diffusion-transformer
rdt-ft-data
Dataset Card
This is the fine-tuning dataset used in the paper RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation.
Source
Project Page: https://rdt-robotics.github.io/rdt-robotics/
Paper: https://arxiv.org/pdf/2410.07864
Code: https://github.com/thu-ml/RoboticsDiffusionTransformer
Model: https://huggingface.co/robotics-diffusion-transformer/rdt-1b
Uses
Download all archive files and use the following command to extract:
cat rdt_data.tar.gz.* |… See the full description on the dataset page: https://huggingface.co/datasets/robotics-diffusion-transformer/rdt-ft-data.aloha-data
Mobile Aloha Dataset for RDT
Dataset
Download the tfrecord_part_a* files from this repository. To reconstruct and extract the complete dataset, execute the following commands:
cat tfrecord_part_a* > tfrecord_part_a.zip
unzip tfrecord_part_a.zip
maniskill-dataBimanualUR5eExample
Dataset Summary
This dataset provides shards in the WebDataset format for fine-tuning RDT-2 or other policy models on bimanual manipulation.
Each sample packs:
a binocular RGB image (left + right wrist cameras concatenated horizontally)
a relative action chunk (continuous control, 0.8s, 30Hz)
a discrete action token sequence (e.g., from an Residual VQ action tokenizer)
a metadata JSON with an instruction key sub_task_instruction_key to index corresponding instruction from… See the full description on the dataset page: https://huggingface.co/datasets/robotics-diffusion-transformer/BimanualUR5eExample.DiffusionTransformersUseSinkRegisters-LinearProbe