act-green-square-test
robot control model for green square selection
2 min read
A manipulation control policy trained using the LeRobot framework and the ACT method (Action Chunking with Transformers — an imitation learning approach that predicts short action sequences instead of single steps). The model takes the robot state and images from two cameras (front and gripper) at a 640x480 resolution as input, and then outputs control vector commands to select the target object. The solution is built for so_follower type robots based on a dataset of 29 episodes and will be useful for robotics developers using the LeRobot ecosystem.
Key features
- ACT architecture: prediction of short action sequences instead of step-by-step control
- Multimodal data processing: joint states and two camera streams (front and gripper)
- Trained on a dataset of 29 episodes (14,236 frames at 30 FPS)
- Integration with LeRobot library version 0.7.1 and the adamw optimizer
What you can do
- Run the ready-made control policy on a real so_follower robot using the lerobot-rollout command
- Train a custom policy on user movement demonstrations using LeRobot scripts
- Configure camera parameters and connection ports for a specific robot hardware setup
Example
lerobot-rollout \
--strategy.type=base \
--robot.type=so_follower \
--robot.port= \
--robot.cameras="{ front: {type: opencv, index_or_path: 0, width: 640, height: 480, fps: 30}, gripper: {type: opencv, index_or_path: 1, width: 640, height: 480, fps: 30}}" \
--policy.path=albarodriguezsalvador/act-green-square-test \
--task="green-square-fix-movement-001 selects the green square between 4 squares"Read more
DetailsTraining parameters: 200 steps, batch size 8, learning rate 1e-05, seed 1000.
Input features: observation.state of dimension (6,), front and gripper images of dimension (3, 480, 640).
Outputs: action vector of dimension (6,).
Evaluation results on a real robot have not yet been provided by the author.










Comments