CN208196806U - A kind of all-purpose robot control system based on ROS - Google Patents
A kind of all-purpose robot control system based on ROS Download PDFInfo
- Publication number
- CN208196806U CN208196806U CN201820357850.0U CN201820357850U CN208196806U CN 208196806 U CN208196806 U CN 208196806U CN 201820357850 U CN201820357850 U CN 201820357850U CN 208196806 U CN208196806 U CN 208196806U
- Authority
- CN
- China
- Prior art keywords
- information
- module
- robot
- perception
- control system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Manipulator (AREA)
Abstract
The utility model provides a kind of all-purpose robot control system based on ROS, including information Perception module, middle control module, output control module and communication management module；Information Perception module is for real-time perception robot interior and external status information；Middle control module is for the characteristic information in extraction machine people status information, according to the corresponding motion model information of characteristic information analysis robot status；Output control module is used to motion model information resolving into robot control instruction information, and control instruction information is transferred to the controller of robot all parts；Communication management module, for the communication between information Perception module, middle control module and output control module and the communication between control system and external host computer.It can be control effectively to all-purpose robot by the system, have many advantages, such as that universal performance is good, can accurately controlling robotary, error resilience performance, good and robot modules information effectively integrates.
Description
Technical field
The utility model belongs to technical field of robot control, and in particular to a kind of all-purpose robot control based on ROS
System.
Background technique
With the fast development of artificial intelligence technology, intelligent robot technology is also constantly mature perfect, and applies in work
Multiple application fields such as industry, business, medical treatment, education, finance.Building for Study of Intelligent Robot Control system is mainly divided to two kinds, one kind
It is open source robot operating system ROS (Robot Operating System), is robot software's platform, can be different
The function of matter computer cluster offer similar operations system, or robot development person provides a standardized, open source
Programming framework, but the real-time thread operability of ROS is bad；Another kind is open source robot operating system OROCOS (Open
Robot Control Software), it has good real-time thread operability, but its opening and versatility are not so good as
ROS。
Currently, most of robot operating systems have the following problems in actual use on the market:
1, the poor universality, handling of existing robot control system are single, and each robot operating system has certainly
Oneself specific gene, the object that can control is very single, can only be to the robot with specific structure corresponding with specific gene
It is controlled.
2, the management module of intelligent robot is various, and the reusability demand of robot code is more and more, various information without
Method is integrated inside a system, and existing robot management system can not adapt to corresponding demand,
3, poor to the control property of robotary, ambient condition locating for robot, various burst things can not be controlled in real time
Part will affect the judgement of robot, and robot is caused to be unable to accurately control.
4, the fault-tolerant ability of existing robot control system is poor, and intelligent robot needs to fully consider distributing layer in operation
With hierarchical relationship, time scale and the Ordered Dependency for implementing interlayer.
Utility model content
In view of the above shortcomings of the prior art, the technical problems to be solved in the utility model is how to design one kind
The general-purpose control system of intelligent robot can be effectively controlled, with universal performance is good, can accurately control robotary, is fault-tolerant
It is functional and the advantages that effectively integrate robot modules information.
In order to solve the above technical problems, the utility model uses the following technical solution:
A kind of all-purpose robot control system based on ROS, including information Perception module, middle control module, output control mould
Block and communication management module；
The information Perception module, for real-time perception robot interior and external status information, and by the machine of perception
Device people's status information is sent to middle control module；
The middle control module, for the characteristic information in extraction machine people's status information, according to characteristic information analysis machine
The corresponding motion model information of people's status, and output control module is sent by motion model information；
The output control module, for motion model information to be resolved into robot control instruction information, and will control
Command information is transferred to the controller of robot all parts；
The communication management module, for the communication between information Perception module, middle control module and output control module, and
Communication between control system and external host computer.
Further, the information Perception module includes internal information sensing module and external information sensing module, outside
Information Perception module includes image capturing device, sound transducer and touch sensor, and internal information sensing module includes being used for
The angular transducer and torque sensor of joint of robot movement are detected, and the temperature for detecting robot internal temperature passes
Sensor.
Further, described image filming apparatus is for obtaining vehicle identification information, recognition of face information, article identification letter
Breath, quality testing information and navigator fix information；The information of sound transducer detection include voice messaging, semantic information and
Voiceprint；The touch sensor includes range sensor, pressure sensor and sliding feeling sensor.
Further, the quality testing information includes black and white area detecting in image, whether there is or not detections, wheel for color component
Exterior feature whether there is or not detection, it is deep or light whether there is or not detection, light and shade bulk number detection, annulus burr detection, sags and crests detection, line linear distance detection
With round distance detection.
Further, the mode of the navigator fix acquisition of information includes NFC radio frequency identification, graphic code identification, Hall magnetic
Field detecting, infrared distance measurement, ultrasonic distance measurement or positioning furniture.
Further, the article identification information includes color information, shape information, characteristic information, bar code information and penetrates
Frequency information.
Further, the robot control instruction information include robot mobile message, robot pose adjustment information,
Robotic arm clamps information, voice output information and expression output information.
Further, the middle control module includes logic analysis module and mechanism module, point of logic analysis module
Analysing information includes task management information, coordinated management information and energy management information, and the analysis information of mechanism module includes
Conditioned reflex information, brain control information and information feedback breath.
Further, the communication management module includes internal communication management module and PERCOM peripheral communication management module, inside
Communication management module be used between information Perception module and logic analysis module, between logic analysis module and mechanism module, fortune
Communication between dynamic analysis module and output control module；PERCOM peripheral communication management module is used between robot and host computer, mutually shuts down
The communication in the device human world.
Compared with prior art, beneficial effects of the present invention:
The versatility of all-purpose robot control system disclosed by the invention based on ROS, the control system is high, is suitable for big
Most all-purpose robots improve the versatility of robot control without specific robot manipulation gene and structure.The system
Multiple functional modules have been subjected to organic combination, the application demand of various robots has been able to satisfy, improves robot control system
It is handling, save development cost.Intelligent robot state in which, Ke Yiying can be accurately controlled in real time by the system
To various emergency situations.The system has a good fault-tolerant ability, distributing layer and implement the hierarchical relationship of interlayer, time scale and
Ordered Dependency is clear and complete.
Detailed description of the invention
Fig. 1 is the functional block diagram of all-purpose robot control system in the embodiment of the present invention；
Fig. 2 is the control flow chart of all-purpose robot control method in the embodiment of the present invention；
Fig. 3 is the vehicle identification flow chart of all-purpose robot control method in the embodiment of the present invention；
Fig. 4 is the recognition of face flow chart of all-purpose robot control method in the embodiment of the present invention；
Fig. 5 is the structural block diagram of all-purpose robot control system in the embodiment of the present invention.
Specific embodiment
It is described in detail below in conjunction with embodiment of the attached drawing to technical solutions of the utility model.Following embodiment is only
For clearly illustrating the technical solution of the utility model, therefore it is intended only as example, and cannot be used as a limitation and limit this reality
With novel protection scope.
Optimum embodiment:
Referring to Fig.1 and Fig. 5, a kind of all-purpose robot control system based on ROS, including information Perception module, middle control mould
Block, output control module and communication management module；
The information Perception module, for real-time perception robot interior and external status information, and by the machine of perception
Device people's status information is sent to middle control module；
The middle control module, for the characteristic information in extraction machine people's status information, according to characteristic information analysis machine
The corresponding motion model information of people's status, and output control module is sent by motion model information；
The output control module, for motion model information to be resolved into robot control instruction information, and will control
Command information is transferred to the controller of robot all parts；
The communication management module, for the communication between information Perception module, middle control module and output control module, and
Communication between control system and external host computer.
In the present embodiment, the information Perception module includes internal information sensing module and external information sensing module, outside
Portion's information Perception module includes image capturing device, sound transducer and touch sensor, and internal information sensing module includes using
In the angular transducer and torque sensor of detection joint of robot movement, and the temperature for detecting robot internal temperature
Sensor.
In the present embodiment, described image filming apparatus is for obtaining vehicle identification information, recognition of face information, article identification
Information, quality testing information and navigator fix information；The information of the sound transducer detection includes voice messaging, semantic information
And voiceprint；The touch sensor includes range sensor, pressure sensor and sliding feeling sensor.
In the present embodiment, the quality testing information include black and white area detecting in image, color component whether there is or not detection,
Profile whether there is or not detection, it is deep or light whether there is or not detection, light and shade bulk number detection, annulus burr detection, sags and crests detection, line linear distance inspection
It surveys and round distance detects.
In the present embodiment, the robot control instruction information includes robot mobile message, robot pose adjustment letter
Breath, robotic arm clamping information, voice output information and expression output information.Wherein voice output can using Baidu's voice or
Iflytek voice, expression is defeated can to use opengl, QT or MFC.
In the present embodiment, the middle control module includes logic analysis module and mechanism module, logic analysis module
Analyzing information includes task management information, coordinated management information and energy management information, the analysis packet of mechanism module
Include conditioned reflex information, brain control information and information feedback breath.
In the present embodiment, the article identification information include color information, shape information, characteristic information, bar code information and
Radio-frequency information.
In the present embodiment, the communication management module includes internal communication management module and PERCOM peripheral communication management module, interior
Portion's communication management module be used between information Perception module and logic analysis module, between logic analysis module and mechanism module,
Communication between mechanism module and output control module；PERCOM peripheral communication management module is used between robot and host computer, is related
The communication in the machine human world.
In above-mentioned all-purpose robot control system, the communication mode between mechanism module and output control module can be adopted
With wifi transparent transmission, NFC, Zigbee, RFID communication, 232 agreements, 485 agreements, IIC agreement, SPI protocol, monobus lin protocol,
ProfiNet bus, EtherNet/IP bus or CAN bus technology.Communication between system and host computer can use CANopen
Mouth mouth, DeviceNet bus, Modbus, ProfiNet bus, BACNet agreement, EtherNet/IP bus, CAN bus skill
Art, industrial Ethernet technology, wifi transparent transmission or Zigbee.The communication in correlation machine people or the process upstream and downstream cooperation machine human world
Mode can using Zigbee, infrared communication, bluetooth communication, wifi transparent transmission, NFC, RFID communication, 232 agreements, 485 agreements,
IIC agreement, SPI protocol or monobus lin protocol.This system, which carries out outdoor activity location navigation, can use GPS, A-GPS, GPRS
Or base station location.Carrying out indoor activity location navigation can be using RFID communication, WLAN and wifi positioning, Zigbee, radio frequency skill
Art, uwb high accuracy positioning, NFC Radio Frequency Identification Technology, Bluetooth technology, A-GPS, planar bar code technology, acoustic location, scene Recognition
Positioning or IP positioning.
In the present embodiment, the mode of the navigator fix acquisition of information includes NFC radio frequency identification, graphic code identification, Hall
Magnetic field detection, infrared distance measurement, ultrasonic distance measurement or positioning furniture.
Referring to Fig. 2, a kind of all-purpose robot control method based on ROS, comprising the following steps:
S1: by information Perception module real-time perception robot interior and external status information, and by the robot of perception
Status information is sent to middle control module；
S2: by the characteristic information in middle control module extraction machine people's status information, according to institute of characteristic information analysis robot
The corresponding motion model information of place's state, and output control module is sent by motion model information；
S3: resolving into robot control instruction information for motion model information by output control module, and by control instruction
Information is transferred to the controller of robot all parts.
Referring to Fig. 3, the method for vehicle identification information is as follows:
S201: vehicle image is obtained by image capturing device, and vehicle image information is transferred to middle control module；
S202: middle control module receives vehicle image information, pre-processes to vehicle image, to eliminate nothing in vehicle image
The information of pass；
S203: it identifies the character in pretreated vehicle image, and character is individually divided into corresponding character block；
S204: being normalized the character block after segmentation, extracts the characteristic information of character block after normalized,
The character block characteristic information of extraction and default storage characteristic information are compared, the identification of character is completed.
Referring to Fig. 4, the method for recognition of face information is as follows:
S211: facial image is obtained by image capturing device, and human face image information is transferred to middle control module；
S212: middle control module receives human face image information, pre-processes to facial image, to eliminate nothing in facial image
The information of pass；
S213: extracting the characteristic information in pretreated facial image, by the face characteristic information of extraction and default people
Face model information is compared, and the similarity of face characteristic information and default faceform's information is analyzed, if similarity is higher than
Preset value, then recognition of face is correct, conversely, then recognition of face mistake.
During above-mentioned face identification method, it is also necessary to be aligned the facial image of shooting and default faceform, use
ASM, AAM or CLM.The algorithm that recognition of face uses has Gabor transformation, PCA, LDA, Ada+gabor and rarefaction representation method.
In above-mentioned all-purpose robot control method, need to pre-establish the models such as various object events, goal task, and root
Corresponding characteristic factor is preset according to corresponding model.
In the present embodiment, the information sensing method of the information Perception module includes the following steps:
Perception information stress to acquire and screen, to shield the garbage or noise information in perception information, and
Classify to perception information；
Corresponding transinformation or frequency are selected according to the type of perception information.
The screening technique of the information Perception module perception information is as follows:
It 1, is screening foundation with object event.In the case where different operation industrial and minerals, external environment and moving target, when
When the object event state of robot perception changes, data acquiring frequency is changed accordingly.For example, setting robot
Normal data sample frequency is 1KHZ, and data sampling frequency of the robot in steady operation is 10HZ, when robot
When working condition changes, then data sampling frequency is improved, sample frequency can be set as 10KHZ, be likely to occur to hold in time
Risk.
It 2, is screening foundation with task objective.For example, robot is screwing, screws and mainly use the hand of robot
Arm motor then carries out high-frequency sampling to arm motor.If robot carry out indoor navigation positioning, we just mainly for
The sensor informations such as chassis, gyroscope, odometer carry out high-frequency acquisition, other positions then reduce sample frequency.
3, it when that can not determine object event and task objective, is screened in the following manner:
(1) more data are obtained.High-frequency data acquisition is carried out for robot movable purpose, carries out training in advance
Process obtains immediate model, we regular evaluation model and can study sample during the training period, to identify those
Most possibly by the sample of mistake classification.This let us can advisably select the sample that algorithm more often learns.
(2) change label target.In practical applications, often needing not distinguish between with robot is which motor is working
(such as: arm motor or hand motor), as long as identify two as long as one of them it is much of that.Two motors are synthesized a mark
Note, regard as mechanical arm can, in this case sampling assessment can simplify problem.
(3) ignore.The part sample for ignoring common class, (such as: hand electricity when the sample number of each classification is substantially close
Machine and wrist motor), this method can be used.
(4) excessive sampling or lack sampling.Excessively sampling refer to algorithm learn rare classification sample frequency it is higher, and owe to adopt
Sample is then opposite situation.In terms of algorithm angle, what both methods generated is all identical result.Compared to former approach,
The advantage of this method is not ignore any sample.
All-purpose robot control system and method provided by the invention based on ROS, has the advantage that robot system
The physics law of the inside is expressed in a manner of information；System itself has the ability of examining oneself property, can perceive and predict itself
The variation of state, to prevent emergency situations；The system can assign " EQ " for robot, realize the cooperative intelligent of device activity；
Gains in depth of comprehension knowledge can be obtained to acquainted management and use.
Finally, it is stated that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although referring to reality
Example is applied to describe the invention in detail, those skilled in the art should understand that, it can be to technical side of the invention
Case is modified or replaced equivalently, and without departing from the objective and range of technical solution of the present invention, should all be covered in the present invention
Protection scope in.
Claims (9)
1. a kind of all-purpose robot control system based on ROS, which is characterized in that including information Perception module, middle control module, defeated
Control module and communication management module out；
The information Perception module, for real-time perception robot interior and external status information, and by the robot of perception
Status information is sent to middle control module；
The middle control module, for the characteristic information in extraction machine people's status information, according to institute of characteristic information analysis robot
The corresponding motion model information of place's state, and output control module is sent by motion model information；
The output control module, for motion model information to be resolved into robot control instruction information, and by control instruction
Information is transferred to the controller of robot all parts；
The communication management module, for the communication between information Perception module, middle control module and output control module, and control
Communication between system and external host computer.
2. all-purpose robot control system according to claim 1, which is characterized in that the information Perception module includes interior
Portion's information Perception module and external information sensing module, external information sensing module include image capturing device, sound transducer
And touch sensor, internal information sensing module include the angular transducer and moment sensing for detecting joint of robot movement
Device, and the temperature sensor for detecting robot internal temperature.
3. all-purpose robot control system according to claim 2, which is characterized in that described image filming apparatus is for obtaining
Take vehicle identification information, recognition of face information, article identification information, quality testing information and navigator fix information；The sound
The information of sensor detection includes voice messaging, semantic information and voiceprint；The touch sensor include range sensor,
Pressure sensor and sliding feeling sensor.
4. all-purpose robot control system according to claim 3, which is characterized in that the quality testing information includes figure
As in black and white area detecting, color component whether there is or not detection, profile whether there is or not detection, it is deep or light whether there is or not detection, light and shade bulk number inspection
It surveys, the detection of annulus burr, sags and crests detection, line linear distance detects and round distance detection.
5. all-purpose robot control system according to claim 3, which is characterized in that the navigator fix acquisition of information
Mode includes NFC radio frequency identification, graphic code identification, Hall magnetic field detection, infrared distance measurement, ultrasonic distance measurement or positioning furniture.
6. all-purpose robot control system according to claim 3, which is characterized in that the article identification information includes color
Multimedia message, shape information, characteristic information, bar code information and radio-frequency information.
7. all-purpose robot control system according to claim 1, which is characterized in that the robot control instruction information
Including robot mobile message, robot pose adjustment information, robotic arm clamping information, voice output information and expression output letter
Breath.
8. all-purpose robot control system according to claim 1, which is characterized in that the middle control module includes logic point
It analyses module and mechanism module, the analysis information of logic analysis module includes task management information, coordinated management information and energy
Management information is measured, the analysis information of mechanism module includes conditioned reflex information, brain control information and information feedback breath.
9. all-purpose robot control system according to claim 1, which is characterized in that the communication management module includes interior
Portion's communication management module and PERCOM peripheral communication management module, internal communication management module are used for information Perception module and logic analysis mould
Communication between block, between logic analysis module and mechanism module, between mechanism module and output control module；PERCOM peripheral communication
Management module be used between robot and host computer, the communication in the correlation machine human world.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820357850.0U CN208196806U (en) | 2018-03-15 | 2018-03-15 | A kind of all-purpose robot control system based on ROS |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820357850.0U CN208196806U (en) | 2018-03-15 | 2018-03-15 | A kind of all-purpose robot control system based on ROS |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN208196806U true CN208196806U (en) | 2018-12-07 |
Family
ID=64527974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201820357850.0U Expired - Fee Related CN208196806U (en) | 2018-03-15 | 2018-03-15 | A kind of all-purpose robot control system based on ROS |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN208196806U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108333974A (en) * | 2018-03-15 | 2018-07-27 | 珠海金萝卜智动科技有限公司 | A kind of all-purpose robot control system and method based on ROS |
| CN110141366A (en) * | 2019-05-06 | 2019-08-20 | 清华大学 | The blood vessel intervention operation robotic actuator that motion control information stream directly transmits |
| CN113188591A (en) * | 2021-04-09 | 2021-07-30 | 苏州大学 | Self-powered multi-mode sensing method for space environment |
-
2018
- 2018-03-15 CN CN201820357850.0U patent/CN208196806U/en not_active Expired - Fee Related
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108333974A (en) * | 2018-03-15 | 2018-07-27 | 珠海金萝卜智动科技有限公司 | A kind of all-purpose robot control system and method based on ROS |
| CN110141366A (en) * | 2019-05-06 | 2019-08-20 | 清华大学 | The blood vessel intervention operation robotic actuator that motion control information stream directly transmits |
| CN113188591A (en) * | 2021-04-09 | 2021-07-30 | 苏州大学 | Self-powered multi-mode sensing method for space environment |
| CN113188591B (en) * | 2021-04-09 | 2023-08-11 | 苏州大学 | Self-powered multi-mode sensing device and method for space on-orbit assembly robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108333974A (en) | A kind of all-purpose robot control system and method based on ROS | |
| CN208196806U (en) | A kind of all-purpose robot control system based on ROS | |
| CN104959989B (en) | A kind of door of elevator feeding localization method under vision guide | |
| Sunny et al. | Applications and challenges of human activity recognition using sensors in a smart environment | |
| CN102999664B (en) | Method for identifying position of indoor pollution source | |
| Gorecky et al. | COGNITO: a cognitive assistance and training system for manual tasks in industry | |
| CN109191939B (en) | Three-dimensional projection interaction method based on intelligent equipment and intelligent equipment | |
| CN108734734A (en) | Indoor orientation method and system | |
| Zhang et al. | Robotic control of dynamic and static gesture recognition | |
| CN115847422A (en) | Gesture recognition method, device and system for teleoperation | |
| WO2019127437A1 (en) | Map labeling method and apparatus, and cloud server, terminal and application program | |
| CN211890823U (en) | Four-degree-of-freedom mechanical arm vision servo control system based on RealSense camera | |
| Duan et al. | HRC of intelligent assembly system based on multimodal gesture control | |
| CN109934155B (en) | Depth vision-based collaborative robot gesture recognition method and device | |
| Pradeep et al. | Advancement of sign language recognition through technology using python and OpenCV | |
| Brás et al. | Gesture recognition from skeleton data for intuitive human-machine interaction | |
| Barranco-Gutiérrez et al. | Camera as position sensor for a ball and beam control system | |
| Kurian et al. | Visual Gesture-Based Home Automation | |
| CN109866226A (en) | A kind of polynary perception information processing system and method for industrial robot | |
| CN109708642B (en) | Indoor robot direction sensing method | |
| Fugini et al. | Gesture Recognition in an IoT environment: a Machine Learning-based Prototype | |
| He et al. | Development of a practical tool in pick-and-place tasks for human workers | |
| Wameed et al. | Tracked robot control with hand gesture based on mediapipe | |
| Hara et al. | Communicative functions to support human robot cooperation | |
| WO2022211384A1 (en) | Systems and methods for automated preloading of actuators |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181207 Termination date: 20200315 |