Cleaning robot zero position and hand-eye matrix calibration method and system
By using an automated method for zero-position and hand-eye matrix calibration of the cleaning robot, the problems of zero-position and hand-eye matrix offset of the robotic arm were solved, realizing a low-cost and automated calibration process and restoring the cleaning effect of the robotic arm.
Patent Information
- Application Number
- CN202210668969.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-14
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2042-06-14
AI Technical Summary
During use, the cleaning effect of cleaning robots decreases due to the zero-position deviation of the robotic arm or the deviation of the hand-eye matrix, and existing technologies make it difficult to calibrate them quickly and effectively.
An automated method for zero-position and hand-eye matrix calibration of a cleaning robot is adopted. The robot arm moves to multiple points to take pictures and record the joint angles. The least squares method is used to calculate the joint zero-position deviation and hand-eye matrix deviation, and the calibration process is completed automatically.
It achieves low-cost automatic calibration without human intervention, restoring the accuracy of the robotic arm and improving cleaning results.
Smart Images

Figure CN115194761B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of robot calibration, and in particular to a cleaning robot zero position and hand-eye matrix calibration method and system. Background Art
[0002] The cleaning robot system mainly includes a mobile chassis module, an arm module, and a vision module. The arm consists of 6 degrees of freedom joints, and a depth camera is installed at the end of the arm. After the robot has been used for a certain period of time, due to collisions and other reasons, the zero position of the robot arm may be offset, or the camera may be offset relative to the end of the robot arm, and the arm may not be able to accurately reach the specified position, affecting the cleaning effect. A method for quickly calibrating the zero position of the robot arm and the hand-eye matrix is needed.
[0003] Patent document CN111390901A (application number: 201910002044.0) discloses a method and a device for automatic calibration of a robotic arm. The calibration method includes the following steps: establishing a pixel coordinate system generated by a camera and establishing a geodetic coordinate system based on the base of the robotic arm; calibrating the geodetic coordinate system and the pixel coordinate system to obtain the scale parameters used to convert the geodetic coordinate system and the pixel coordinate system and the range of motion of the robotic arm that can capture the marker; obtaining the point position information of the camera directly above the marker under at least three different rotation angles of the robotic arm; calculating the relative position parameters of the center position of the camera and the position of the end of the axis system; obtaining the point position information of the marking point at different positions under the same rotation angle of the robotic arm, where the marking point is a fixed point on the marker; and calculating the coordinate correction parameters based on the point position information. Summary of the invention
[0004] In view of the defects in the prior art, the object of the present invention is to provide a cleaning robot zero position and hand-eye matrix calibration method and system.
[0005] A cleaning robot zero position and hand-eye matrix calibration method provided by the present invention comprises:
[0006] Step S1: The robot arm moves n points according to the preset program, takes a photo of the visual mark at each point and records the current robot joint angle θ;
[0007] Step S2: Calculate the position and orientation of the visual marker relative to the camera coordinate system based on the visual marker image obtained by taking a photo The position of the robot end relative to the base coordinate system And the position of the camera relative to the end of the robot
[0008] Step S3: According to the position of the visual landmark relative to the camera coordinate system The position of the robot end relative to the base coordinate system And the position of the camera relative to the end of the robot The least square method is used to solve the joint zero position deviation Δθ and the hand-eye matrix deviation Δδ;
[0009] Step S4: Complete the calibration of the robot zero position and hand-eye matrix according to the joint zero position deviation Δθ and the hand-eye matrix deviation Δδ.
[0010] Preferably, the step S2 adopts:
[0011]
[0012] Among them, θ represents the robot joint angle, and Δθ represents the robot zero position deviation that needs to be calibrated.
[0013] Preferably, the step S2 adopts:
[0014]
[0015] Among them, (x, y, z, α, β, γ) are the parameters before the camera moves, and Δδ = (Δx, Δy, Δz, Δα, Δβ, Δγ) is the hand-eye matrix deviation.
[0016] Preferably, the step S3 adopts:
[0017]
[0018] Among them, n means moving the nth point.
[0019] Preferably, step S4 adopts: θ+Δθ, x+Δx, y+Δy, z+Δz, α+Δα, β+Δβ, γ+Δγ.
[0020] A cleaning robot zero position and hand-eye matrix calibration system provided by the present invention comprises:
[0021] Module M1: The robot moves n points according to the preset program, takes a photo of the visual mark at each point and records the current robot joint angle θ;
[0022] Module M2: Calculate the position of the visual landmark relative to the camera coordinate system based on the visual landmark image obtained by taking a photo The position of the robot end relative to the base coordinate system And the position of the camera relative to the end of the robot
[0023] Module M3: Position and orientation of visual landmarks relative to the camera coordinate system The position of the robot end relative to the base coordinate system And the position of the camera relative to the end of the robot The least square method is used to solve the joint zero position deviation Δθ and the hand-eye matrix deviation Δδ;
[0024] Module M4: Complete the calibration of the robot zero position and hand-eye matrix according to the joint zero position deviation Δθ and the hand-eye matrix deviation Δδ.
[0025] Preferably, the module M2 adopts:
[0026]
[0027] Among them, θ represents the robot joint angle, and Δθ represents the robot zero position deviation that needs to be calibrated.
[0028] Preferably, the module M2 adopts:
[0029]
[0030] Among them, (x, y, z, α, β, γ) are the parameters before the camera moves, and Δδ = (Δx, Δy, Δz, Δα, Δβ, Δγ) is the hand-eye matrix deviation.
[0031] Preferably, the module M3 adopts:
[0032]
[0033] Among them, n means moving the nth point.
[0034] Preferably, the module M4 adopts: θ+Δθ, x+Δx, y+Δy, z+Δz, α+Δα, β+Δβ, γ+Δγ.
[0035] Compared with the prior art, the present invention has the following beneficial effects: the present invention has low cost, does not rely on human participation in operation, and the robot automatically runs a preset program to complete the calibration process. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:
[0037] Figure 1 Schematic diagram of the cleaning robot's zero position and hand-eye matrix calibration. DETAILED DESCRIPTION
[0038] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.
[0039] Example 1
[0040] The present invention provides a method for calibrating the zero position and hand-eye matrix of a cleaning robot. The method provided by the present invention solves the problem that after the end precision of a robotic arm is lost, the robotic arm automatically moves to several preset points and quickly retrieves the zero position and the hand-eye matrix through calculation.
[0041] The present invention provides a cleaning robot zero position and hand-eye matrix calibration method, such as Figure 1 As shown, including:
[0042] Step 1: Set the visual mark on the base of the cleaning robot, fix the visual mark to the robot base, and ensure the relative position relationship between the visual mark and the robot base coordinate system constant.
[0043] Step 2: The relative relationship between the visual mark and the base remains unchanged. The robot arm moves to n points (n ≥ 24) according to the preset program. The visual mark is photographed at each point and the current robot joint angle θ is recorded.
[0044] Step 3: Calculate the position of the sign relative to the camera coordinate system based on the image of the visual sign The position of the robot end relative to the base coordinate system The position of the camera relative to the robot end is the hand-eye matrix Where (x, y, z, α, β, γ) is the parameter before the camera moves, and Δδ = (Δx, Δy, Δz, Δα, Δβ, Δγ) is the hand-eye matrix deviation. Where θ represents the robot joint angle, and Δθ represents the robot zero position deviation that needs to be calibrated;
[0045] Step 4: Position relationship of visual landmarks relative to robot base coordinates Due to the relationship between the postures during multiple measurements According to the two sets of data, we can get For n sets of data, we can get n / 2 sets of the above equations
[0046] Step 5: Use the least squares method to obtain the joint zero position deviation Δθ and the hand-eye matrix deviation Δδ.
[0047] Step 6: Add the joint zero position deviation to the robot joint angle and the hand-eye matrix deviation to the hand-eye matrix parameters to complete the calibration of the robot zero position and hand-eye matrix.
[0048] The present invention provides a cleaning robot zero position and hand-eye matrix calibration system, such as Figure 1 As shown, including:
[0049] Module 1: Set a visual mark on the base of the cleaning robot, fix the visual mark to the robot base, and ensure the relative position relationship between the visual mark and the robot base coordinate system constant.
[0050] Module 2: The relative relationship between the visual mark and the base remains unchanged. The robot arm moves to n points (n≥24) according to the preset program. The visual mark is photographed at each point and the current robot joint angle θ is recorded.
[0051] Module 3: Calculate the position of the sign relative to the camera coordinate system based on the image of the visual sign The position of the robot end relative to the base coordinate system The position of the camera relative to the robot end is the hand-eye matrix Where (x, y, z, α, β, γ) is the parameter before the camera moves, and Δδ = (Δx, Δy, Δz, Δα, Δβ, Δγ) is the hand-eye matrix deviation. Where θ represents the robot joint angle, and Δθ represents the robot zero position deviation that needs to be calibrated;
[0052] Module 4: Relationship between visual landmarks and robot base coordinates Due to the relationship between the postures during multiple measurements According to the two sets of data, we can get For n sets of data, we can get n / 2 sets of the above equations
[0053] Module 5: Use the least squares method to obtain the joint zero position deviation Δθ and the hand-eye matrix deviation Δδ.
[0054] Module 6: Add the joint zero position deviation to the robot joint angle and the hand-eye matrix deviation to the hand-eye matrix parameters to complete the calibration of the robot zero position and hand-eye matrix.
[0055] In the description of the present application, it should be understood that the terms "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.
[0056] Those skilled in the art know that, in addition to implementing the system, device and its various modules provided by the present invention in a purely computer-readable program code, it is entirely possible to implement the same program in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers and embedded microcontrollers by logically programming the method steps. Therefore, the system, device and its various modules provided by the present invention can be considered as a hardware component, and the modules included therein for implementing various programs can also be considered as structures within the hardware component; the modules for implementing various functions can also be considered as both software programs for implementing the method and structures within the hardware component.
[0057] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.
Claims
1. A cleaning robot zero position and hand-eye matrix calibration method, characterized in that: include: Step S1: The robot arm moves n points according to the preset program, takes a photo of the visual mark at each point and records the current robot joint angle θ; Step S2: Calculate the position and orientation of the visual marker relative to the camera coordinate system based on the visual marker image obtained by taking a photo The position of the robot end relative to the base coordinate system And the position of the camera relative to the end of the robot Step S3: According to the position of the visual landmark relative to the camera coordinate system The position of the robot end relative to the base coordinate system And the position of the camera relative to the end of the robot The least square method is used to solve the joint zero position deviation Δθ and the hand-eye matrix deviation Δδ; Step S4: completing the calibration of the robot zero position and the hand-eye matrix according to the joint zero position deviation Δθ and the hand-eye matrix deviation Δδ; The step S2 adopts: Among them, θ represents the robot joint angle, and Δθ represents the robot zero position deviation that needs to be calibrated; The step S2 adopts: Among them, (x, y, z, α, β, γ) are the parameters before the camera moves, and Δδ = (Δx, Δy, Δz, Δα, Δβ, Δγ) is the hand-eye matrix deviation; The step S3 adopts: Among them, n means moving the nth point; The step S4 adopts: θ+Δθ, x+Δx, y+Δy, z+Δz, α+Δα, β+Δβ, γ+Δγ.
2. A cleaning robot zero position and hand-eye matrix calibration system, characterized in that: include: Module M1: The robot moves n points according to the preset program, takes a photo of the visual mark at each point and records the current robot joint angle θ; Module M2: Calculate the position of the visual landmark relative to the camera coordinate system based on the visual landmark image obtained by taking a photo The position of the robot end relative to the base coordinate system And the position of the camera relative to the end of the robot Module M3: Position and orientation of visual landmarks relative to the camera coordinate system The position of the robot end relative to the base coordinate system And the position of the camera relative to the end of the robot The least square method is used to solve the joint zero position deviation Δθ and the hand-eye matrix deviation Δδ; Module M4: complete the calibration of the robot zero position and hand-eye matrix according to the joint zero position deviation Δθ and the hand-eye matrix deviation Δδ; The module M2 adopts: Among them, θ represents the robot joint angle, and Δθ represents the robot zero position deviation that needs to be calibrated; The module M2 adopts: Among them, (x, y, z, α, β, γ) are the parameters before the camera moves, and Δδ = (Δx, Δy, Δz, Δα, Δβ, Δγ) is the hand-eye matrix deviation; The module M3 adopts: Among them, n means moving the nth point; The module M4 adopts: θ+Δθ, x+Δx, y+Δy, z+Δz, α+Δα, β+Δβ, γ+Δγ.
