Welcome to DOFBOT-Ultra repository

Memory Learning Mode

Please ensure that the web control program backend process is not running in the background. To close it, refer to the [Get Started Quickly - 2. Access the Terminal] section in [Disable the Auto-Start Web Control Backend Process]. After closing, please restart DofbotUltra!!!

1. Operation Instructions

1.1. Startup

Before running the function, you need to shut down the web control program backend process. For the shutdown method, please refer to the [4. Preparation - 1. Manage Web control services].

Raspberry Pi version (in Docker environment), enter the following command:

python3 /home/yahboom/dofbot_ultra/2d/dofbot_voice/scripts/learning_model.py

RDK X5 version (native environment), enter the following command:

xxxxxxxxxx
python3 /home/sunrise/dofbot_ultra_ws/src/2d/dofbot_voice/scripts/learning_model.py

1.2. Command Words

Then say "Hello, yahboom" to the voice module. The voice module will reply "here" to indicate successful wake-up.

1.2.1 Learn Action

Move the robotic arm to the desired position, then say "Record it" to the voice module. If fewer than 20 action groups have been entered, the voice module will reply "ok". If 20 action groups have already been entered, the voice module will reply "Too many actions, I Can't record them". If you want to end input, say "Over" to the voice module, and the voice module will reply "ok".

1.2.2 Executing Actions

Say "Display actions" to the voice module. The voice module will reply "ok", and the robotic arm will sequentially move to the previously learned positions.

1.2.3 Clearing Actions

Say "Clear actions" to the voice module. The voice module will reply "ok", and then you can proceed with the next learning session.

2. Code Logic

This case calls the robotic arm's action group library, implementing a "learn-run-clear" workflow.

When learning, it first checks if the number of already learned action groups is less than 20. If so, it calls Arm_Action_Study() to learn the current pose. When running, it calls Arm_Action_Mode(1) to execute all learned action groups in sequence. When clearing, it calls Arm_Clear_Action() to delete all learned data.

3. Source Code

Raspberry Pi: /home/yahboom/dofbot_ultra/2d/dofbot_voice/scripts/learning_model.py

RDK X5: /home/sunrise/dofbot_ultra_ws/src/2d/dofbot_voice/scripts/learning_model.py

xxxxxxxxxx
result = mySpeech.speech_read()
if result == 55:
    time.sleep(.1)
    Arm.Arm_Action_Study()
    time.sleep(.5)
    num = Arm.Arm_Read_Action_Num()
    if num < 20:
        mySpeech.void_write(55)
    elif num >= 20:  
        mySpeech.void_write(56)
elif result == 56:
    mySpeech.void_write(57)
    Arm.Arm_Button_Mode(0)
elif result == 57:
    mySpeech.void_write(58)
    Arm.Arm_Action_Mode(1)
elif result == 58:
    mySpeech.void_write(59)
    Arm.Arm_Clear_Action()

• Arm_Action_Study() - Learn the current robotic arm pose into action groups
• Arm_Read_Action_Num() - Read the number of currently learned action groups
• Arm_Action_Mode(1) - Run all learned action groups in sequence mode
• Arm_Clear_Action() - Clear all learned action groups
• Arm_Button_Mode(0) - Turn off button interrupt mode