Welcome to DOFBOT Pro repository

AI Encyclopedia-English Spelling

Before running the function, you need to close the App and large programs. For the closing method, refer to [4. Preparation] - [1. Manage APP control services].

1. Function Description

After the program starts, ask the large model what the word on the desktop might mean. After thinking, the large model will reply with the answer to the question and will check the spelling of the word, and control the robotic arm to point to the missing word.

2. Startup

Taking the text version as an example, users with Jetson-Nano mainboard version need to enter the docker container first and then input the following command. Users with Orin mainboard can directly open the terminal and input the following command,

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

Then open a second terminal and input the following command,

xxxxxxxxxx
ros2 run text_chat text_chat

Then input "Guess what the word on the desktop might mean?" in the text_chat terminal and press Enter; if it's the voice version, wake up the voice module and directly say to the voice module "Guess what the word on the desktop might mean?", then wait for the large model to think and reply, as shown in the figure below,

Then the robotic arm will point to the letter c,

3. Task Planning

1. Call seehat() to observe the environment and check the words on the desktop;
2. Reply with what the word on the desktop might be;
3. Call seehat() to observe the environment and check if the word on the desktop is spelled completely:

If incomplete: execute the following steps: (1) Call seehat() to observe the environment and get the position of the letters that can complete the word spelling;

(2) Call the point_to(x1, y1, x2, y2) function to point to that letter

If complete, call the finishtask() function.