Semantic Understanding and Command Compliance

1. Course Content

Run the example program to interact with the robot solely through terminal text; there is no voice input or voice response.

2. Start the Agent

Note: If it's already started, you don't need to start it again.

Enter the command on the vehicle's terminal:

start_agent

The terminal will print the following information, indicating a successful connection:

3. Running the Example

3.1 Starting the Program

For Raspberry Pi 5 users, if the ROS container is not running, you need to start it first.

xxxxxxxxxx
bringup_m3

Open the terminal inside the container.

xxxxxxxxxx
exec_m3

• Open the terminal on the vehicle's terminal and enter the command:

xxxxxxxxxx
ros2 launch m3_bringup llm_agent_control.launch.py text_chat_mode:=True

• Start the text-based interactive terminal. You can start it on either the vehicle's infotainment system or a virtual machine. Choose one; you don't need to start it repeatedly on both the virtual machine and the vehicle's infotainment system:

xxxxxxxxxx
ros2 run m3_common_demo text_chat

3.2 Test Cases

Here are some sample test cases. Users can create their own dialogue commands.

• Please move forward quickly 1 meter, then slowly retreat 0.5 meters like a tortoise, then turn 30 degrees to the left, 90 degrees to the right, then move horizontally 0.5 meters to the left, and then horizontally 10 centimeters to the right.
• Please perform a dance first, then tell me a joke about cats and dogs.

3.2.1 Case 1

Open a terminal in the virtual machine, enter the test case in the terminal, wait for the model to think, and the AI agent will reply

3.2.2 Case 2

Similar to Case 1, enter Case 2 in the terminal, and the model will respond and execute the action according to the command.

4. Code Analysis

This lesson applies the basic program framework of AI embodied intelligence gameplay. For code analysis, refer to the chapter [4.Embodied intelligent functions core source code]