← back

targeted synthetic data finds policy failure regions

We map where robot policies fail, generate synthetic demos in those regions, and test whether the data improves training. Square_D1 shows a +7.0pp transfer result; Square_D0 is high-variance across five seeds.

Before and after

The videos are an illustrative Square_D0 scene: same seed, same scene, same BC-RNN architecture. The aggregate scientific read comes from the five-seed table below.

Before
Seed policy misses the grasp. 1000 seed demos · never grasped
After
Synthetic adversarial data solves this scene. 1000 seed + 95 synthetic demos · success

Benchmark

Square_D0 success rate across five independent training seeds with 200 rollouts per seed. The original single-seed lift was not robust; targeted data beats uniform on mean, but not the seed baseline.

Policy Training data Mean success
Seed baseline 1000 seed demos 73.9% ± 9.0pp
Uniform control 1000 seed + 95 uniform MimicGen demos 67.5% ± 8.6pp
Mild KDE adversarial 1000 seed + 95 adversarial MimicGen demos 70.6% ± 8.8pp

Failure modes

Counts below are from the original 200-rollout Square_D0 example used for the visual demo. They explain the failure regions the sampler targets; they are not the five-seed aggregate result.

Outcome Seed Uniform Adversarial
Successes 139 143 148
Placement near misses 45 27 28
Never grasped 13 27 22
Dropped 3 3 1