Data Pyramid for Embodied Manipulation
- Published
- Source
- arXiv
- Paper number
- 728
- Field
- Robotics
- arXiv ID
- 2607.24744
Key points
- It organizes embodied-manipulation data into five sources: real robots, UMI-based collection, first-person and third-person video, simulation, and general vision-language data.
- It situates each source within the tension between scalability and robot alignment, comparing quality, diversity, reusability, and physical fidelity.
- It analyzes how embodied brains, VLAs, and world-action models select and mix multiple data sources during pretraining.
- This classification can serve as a reference framework for robotics researchers designing data mixtures around target capabilities and collection costs.
- A limitation is that six challenges remain unresolved, including large-scale tactile data, failure and recovery records, and action alignment across different robots.
Paper links
External research summaries. These are not HDATF publications or measured product results.