Model Card for act_so100_cls_block_color

Action Chunking Transformer Policy trained for the classification with block colort blue or green.

When found blue block in circle, SO-ARM100 pick up block and place on right side, also when to found green block then place left side.

How to Get Started with the Model

See the Lerobot library

We strong recommend the environment needs to be the same as the video. I use the camera of Macbook Air M2, Also The model was inference by Macbook Air M2 16GB.

Training Details

Trained with LeRobot@674e784.

The model was trained using LeRobot's training script and with the masato-ka/so100_grasp_lego dataset, using this command:

python lerobot/scripts/train.py \
  --dataset.repo_id='masato-ka/so100_lego_sort' \
  --policy.type=act \
  --output_dir=outputs/train/act_so100_lego_sort \
  --job_name=act_so100_lego_sort \
  --policy.device=cuda \
  --wandb.enable=true

The training curves may be found at https://wandb.ai/masato-ka-personal/lerobot/runs/q9wlvme3. The current model corresponds to the checkpoint at 100k steps.

This took about 1h35m to train on an Nvida A100.