BorjaBG/modelo_servir_2
Robotic policy for a manipulator arm
1 min read
Trained using ACT (Action Chunking with Transformers — an imitation learning method that predicts short action chunks instead of single steps), this model is designed for the so_follower robotic manipulator arm. It enables the task of serving a bowl to a human based on teleoperation data. Created using the LeRobot library, the model utilizes both a front-facing camera and an end-effector camera on the robot's gripper. This is useful for researchers and practitioners in home and laboratory robotics using LeRobot.
Key features
- ACT architecture built on the LeRobot robotics framework.
- Visual observation processing from two cameras (front and gripper-mounted).
- Tailored for performing a specific household serving task.
- Trained on a dataset of 30 episodes and 10,325 frames.
What you can do
- Run the policy on a compatible so_follower robot to autonomously execute the serving task.
- Train your own similar model on a custom dataset using LeRobot utilities.
Example
Running the ready-made robot control policy:
lerobot-rollout \
--strategy.type=base \
--robot.type=so_follower \
--robot.port= \
--policy.path=BorjaBG/modelo_servir_2 \
--task="Servir el bol a una persona" \
--duration=60Read more
DetailsTraining configuration: 18,000 steps, batch size 8, AdamW optimizer, learning rate 1e-05.
Hardware: 640x480 cameras at 30 FPS, 6-DOF manipulator state.
Dataset: BorjaBG/Servir (30 episodes, 10,325 frames).










Comments