FTG64mit
ACT action chunking under delay and disturbance: per-episode results
Raw outputs from a study evaluating ACT action chunking with simulated delays and disturbances on ALOHA transfer cube tasks, stored as per-episode JSON records with detailed performance metrics and condition parameters.
Downloads168
Technical Profile
- Robot Embodiments
- ALOHA
- Environment
- simulation
- Task Types
- manipulationpick_and_place
- Data Format
- json
- License
- mit
Access
Need custom physical AI data?
Claru builds purpose-built datasets for simulation applications with dense human annotations and quality assurance.
Request a Sample Pack