yahboom
HomeLearn
Solution
Blog
Online Store
About Us
EN/中文
DOFBOT SE📖
1.First Trial
  • 1.First Trial
  • 2.Analysis of common problems
  • 3.Calibration offset
  • 4.Precautions for DIY Robotic Arm
  • 5.Robotic arm gripping anomaly solutions
2.Assembly Course
  • 1.Installation video
  • 2.Calibrate the Robotic Arm
  • 3.Install the map
3.Remote Control Course
  • 1.Mobile APP control
  • 2.USB handle control
  • 3.PC software control
4.Preparation
  • 1.Manage APP control service
  • 2.Manage JupyterLab service
  • 3.Write STM32 firmware
  • 4.Introduction to expansion board
5.Basic Control Course
  • 1.Control RGB light
  • 2.Control buzzer
  • 3.Control single servo
  • 4.Read servo angle
  • 5.Control all servo
  • 6.DOFBOT up down left right
  • 7.DOFBOT dancing
  • 8.DOFBOT memory action
  • 9.DOFBOT grab block
  • 10.Porter
  • 11.Stack block
  • 12.USB camera display
  • 13.Synchronous action
6.AI Vision Basic Course
  • 1.Gesture Recognition
  • 2.Color threshold adjustment Color calibration
  • 3.Color recognition
  • 4.Face recognition
  • 5.Garbage recognition
  • 6.Yolo object recognition
  • 7.Real-time web view
7.2D Visual Tracking Course
  • 1.PID algorithm basics
  • 2.Color block positioning
  • 3.Color block tracking
  • 4.Face positioning
  • 5.Face tracking
  • 6.Gesture recognition fixed action
8.2D Visual Grasping Course
  • 0.Visual positioning
  • 1.Gesture recognition stack blocks
  • 2.Color recognition grab blocks
  • 3.Catch game
  • 4.Color sorting and stacking
  • 5.Garbage sorting
  • 6.Color interaction
9.2D Mediapipe Course
  • 1.Hand detection
  • 2.Posture detection
  • 3.Overall inspection
  • 4.Face detection
  • 5.Face recognition
  • 6.Face effects
  • 7.3D object recognition
  • 8.Paintbrush
  • 9.Finger control
  • 10.Gesture recognition
  • 11.Gesture control robotic arm action group
  • 12.Arm posture control robotic arm
  • 13.Palm Targeting
  • 14.Robotic arm tracks the palm
  • 15.Fingertip trajectory recognition
  • 16.Fingertip trajectory control robotic arm
  • 17.Gesture Grasp and Release Objects
  • 18.Finger Control Robot Arm
10.AI Large Model Voice Module (Must Read)
  • 1. Introduction to AI Large Model Voice Module
  • 2. Flash the firmware (Must read)
  • 3. Modify the wake-up word and command word
11.2D Voice Control Course
  • 1.Simple Voice Control
  • 2.Smart Voice Control
  • 3.Voice Action Control
  • 4.Memory Learning Mode
  • 5.Color Recognition with Voice Broadcast
  • 6.Color Recognition and Grasping with Voice Broadcast
  • 7.Color Recognition and Sorting with Voice Broadcast
  • 8.Voice Recognition Target Tracking
  • 9.Voice Control Stacking
  • 10.Voice Control Color Sorting
  • 11.Garbage Recognition with Voice Broadcast
  • 12.Garbage Sorting with Voice Broadcast
12.Robotic Arm Control and Inverse Kinematics
  • 1. Robotic arm ROS control
  • 2. Inverse solution
13.3D Sorting and Grasping Course
  • 1.AprilTag ID sorting
  • 2.MediaPipe Gesture-AprilTag ID sorting
  • 3.MediaPipe Gesture-AprilTag distance sorting
  • 4.Block color sorting
  • 5.Block different shape sorting
  • 6.Yolov11 garbage sorting
14.3D Tracking Course
  • 1.AprilTag Tracking
  • 2.Color Block Tracking
  • 3.KCF Object Tracking
15.3D Voice Control for Sorting & Tracking Course
  • 1.Voice Control AprilTag ID Sorting
  • 2.Voice Control Color Block Sorting
  • 3.Voice Control Yolov11 Garbage Recognition Sorting
  • 4.Voice Control AprilTag Tracking
  • 5.Voice Control Color Block Tracking
  • 6.Voice Control Object Tracking
16.AI Model Basics
  • 1.AI large model types and principles
  • 2.RAG retrieval enhancement and model training samples
  • 3.Embodied intelligent robot system architecture
  • 4.Embodied intelligent functions core source code
17.AI Model Development
  • 1. Register a model service provider account
  • 2. Configure API-KEY
  • 3. Introduction to Dify
  • 4. Basic Dify Features
  • 5. AI Large Model Development - chatbot
  • 6. Deploy the RAG knowledge base
  • 7. RAG knowledge base + chatbot
  • 8. AI agent workflow
18.AI Model – Text Version
  • 1.Semantic understand instruction following
  • 2.Multimodal visual understand
  • 3.Text Large Model + robotic arm control
  • 4.Multimodal Large Model+video understanding
  • 5.Multimodal Large Model+robotic arm gripping
  • 6.Multimodal Large Model+robotic arm tracking
  • 7.Multimodal Large Model+robotic arm sorting
  • 8.Multimodal Large Model+robotic arm handling
  • 9.Multimodal Large Model+Color Blocks Back In Place
  • 10.Multimodal Large Model + Intent Prediction + Robotic Arm Gripping
  • 11.Text Large Model + YOLOv11 + Intelligent Garbage Classification
19.AI Model – Voice Version
  • 1.Semantic understand instruction following
  • 2.Multimodal visual understand
  • 3.Text Large Model + robotic arm control
  • 4.Multimodal Large Model+video understanding
  • 5.Multimodal Large Model+robotic arm gripping
  • 6.Multimodal Large Model+robotic arm tracking
  • 7.Multimodal Large Model+robotic arm sorting
  • 8.Multimodal Large Model+robotic arm handling
  • 9.Multimodal Large Model+Color Blocks Back In Place
  • 10.Multimodal Large Model + Intent Prediction + Robotic Arm Gripping
  • 11.Text Large Model + YOLOv11 + Intelligent Garbage Classification
20.AI Model – Fun Applications
  • 1.AI Butler-Intent Inference
  • 2.AI Encyclopedia-Arithmetic Master
  • 3.AI Encyclopedia-You asked I Pointed
  • 4.AI Encyclopedia-Nutritional Analysis
  • 5.AI Encyclopedia-Problem Solving Expert
  • 6.AI Encyclopedia-English Spelling
  • 7.AI Butler-Garbage Sorting
  • 8.AI Top Chef
21.MoveIt2 Course
  • 1. MoveIt Configuration
  • 2. MoveIt Usage
  • 3. MoveIt Drive Real Robot
  • 4. MoveIt Random Movement
  • 5. MoveIt Forward Kinematics Design
  • 6. MoveIt Inverse Kinematics Design
  • 7. MoveIt Cartesian Path
  • 8. MoveIt Scene Design
  • 9. MoveIt Trajectory Planning
  • 10. MoveIt Collision Detection
22.YOLOv11 Development Course
  • 1. YOLO Environment Setup
  • 2. CLI Usage
  • 3. Object Detection
  • 4. Instance Segmentation
  • 5. Pose Estimation
  • 6. Image Classification
  • 7. Oriented Bounding Boxes Object Detection
  • 8. Model Conversion
  • 9. Model Prediction
23. Linux Operating System
  • 1.Introduction to Linux system
  • 2.Ubuntu file system
  • 3.Ubuntu common commands
  • 4.Ubuntu common editors
  • 5.Ubuntu software operation commands
  • 6.Virtual machine installation
  • 7.SSH remote control
  • 8.VNC remote control
  • 9.Transfer files remotely
  • 10.Driver library and communication
  • 11.Static IP and hotspot mode
  • 12.Bind device ID
  • 13.Capacity expansion and resource allocation
  • 14.Update system software sources
  • 15.Set root user password
  • 16.sudo free password
  • 17.Connect to WiFi network
  • 18.View system version
  • 19.Customized service management
  • 20.Back up system image
24.OpenCV Course
  • 1.Introduction to Open Source CV
  • 2.Image reading and display
  • 3.Picture writing
  • 4.Image Quality
  • 5.Pixel operations
  • 6.Image zoom
  • 7.Picture cut
  • 8.Picture pan
  • 9.Picture mirroring
  • 10.Affine transformation
  • 11.Picture rotation
  • 12.perspective transformation
  • 13.Grayscale processing
  • 14.Binary image
  • 15.Edge green detection
  • 16.Line segment drawing
  • 17.Rectangular circle drawing
  • 18.Text and picture drawing
25.Advanced Visuals Course
  • 1. QR Code
  • 2. Human Pose Estimation
  • 3. Object Detection
  • 4. AR Vision
  • 5. ROS + OpenCV Basics
26.ROS2 Basic Course
  • 1.Introduction to ROS2
  • 2.ROS2 install Humble
  • 3.ROS2 development environment
  • 4.ROS2 workspace
  • 5.ROS2 function package
  • 6.ROS2 node
  • 7.ROS2 topic communication
  • 8.ROS2 service communication
  • 9.ROS2 action communication
  • 10.ROS2 custom interface message
  • 11.ROS2 parameter service case
  • 12.ROS2 meta-function package
  • 13.ROS2 distributed communication
  • 14.ROS2 DDS
  • 15.ROS2 time related API
  • 16.ROS2 common command tools
  • 17.ROS2 rviz2 use
  • 18.ROS2 rqt toolbox
  • 19.ROS2 Launch startup file configuration
  • 20.ROS2 recording and playback tool
  • 21.ROS2 URDF model
  • 22.ROS2 Gazebo simulation platform
  • 23.ROS2 TF2 coordinate transformation
27.Jupyter Lab Usage Course
  • 0.Read the document before operation
  • 1.Jupyter Lab environment construction
  • 2.Basic use of Jupyter Widgets
  • 3.Launch JupyterLab
  • 4.How to Use JupyterLab
Download
  • APP(iOS/Android)
  • VM File
  • Instruction manual
  • Hardware_3DModelFile
  • PC_Software
  • Code
  • Communication Protocol-Python Library
  • Tools
Download ZIP

Welcome to DOFBOT SE repository

9.Multimodal Large Model+Color Blocks Back In Place

Multimodal Large Model + Color Blocks Back In Place

Function Description

After the program runs, first input the command to remember the current color block positions in the terminal. After the program completes recording, shuffle the color block positions. Then input the command to return the color blocks on the desktop to their original positions in the terminal. After thinking, the large model will plan an action list, and the program will control the robotic arm to complete the color block reset task based on the action functions in the action list.

Startup

Open the terminal and enter the following command:

xxxxxxxxxx
ros2 launch largemodel largemodel_control.launch.py text_chat_mode:=True

Then open a second terminal and enter the following command:

xxxxxxxxxx
ros2 run text_chat text_chat

Now input the command to remember the current color block positions in the terminal. You can refer to the following examples:

xxxxxxxxxx
Remember the current positions of the color blocks

image-20251129151258160

After recording the color block positions, input the end task command in the terminal:

xxxxxxxxxx
End the position recording task

Then you can shuffle the color block positions. After shuffling, input the color block reset command in the terminal. You can refer to:

xxxxxxxxxx
Return the blocks on the desktop to their original positions

image-20251129154127570

After the buzzer beeps once, it starts gripping the color blocks and returning them to their original positions in the order recorded by the program. If there are other color blocks on top of the color block that needs to be returned, it will first remove the color blocks on top, then grip and return to the original position.

Task Planning

Record Current Color Block Positions

  1. Call seewhat() to observe the environment;

  2. Call seewhat() again to observe the environment, then determine which color block is the top block;

  3. If there are two or more piles of color blocks in the environment, select and execute the following content based on whether a color block is a single one. Calculate for each pile of color blocks. Only one action function can be output at a time here:
    (1) If it is a single color block, pass the outer frame coordinates of the color block into the function compute_pose(x1, y1, x2, y2, 'name'), where name represents the color of the color block, and its value can be red, blue, green, or yellow;
    (2) If it is not a single color block, pass the outer frame coordinates of the top color block into the function compute_pose_order(x1, y1, x2, y2, 'name', 'order'), where name represents the color of the color block (with values red, blue, green, or yellow), and order represents the top-to-bottom arrangement order of the color blocks. Its value is a string composed of the initial letters of the colors of each layer of color blocks from top to bottom. For example, if the top-to-bottom arrangement order of the color blocks is red, blue, green, yellow, then the value of order is rbgy, and so on.

  4. If there is only one pile of color blocks, pass the outer frame coordinates of the top color block into the function compute_pose_order(x1, y1, x2, y2, 'name', 'order'), where name represents the color of the color block (with values red, blue, green, or yellow), and order represents the top-to-bottom arrangement order of the color blocks. Its value is a string composed of the initial letters of the colors of each layer of color blocks from top to bottom. For example, if the top-to-bottom arrangement order of the color blocks is red, blue, green, yellow, then the value of order is rbgy, and so on.

Color Blocks Back In Place

  1. First, call the color_back_to_orin() function to control the color blocks to return to their original positions.

  2. Call the check_remove(color) function to check whether the target color block exists in the removal list (where color is the color of the target color block, and its value range is red, blue, green, or yellow).

  3. If the target color block exists in the removal list, perform the following operations:
    (1) Call the grasp_from_rm_list(color) function to grasp the target color block from the removal list (the meaning of the color parameter is the same as above);
    (2) Pass the color of the target color block as a parameter into the return_to_orin(color) function. For example, when the target color block is red, call return_to_orin(red) (the value range of the color parameter is the same as above).

  4. If the target color block does not exist in the removal list, follow the steps below to put the color block back to its original position (only one action function can be output at a time):
    (1) Call the seewhat() function to observe the environment;
    (2) Determine whether there are other color blocks on top of the target color block that needs to be returned to its original position;
    (3) If there are no other color blocks on top of the target color block that needs to be returned to its original position, perform the following steps: ①Call the grasp_obj(x1, y1, x2, y2) function to grasp the target color block that needs to be returned to its original position (where (x1, y1, x2, y2) are the border coordinates of the top surface of the target color block that needs to be returned to its original position);
    ②Pass the color of the target color block as a parameter into the return_to_orin(color) function (the value range of the color parameter is the same as above).
    (4) If there are other color blocks on top of the target color block that needs to be returned to its original position, perform the following steps:
    ①Call the remove_obj(x1, y1, x2, y2, color) function to remove the color block (where (x1, y1, x2, y2) are the border coordinates of the top surface of this color block, and color is the color of this color block, with a value range of red, blue, green, or yellow);
    ②Call the seewhat() function to observe the environment;
    ③If there are no other color blocks above the target color block that needs to be returned to its original position, call the grasp_obj(x1, y1, x2, y2) function to grasp the target color block (where (x1, y1, x2, y2) are the border coordinates of the top surface of the target color block); ④Pass the color of the target color block as a parameter into the return_to_orin(color) function (the value range of the color parameter is the same as above).

Core Code Analysis

compute_pose_order Record Stacked Color Block Positions

Source code path: LargeModel_ws/src/largemodel/largemodel/action_service.py

​x
#Parameter description
#x1,y1,x2,y2: Top surface outer frame coordinates of the top color block, x1,y1 represent
#name: Color of the top color block
#order: Represents the top-to-bottom stacking order list of color blocks. For example, if the stacking colors from top to bottom are red and yellow, then the passed order is ry
def compute_pose_order(self,x1,y1,x2,y2,name,order):
    #Get the current color block parameter
    cur_name = name.strip("'\"")  
    color_order = order.strip("'\"")
    #Create an intermediate list to store the top-to-bottom stacking order of color blocks
    order_list = list(color_order[1:])
    self.get_logger().info(f"order_list:{order_list}")
    self.cur_name = cur_name
    self.cur_pose[self.cur_name] = []
    #Start calculating position information
    cmd1 = "ros2 run largemodel_arm Record_pose"
    proc = subprocess.Popen(
        [
            "gnome-terminal",
            "--title=compute_pose",
            "--",
            "bash",
            "-c",
            f"{cmd1}; exec bash",
        ]
    )
    self.pid_num = proc.pid   
    self.get_logger().info(f"self.pid_num:{self.pid_num}")
    time.sleep(5.0)
    x1 = int(x1)
    y1 = int(y1)
    x2 = int(x2)
    y2 = int(y2)
    self.object_position_pub.publish(Int16MultiArray(data=[x1, y1, x2, y2]))

    while not self.compute_pose_future.done():
        if self.interrupt_flag:
            self.check_close_compute_pose()
            Arm.Arm_serial_servo_write6(90,150,12,20,90,30,1000)
            self.stop()
            return
        time.sleep(0.1)

    result = self.compute_pose_future.result()
    self.check_close_compute_pose()
    if not self.interrupt_flag:
        if result.data == "compute_pose_done":
            for i in range(0,len(order_list)):
                #Here we consider that the xy direction is consistent with the top color block, only the height changes, so we only need to change the z value, decreasing by about 2.8 centimeters, which is approximately the height of one color block
                x = self.cur_pose[cur_name][0]
                y = self.cur_pose[cur_name][1]
                z = self.cur_pose[cur_name][2] - (i+1)*0.028
                if order_list[i] == 'r' or  order_list[i] == 'R':
                    self.cur_pose['red'] = []
                    self.cur_pose['red'].append(x) 
                    self.cur_pose['red'].append(y) 
                    self.cur_pose['red'].append(z) 
                elif order_list[i] == 'b' or  order_list[i] == 'B':
                    self.cur_pose['blue'] = []
                    self.cur_pose['blue'].append(x) 
                    self.cur_pose['blue'].append(y) 
                    self.cur_pose['blue'].append(z)                
                elif order_list[i] == 'y' or  order_list[i] == 'Y':
                    self.cur_pose['yellow'] = []
                    self.cur_pose['yellow'].append(x) 
                    self.cur_pose['yellow'].append(y) 
                    self.cur_pose['yellow'].append(z)  
                elif order_list[i] == 'g' or  order_list[i] == 'G':
                    self.cur_pose['green'] = []
                    self.cur_pose['green'].append(x) 
                    self.cur_pose['green'].append(y) 
                    self.cur_pose['green'].append(z)  
                    
            self.get_logger().info(f"self.cur_pose:{self.cur_pose}")
            #Feedback to the large model that recording the stacked color block positions is complete
            self.action_status_pub("compute_pose_order_done", x1=x1, y1=y1, x2=x2, y2=y2,name=name,order=order)
        else:
            self.action_status_pub("compute_pose_failed", x1=x1, y1=y1, x2=x2, y2=y2)

color_back_to_orin Publish Color Block Reset Sequence

Source code path: LargeModel_ws/src/largemodel/largemodel/action_service.py

xxxxxxxxxx
def color_back_to_orin(self):
    self.back_list = True
    #Buzzer beeps once
    Arm.Arm_Buzzer_On()
    time.sleep(0.5)
    Arm.Arm_Buzzer_Off()
    #Traverse the reversed list of stored color block positions and feedback the current color block reset command to the large model
    for key in reversed(self.cur_pose.keys()):
        if key == 'red':
            self.action_status_pub("send_red_back_to_orin")
        elif  key == 'green':
            self.action_status_pub("send_green_back_to_orin")
        elif key == 'blue':
            self.action_status_pub("send_blue_back_to_orin")
        elif key == 'yellow':
            self.action_status_pub("send_yellow_back_to_orin") 
        while not self.return_done:
            time.sleep(0.1)
        self.return_done = False
    self.action_status_pub("return_to_orin_done")
    self.back_list = False
"send_red_back_to_orin": "Robot feedback: Place the red block back to its original position",
"send_green_back_to_orin": "Robot feedback: Place the green block back to its original position",
"send_blue_back_to_orin": "Robot feedback: Place the blue block back to its original position",
"send_yellow_back_to_orin": "Robot feedback: Place the yellow block back to its original position"

check_remove(color) Check if Current Color Block to Reset Exists in Removal List

Source code path: LargeModel_ws/src/largemodel/largemodel/action_service.py

xxxxxxxxxx
def check_remove(self,color):
    #Get the current color block color
    check_color = color.strip("'\"")
    #If the current color block color can be found in the removal list, then feedback to the large model that the current color block can be found in the removal list
    if check_color in self.cur_rm_pose:
        self.action_status_pub("color is in the rm_list")
    else:
        self.action_status_pub("color is not in the rm_list")
        
"color is in the rm_list" : "The color block exists in the removal list, grip the color block from the removal list",
"color is not in the rm_list" : "The color block does not exist in the removal list, determine if there are other objects on top of the color block"

grasp_from_rm_list Grip Color Block from Removal List

Source code path: LargeModel_ws/src/largemodel/largemodel/action_service.py

def grasp_from_rm_list(self,color):
    #Get the current color block color
    tar_color = color.strip("'\"")
    #According to the current color, find the corresponding robotic arm pose value in the removal dictionary
    tar_joints = self.cur_rm_pose.get(tar_color)
    Arm.Arm_serial_servo_write6(tar_joints[0], tar_joints[1], tar_joints[2], tar_joints[3], tar_joints[4], tar_joints[5],2000)
    time.sleep(2.0)
    Arm.Arm_serial_servo_write(6, 140, 1000)
    time.sleep(2.0)
    Arm.Arm_serial_servo_write6(90,120,10,10,90,140,2000)
    time.sleep(2.0)
    #Feedback to the large model that gripping the color block from the removal list is complete
    self.action_status_pub("grasp_from_rm_list_done")
Multimodal Large Model+robotic arm handling
Multimodal Large Model + Intent Prediction + Robotic Arm Gripping

COMPANY

  • About us
  • Team Style
  • Blog

LEARNING & EXPLORATION

  • Tutorials
  • Edge AI hardware
  • Educational robots
  • Embedded intelligent hardware

WHERE TO BUY

  • Yahboom Online Store
  • Amazon
  • Alibaba
  • AliExpress
  • Mercado

TECHNOLOGY SUPPORT

  • Email: support@yahboom.com

BE A DISTRIBUTOR

  • Email: sales@yahboom.com
QR Code

Copyright © 2017-2026 Yahboom. All Rights Reserved.

EN/中文