SciEdu_steps_20261119_relabel_100k_pi05
robot arm control policy for educational experiments
2 min read
The model is a specialized checkpoint based on the pi05 architecture (a Vision-Language-Action model by Physical Intelligence) and adapted for the LeRobot framework (a PyTorch library for real-world robotics). It was trained on a dataset of 2,915 episodes for laboratory manipulation tasks involving chemical and physical equipment. The model takes the robot state and images from three cameras (a main camera and two wrist cameras) as input and outputs control actions. It is useful for researchers and engineers working with bi_openarm_follower robot arms in educational or research laboratories.
Key features
- Base model: trained on lerobot/pi05_base using the LeRobot library.
- Multimodality: processes a 16-dimensional system state and high-resolution visual data from three cameras.
- Wide range of tasks: includes handling leaves, laboratory beakers, pipettes, microscopes, electroscopes, and reagents.
- Ready to run: includes a training configuration for 100,000 steps using the AdamW optimizer.
What you can do
- Run on a robot: apply the ready-made control policy to perform laboratory operations using the
lerobot-rolloutscript. - Conduct experiments: automate school or student chemistry and physics experiments using a robot arm.
- Fine-tune the model: use the checkpoint for further fine-tuning on custom datasets via
lerobot-train.
Example
Running the pre-built robot control policy to perform an object relocation task:
lerobot-rollout \
--strategy.type=base \
--robot.type=bi_openarm_follower \
--robot.port= \
--robot.cameras="{ : {type: opencv, index_or_path: , width: 640, height: 480, fps: 30}, : {type: opencv, index_or_path: , width: 640, height: 480, fps: 30}}" \
--policy.path=leapshared/SciEdu_steps_20261119_relabel_100k_pi05 \
--task="put the leaf on the right side" \
--duration=60Read more
DetailsLicense: apache-2.0
Size: 4.14 billion parameters
Dataset: 2,915 episodes, 903,521 frames (30 FPS)
Training parameters: 100,000 steps, batch size 32, learning rate 2.5e-05, seed 42










Comments