sim2real.world · gap index · arXiv:2610.39429
ScheduleGen: Demonstration Generation via Skill Scheduling for Multi-Arm Imitation Learning
- task
- multi-arm contact-rich manipulation
- hardware
- not stated
- simulator
- not stated
- transfer
- zero-shot
- sim result
- 65.5%
- real result
- 50–80%
The paper does not report a comparable success rate on both sides, so the gap cannot be computed.
What the paper says
We evaluate ScheduleGen on 28 simulation task variants, including seven externally authored RoboDojo tasks and settings inaccessible to prior systems; it achieves 79.6% mean data-generation success and trains policies with 65.5% mean success.
ScheduleGen policies outperform those trained on a state-of-the-art data generation baseline, and achieve 50–80% success across eight real-world variants through zero-shot sim-to-real and real-to-sim-to-real transfer.
What it does not report
- real-world mean success rate
- per-task real-world success rates
- number of real-world trials per variant
Extraction is automated; every quote above was checked as a verbatim substring of the paper text. If a row is wrong, say so and the correction is recorded and credited: [email protected].