Goal: Create a pipeline that takes a few episodes of OpenArm manipulation and generates over a few K episodes. Main Tasks: - [x] Obtain Doga's OpenARM robot manipulation dataset as human-guided episode - [ ] Try tools like [DexMimicGen](https://github.com/NVlabs/dexmimicgen/) and design the pipeline - [ ] Generate few K episodes for a couple of robot tasks (e.g., pick-and-place cubic and open closet door) - [ ] Replay episodes in Isaac Sim Optional Tasks: - [ ] Augment other sensor data (e.g., tactile) in generated synthetic dataset - [ ] Analyze # of episodes VS training accuracy (if we can finetune a VLA model with this dataset) Success Criteria: - [ ] End-to-end workflow document showing an example workflow from putting episodes for a task and getting x1000 dataset - [ ] Getting thousands of episode for the two robot tasks
Goal: Create a pipeline that takes a few episodes of OpenArm manipulation and generates over a few K episodes.
Main Tasks:
Optional Tasks:
Success Criteria: