sim2real.world · gap index
Sim-to-real gap index
What each paper reported in simulation, what it reported on hardware, and the number it did not give. Every value carries a verbatim quote from the paper's own text; an empty cell means the paper does not report it.
| paper | task | sim | real | not reported |
|---|---|---|---|---|
| ScheduleGen: Demonstration Generation via Skill Scheduling for Multi-Arm Imitation Learning | — | 65.5%mean policy success | 50–80%success across eight real-world variants |
|
| Explore Where It Matters: Targeted Exploration for Efficient Rover Adaptation | DARTS | approximately 90%slope-climbing success | within three to five real-world trialsrecovery of coordinated active-suspension locomotion |
|
| SimRetract: Zero-Shot Sim-to-Real Robotic Assistance for Retractor Take-Over in Open Surgery | Isaac Sim | 94%grasp success rate on held-out simulated presentations | 90%grasp success rate on surgeon-defined real presentations+4.0 pp |
|
| Omni-IGN: Onboard Image-Goal Navigation for Drones with Omnidirectional Vision | Habitat, IsaacSim | not reported | not reported |
|
| ActiveAlign: Aligning Egocentric Manipulation via Active Perception | MuJoCo | not reported | not reported |
|
| From Biological Curves to Soft Modular Robots: Learning-Based Inverse Design with Uncertainty-Guided Refinement | — | 93%shape reconstruction success rate | not reported |
|
6 rows · extracted by an automated pass, every value quote-verified against the paper text · built 2026-10-31 · gaps.json
This is a record of reporting, not a ranking. A missing number is a finding, not an error: the last column lists metrics a reader needs to judge transfer that the paper does not supply.
This is a record of reporting, not a ranking. A missing number is a finding, not an error: the last column lists metrics a reader needs to judge transfer that the paper does not supply.