is accurately positioned again, and is aligned according to the feedback pulse signal, and sends a sensor command to the MCU of the charging post. After receiving the sensor command, the MCU starts to calculate the alignment time of the robot. The sensor command according to the present invention may be, but not limited to, an infrared sensor command of an infrared type.

Step S180, it is determined whether the alignment time is within a preset time threshold; if yes, step S190 is performed; otherwise, step S170 is re-executed;

In step S190, the robot starts charging.

Specifically, the time threshold may be 30 seconds; if the alignment time exceeds 30 seconds, the infrared sensor is turned off, and the process returns to step S170 to restart the alignment; if the alignment time is within 30 seconds, after the alignment is completed, The robot starts charging; the four blue LED point lights on the charging post are used to display the charging power. One LED point light is on to indicate charging 25%, two are 50%, three are 75%, and four are fully charged. %; After charging, the charging post is automatically powered off.

According to the embodiment of the present invention, as shown in FIG. 2, in the automatic return charging method of the robot in the above embodiment, step S140 can be implemented by the following steps, including:

Step S210, normalizing the first image to obtain a normalized image;

In step S220, the normalized image is binarized to obtain a black and white image.

Specifically, referring to FIG. 3, step S210 can be implemented by the following steps:

Step S310, performing channel separation on the first image to obtain a first channel, a second channel, and a third channel, respectively;

The first channel, the second channel, and the third channel include: the first image includes four blue LED point light sources, and the first image is r (red, red), g (green, green), b (blue, Blue) three-channel separation, respectively obtaining r channel, g channel and b channel;

Step S320, acquiring a second image according to the value of the first channel, the value of the second channel, and the value of the third channel;

After separating, for each pixel of the image, subtract the value of the r channel from the value of the b channel, and subtract the value of the g channel to obtain the second image;

Step S330, normalizing the second image to obtain a normalized image.

Wherein, the second image is normalized, so that the image with the highest value of the pure blue region in the b channel and the lowest value of the region without the blue color is obtained, and the r channel and the g channel are avoided. interference.

Referring to FIG. 4, step S220 can be implemented by the following steps:

Step S410, determining whether the pixel value of any pixel in the normalized image is lower than a preset pixel threshold; if lower, Step S421 is performed; if not, step S422 is performed;

Step S421, setting the pixel value to the first value;

Step S422, setting the pixel value to the second value;

Step S430, obtaining a black and white image by binarization processing.

The preset pixel threshold is 100, the first value is 0, and the second value is 255; each pixel of the normalized image is decomposed, and if the pixel value of a certain pixel is lower than 100, the pixel value is changed to 0; if the pixel value of a certain pixel is higher than 100, the pixel value is set to a maximum of 255; after the binarization process, a black and white image is obtained.

According to an embodiment of the present invention, as shown in FIG. 5, the method for establishing a Cartesian coordinate system according to a black and white image in step S150 includes:

Step S510, drawing a minimum rectangle that circumscribes the white area in the black and white image, so that the smallest rectangle frames the red light area in the first channel image;

Specifically, the red light area is picture information of the LED point light source in the r channel obtained by separating the first picture by three channels. The white area in the black and white image is framed by the minimum circumscribed rectangle, and the position of the rectangle is recorded, at which the four circular red areas in the separated r channel image are framed.

Step S520, determining the optical center of the red light region, and obtaining the coordinates of the LED point light source in the camera coordinate system in the target system by using the binocular ranging principle;

Specifically, the optical centers of the four red light regions are determined, and the optical centers of the four red light regions in the left camera image are respectively matched with the optical centers of the four red light regions of the right camera image, and the binocular test is used. The distance principle obtains four coordinates corresponding to the four blue LED point sources in the camera coordinate system.

Step S530, calling coordinates in the camera coordinate system to obtain coordinates of the LED point light source in the robot coordinate system;

Specifically, the coordinates of the four blue LED point sources in the robot coordinate system are: upper left (x1, y1), upper right (x2, y2), lower left (x3, y3), and lower right (x4, Y4).

Step S540, obtaining a center point according to coordinates in a robot coordinate system;

Specifically, according to the left reference point obtained in the previous step

Right reference point

And the center point (x ₀ , y ₀ ), which is known by the formula (1):

In step S550, a Cartesian coordinate system is established with the center point as the origin.

Specifically, the center point (x ₀ , y ₀ ) is taken as the origin, and the left reference point points to the right reference point as the x positive axis, and the Cartesian coordinate system XOY coordinate system is established.

According to an embodiment of the present invention, as shown in FIG. 6, the method for controlling the movement of the robot to the preset correction point according to the Cartesian coordinate system in step S150 includes:

Step S610, calculating a distance and an angle of the robot relative to the first correction point, and controlling the movement of the robot to the first correction point;

Specifically, the coordinates of the robot in the XOY coordinate system are set to (xr, yr); the distance d1 and the angle θ1 of the robot relative to the first correction point (0, -1200) in the XOY coordinate system are calculated, by the formula (2) And formula (3) shows:

Control the robot to move to the first correction point.

Step S620, calculating a distance and an angle of the robot relative to the second correction point, and controlling the movement of the robot to the second correction point;

Specifically, at this time, the robot is at the first correction point, and calculates the distance d2 and the angle θ2 of the robot relative to the second correction point (0, -800) in the XOY coordinate system, by formula (4) and formula (5). It can be known that:

Control the robot to move to the second correction point.

Step S630, calculating the distance and angle of the robot relative to the third correction point, controlling the movement of the robot to the third correction point, and ending the visual alignment.

Specifically, at this time, the robot is at the second correction point, and calculates the distance d3 and the angle θ3 of the robot relative to the third correction point (0, -400) in the XOY coordinate system, by formula (6) and formula (7). It can be known that:

The robot is controlled to move to the third correction point; the robot reaches the third correction point from the second correction point, and the robot is at a distance of 30 cm from the charging pile, and is in the visual alignment end state.

According to an embodiment of the present invention, as shown in FIG. 7, the method for the robot to perform alignment with the target system in step S170 includes:

Step S710, performing voltage detection by using an infrared receiving tube;

Specifically, the infrared receiving tube is mounted on the robot, the number is three, at the same horizontal line, and the spacing is the same.

Step S720, detecting a high-low relationship between voltages of the infrared receiving tubes;

Step S730, if the voltage of the infrared receiving tube on the right side is lower, the robot moves to the right;

Step S740, if the voltage of the infrared receiving tube on the left side is lower, the robot moves to the left;

In step S750, if the voltages of the infrared receiving tubes on the left and right sides are the same, and the voltage of the receiving tube in the middle is large, the robot goes straight.

Specifically, after accurate positioning by the infrared sensor again, after the robot rotates 180° and retreats, the voltage is simultaneously detected by the three infrared receiving tubes that are provided, and the closer the output voltage is, the more the left and right movement is moved until the charging is under the self. The piece is completely against the charging contact under the charging post and begins to charge.

The invention provides a robot automatic return charging method, which acquires current field of view information by the robot, determines whether the target system is within the current field of view information according to the current field of view information, and if the target system is within the current field of view information, photographs the target system. Thereby acquiring the first image, processing the first image to obtain a black and white image, establishing a Cartesian coordinate system according to the black and white image, and controlling the motion of the robot to the preset correction point according to the Cartesian coordinate system, and moving the robot to the preset correction point Afterwards, the robot sends a driving instruction to the target system, so that the target system feeds back the pulse signal to the robot according to the driving instruction, and the robot performs alignment with the target system, and sends a sensor instruction to the target system, so that the target system calculates the alignment time of the robot. If the alignment time of the robot is within a preset time threshold, the robot starts charging, and if the alignment time of the robot is not within the preset time threshold, the robot re-aligns with the target system and re-sends to the target system. Sensor instruction. The invention can quickly and accurately identify the target system, save the equipment cost of the obstacle avoidance navigation of the robot, and improve the stability of the motion state, and has stronger practicability.

Embodiment 2:

Referring to FIG. 8 , the robot automatic return charging system includes a robot 100 and a target system, wherein the robot 100 includes a central controller 120, a camera 110 and a motion unit 130. The target system includes a charging post 200, and the charging post 200 includes an MCU 210, a sensor 220, and LED point light source 230;

The camera 110 is configured to acquire current field of view information by the robot 100, determine whether the target system is within the current field of view information according to the current field of view information, and if the target system is within the current field of view information, take a picture of the target system to obtain the first image;

Specifically, the number of cameras 110 is two and is at the same horizontal line. As the binocular of the robot 100, the camera 110 looks for the LED point light source 230 provided at the head of the charging post 200, and takes a picture of the LED point light source 230 to acquire a first image. Further, the LED point light source 230 is four blue LED point light sources arranged in a rectangular shape, and the charging post 200 charges the battery of the robot 100.

The central controller 120 is configured to process the first image, obtain a black and white image, and establish a Cartesian according to the black and white image. a coordinate system, and after the robot 100 moves to a preset correction point, the robot 100 sends a drive command to the target system, while controlling the robot 100 to perform alignment with the target system, and transmitting a sensor command to the target system;

Specifically, the central controller 120 is further configured to control the motion unit 130 to perform navigation avoidance according to the A* algorithm until the charging station 200 is within the current visual field information range;

The central controller 120 obtains a normalized image by normalizing the first image; performing binarization processing on the normalized image to obtain a black and white image;

The central controller 120 controls the robot 100 to finally move to the third correction point by calculating the distance and angle of the robot 100 with respect to the first correction point, the second correction point, and the third correction point, respectively, and ends the visual pair. Positive; then, the central controller 120 sends a drive command to the MCU 210;

The central controller 120 performs voltage detection by using an infrared receiving tube; detects the relationship between the voltage of the infrared receiving tube; if the voltage of the infrared receiving tube on the right side is lower, the robot 100 moves to the right; if the infrared receiving tube on the left side When the voltage is low, the robot 100 moves to the left; if the voltages of the infrared receiving tubes on the left and right sides are the same, and the intermediate receiving tube voltage is large, the robot 100 goes straight; at this time, the pair of the robot 100 and the charging pile 200 is completed. Positive, central controller 120 sends sensor commands to MCU 210.

a motion unit 130, configured to control the robot 100 to move to a preset correction point according to a Cartesian coordinate system;

Specifically, the motion unit 130 is controlled by the control of the central controller 120; the motion unit 130 sequentially moves to three preset correction points according to the Cartesian coordinate system to end the visual alignment; the motion unit 130 completes the 180° of the robot 100. After the rotation, the left and right movement is performed according to the relationship between the detection voltages, so that the charging contact under the robot 100 is completely close to the charging contact under the charging post 200 to start charging.

The MCU 210 is configured to receive a driving instruction, and control the sensor 220 according to the driving instruction, receive the sensor instruction, and calculate a matching time required by the robot 100. If the alignment time of the robot 100 is within a preset time threshold, the robot is 100 starts charging;

Specifically, the MCU 210 is disposed inside the charging post 200, receives a driving command from the central controller 120, and controls the sensor 220 to feed back the pulse signal to the robot 100 according to the driving instruction. After receiving the sensor command, the MCU 210 starts to calculate the alignment time of the robot 100. When the alignment time is within the preset time threshold, the charging post 200 starts charging the robot 100; the alignment time is not at the preset time threshold. In the case of the inside, the central controller 120 re-aligns the robot 100 with the charging post 200, and the MCU 210 receives the sensor command from the central controller 120 again. The sensor command according to the present invention may be, but not limited to, an infrared sensor command of an infrared type.

The sensor 220 is configured to feed back a pulse signal to the robot 100 according to the driving instruction.

Specifically, the sensor 220 is controlled by the MCU 210 to emit a pulse having a fixed frequency of 5 kHz, and the feedback signal is sent to the robot 100.

According to an embodiment of the invention, the central controller 120 is further configured to draw a minimum of the white area in the black and white image. Rectangular, so that the smallest rectangle frames the red light region in the first channel image, determines the optical center of the red light region, and uses the binocular ranging principle to obtain the coordinates of the LED point light source 230 in the camera coordinate system in the target system, and call the camera coordinates. Based on the coordinates, the coordinates of the LED point source 230 in the robot coordinate system are obtained, the center point is obtained according to the coordinates in the robot coordinate system, and the Cartesian coordinate system is established with the center point as the origin.

The invention provides a robot automatic return charging system, comprising a robot and a target system, acquiring current field of view information by the robot, determining whether the target system is within the current field of view information according to the current field of view information, and if the target system is within the current field of view information, The target system takes a picture to obtain a first image, processes the first image to obtain a black and white image, establishes a Cartesian coordinate system according to the black and white image, and controls the robot to move to a preset correction point according to the Cartesian coordinate system, and the robot moves to After the preset correction point, the robot sends a drive command to the target system, so that the target system feeds back the pulse signal to the robot according to the drive command, and the robot performs alignment with the target system, and sends a sensor command to the target system to calculate the target system. The alignment time of the robot, if the alignment time of the robot is within a preset time threshold, the robot starts charging, and if the alignment time of the robot is not within the preset time threshold, the robot re-aligns with the target system, Re-targeting system Feed sensor instruction. The invention can quickly and accurately identify the target system, save the equipment cost of the obstacle avoidance navigation of the robot, and improve the stability of the motion state, and has stronger practicability.

A computer program product for a robot automatic return charging method and system according to an embodiment of the present invention, comprising a computer readable storage medium storing program code, the program code comprising instructions for performing the method described in the foregoing method embodiment For the specific implementation, refer to the method embodiment, and details are not described herein again.

A person skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the system and the device described above can refer to the corresponding process in the foregoing method embodiments, and details are not described herein again.

In addition, in the description of the embodiments of the present invention, the terms "installation", "connected", and "connected" are to be understood broadly, and may be a fixed connection or a detachable connection, unless otherwise explicitly defined and defined. , or connected integrally; may be mechanical connection or electrical connection; may be directly connected, or may be indirectly connected through an intermediate medium, and may be internal communication between the two elements. The specific meaning of the above terms in the present invention can be understood in a specific case by those skilled in the art.

The functions may be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a standalone product. Based on such understanding, the technical solution of the present invention, which is essential or contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium, including The instructions are used to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and the like, which can store program codes. medium.

In the description of the present invention, it is to be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. The orientation or positional relationship of the indications is based on the orientation or positional relationship shown in the drawings, and is merely for the convenience of the description of the invention and the simplified description, rather than indicating or implying that the device or component referred to has a specific orientation, in a specific orientation. The construction and operation are therefore not to be construed as limiting the invention. Moreover, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

In the description of the present invention, it should be noted that the terms "installation", "connected", and "connected" are to be understood broadly, and may be fixed or detachable, for example, unless otherwise explicitly defined and defined. Connected, or integrally connected; can be mechanical or electrical; can be directly connected, or indirectly connected through an intermediate medium, can be the internal communication of the two components. The specific meaning of the above terms in the present invention can be understood in a specific case by those skilled in the art.

Finally, it should be noted that the above-mentioned embodiments are merely specific embodiments of the present invention, and are used to explain the technical solutions of the present invention, and are not limited thereto, and the scope of protection of the present invention is not limited thereto, although reference is made to the foregoing. The present invention has been described in detail, and those skilled in the art should understand that any one skilled in the art can still modify the technical solutions described in the foregoing embodiments within the technical scope disclosed by the present invention. The changes may be easily conceived, or equivalents may be substituted for some of the technical features. The modifications, variations, or substitutions of the present invention are not intended to depart from the spirit and scope of the technical solutions of the embodiments of the present invention. Within the scope of protection. Therefore, the scope of the invention should be determined by the scope of the claims.

Claims

A robot automatic return charging method, characterized in that it comprises:

The robot acquires current view information;

Determining, according to the current view information, whether the target system is within the current view information range;

If the target system is within the current field of view information, taking a picture of the target system to obtain a first image;

Processing the first image to obtain a black and white image;

Establishing a Cartesian coordinate system according to the black and white image, and controlling the robot to move to a preset correction point according to the Cartesian coordinate system;

After the robot moves to the preset correction point, the robot sends a driving instruction to the target system, so that the target system feeds back a pulse signal to the robot according to the driving instruction;

The robot performs alignment with the target system and sends a sensor command to the target system to cause the target system to calculate a alignment time required by the robot;

Determining whether the alignment time is within a preset time threshold;

If the alignment time of the robot is within the preset time threshold, charging the robot to start;

If the alignment time of the robot is not within the preset time threshold, the robot re-aligns with the target system and re-sends sensor commands to the target system to make the target system Calculate the alignment time required for the robot.
The robot automatic return charging method according to claim 1, wherein the determining, according to the current view information, whether the target system is within the current view information range comprises:

If the target system is not within the current view information range, the navigation obstacle avoidance is performed according to the A* algorithm until the target system is within the current view information range.
The automatic return charging method of the robot according to claim 1, wherein the processing the first image to obtain a black and white image comprises:

Normalizing the first image to obtain a normalized image;

The normalized image is binarized to obtain a black and white image.
The robot automatic return charging method according to claim 3, wherein the normalizing the first image to obtain a normalized image comprises:

Performing channel separation on the first image to obtain a first channel, a second channel, and a third channel, respectively;

Obtaining a second image according to the value of the first channel, the value of the second channel, and the value of the third channel;

The second image is normalized to obtain the normalized image.
The robot automatic return charging method according to claim 3, wherein the performing the binarization processing on the normalized image to obtain a black and white image comprises:

Determining whether a pixel value of any pixel in the normalized image is lower than a preset pixel threshold;

If it is lower, the pixel value is set to a first value;

If it is higher, the pixel value is set to a second value;

The black and white image is acquired by binarization processing.
The robot automatic return charging method according to claim 1, wherein the establishing a Cartesian coordinate system according to the black and white image comprises:

Draw a minimum rectangle circumscribing the white area in the black and white image, so that the minimum rectangle frames the red light area in the first channel image;

Determining an optical center of the red light region, and obtaining a coordinate of the LED point light source in the camera coordinate system in the target system by using a binocular ranging principle;

Calling coordinates of the camera coordinate system to obtain coordinates of the LED point source in the robot coordinate system;

Obtaining a center point according to coordinates in the robot coordinate system;

The Cartesian coordinate system is established with the center point as an origin.
The robot automatic return charging method according to claim 1, wherein the controlling the movement of the robot to a preset correction point according to the Cartesian coordinate system comprises:

Calculating the distance and angle of the robot relative to the first correction point, and controlling the movement of the robot to the first correction point;

Calculating a distance and an angle of the robot relative to the second correction point, and controlling the movement of the robot to the second correction point;

Calculate the distance and angle of the robot relative to the third correction point, control the robot movement to the third correction point, and end the visual alignment.
The robot automatic return charging method according to claim 1, wherein the robot performs alignment with the target system, including:

Using an infrared receiving tube for voltage detection;

Detecting a relationship between a voltage of the infrared receiving tube;

If the voltage of the infrared receiving tube on the right side is lower, the robot moves to the right;

If the voltage of the infrared receiving tube on the left side is low, the robot moves to the left;

If the voltages of the infrared receiving tubes on the left and right sides are the same, and the voltage of the receiving tube in the middle is large, the robot goes straight.
A robot automatic return charging system, comprising: a robot (100) and a target system, wherein the robot (100) comprises a central controller (120), a camera (110) and a motion unit (130), The target system includes a charging pile (200), and the charging pile (200) is provided with an MCU (210) and a sensor (220);

The camera (110) is configured to acquire the current visual field information by the robot (100), determine, according to the current visual field information, whether the target system is within the current visual field information range, if the target system is in the current visual field Within the scope of the information, the target system is photographed to obtain the first image;

The central controller (120) is configured to process the first image, acquire a black and white image, establish a Cartesian coordinate system according to the black and white image, and after the robot (100) moves to a preset correction point The robot (100) sends a drive command to the target system while controlling the robot (100) to perform alignment with the target system and send a sensor command to the target system;

The motion unit (130) is configured to control the movement of the robot (100) to a preset correction point according to the Cartesian coordinate system;

The MCU (210) is configured to receive the driving instruction, and control the sensor (220) according to the driving instruction, simultaneously receive the sensor instruction, and calculate a required alignment of the robot (100) Time, if the alignment time of the robot (100) is within a preset time threshold, charging the robot (100) begins;

The sensor (220) is configured to feed back a pulse signal to the robot (100) in accordance with the drive command.
The robot automatic return charging system according to claim 9, wherein said central controller (120) is further configured to draw a minimum rectangle circumscribing a white area in said black and white image to minimize said minimum Rectangularly framing the red light region in the image of the first channel, determining the optical center of the red light region, using the binocular ranging principle to obtain the coordinates of the LED point light source (230) in the target system in the camera coordinate system, calling a coordinate of the camera coordinate system, obtaining coordinates of the LED point light source (230) in a robot coordinate system, obtaining a center point according to coordinates in the robot coordinate system, and establishing the center point with the center point as an origin Cartesian coordinate system.