CN114224226A

CN114224226A - Obstacle avoidance cleaning robot, robot mechanical arm obstacle avoidance planning system and method

Info

Publication number: CN114224226A
Application number: CN202111583499.XA
Authority: CN
Inventors: 谢能达; 郭震
Original assignee: Shanghai Jingwu Trade Technology Development Co Ltd
Current assignee: Shanghai Jingwu Trade Technology Development Co Ltd
Priority date: 2021-12-22
Filing date: 2021-12-22
Publication date: 2022-03-25

Abstract

The invention provides an obstacle avoidance cleaning robot, a robot mechanical arm obstacle avoidance planning system and a method, wherein the obstacle avoidance cleaning robot comprises: a man-machine interaction interface is configured on the mobile chassis, and cleaning tasks are set and displayed; the mechanical arm is formed by 6 rotary joints and is connected with the movable chassis through a mechanical arm base at the right center of the movable chassis; the visual module is arranged at the tail end of the mechanical arm and has rotational freedom degree, so that the position of an object is positioned; the tail end tool of the mechanical arm is arranged at the extending position of the tail end of the mechanical arm and is controlled by a mechanical arm controller; the industrial personal computer of the mobile chassis communicates with the mechanical arm controller to realize the cooperation of cleaning actions.

Description

Obstacle avoidance cleaning robot, robot mechanical arm obstacle avoidance planning system and method

Technical Field

The invention relates to the technical field of intelligent sweeping robots, in particular to an obstacle avoidance sweeping robot, and an obstacle avoidance planning system and method for a robot mechanical arm.

Background

At present, the cleaning workload of hotel rooms is large, the cost is high, the quality is difficult to guarantee, the hotel room cleaning is a standardized process, the cleaning work of each room is almost completely consistent, a large amount of repeatable work exists, and the robot is suitable for robot operation.

In the cleaning process of the hotel, the dust collector needs to be used for carrying out dust collection treatment on the whole room and the toilet area in the last link, and the work is time-consuming and labor-consuming. The traditional dust collector needs cleaning personnel to push the dust collector to any place, is heavy and inconvenient to clean, and greatly reduces the working efficiency;

patent document CN109144067A (application number: 201811083718.6) discloses an intelligent cleaning robot and a path planning method thereof, wherein a sensor module is used for analyzing and feeding back real-time cleaning environment information; the accurate positioning module is used for acquiring the position of the current intelligent cleaning robot on an environment map; establishing an environment map by using a geometric-topological mixed map technology, planning an optimal cleaning path by using an advanced path planning algorithm by combining the environment map and a real-time position, and uploading data to a cloud platform to realize real-time analysis, recording and control; the driving module is used for driving the intelligent cleaning robot to operate and perform cleaning work according to the planned optimal path; the man-machine interaction module can utilize a temperature and humidity sensor to combine with a camera to realize the display of the working state and performance of the intelligent cleaning robot, and can complete the remote control and the reservation function of the intelligent cleaning robot through the wifi/Bluetooth technology.

Emerging sweeping robots all have the capability to scan the entire room to establish the best route to avoid obstacles. However, due to the shape and size limitations of the sweeping robot, the robot cleaner is often stuck under a table or in narrow corners, requiring an operator to rescue. Meanwhile, for narrow areas such as a toilet and the like, the sweeping robot cannot enter special areas for dust collection due to the volume limitation of the sweeping robot, for example, the side areas of a toilet seat and the areas behind the toilet are inaccessible, and therefore the areas need to be cleaned manually.

Disclosure of Invention

Aiming at the defects in the prior art, the invention aims to provide an obstacle avoidance cleaning robot, a robot mechanical arm obstacle avoidance planning system and a robot mechanical arm obstacle avoidance planning method.

According to the invention, the obstacle avoidance cleaning robot comprises: the system comprises a mobile chassis, a mechanical arm, a visual module, a mechanical arm tail end tool, a mobile chassis industrial personal computer and a mechanical arm controller;

a man-machine interaction interface is configured on the mobile chassis, and cleaning tasks are set and displayed;

the mechanical arm is formed by 6 rotary joints and is connected with the movable chassis through a mechanical arm base at the right center of the movable chassis;

the vision module is arranged at the tail end of the mechanical arm and has rotational freedom degree, so that the object position is positioned;

the mechanical arm tail end tool is arranged at the extension part of the mechanical arm tail end and is controlled by a mechanical arm controller;

the industrial personal computer of the mobile chassis is communicated with the mechanical arm controller, so that the cooperation of cleaning actions is realized.

The invention provides a robot mechanical arm obstacle avoidance planning system, which comprises:

an application layer module: displaying and setting a cleaning task, and issuing the cleaning task to an industrial personal computer logic layer module according to a preset protocol format;

the industrial personal computer logic layer module: receiving and analyzing the cleaning task to obtain position information of the cleaning task, and sending the position information of the cleaning task to a chassis control system module according to a preset format;

a chassis control system module: receiving a fixed-point task issued by an industrial personal computer logic layer module, performing navigation planning to a fixed-point position, and reporting mobile chassis state information to the industrial personal computer logic layer module;

mechanical arm control system module: receiving a cleaning task issued by a logic layer of an industrial personal computer, communicating with a visual system module, acquiring current local map position information uploaded by the visual system module, performing path planning, speed planning and track interpolation based on visual data, and issuing the position to a servo system module;

a vision system module: receiving a photographing instruction issued by a mechanical arm control system module, identifying object position information in a current photographing view, calculating to obtain an object contour position, and reporting position data to the mechanical arm control system module;

a servo bus module: and receiving the periodic position issued by the mechanical arm control system, and driving the mechanical arm to move to the issued position.

Preferably, the robot arm control system module employs:

module M1: calculating the position of a transition point according to a local map acquired by a vision system module;

module M2: and calculating to obtain the attitude value of the transition point according to the current working plane.

Preferably, the module M2 employs: the angle between the tail end tool of the mechanical arm and the normal direction of the current working plane is within a preset range.

Preferably, when the transition point is not reachable, the mechanical arm controller system module sends information to the chassis control system module, the chassis is controlled to move a preset distance along the direction close to the obstacle, and the mechanical arm control system module performs path planning, speed planning and track interpolation again based on the current visual data and sends the position to the servo bus module.

Preferably, the robot arm controls the start and stop actions of the tool at the end of the mechanical arm during the movement process.

The obstacle avoidance planning method for the mechanical arm of the robot provided by the invention comprises the following steps:

step S1: the cleaning task is issued to an industrial personal computer logic layer module according to a preset protocol format;

step S2: the industrial personal computer logic layer module receives and analyzes the cleaning task to obtain position information of the cleaning task, and the position information of the cleaning task is issued to the chassis control system module according to a preset format;

step S3: the chassis control system module receives a fixed-point task issued by the industrial personal computer logic layer module, performs navigation planning to a fixed-point position, and reports the mobile chassis state information to the industrial personal computer logic layer module;

step S4: after receiving the information, the logic layer module of the industrial personal computer sends the task to the mechanical arm control system module;

step S5: the mechanical arm control system module receives a cleaning task issued by the logic layer of the industrial personal computer, communicates with the visual system module, acquires current local map position information uploaded by the visual system module, performs path planning, speed planning and track interpolation based on visual data, and issues the position to the servo system module;

step S6: the servo bus module receives the periodic position issued by the mechanical arm control system and drives the mechanical arm to move to the issued position.

Preferably, the vision system module: and receiving a photographing instruction sent by the mechanical arm control system module, recognizing the object position information in the current photographing view field, calculating to obtain the object contour position, and reporting the position data to the mechanical arm control system module.

Preferably, the step S5 adopts:

step S5.1: calculating the position of a transition point according to a local map acquired by a vision system module;

step S5.2: and calculating to obtain the attitude value of the transition point according to the current working plane.

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

1. the hotel cleaning robot is not available in the market at present, fills the market blank and has wide prospect;

2. the mobile robot and the industrial mechanical arm are cooperatively fused, a plurality of use scenes are newly added, the mobile robot is limited by the volume of the mobile robot, a plurality of areas cannot be reached in the movement process, the industrial mechanical arm is not provided with chassis movement planning and can only be used on a fixed production line, the mobile robot and the industrial mechanical arm are cooperated, and more use scenes are increased; the previous work which can only be manually finished can also be replaced by a robot, so that the efficiency of workers is greatly improved.

4. By adopting an MQTT protocol, the invention integrates five independent modules of an application layer, an industrial personal computer logic layer, a chassis system, a mechanical arm control system and a visual system, and effectively controls the chassis to complete a sequence of fixed-point navigation tasks and the mechanical arm to complete a cleaning task;

5. according to the invention, the map acquired by the laser radar sensor is adopted, so that the robot chassis system can be accurately positioned in a fixed-point navigation mode, and a controllable optimal navigation line is planned;

6. according to the invention, the 3D depth camera vision system is adopted to construct the local map, so that the robot arm can realize obstacle avoidance at local positions, an optimal path for bypassing obstacles in the current area is planned, and zero-hour obstacle avoidance of the robot is realized;

7. the obstacle avoidance cleaning robot can independently complete dust collection and cleaning work of rooms and toilets.

8. The obstacle avoidance cleaning robot is intelligent, can start to absorb dust by one key only when being started, and can automatically recharge when no electricity is available. Once the work is completed, the sweeping robot is also connected to the docking station to charge itself.

9. The obstacle avoidance cleaning robot can be synchronously operated with the work of cleaning personnel, the cleaning time of each guest room is shortened from 30 minutes to 15 minutes, and the cleaning efficiency of the existing guest room is improved by 1 time.

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 diagram of hardware distribution.

Fig. 2 is a flowchart of a robot mechanical arm obstacle avoidance planning method.

Fig. 3 is a flowchart of an obstacle avoidance planning method for a robot mechanical arm.

Fig. 4 is a schematic diagram of an obstacle avoidance planning system of a robot mechanical arm.

Fig. 5 is a schematic diagram of path planning calculation transition points.

Fig. 6 is a schematic diagram of path planning pose selection calculation.

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

Specifically, the robot arm control system module adopts:

Specifically, the module M2 employs: the angle between the tail end tool of the mechanical arm and the normal direction of the current working plane is within a preset range.

Specifically, when the transition point is not reachable, the mechanical arm controller system module sends information to the chassis control system module, the chassis is controlled to move a preset distance along the direction close to the obstacle, and the mechanical arm control system module performs path planning, speed planning and track interpolation again based on the current visual data and sends the position to the servo bus module.

Specifically, the robot arm controls the start and stop actions of the tool at the tail end of the mechanical arm during the movement process.

Specifically, the vision system module: and receiving a photographing instruction sent by the mechanical arm control system module, recognizing the object position information in the current photographing view field, calculating to obtain the object contour position, and reporting the position data to the mechanical arm control system module.

Specifically, the step S5 employs:

Example 2

Example 2 is a preferred example of example 1

The invention provides a hotel obstacle avoidance cleaning robot, which realizes obstacle avoidance cleaning work by combining a mobile robot and an industrial mechanical arm. The hardware module comprises a mobile chassis, a chassis industrial personal computer system, a human-computer interaction interface, a mechanical arm controller, a vision module and a tail end dust collection tool. The distribution diagram of the hardware structure is shown in fig. 1.

The mobile chassis is mainly composed of a power module, an industrial personal computer, a mechanical arm control panel, a laser radar, a 4G module and the like, and realizes SLAM and obstacle avoidance functions.

The mechanical arm is arranged at the upper part of the movable chassis, and the mechanical arm base is positioned at the right center of the movable chassis; the visual module is arranged at the upper part of the tail end of the mechanical arm, and the dust collection tool is arranged at the tail end of the mechanical arm; the connection relation is shown in FIG. 1;

a man-machine interaction interface is configured on the mobile chassis, and cleaning tasks can be set. And displaying information such as the number of rooms and the number of rooms which are cleaned at present, and simultaneously displaying the current electric quantity, the current working time and the like on the interface.

The mechanical arm is a mechanical arm formed by 6 rotary joints. The 6-degree-of-freedom mechanical arm ensures the flexibility of the tail end position and the posture flexibility, ensures that all the postures can be reached, and enables the cleaning obstacle avoidance robot to be more flexible as a whole.

The vision module is arranged at the hand part at the tail end of the mechanical arm, has a rotational degree of freedom and is mainly responsible for pattern recognition, indoor environment reconstruction and auxiliary positioning. The vision module mainly comprises a binocular depth camera and a corresponding processing chip, and the object position positioning is realized through a depth learning technology. And meanwhile, a depth camera is also arranged right in front of the movable chassis and used for assisting in identification and positioning.

The dust collection tool is arranged at the tail end of the mechanical arm and is responsible for dust collection work, and the dust collection tool is mainly controlled by a mechanical arm control system.

Data are interacted between the mechanical arm and the chassis through mqtt communication, and a cleaning task is completed in a cooperative manner; in the cooperation process of the mechanical arm and the chassis, when the chassis reaches a fixed position, the mechanical arm requests local map data shot by a camera, before the mechanical arm moves, whether all the current shooting area position points can be reached is judged firstly (because the arm length of the mechanical arm is limited), if the current shooting area position points cannot be reached, the mechanical arm calculates an inaccessible area according to local map information, then the mechanical arm feeds back the position points to a chassis system for position fine adjustment, and the mechanical arm also feeds back the advancing direction and the advancing distance to the chassis at the same time, and the mechanical arm and the chassis cooperate to complete a cleaning task.

The invention discloses a planning method for obstacle avoidance of a mechanical arm, wherein after a robot receives a cleaning task, a chassis is moved to a fixed point position, the mechanical arm can control a camera to take a picture, then the mechanical arm calculates a position point of a cleaning area according to data of the camera, as shown in fig. 4, if a pos _ start area to a pos _ end area needs to be cleaned, the mechanical arm firstly moves to the pos _ start position, and a path is required to be planned in the process of moving from the pos _ start area to the pos _ end area until the area is moved.

In particular, the invention relates to a planning method for obstacle avoidance in a complex environment of a joint robot arm, which uses a set of transition points around an obstacle as intermediate points between an initial position and a target position. The method is implemented by generating a local map by using visual perception, then calculating and generating a transition point according to data of a camera, wherein an attitude value of the transition point is calculated by a controller according to a current working plane, an angle between a tool at the tail end of a mechanical arm and the normal direction of the current working plane is ensured to be about 30-45 degrees, smoothness of a middle transition path is ensured, and accessibility of the transition point and accessibility of a target point are protected before movement is executed. If the transition point is not reachable, the mechanical arm controller system can signal the chassis system to control the chassis to move a certain distance along the direction close to the obstacle, and then the mechanical arm carries out a new round of planning control again.

The invention provides a robot mechanical arm obstacle avoidance planning method, as shown in fig. 2-3, the specific flow comprises the following steps:

(1) a main switch button is arranged on the chassis, and when the robot system starts up by pressing down, the robot system starts to work;

(2) a man-machine interaction interface is arranged on the chassis, information such as floors, room numbers, cleaning tasks and the like is arranged on the interface, and then a start button on the interface is pressed. If a task is in the process of being performed, the interface pops up prompt information; if the motion condition is met, the robot starts a cleaning task;

(3) the interface issues the task information to an industrial personal computer system;

(4) after receiving the task information, the logic layer control system of the industrial personal computer starts to decompose the task; if the motion condition is met, the logic layer system of the industrial personal computer can issue a task to the chassis control system;

(5) the mobile chassis system is provided with a laser radar to realize the barrier avoidance function of slam and the chassis, after receiving a motion task, the mobile chassis can automatically navigate and move to the vicinity of preset points of each room of a hotel, and the mobile chassis is responsible for moving to the vicinity of corners of the room, the vicinity of tables, the vicinity of beds, the toilet area and the like;

(6) after the chassis moves to a preset area, an arrival signal is sent to the logic layer of the industrial personal computer;

(7) after receiving an arrival signal of the chassis system, the logic layer of the industrial personal computer sends a task to the mechanical arm control system;

(8) after receiving the task, the mechanical arm sends information to a visual system and requests a terminal camera to shoot and construct a current local map;

(9) the camera photographs and calculates to obtain local map information, and the data are sent to the robot control system;

(10) the mechanical arm plans a path according to a local map shot by the terminal camera, presets an advancing path for the robot, plans a speed and interpolates a track according to the preset path, realizes the motion of the robot, and controls the start and stop of the dust collector during the motion;

after receiving local map data fed back by the camera, the mechanical arm calculates a transition point according to the following description method; the specific principle of calculating the transition point is as follows: as shown in fig. 4, assuming that the mechanical arm needs to move from the pos _ start position to the pos _ end position, the camera takes a picture first to obtain local map data of the area, and according to data feedback of the camera, there is an obstacle in the local map, and when the path of the mechanical arm is planned, a straight line pos _ satrt to pos _ end cannot be planned; calculating a unit transition point near the obstacle, wherein the transition point bypasses the obstacle, and then replanning a group of paths according to pos _ start, pos0, pos1, pos2 and pos _ end; the position data of the transition point is obtained by calculation according to the camera feedback data, the attitude value is determined according to the following description method, because the Z direction of the mechanical arm base coordinate system is vertical to the ground, as shown in FIGS. 5-6, a plane is determined with the Z axis according to the direction vector of pos1 and the point of the center position of the obstacle, then the tail end of the tool keeps 30-45 degrees with the Z axis, namely the tail end direction of the tool is determined, namely the attitude value of the tail end can be determined, the attitude value of pos1 can be determined based on the method, and the position and the attitude value of pos1 are obtained; similarly, the position attitude values of other transition points can be determined;

(11) in the motion process of the mechanical arm, whether collision barriers exist in all joint shafts is detected in real time through a dynamic model, and if the collision barriers exist in the tail end, the mechanical arm stops current motion; then the mechanical arm requests the camera to shoot again to construct a local map, a depth camera arranged on the robot deflects to left and right angles to shoot to obtain a depth map, the depth map is processed to obtain a local environment map, the traveling spaces of the left and right sides of the obstacle are detected in the local environment map, one side with larger width is selected as a bypassing traveling space, a bypassing movement range map is drawn, bypassing feasible points are generated in a bypassing movement range, bypassing points are selected from the bypassing movement range to generate a bypassing path, and the mechanical arm carries out path planning again based on the current position;

a mechanical arm model in the mechanical arm controller is a dynamic model; the principle of collision detection is based on the comparison of actual torque values fed back by all joints and predicted torque values calculated by the mechanical arm according to planned position, speed and acceleration information, and when the actual torque values are larger than the predicted torque values, collision is considered to occur;

(12) after the re-planning, the pose of the tail end of the mechanical arm changes, and the re-planned path bypasses the area of the obstacle and moves along the periphery of the obstacle to perform dust collection and cleaning actions. Based on the map shot by the camera, the self-planning of the pose of the robot is realized, and the intelligence of the robot is improved.

(13) After the current region cleans and accomplishes, the arm returns to preset safe preparation point, and then the arm controller can signal to chassis industrial computer system, and the chassis moves to next work area next. And then returning to the step (7) to repeat the movement.

(14) After the logic layer of the industrial personal computer judges that all the movements are finished, information is sent to the application layer;

(15) and the application layer receives the task completion signal, and the interface displays that the task is completed and prompts.

The application layer module relates to the setting and addition of cleaning tasks, adds the sequence points and displays the current task progress in real time; the industrial personal computer module relates to an industrial personal computer logic layer and a chassis control system layer; the mechanical arm control system module relates to task processing of a mechanical arm, mechanical arm motion control, a dynamic algorithm and the like, and ethercat communication with servo equipment and the like; the visual system is mainly used for photographing and identifying the current object position information, constructing a local map and communicating with the mechanical arm control system.

an application layer module: the application layer is mainly used for displaying and setting a cleaning task, and when the task is started by clicking execution, the task is issued to the industrial personal computer logic layer according to a protocol format preset by the industrial personal computer logic layer through the MQTT protocol.

The industrial personal computer logic layer module: the industrial personal computer logic layer is a core center of the whole system, and after receiving a task list issued by the application layer, the industrial personal computer disassembles the task list, issues position information in the task list to the chassis control system one by one through an MQTT protocol according to a protocol format preset by the chassis control system, and waits for the chassis control system to report state information of the arrival of a fixed point position; and after the position is reached, the task is issued to the mechanical arm control system through an MQTT protocol according to the task logic, and the state information of task completion reported by the mechanical arm control system is waited.

A chassis control system module: the chassis control system is mainly used for receiving fixed-point tasks issued by the logic layer of the industrial personal computer, taking charge of navigation planning to fixed-point positions and reporting state information to the logic layer of the industrial personal computer, wherein the state information comprises whether the chassis is in a motion state and whether the chassis has errors.

Mechanical arm control system module: the mechanical arm control system is mainly used for receiving a cleaning task issued by a logic layer of an industrial personal computer, is in charge of communication with a visual system, acquires current local map position information uploaded visually, performs path planning, speed planning, track interpolation and the like based on visual data, and issues the position to a servo through an Ethercat protocol.

A vision system module: the vision system module is mainly used for receiving a photographing instruction issued by the mechanical arm control system, identifying object position information in a current photographing field of view, calculating to obtain an object contour position, and reporting position data to the mechanical arm control system.

A servo bus module: the servo bus module system is mainly used for receiving the periodic position issued by the mechanical arm control system and is responsible for driving the mechanical arm to the issuing position. The period position refers to a position obtained by planning and interpolating each servo period of the mechanical arm, each period is sent to a servo, and then the servo moves to the position; the planned position of each period of the mechanical arm is the period position.

The invention realizes the moving cleaning task under the complex working condition by combining the mobile robot and the mechanical arm. The mobile chassis system realizes a fixed-point navigation method based on a laser map, and can effectively solve the problem that precise fixed-point navigation cannot be realized due to a series of internal and external factors such as difficult positioning, uncontrollable navigation route and the like; and the mechanical arm can also carry out a series of tasks of cleaning in the location position, and the mechanical arm system combines with visual system, has realized the mechanical arm and has kept away the barrier temporarily based on the degree of depth camera, lets the mechanical arm become more intelligent, more diversified. The obstacle avoidance cleaning robot is intelligent, can start to absorb dust by one key, and can automatically recharge when no electricity is available; once the work is finished, the sweeping robot is also connected with the docking station to charge the robot; the chassis system can obtain the current battery electric quantity, when the current electric quantity of the system is smaller than a set threshold value, the chassis system can send a message to the mechanical arm through an mqtt protocol, the mechanical arm can terminate the current task and return to a preset point, and after the position posture of the mechanical arm is reset, the chassis system returns a message to the chassis system through the mqtt protocol; then planning the chassis to return to a charging point; simultaneously the arm cleans the task and can do not have each square corner of dead angle clearance, compares traditional robot of sweeping the floor more nimble, and clean effect is more ideal.

By integrating the characteristics, the difference between the traditional sweeping robot method and the method adopted by the patent is described through comparison of aspects such as operation mode, positioning accuracy, functionality, cleanliness, user experience and the like:

table 1 comparison of the conventional sweeping robot method and the obstacle avoidance sweeping robot system method of the present invention

In the description of the present application, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience in describing the present application and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present application.

Those skilled in the art will appreciate that, in addition to implementing the systems, apparatus, and various modules thereof provided by the present invention in purely computer readable program code, the same procedures can be implemented entirely by logically programming method steps such that the systems, apparatus, and various modules thereof are provided in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.

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.

Claims

1. The utility model provides an obstacle avoidance cleans machine people which characterized in that includes: the system comprises a mobile chassis, a mechanical arm, a visual module, a mechanical arm tail end tool, a mobile chassis industrial personal computer and a mechanical arm controller;

2. The robot mechanical arm obstacle avoidance planning system of the obstacle avoidance cleaning robot according to claim 1, characterized by comprising:

3. The robotic arm obstacle avoidance planning system of claim 2, wherein the robotic arm control system module employs:

4. The robotic arm obstacle avoidance planning system of claim 2, wherein the module M2 employs: the angle between the tail end tool of the mechanical arm and the normal direction of the current working plane is within a preset range.

5. The robot arm obstacle avoidance planning system of claim 2, wherein when the transition point is not reachable, the robot arm controller system module sends information to the chassis control system module to control the chassis to move a preset distance in a direction close to the obstacle, and the robot arm control system module performs path planning, speed planning and trajectory interpolation again based on current visual data and sends the position to the servo bus module.

6. The obstacle avoidance planning system for the robot manipulator of claim 2, wherein the robot manipulator controls start and stop of a tool at the end of the manipulator during movement.

7. A robot mechanical arm obstacle avoidance planning method is characterized by comprising the following steps:

8. The robotic arm obstacle avoidance planning method of claim 7, wherein the vision system module: and receiving a photographing instruction sent by the mechanical arm control system module, recognizing the object position information in the current photographing view field, calculating to obtain the object contour position, and reporting the position data to the mechanical arm control system module.

9. The obstacle avoidance planning method for the robot mechanical arm according to claim 7, wherein the step S5 includes:

10. The obstacle avoidance planning method for the robot manipulator as claimed in claim 7, wherein when the transition point is not reachable, the manipulator controller system module sends information to the chassis control system module to control the chassis to move a preset distance in the direction close to the obstacle, and the manipulator control system module performs path planning, speed planning and trajectory interpolation again based on the current visual data and sends the position to the servo bus module.