阅读说明：本技术 动态自适应定位方法、定位系统、机器人及存储介质 (Dynamic self-adaptive positioning method, positioning system, robot and storage medium ) 是由 廖志祥 郭震 于 2021-09-14 设计创作，主要内容包括：本发明提供了一种动态自适应定位方法、定位系统、机器人及存储介质,包括如下步骤：步骤1：控制复合型机器人的移动机器人模块SLAM建图；步骤2：根据建好的图,控制复合型机器人运动至工作地点附近；步骤3：复合型机器人到达工作地点附近后,控制复合型机器人的视觉模块识别关键特征点；步骤4：根据识别到的关键特征点和复合型机器人的机械臂模块工作空间限制优化复合型机器人的位姿,得到优化位姿；步骤5：控制复合型机器人的运动至优化位姿处。本发明提高部署效率和工作效率,提升复合型机器人智能性和适应性。(The invention provides a dynamic self-adaptive positioning method, a positioning system, a robot and a storage medium, comprising the following steps: step 1: controlling a mobile robot module SLAM of the composite robot to build a map; step 2: controlling the composite robot to move to the position near the working place according to the established diagram; and step 3: after the composite robot reaches the position near the working place, a vision module of the composite robot is controlled to identify key characteristic points; and 4, step 4: optimizing the pose of the composite robot according to the identified key characteristic points and the limit of the working space of the mechanical arm module of the composite robot to obtain an optimized pose; and 5: and controlling the movement of the composite robot to an optimized pose. The invention improves the deployment efficiency and the working efficiency and improves the intelligence and the adaptability of the composite robot.)

1. A dynamic adaptive positioning method is characterized by comprising the following steps:

step 1: controlling a mobile robot module SLAM of the composite robot to build a map;

step 2: controlling the composite robot to move to the position near the working place according to the established diagram;

and step 3: after the composite robot reaches the position near the working place, a vision module of the composite robot is controlled to identify key characteristic points;

and 4, step 4: optimizing the pose of the composite robot according to the identified key characteristic points and the limit of the working space of the mechanical arm module of the composite robot to obtain an optimized pose;

and 5: and controlling the movement of the composite robot to an optimized pose.

2. The dynamic adaptive positioning method according to claim 1, wherein the step 1 specifically comprises: and controlling the mobile robot to move in the full map and traverse all spaces in the full map, establishing a plane map of the working space of the mobile robot according to data returned by the laser radar, and simply marking nearby a working place on the map.

3. The dynamic adaptive positioning method according to claim 1, wherein the step 2 specifically comprises: and controlling the mobile robot to move to the vicinity of the working point according to the navigation control algorithm.

4. The dynamic adaptive positioning method according to claim 1, wherein the step 3 specifically comprises: after the mobile robot moves to a working point, the vision module acquires image information of the working table, and key characteristic points of the working table are acquired by using a three-dimensional point cloud matching technology.

5. The dynamic adaptive positioning method according to claim 1, wherein the step 4 specifically comprises:

the pose of the robot is represented by [ x y theta ]]^TThree parameter decisions, wherein x and y represent the position coordinates of the robot on the plane map in step 2, and theta represents the posture of the robot on the plane map in step 2;

setting traversal step length, traversing all poses of the robot within the pose range, obtaining the distance between the key feature points and the mechanical arm base under each pose working condition, obtaining the maximum value of the distances between all the key feature points and the mechanical arm base under each working condition, and obtaining the maximum distances under a series of different pose working conditions;

and obtaining the minimum value of the distances from all key characteristic points to the mechanical arm base under a series of working conditions with different poses according to the method, wherein the pose of the robot corresponding to the minimum value is the optimized pose near the working point.

6. The dynamic adaptive positioning method according to claim 1, wherein the step 5 specifically comprises: and the mechanical arm module of the composite robot transmits the optimized pose obtained by solving to the mobile robot module, and the mobile robot module controls the composite robot to reach the optimized pose.

7. The dynamic adaptive positioning method according to claim 1, wherein the hybrid robot comprises the following modules:

a mobile robot module: the mobile robot module comprises a mobile robot, a laser radar and a driving motor, wherein the laser radar and the driving motor are used for supporting the mobile robot to independently complete SLAM, navigation and motion planning;

a mechanical arm module: the mechanical arm module comprises a mechanical arm and a clamping jaw and is used for grabbing and transferring objects;

a vision module: the visual module is a depth camera and is used for providing point cloud data of a target plane and a three-dimensional plane and acquiring target characteristic points according to the point cloud data.

8. A dynamic adaptive positioning system, comprising the following modules:

a drawing establishing module: controlling a mobile robot module SLAM of the composite robot to build a map;

a moving module: controlling the composite robot to move to the position near the working place according to the established diagram;

an identification module: after the composite robot reaches the position near the working place, a vision module of the composite robot is controlled to identify key characteristic points;

a pose module: optimizing the pose of the composite robot according to the identified key characteristic points and the limit of the working space of the mechanical arm module of the composite robot to obtain an optimized pose;

a motion module: and controlling the movement of the composite robot to an optimized pose.

9. A robot, characterized in that said compound robot comprises a processor and a memory, said memory storing a plurality of instructions, said processor implementing the dynamic adaptive positioning method according to any one of claims 1 to 7 by executing said plurality of instructions.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the dynamic adaptive positioning method of any one of claims 1 to 7.

Technical Field

The invention relates to the technical field of robots, in particular to a dynamic self-adaptive positioning method, a positioning system, a robot and a storage medium, and particularly relates to a dynamic self-adaptive positioning method of a composite robot.

Background

The composite robot is a novel robot integrating two functions of a mobile robot and a universal mechanical arm, the mobile robot replaces the walking function of legs and feet of a human, and the universal mechanical arm replaces the grabbing function of arms of the human. Therefore, the composite robot integrates the advantages of two types of robots, the mobile robot can only complete single tasks such as fixed-point patrol, alarm and the like, the universal mechanical arm can only complete fixed actions such as grabbing, stacking and spraying, when the two types of robots are combined into the composite robot, the advantages of the two types of robots are added to achieve the effect of 1+1>2, and the composite robot can be applied to more complex task scenes to switch back and forth between different working places to complete various types of tasks.

In general, all complex robots need to build a map in advance and mark different working places, and when different working tasks are switched, the mobile chassis is controlled to move to the designated working place and start working. However, this solution is extremely poor in versatility and adaptability, and when the target on the work table is changed, the robot arm may not be able to complete the work, resulting in an interruption of the work task. Therefore, an adaptive positioning method is designed to help the composite robot to perform pose fine adjustment near the working table surface so as to help the mechanical arm to obtain a good working environment, which is a major trend in development of the composite robot in the future.

Patent document No. CN110530375B discloses a robot adaptive positioning method, a positioning device, a robot, and a storage medium. The method comprises the following steps: acquiring linear characteristics of the surrounding environment of the robot to obtain a first linear characteristic set, wherein the linear characteristics comprise the starting endpoint position and the ending endpoint position of a line segment; performing mean clustering on the linear features in the first linear feature set to obtain a plurality of clustering subsets; performing linear fitting on each clustering subset; and determining the position of the robot according to the result of the straight line fitting. However, the patent document still has the defect that when the target on the working table is changed, the mechanical arm may not complete the work, and the work task is interrupted.

Disclosure of Invention

In view of the defects in the prior art, the present invention provides a dynamic adaptive positioning method, a positioning system, a robot and a storage medium.

The invention provides a dynamic self-adaptive positioning method, which comprises the following steps:

step 1: controlling a mobile robot module SLAM of the composite robot to build a map;

step 2: controlling the composite robot to move to the position near the working place according to the established diagram;

and step 3: after the composite robot reaches the position near the working place, a vision module of the composite robot is controlled to identify key characteristic points;

and 4, step 4: optimizing the pose of the composite robot according to the identified key characteristic points and the limit of the working space of the mechanical arm module of the composite robot to obtain an optimized pose;

and 5: and controlling the movement of the composite robot to an optimized pose.

Preferably, the step 1 specifically comprises: and controlling the mobile robot to move in the full map and traverse all spaces in the full map, establishing a plane map of the working space of the mobile robot according to data returned by the laser radar, and simply marking nearby a working place on the map.

Preferably, the step 2 specifically comprises: and controlling the mobile robot to move to the vicinity of the working point according to the navigation control algorithm.

Preferably, the step 3 specifically comprises: after the mobile robot moves to a working point, the vision module acquires image information of the working table, and key characteristic points of the working table are acquired by using a three-dimensional point cloud matching technology.

Preferably, the step 4 specifically comprises:

the pose of the robot is represented by [ x y theta ]]^TThree parameter decisions, wherein x and y represent the position coordinates of the robot on the plane map in step 2, and theta represents the posture of the robot on the plane map in step 2;

setting traversal step length, traversing all poses of the robot within the pose range, obtaining the distance between the key feature points and the mechanical arm base under each pose working condition, obtaining the maximum value of the distances between all the key feature points and the mechanical arm base under each working condition, and obtaining the maximum distances under a series of different pose working conditions;

and obtaining the minimum value of the distances from all key characteristic points to the mechanical arm base under a series of working conditions with different poses according to the method, wherein the pose of the robot corresponding to the minimum value is the optimized pose near the working point.

Preferably, the step 5 specifically comprises: and the mechanical arm module of the composite robot transmits the optimized pose obtained by solving to the mobile robot module, and the mobile robot module controls the composite robot to reach the optimized pose.

Preferably, the composite robot comprises the following modules:

a mobile robot module: the mobile robot module comprises a mobile robot, a laser radar and a driving motor, wherein the laser radar and the driving motor are used for supporting the mobile robot to independently complete SLAM, navigation and motion planning;

a mechanical arm module: the mechanical arm module comprises a mechanical arm and a clamping jaw and is used for grabbing and transferring objects;

a vision module: the visual module is a depth camera and is used for providing point cloud data of a target plane and a three-dimensional plane and acquiring target characteristic points according to the point cloud data.

The invention also provides a dynamic self-adaptive positioning system, which comprises the following modules:

a drawing establishing module: controlling a mobile robot module SLAM of the composite robot to build a map;

a moving module: controlling the composite robot to move to the position near the working place according to the established diagram;

an identification module: after the composite robot reaches the position near the working place, a vision module of the composite robot is controlled to identify key characteristic points;

a pose module: optimizing the pose of the composite robot according to the identified key characteristic points and the limit of the working space of the mechanical arm module of the composite robot to obtain an optimized pose;

a motion module: and controlling the movement of the composite robot to an optimized pose.

The invention also provides a robot, which comprises a processor and a memory, wherein the memory stores a plurality of instructions, and the processor realizes the dynamic self-adaptive positioning method by executing the instructions.

The present invention also provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the above-mentioned dynamic adaptive positioning method.

Compared with the prior art, the invention has the following beneficial effects:

1. the invention improves the deployment efficiency, and the working range of the mechanical arm needs to be fully considered by manpower when the existing composite robot is positioned, and the working place of the mobile robot is determined on the basis of the working range;

2. the invention improves the working efficiency, can actively adapt to the change of the working table surface, automatically adjusts the pose of the mobile robot aiming at the slow change of the work and reduces the work interruption rate;

3. the invention improves the intelligence and the adaptability of the composite robot.

Drawings

Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:

FIG. 1 is a schematic view of a composite robot according to the present invention;

FIG. 2 is a SLAM map of the composite robot of the present invention;

fig. 3 is a diagram illustrating a layout of a robot arm workspace of the hybrid robot of the present invention.

Detailed Description

The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.

Example 1:

the invention provides a dynamic self-adaptive positioning method, which comprises the following steps:

step 1: controlling a mobile robot module SLAM of the composite robot to build a map, wherein the step 1 specifically comprises the following steps: and manually controlling the mobile robot to move in the full map and traverse all spaces in the full map, establishing a plane map of the working space of the mobile robot according to data returned by the laser radar, and simply marking the position near the working place on the map.

Step 2: controlling the composite robot to move to the position near the working place according to the established diagram, wherein the step 2 specifically comprises the following steps: and controlling the mobile robot to move to the vicinity of the working point according to the navigation control algorithm.

And step 3: after the composite robot reaches the place nearby, the vision module of the control composite robot recognizes key characteristic points, and step 3 specifically is: after the mobile robot moves to a working point, the vision module acquires image information of the working table, and key characteristic points of the working table are acquired by using a three-dimensional point cloud matching technology.

And 4, step 4: optimizing the pose of the composite robot according to the identified key characteristic points and the limitation of the working space of the mechanical arm module of the composite robot to obtain an optimized pose, wherein the step 4 specifically comprises the following steps: the pose of the robot is represented by [ x y theta ]]^TThree parameter decisions, wherein x and y represent the position coordinates of the robot on the plane map in step 2, and theta represents the posture of the robot on the plane map in step 2; setting traversal step length, traversing all poses of the robot within the pose range, obtaining the distance between the key feature points and the mechanical arm base under each pose working condition, obtaining the maximum value of the distances between all the key feature points and the mechanical arm base under each working condition, and obtaining the maximum distances under a series of different pose working conditions; working out all working conditions under a series of different poses according to the methodAnd the minimum value of the distance between the key characteristic point and the mechanical arm base is the optimal pose near the working point.

And 5: controlling the movement of the composite robot to an optimized pose, wherein the step 5 specifically comprises the following steps: and the mechanical arm module of the composite robot transmits the optimized pose obtained by solving to the mobile robot module, and the mobile robot module controls the composite robot to reach the optimized pose.

The composite robot comprises the following modules:

a mobile robot module: the mobile robot module comprises a mobile robot, a laser radar and a driving motor, wherein the laser radar and the driving motor are used for supporting the mobile robot to independently complete SLAM, navigation and motion planning;

a mechanical arm module: the mechanical arm module comprises a mechanical arm and a clamping jaw and is used for grabbing and transferring objects;

a vision module: the vision module is a depth camera and is used for providing point cloud data of a target plane and a three-dimensional space and acquiring target characteristic points according to the point cloud data.

The embodiment also provides a robot, wherein the composite robot comprises a processor and a memory, the memory stores a plurality of instructions, and the processor implements the dynamic self-adaptive positioning method by executing the plurality of instructions.

The present embodiment also provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the above dynamic adaptive positioning method.

Example 2:

the dynamic adaptive positioning system provided by the embodiment comprises the following modules:

a drawing establishing module: controlling a mobile robot module SLAM of the composite robot to build a map;

a moving module: controlling the composite robot to move to the position near the working place according to the established diagram;

an identification module: after the composite robot reaches the position near the working place, a vision module of the composite robot is controlled to identify key characteristic points;

a pose module: optimizing the pose of the composite robot according to the identified key characteristic points and the limit of the working space of the mechanical arm module of the composite robot to obtain an optimized pose;

a motion module: and controlling the movement of the composite robot to an optimized pose.

Example 3:

those skilled in the art will understand this embodiment as a more specific description of embodiments 1 and 2.

The composite robot of the embodiment is composed of three modules: the robot system comprises a mobile robot module, a mechanical arm module and a vision module. As shown in fig. 1, the three modules are all modules with independent working performance, and corresponding tools are also distributed in each module.

A mobile robot module: the mobile robot module is provided with universal equipment such as a laser radar and a driving motor, and the mobile robot can be guaranteed to independently complete common functions such as SLAM, navigation and motion planning.

A mechanical arm module: the mechanical arm module comprises a clamping jaw except the mechanical arm body, and the mechanical arm can complete the operations of grabbing, transferring objects and the like.

A vision module: the vision module mainly comprises a depth camera, can provide point cloud data of a target plane and a solid, and can acquire target feature points according to the data.

The adaptive positioning method provided in this embodiment is based on the SLAM technology of the mobile robot module and the three-dimensional point cloud matching technology of the vision module, both of which are mature and stable technologies in the industry, and therefore, detailed description is omitted.

The method can be summarized into the following 5 steps:

step 1: mobile robot SLAM map building;

step 2: the mobile robot moves to the vicinity of a work place;

and step 3: the vision module identifies key feature points;

and 4, step 4: optimizing the pose of the mobile robot according to the limit of the working space of the mechanical arm;

and 5: and moving the mobile robot to an optimized pose.

Wherein the detailed content of the step 1 is as follows: the composite robot is manually controlled to move in the full map and traverse all spaces in the full map, a plane map of the working space of the mobile robot can be established according to data returned by the laser radar, and simple marking is carried out near the working place on the map, as shown in fig. 2.

Wherein the detailed content of the step 2 is as follows: the method controls the composite robot to move to the position near the working point according to the navigation control algorithm, the navigation control algorithm is not particularly described, and an A algorithm, a D algorithm, an artificial potential field method and the like which are commonly used in the industry can be used for controlling the composite robot involved in the patent.

Wherein the detailed content of the step 3 is as follows: after the composite robot moves to the working point, the vision module can acquire the image information of the working table, and the key characteristic points of the working table are acquired by using a three-dimensional point cloud matching technology.

Wherein the detailed content of the step 4 is as follows: the working space of the mechanical arm is determined by the lengths of all the connecting rods of the mechanical arm and the motion range of all the joints, so that after one mechanical arm is designed and produced, the working space is determined, generally speaking, for a common spatial six-axis mechanical arm, the working space is a sphere, the radius of the sphere is determined by the lengths of all the connecting rods of the mechanical arm, the working space of the mechanical arm can be divided into a smart working space and a reachable working space, the smart working space means that the mechanical arm can reach the position in multiple postures, the reachable working space means that the mechanical arm can only reach the position in one posture, and the distribution of the working space of the mechanical arm is shown in fig. 3.

The pose of the mobile robot is represented by [ x y theta ]]^TThree parameters are determined, wherein x and y represent the position of the composite robot on the plane map of fig. 2, and θ represents the attitude of the composite robot on the plane map of fig. 2. Different mobile robot poses determine whether the working space of the mechanical arm covers key feature points on the working table. Due to obstacle restrictions on the planar map, thereforeWhen the working point finely adjusts the pose of the mobile robot, x, y and theta are limited by the maximum value and the minimum value, so that the set traversal step length delta can be considered, all poses of the mobile robot are traversed within the pose range of the mobile robot, the distance between a key characteristic point and a mechanical arm base can be obtained under each pose working condition, the maximum value of the distance between all key characteristic points and the base can be obtained under each working condition, and the maximum distances under a series of working conditions with different poses can be obtained according to the scheme: { D_max1 … D_maxnAnd further, obtaining the minimum value of the series of distances, wherein the pose of the mobile robot corresponding to the minimum value is the optimized pose near the working point.

Wherein the detailed content of the step 5 is as follows: and the mechanical arm module transmits the optimized pose obtained by solving to the mobile robot module, and the mobile robot module controls the composite robot to reach the optimized pose.

The invention discloses a dynamic self-adaptive positioning method for a composite robot, which avoids the situation that a work task is interrupted due to the change of a working table surface, improves the environmental adaptability of the composite robot, can adjust the pose of the mobile robot according to different complex environments, and is convenient for a mechanical arm to complete the work task.

Those skilled in the art will appreciate that, in addition to implementing the system and its various devices, modules, units provided by the present invention as pure computer readable program code, the system and its various devices, modules, units provided by the present invention can be fully implemented by logically programming method steps in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system and various devices, modules and units thereof provided by the invention can be regarded as a hardware component, and the devices, modules and units included in the system for realizing various functions can also be regarded as structures in the hardware component; means, modules, units for performing the various functions may also be regarded as structures within both software modules and hardware components for performing the method.

The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.