Intelligent grooving robot based on binocular vision and laser radar system

Abstract

The invention relates to the technical field of building construction equipment, and particularly discloses an intelligent grooving robot based on binocular vision and a laser radar system.The intelligent grooving robot comprises a moving flat plate, the binocular vision and laser radar system and a dust collecting device, and a moving mechanism is arranged at the bottom of the moving flat plate; the moving mechanism comprises universal wheels symmetrically arranged at the four corners of the bottom of the moving flat plate and a braking mechanism arranged at the bottom of the moving flat plate, a multi-joint mechanical arm is arranged at the top of the moving flat plate, and a plurality of overturning driving mechanisms connected with the multi-joint mechanical arm are arranged on the moving flat plate. According to the intelligent grooving robot based on binocular vision and the laser radar system, the AVG trolley guiding technology is applied to the grooving robot, and then the grooving robot completes automatic grooving work under the unmanned operation condition, so that the technical problems existing in an existing building grooving robot are solved, and the construction efficiency is improved. The method is suitable for large-scale popularization.

Description

Technical Field

[0001] The present invention relates to the technical field of building construction equipment, and in particular to an intelligent grooving robot based on binocular vision and laser radar system. Background Art

[0002] With the development of information technology and automatic control technology, robots have gradually penetrated into people's lives. Robots can replace human work in various complex environments. Among them, mobile robots that can move autonomously have also been widely used in all walks of life. For mobile robots, the key technologies include accurately sensing and building external environment maps (mapping), determining the robot's own position in the external environment (positioning), and planning the path to reach the target point and completing the movement of the target path (path planning). Accurately completing the movement of the target path is crucial for mobile robots that need to have a clear working path. Taking the intelligent slotting robot as an example, the intelligent slotting robot needs to move autonomously along one side of the wall to be slotted when opening vertical slots and when opening diagonal slots according to different indoor environments to complete the automated slotting operation of the wall. During the slotting operation, the distance and angle between the robot and the wall will seriously affect the slotting quality. Therefore, it is crucial to ensure that the motion trajectory is parallel to the wall during the slotting process.

[0003] Traditional slotting operations mostly rely on manual slotting, which is labor-intensive and has uneven slotting quality, requiring a lot of filling and finishing work in the later stage. Although there are slotters as auxiliary tools for slotting operations, they still require manual operation and are somewhat dangerous. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent grooving robot based on binocular vision and laser radar system, which solves the technical problems existing in the existing grooving devices when grooving pipelines in building walls. It has a reasonable overall design, simple structure, high working efficiency, good grooving quality and high safety, and is suitable for large-scale promotion.

[0005] To achieve the above-mentioned purpose, the present invention provides an intelligent slotting robot based on binocular vision and laser radar system, comprising a mobile plate, a binocular vision and laser radar system and a dust collection device, wherein a mobile mechanism is arranged at the bottom of the mobile plate, and the mobile mechanism comprises universal wheels symmetrically arranged at the four corners of the bottom of the mobile plate and a braking mechanism arranged inside the universal wheels, a multi-joint mechanical arm is arranged at the top of the mobile plate, and a plurality of flipping drive mechanisms connected to the multi-joint mechanical arm are arranged on the mobile plate; The binocular vision and laser radar system is used to adjust the posture relationship of the robot relative to the wall and to correct the length, width and depth of the slot; The posture relationship of the robot relative to the wall is adjusted by obtaining distance data through laser radar scanning, and analyzing and judging the posture relationship between the robot and the wall at the current moment.

[0006] Preferably, the multi-joint mechanical arm comprises three sections of hollow cylindrical mechanical arms, and the mechanical arms are connected by the flip driving mechanism; The head of the multi-joint mechanical arm is provided with a slotting mechanism, which includes a slotting arm and a double saw blade rotatably arranged at the end of the slotting arm, a hollow shaft is arranged at the center of the double saw blade, and a slotting motor is fixedly arranged on the hollow shaft.

[0007] Preferably, the dust collection device comprises a dust collector, a dust collection nozzle, a dust conveying pipeline and a detachable dust storage box, and the detachable dust storage box is provided with a safety light; The vacuum cleaner is arranged on the mobile flat plate, the vacuum pipe openings are arranged on both sides of the slotting mechanism, and the dust conveying pipeline is arranged inside the multi-joint mechanical arm.

[0008] Preferably, the dust conveying pipeline is connected to the dust suction pipe opening through a three-way valve, the valve openings of the three-way valve on the same straight line are connected to the dust suction pipe opening, the remaining valve opening of the three-way valve is connected to the dust conveying pipeline, and the detachable dust storage box is arranged at the bottom of the movable plate.

[0009] Preferably, the dust conveying pipeline is a plastic flexible pipeline with a smooth inner wall.

[0010] Preferably, the binocular vision and laser radar system includes a control platform, an optical sensor and a CCD camera, fixed laser radar transmitting devices A and B, universal wheels and a braking mechanism; The optical sensor and the CCD camera are arranged outside the dust suction pipe opening, the fixed laser radar transmitting devices A and B are arranged on the top of the mobile flat plate, and the control pan / tilt is arranged on the top of the mobile flat plate; The control platform is provided with a visual guidance control board for controlling the mobile flat panel, the multi-joint mechanical arm, the optical sensor and the CCD camera, and the visual guidance control board is provided with a central processing unit.

[0011] Preferably, the specific process of analyzing and judging the posture relationship between the robot and the wall at the current moment is as follows: S1. The side of the slotting robot with the laser radar fixed faces the wall, and the laser radar is used to measure the distance between points A and B to obtain the distance between points A and B and the wall along the fixed direction. S2. Determine whether the distance from points A and B to the wall along a fixed direction is a valid distance: If the distance from points A and B to the wall along a fixed direction is less than the robot's maximum slotting operation range and is between the maximum scanning range and the minimum scanning range of the laser radar, then it is an effective distance; If the distance from points A and B to the wall along a fixed direction is greater than the robot's maximum slotting range and is not between the maximum scanning range and the minimum scanning range of the laser radar, it is an invalid distance and needs to be remeasured; S3, denote the distances from points A and B to the wall along a fixed direction as La and Lb respectively, denote the vertical distance between points A and B as L, denote the absolute value of the difference between the distances from points A and B to the wall along a fixed direction as C, and denote the set threshold as e; If C is less than the set threshold e, it is judged that the robot is parallel to the wall at this time; If C is greater than the set threshold e, and La is greater than Lb, then it is determined that the robot is tilted to the left relative to the wall; If C is greater than or equal to the set threshold e, and La is less than Lb, then it is determined that the robot is tilted to the right relative to the wall; S4, estimate the current inclination angle of the robot relative to the wall, and record the inclination angle as θ; The inclination angle θ is equal to the arc tangent of the absolute value C of the difference between the distances from points A and B to the wall along a fixed direction divided by the vertical distance L between points A and B. The expression is: ; Where θ is the current tilt angle of the robot relative to the wall, C is the absolute value of the difference between the distances of points A and B to the wall along a fixed direction, and L is the vertical distance between points A and B. S5: Adjust the robot’s posture angle relative to the wall in real time until it is parallel; S6. Calibrate the length, width and depth of the slot, and compare the length, width and depth obtained by the optical sensor and CCD camera with the length, width and depth of the slot input in the drawing: The absolute value of the difference between the slot length and the drawing length, the absolute value of the difference between the slot width and the drawing width, and the absolute value of the difference between the slot depth and the drawing depth shall not exceed the set threshold.

[0012] Preferably, the initial position of the robot is between the maximum scanning range and the minimum scanning range of the laser radar, and the distance between the robot and the wall to be grooved does not exceed the maximum groove operation range of the robot.

[0013] Preferably, laser radar transmitters are fixed at points A and B on the mobile flat plate to measure the distances from the two points to the wall along a fixed direction, thereby adjusting the posture relationship of the robot relative to the wall.

[0014] Therefore, the present invention adopts the above-mentioned intelligent slotting robot based on binocular vision and laser radar system, and the beneficial effects are as follows: (1) The present invention utilizes a moving mechanism to provide a moving function for the device. The braking mechanism can keep the device in a stable working state. The flipping drive mechanism can enable the multi-joint robot to operate on the horizontal working surface and the vertical working surface. The binocular vision and laser radar system can adjust the posture relationship of the slotting robot relative to the wall in real time, and reasonably plan the reasonable path between the slotting working position and the working position and avoid obstacles.

[0015] (2) The present invention is provided with a dust collection device which can timely collect and process the dust generated by the slotting robot during the slotting operation, thereby reducing environmental pollution.

[0016] (3) The overall device of the present invention has a reasonable design, a simple structure, can handle dust in a timely manner, and has high safety, which greatly improves the efficiency of grooving and is suitable for large-scale promotion.

[0017] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a side view of the overall structure of an embodiment of an intelligent slotting robot based on binocular vision and laser radar system of the present invention; Figure 2 This is an embodiment of an intelligent slotting robot based on binocular vision and laser radar system of the present invention. Figure 1 Enlarged view of the circled part; Figure 3 It is a front view of an embodiment of an intelligent slotting robot based on binocular vision and laser radar system of the present invention; Figure 4 This is an embodiment of an intelligent slotting robot based on binocular vision and laser radar system of the present invention. Figure 3 Enlarged view of the circled part; Figure 5 It is a side view from another angle of an embodiment of an intelligent slotting robot based on binocular vision and laser radar system of the present invention; Figure 6 It is a schematic diagram of a scanning of processed laser radar data when the slotting robot is parallel to a wall surface in an embodiment of an intelligent slotting robot based on binocular vision and laser radar system of the present invention; Figure 7 It is a schematic diagram of a scanning of processed laser radar data when the slotting robot of an embodiment of an intelligent slotting robot based on binocular vision and laser radar system of the present invention is tilted to the left relative to the wall; Figure 8It is a schematic diagram of a scanning of processed laser radar data when the slotting robot of an embodiment of an intelligent slotting robot based on binocular vision and laser radar system of the present invention is tilted to the right relative to the wall; Fig. 9 It is a side view of the overall structure of an embodiment of an intelligent slotting robot based on binocular vision and laser radar system of the present invention after adding a bowl-shaped dust cover; Fig.10 It is a front view of the overall structure of an embodiment of an intelligent grooving robot based on binocular vision and laser radar system of the present invention with a bowl-shaped dust cover added.

[0019] Reference numerals 1. Mobile plate; 2. Universal wheel; 3. Braking mechanism; 4. Robotic arm; 401. First robot arm; 402. Second robot arm; 403. Third robot arm; 5. Flipping drive mechanism; 501. First flipping mechanism; 502. Second flipping mechanism; 503. Third flipping mechanism; 504. Fourth flipping mechanism; 6. Slotting arm; 7. Double saw blades; 8. Hollow shaft; 9. Vacuum cleaner; 10. Dust suction pipe; 11. Removable dust storage box; 12. Optical sensor and CCD camera; 13. Control pan / tilt; 14. Dust hood. DETAILED DESCRIPTION

[0020] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0021] Unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0022] like Figure 1As shown, an intelligent grooving robot based on binocular vision and laser radar system includes a mobile plate 1, a binocular vision and laser radar system and a dust collection device. A moving mechanism is arranged at the bottom of the mobile plate 1, and a multi-joint robotic arm is arranged at the top of the mobile plate 1. The moving mechanism provides a moving function for the device, which is convenient for movement between floors, and can also expand the limited working range of the multi-joint robotic arm to meet the requirements of grooving on building walls.

[0023] The moving mechanism includes universal wheels 2 symmetrically arranged at the four corners of the bottom of the moving plate 1 and a brake mechanism 3 arranged inside the universal wheels 2. The arrangement of the universal wheels 2 enables the robot to move in any direction. The brake mechanism 3 has a braking function, which mainly keeps the device in a stable working state and ensures the working stability of the multi-joint robot arm.

[0024] The multi-joint robot arm comprises three sections of hollow cylindrical robot arms 4, such as Figure 1 As shown in the figure, the robot arm 4 is composed of a first robot arm 401, a second robot arm 402 and a third robot arm 403. The mobile plate 1 is provided with a plurality of flipping drive mechanisms 5 connected to the multi-joint robot arm, and the flipping drive mechanism 5 is composed of a first flipping mechanism 501, a second flipping mechanism 502, a third flipping mechanism 503 and a fourth flipping mechanism 504. The robot arms 4 are connected by the flipping drive mechanism 5, and the flipping drive mechanism 5 is used to flip the multi-joint robot arm 90 degrees on the vertical working plane.

[0025] The head of the multi-joint mechanical arm is provided with a slotting mechanism, and the end of the multi-joint mechanical arm near the slotting mechanism is provided with a safety cover. The slotting mechanism includes a slotting arm 6 and a double saw blade 7 rotatably provided at the end of the slotting arm 6, a hollow shaft 8 is provided at the center of the double saw blade 7, a slotting motor is fixedly provided on the hollow shaft 8, and the slotting motor is used to drive the double saw blade 7 to rotate.

[0026] During specific operation, the operation of the flip driving mechanism 5 is to divide the main working plane of the multi-joint mechanical arm into a horizontal working plane and a vertical working plane. For example, if the first working plane of the multi-joint mechanical arm is a vertical plane (or a horizontal plane), the flip driving mechanism 5 is started and performs an action, and the multi-joint mechanical arm flips 90 degrees under the action of the flip driving mechanism 5 to reach the second working plane, that is, the horizontal plane (or a vertical plane). In this way, the multi-joint mechanical arm can successively operate in the horizontal working plane and the vertical working plane, so that the double saw blades 7 of the slotting mechanism can open cross-staggered slots. The double saw blades 7 rotate under the drive of the slotting motor, and at the same time, under the front push action of the slotting arm 6, a reference slot edge with a certain depth can be slotted.

[0027] In order to solve the dust problem generated during the grooving process, a dust collection device is provided on the grooving robot in this embodiment. The dust collection device includes a vacuum cleaner 9, a vacuum pipe mouth 10, a dust conveying pipe and a detachable dust storage box 11. The vacuum cleaner 9 is arranged on the mobile plate 1, the vacuum pipe mouth 10 is arranged on both sides of the grooving mechanism, and the dust conveying pipe is arranged inside the multi-joint robotic arm.

[0028] The dust conveying pipeline is connected to the dust suction pipe port 10 through a three-way valve. The valve ports of the three-way valve on the same line are connected to the dust suction pipe port 10, and the remaining valve port of the three-way valve is connected to the dust conveying pipeline. A detachable dust storage box 11 is arranged at the bottom of the mobile flat plate 1.

[0029] In order to improve the dust collection effect of the device, Figure 7 , Figure 8 As shown, a bowl-shaped dust cover 14 can be added to the slotted arm 6 of the slotting mechanism to enhance the dust absorption effect. The dust collected by the dust suction pipe mouth 10 is transported to the detachable dust storage box 11 for storage through the dust conveying pipe arranged inside the hollow cylindrical mechanical arm 4. The dust conveying pipe adopts a plastic flexible pipe with a smooth inner wall to facilitate dust collection and avoid clogging the dust conveying pipe.

[0030] The detachable dust storage box 11 is provided with a safety light. When the sensor installed in the detachable dust storage box 11 detects that the volume of the collected dust accounts for less than 80% of the volume of the detachable dust storage box 11, the safety light is green.

[0031] If the volume of collected dust accounts for more than 80% and less than 90% of the volume of the detachable dust storage box 11, the safety light is yellow at this time, and the operator can take out the detachable dust storage box 11, clean the dust inside, and install it back.

[0032] If the volume of the collected dust accounts for more than 90% of the volume of the detachable dust storage box 11, the safety light will be red, the slotting robot will stop working, and a warning sound will be issued to remind the operator to clean the dust. The slotting robot will resume normal work after the dust is cleaned. This can prevent the collected dust from affecting the circuit work, avoid causing circuit damage, and reduce financial and material consumption.

[0033] The binocular vision and laser radar system in this embodiment includes a control platform 13, an optical sensor and a CCD camera 12, and fixed laser radar transmitting devices A and B (such as Figure 1 As shown in the figure), universal wheels 2 and braking mechanism 3; optical sensors and CCD cameras 12 are arranged on the outside of the dust suction pipe mouth 10, fixed laser radar transmitting devices A and B are arranged on the top of the mobile flat plate 1, and the control pan-tilt platform 13 is arranged on the top of the mobile flat plate 1.

[0034] The control platform 13 is provided with a visual guidance control board for controlling the mobile flat panel 1, the multi-joint mechanical arm, the optical sensor and the CCD camera 12, and the visual guidance control board is provided with a central processing unit. The central processing unit is provided with a prefabricated guidance program, and the slotting robot uses the common AVG trolley guidance technology and adopts a laser radar system for slotting and obstacle avoidance path planning.

[0035] The pre-made bootloader is based on the following steps to move: First, import the architectural drawings, determine the depth, length, and width of the groove, select one side of the wall as the starting groove wall, and set a reflective sheet that can be identified by the CCD camera at the starting groove position; Second, the slotting robot recognizes the pre-set reflective sheet according to the CCD camera and reaches the starting slotting position; Third, adjust the position relationship of the slotting robot relative to the wall, and finally make the slotting robot parallel to the wall; Fourth, the slotting robot performs slotting operations along the slotting direction according to the slotting depth, length and width input in the drawing; Fifth, calibrate the length, width and depth of the slot; Sixth, the slotting robot processes and analyzes the obstacle data of the room plane scanned by the laser radar, calculates a reasonable obstacle avoidance path, and reaches the slotting position on the next wall along the obstacle avoidance path; Repeat the third, fourth, fifth and sixth steps in sequence to complete the grooving work in the entire room.

[0036] The binocular vision and lidar system is used to adjust the robot's posture relative to the wall and to correct the length, width and depth of the slots. The robot's posture relative to the wall is adjusted by obtaining distance data through lidar scanning, and the robot's current posture relationship with the wall is analyzed and judged.

[0037] The following is a further detailed description of the position and posture adjustment of the slotting robot relative to the wall in conjunction with the accompanying drawings and embodiments.

[0038] The specific process of analyzing and judging the current posture relationship between the robot and the wall is as follows: The laser radar transmitters are fixed at points A and B on the mobile plate 1 to measure the distances from the two points to the wall along a fixed direction, thereby adjusting the posture relationship of the robot relative to the wall.

[0039] S1. The side of the slotting robot with the laser radar fixed to it faces the wall. Figure 4 , Figure 5 , Figure 6 The laser radar distance measurement is performed at two points (as shown) to obtain the distance between points A and B and the wall along a fixed direction; S2. Determine whether the distance from points A and B to the wall along a fixed direction is a valid distance: If the distance from points A and B to the wall along the fixed direction is less than the maximum slotting operation range of the robot and is between the maximum scanning range and the minimum scanning range of the laser radar, then it is an effective distance and step S3 is executed; If the distance from points A and B to the wall along a fixed direction is greater than the maximum slotting operation range of the robot and is not between the maximum scanning range and the minimum scanning range of the laser radar, the measured distance is invalid and step S1 needs to be executed to re-measure; S3, denote the distances from points A and B to the wall along a fixed direction as La and Lb respectively, denote the vertical distance between points A and B as L, denote the absolute value of the difference between the distances from points A and B to the wall along a fixed direction as C, and denote the set threshold as e; Determine the position relationship of the slotting robot relative to the wall: If C is less than the set threshold e, it is judged that the robot is parallel to the wall at this time; If C is greater than the set threshold e, and La is greater than Lb, then it is determined that the robot is tilted to the left relative to the wall; If C is greater than or equal to the set threshold e, and La is less than Lb, then it is determined that the robot is tilted to the right relative to the wall. Figure 6 As shown, and step S4 is executed. In this embodiment, the threshold value e is set to 3-5; S4, estimate the current inclination angle of the robot relative to the wall, and record the inclination angle as θ; The inclination angle θ is equal to the arc tangent of the absolute value C of the difference between the distances from points A and B to the wall along a fixed direction divided by the vertical distance L between points A and B. The expression is: ; Where θ is the current tilt angle of the robot relative to the wall, C is the absolute value of the difference between the distances of points A and B to the wall along a fixed direction, and L is the vertical distance between points A and B. S5, adjusting the posture relationship of the slotting robot relative to the wall according to the posture relationship of the slotting robot relative to the wall determined in step S3 and the inclination angle of the robot relative to the wall estimated in step S4 at the current moment, and the posture relationship of the robot is adjusted in a closed-loop feedback manner; Adjust the robot's posture angle relative to the wall in real time until it is parallel. The specific steps are as follows: If step S3 determines that the slotting robot is tilted to the left relative to the wall, Figure 5As shown, the slotting robot is adjusted to rotate clockwise by an inclination angle θ, and then steps S1 to S4 are executed.

[0040] If the slotting robot is tilted to the right relative to the wall, Figure 6 As shown, the slotting robot is adjusted to rotate counterclockwise by an inclination angle θ, and then steps S1 to S4 are executed.

[0041] If step S3 determines that the position relationship between the slotting robot and the wall is that the robot is parallel to the wall, Figure 4 As shown, the grooving operation is performed.

[0042] In the above process, the robot's maximum grooving operation range, the maximum scanning range and minimum scanning range of the laser radar, the laser radar scanning cycle, the scanning frequency, and the angular resolution are all obtained by reading the laser radar scanning data header information or the laser radar setting parameter manual.

[0043] The initial position of the robot is between the maximum scanning range and the minimum scanning range of the laser radar, and the distance between the robot and the wall to be grooved does not exceed the maximum groove operation range of the robot.

[0044] S6. Calibrate the length, width and depth of the groove based on the binocular vision of the groove robot, and compare the length, width and depth obtained by the optical sensor and the CCD camera 12 with the length, width and depth of the groove on the input drawing. The absolute value of the difference between the groove length and the length of the drawing, the absolute value of the difference between the groove width and the width of the drawing, and the absolute value of the difference between the groove depth and the depth of the drawing shall not exceed the set threshold.

[0045] The specific process is as follows: First, select a wall of the room where the groove needs to be cut, determine the starting position of the groove according to the drawing, and stick a reflective sheet at the starting position of the groove; Second, import the drawings of the room to be grooved into the binocular vision recognition system to determine the depth, length, and width of the groove; Third, the slotting robot arrives at the slotting position, uses the binocular vision recognition system to identify the reflective sheet, confirms the slotting point, and determines the slotting direction based on the drawing information; The binocular recognition system uses the SURF algorithm, which is an enhanced version of the SIFT algorithm. The SIFT (Scaleinvariant feature Transform) algorithm is a scale-invariant feature transformation algorithm proposed by David Lowe. The algorithm is a local feature descriptor of an image that is based on scale space and remains invariant to image scaling transformation. The advantages of the SIFT algorithm are stable features, invariance to rotation, scale transformation, and brightness, and a certain degree of stability to perspective transformation and noise; the disadvantages are low real-time performance and weak feature point extraction capabilities for targets with smooth edges. Therefore, a faster feature extraction algorithm SURF came into being, so this embodiment uses the SURF algorithm.

[0046] Fourth, the slotting operation is performed. The slotting robot performs slotting operations according to the imported drawings, and slots the depth, length, and width required by the drawings; Fifth, calibrate the length, width and depth of the groove, and use binocular vision recognition and lidar ranging to measure the actual length, width and depth of the groove.

[0047] The specific steps for correcting the length, width and depth of the slot are as follows: 1. Use binocular vision recognition and laser radar ranging to measure the actual length, width and depth of the slot; 2. Measure the actual slot length, width and depth, subtract them from the slot length, width and depth of the input drawing and take the absolute value; 3. Determine whether the actual slot length, width and depth meet the slot requirements: If the absolute value of the difference between the slot length and the drawing length, the absolute value of the difference between the slot width and the drawing width, and the absolute value of the difference between the slot depth and the drawing depth do not exceed the set threshold, it means that the actual slot length, width, and depth meet the slot requirements; If at least one of the absolute value of the difference between the slot length and the drawing length, the absolute value of the difference between the slot width and the drawing width, and the absolute value of the difference between the slot depth and the drawing depth exceeds the set threshold, the slot length, width, and depth will be marked as not meeting the requirements and will be processed by subsequent engineers after the slotting is completed; Sixth, after the slotting operation is completed, the distance between the next slotting position and the current robot position is calculated according to the drawing, recorded as L1, and the same distance L1 is measured by laser radar, and the wall point L1 away from the current robot is identified by binocular vision, recorded as C; Seventh, the slotting robot processes and analyzes the obstacle data of the room plane scanned by the laser radar, calculates a reasonable obstacle avoidance path, and reaches the next slotting point C along the planned path; Repeat steps 3 to 7 above until the grooving of the entire room is completed.

[0048] When the grooving operation of the entire room is completed, the engineer reads the grooving robot data and finds out the grooves whose length, width and depth do not meet the grooving requirements. The engineer should handle it by himself.

[0049] Therefore, the present invention adopts the above-mentioned intelligent grooving robot based on binocular vision and laser radar system, and applies the common AVG trolley guidance technology to the grooving robot. Then, when the grooving robot is unmanned, the binocular vision system based on laser radar data completes the correction of the grooving depth, length and width by processing the laser radar data, judges the posture relationship between the mobile robot and the wall, and estimates the inclination angle of the robot relative to the wall according to the laser radar data, so as to adjust the posture relationship of the robot through real-time feedback, and then plans the path from one work position to another according to the laser radar data, and arrives at the next work location to perform grooving operations, thereby solving the technical problems existing in the existing construction grooving robots and being suitable for large-scale promotion and use.

[0050] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. An intelligent slotting robot based on binocular vision and laser radar system, characterized in that: It includes a mobile flat plate, a binocular vision and laser radar system and a dust collection device. A mobile mechanism is arranged at the bottom of the mobile flat plate. The mobile mechanism includes universal wheels symmetrically arranged at the four corners of the bottom of the mobile flat plate and a brake mechanism arranged inside the universal wheels. A multi-joint mechanical arm is arranged at the top of the mobile flat plate. A plurality of flip driving mechanisms connected to the multi-joint mechanical arm are arranged on the mobile flat plate. The binocular vision and laser radar system is used to adjust the posture relationship of the robot relative to the wall and to correct the length, width and depth of the slot; The posture relationship of the robot relative to the wall is adjusted by obtaining distance data through laser radar scanning, and analyzing and judging the posture relationship between the robot and the wall at the current moment.

2. The intelligent slotting robot based on binocular vision and laser radar system according to claim 1 is characterized in that: The multi-joint mechanical arm comprises three sections of hollow cylindrical mechanical arms, and the mechanical arms are connected by the flip driving mechanism; The head of the multi-joint mechanical arm is provided with a slotting mechanism, which includes a slotting arm and a double saw blade rotatably arranged at the end of the slotting arm, a hollow shaft is arranged at the center of the double saw blade, and a slotting motor is fixedly arranged on the hollow shaft.

3. The intelligent slotting robot based on binocular vision and laser radar system according to claim 2 is characterized in that: The dust collection device comprises a dust collector, a dust collection nozzle, a dust conveying pipeline and a detachable dust storage box, wherein the detachable dust storage box is provided with a safety light; The vacuum cleaner is arranged on the mobile flat plate, the vacuum pipe openings are arranged on both sides of the slotting mechanism, and the dust conveying pipeline is arranged inside the multi-joint mechanical arm.

4. The intelligent slotting robot based on binocular vision and laser radar system according to claim 3 is characterized in that: The dust conveying pipeline is connected to the dust suction pipe port through a three-way valve, the valve ports of the three-way valve on the same line are connected to the dust suction pipe port, the remaining valve port of the three-way valve is connected to the dust conveying pipeline, and the detachable dust storage box is arranged at the bottom of the mobile flat plate.

5. The intelligent slotting robot based on binocular vision and laser radar system according to claim 4 is characterized in that: The dust conveying pipeline is a plastic flexible pipeline with a smooth inner wall.

6. The intelligent slotting robot based on binocular vision and laser radar system according to claim 5, characterized in that: The binocular vision and laser radar system includes a control platform, an optical sensor and a CCD camera, fixed laser radar transmitting devices A and B, universal wheels and a braking mechanism; The optical sensor and the CCD camera are arranged outside the dust suction pipe opening, the fixed laser radar transmitting devices A and B are arranged on the top of the mobile flat plate, and the control pan / tilt is arranged on the top of the mobile flat plate; The control platform is provided with a visual guidance control board for controlling the mobile flat panel, the multi-joint mechanical arm, the optical sensor and the CCD camera, and the visual guidance control board is provided with a central processing unit.

7. The intelligent slotting robot based on binocular vision and laser radar system according to claim 6 is characterized in that: The specific process of analyzing and judging the posture relationship between the robot and the wall at the current moment is as follows: S1. The side of the slotting robot with the laser radar fixed faces the wall, and the laser radar is used to measure the distance between points A and B to obtain the distance between points A and B and the wall along the fixed direction. S2. Determine whether the distance from points A and B to the wall along a fixed direction is a valid distance: If the distance from points A and B to the wall along a fixed direction is less than the robot's maximum slotting operation range and is between the maximum scanning range and the minimum scanning range of the laser radar, then it is an effective distance; If the distance from points A and B to the wall along a fixed direction is greater than the robot's maximum slotting range and is not between the maximum scanning range and the minimum scanning range of the laser radar, it is an invalid distance and needs to be remeasured; S3, denote the distances from points A and B to the wall along a fixed direction as La and Lb respectively, denote the vertical distance between points A and B as L, denote the absolute value of the difference between the distances from points A and B to the wall along a fixed direction as C, and denote the set threshold as e; If C is less than the set threshold e, it is judged that the robot is parallel to the wall at this time; If C is greater than the set threshold e, and La is greater than Lb, then it is determined that the robot is tilted to the left relative to the wall; If C is greater than or equal to the set threshold e, and La is less than Lb, then it is determined that the robot is tilted to the right relative to the wall; S4, estimate the current inclination angle of the robot relative to the wall, and record the inclination angle as θ; The inclination angle θ is equal to the arc tangent of the absolute value C of the difference between the distances from points A and B to the wall along a fixed direction divided by the vertical distance L between points A and B. The expression is: ； Where θ is the current tilt angle of the robot relative to the wall, C is the absolute value of the difference between the distances of points A and B to the wall along a fixed direction, and L is the vertical distance between points A and B. S5: Adjust the robot’s posture angle relative to the wall in real time until it is parallel; S6. Calibrate the length, width and depth of the slot, and compare the length, width and depth obtained by the optical sensor and CCD camera with the length, width and depth of the slot input in the drawing: The absolute value of the difference between the slot length and the drawing length, the absolute value of the difference between the slot width and the drawing width, and the absolute value of the difference between the slot depth and the drawing depth shall not exceed the set threshold.

8. The intelligent slotting robot based on binocular vision and laser radar system according to claim 7 is characterized in that: The initial position of the robot is between the maximum scanning range and the minimum scanning range of the laser radar, and the distance between the robot and the wall to be grooved does not exceed the maximum groove operation range of the robot.

9. The intelligent slotting robot based on binocular vision and laser radar system according to claim 8, characterized in that: A laser radar transmitter is fixed at points A and B on the mobile flat plate to measure the distance from the two points to the wall along a fixed direction, thereby adjusting the posture relationship of the robot relative to the wall.

Images