Choose data for a manipulation experiment
Human motion, simulated trajectories and robot demonstrations answer different questions.
Match dataset fields and embodiment to a concrete learning question.
Write down what your learner needs
Does your experiment need images and poses, contact annotations, robot actions, or complete task trajectories? Specify the hand, sensors and task before choosing a dataset. A large collection can still lack the labels you need.
Match data to the question
ARCTIC and OakInk2 are starting points for bimanual human–object motion. DexMimicGen provides simulated robot demonstrations. DROID and Open X-Embodiment provide broader robot-learning data; do not assume they contain multi-finger hand actions.
Check one sample and its terms
Use the publisher’s access route and inspection tools. Check coordinate frames, units, action definitions, missing observations and train/test splits. Read dataset, code and body-model licenses separately. ARCTIC restricts commercial use and redistribution; DexMimicGen data and code have different licenses.
Make the choice explainable
Record the dataset release, task, inputs, labels, access terms and the main mismatch with your intended robot. Share that comparison and a small permitted result before investing in a larger training run.
Try it yourself
DATA FIT EXPLORER
Start with the learning question.
These are entry points for inspection, not ready-made compatibility recommendations. Follow the original release and check access terms before using data.
Your practical task
- Choose perception, action learning or simulated-grasp research in the data selector.
- Open one original dataset and inspect its schema and license.
- Write the required fields, available fields and the main mismatch.
What to produce: A dataset fit note with a concrete limitation and original source.
Check your understanding
Original sources & next steps
ARCTIC project and access ↗OakInk2 project ↗DexMimicGen release and licenses ↗DexYCB: hand and object observations, tasks and access ↗Original Dexhands teaching material. Interactive models and added references reviewed September 23, 2026; the introductory reading retains its September 22 review. Research links are not endorsements or evidence of hardware compatibility.