ScheduleGen: Demonstration Generation via Skill Scheduling for Multi-Arm Imitation Learning
ScheduleGen: Demonstration Generation via Skill Scheduling for Multi-Arm Imitation Learning
This paper presents ScheduleGen, an integrated planning and scheduling algorithm for generating safe demonstrations for multi-arm robots. Evaluated on 28 simulation tasks, it achieves 79.6% mean data-generation success and outperforms state-of-the-art baselines in real-world transfer with 50-80% success across eight variants.
ScheduleGen introduces a planning and scheduling algorithm for generating safe multi-arm robot demonstrations, improving data-generation success in simulation and real-world transfer.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S4
Reported numbers
simulation task variants
28
View original evidence
grated planning & scheduling algorithm for multi-arm demonstration generation. 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
Open source S4real-world variants
8
View original evidence
achieve 50-80% success across eight real-world variants through zero-shot sim-to-real and real-to-sim-to-real transfer. Videos and more at: https://schedulegen.github.io/
Open source S5RoboDojo tasks
7
View original evidence
grated planning & scheduling algorithm for multi-arm demonstration generation. 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
Open source S4
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
grated planning & scheduling algorithm for multi-arm demonstration generation. 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
Open source S4
achieve 50-80% success across eight real-world variants through zero-shot sim-to-real and real-to-sim-to-real transfer. Videos and more at: https://schedulegen.github.io/
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org