12V/Assembled

Your kit has been calibrated and teleoperated to make sure that it works well.

Upon receiving the assembled arm, follow these additional steps to complete the assembly.

Refer to the images and position the electronics and hardware appropriately.

You package consists of one leader + one follower arm + one mobile base.

Place a 12V power supply and a servo board in the empty spots on your base plate as shown below.

Then,

1. Connect the wires from the 12V battery, DC plug connector, and power converter to the lever connector.

2. Attach the DC plug connector to the servo board to power the motor control board.

3. Connect the wires from the follower arm and mobile base to the motor control board.

4. You may find it easier to screw the follower arm to the top plate before connecting the top plate to the base plate.

Attach the Raspberry Pi to the top plate using M3 x 16 screws and nuts. Then, secure the top plate to the base plate with four more M3 x 16 screws

Connect follower arm to top plate using 2 m3 x 30 screws. You are now ready for software!

Part II

1. For setting up the Raspberry Pi and its SD-card see: Setup PI. Here is explained how to download the Imager to install Raspberry Pi OS or Ubuntu.

2. Take the sd card and connect it to your laptop.

3. After setting up your Pi, you should enable and set up SSH (Secure Shell Protocol) so you can log in to the Pi from your laptop without requiring a screen, keyboard, and mouse on the Pi. A great tutorial on how to do this can be found here. Logging into your Pi can be done in your Command Prompt (cmd) or, if you use VSCode you can use this extension. Here's a video on how to do it.

4. 1. Download source code on both pc as well as raspberry pi:

      git clone https://github.com/huggingface/lerobot.git
      cd lerobot

   2. Install miniconda (for raspberry pi)

      1. wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-aarch64.sh
         bash Miniconda3-latest-Linux-aarch64.sh

      2. source ~/.bashrc

   3. Install miniconda (for pc)

   4. Create a virtual environment with Python 3.10,

      conda create -y -n lerobot python=3.10

   5. Then activate your conda environment, you have to do this each time you open a shell to use lerobot:

      conda activate lerobot

   6. When using miniconda, install ffmpeg in your environment:

      conda install ffmpeg -c conda-forge

   7. Install 🤗 LeRobot:

      pip install -e .

   8. In addition to these instructions, you need to install the Feetech sdk on your Pi which you can skip on your laptop:

      Copied

      pip install -e ".[feetech]"

   9. Don't forget to Install LeRobot on laptop using the same steps as above [step 4].

5. Make sure that one motor board is connected to you pc [leader arm] and another to raspberry pi [follower arm] and run on both:

python -m lerobot.find_port

Example output:

Finding all available ports for the MotorBus.
['/dev/tty.usbmodem575E0032081']
Remove the USB cable from your MotorsBus and press Enter when done.

[...Disconnect corresponding leader or follower arm and press Enter...]

The port of this MotorsBus is /dev/tty.usbmodem575E0032081
Reconnect the USB cable.

The port for the follower arm willl look like

Finding all available ports for the MotorBus.
['/dev/ttyACM0']
Remove the USB cable from your MotorsBus and press Enter when done.

[...Disconnect corresponding leader or follower arm and press Enter...]

The port of this MotorsBus is /dev/ttyACM0
Reconnect the USB cable.

7. Calibration

Now we have to calibrate the leader arm and the follower arm. The wheel motors don’t have to be calibrated. The calibration process is very important because it allows a neural network trained on one robot to work on another.

8. Calibrate follower arm (on mobile base)

Make sure the arm is connected to the Raspberry Pi and run this script or API example (on the Raspberry Pi via SSH) to launch calibration of the follower arm:

python -m lerobot.calibrate \
    --robot.type=lekiwi \
    --robot.id=my_awesome_kiwi # <- Give the robot a unique name

9. Calibrate leader arm

Then, to calibrate the leader arm (which is attached to the laptop/pc). Run the following command of API example on your laptop:

python -m lerobot.calibrate \
    --teleop.type=so101_leader \
    --teleop.port=/dev/tty.usbmodem58760431551 \ # <- The port of your robot
    --teleop.id=my_awesome_leader_arm # <- Give the robot a unique name

1. Teleoperate LeKiwi

If you’re using a Mac, you might need to give Terminal permission to access your keyboard for teleoperation. Go to System Preferences > Security & Privacy > Input Monitoring and check the box for Terminal.

To teleoperate, SSH into your Raspberry Pi, and run conda activate lerobot and this command:

python -m lerobot.common.robots.lekiwi.lekiwi_host --robot.id=my_awesome_kiwi

Then on your laptop, also run conda activate lerobot and run the API example, make sure you set the correct remote_ip and port in examples/lekiwi/teleoperate.py.

python examples/lekiwi/teleoperate.py

Now you can move the leader arm and use the keyboard (w,a,s,d) to drive forward, left, backwards, right. And use (z,x) to turn left or turn right. You can use (r,f) to increase and decrease the speed of the mobile robot. Refer to the following table for more information on commands.

W	Move forward
A	Move left
S	Move backward
D	Move right
Z	Turn left
X	Turn right
R	Increase speed
F	Decrease speed

1. Here's a concise guide to recording a dataset using Hugging Face's documentation for more information

Should you have any issue, reach out to [e-mail] !