dp-blockpick-cap1k-dr2

LeRobot diffusion policy (ROBOTIS lerobot-cyclo fork, 288 M parameters) for a top-down block pick with the left arm of the ROBOTIS FFW SG2 (SG2 + ROBOTIS CAD gripper, calibrated wrist cameras, 29.25 in table).

Files at the repo root = step 100k (DiffusionPolicy.from_pretrained("padiredd/dp-blockpick-cap1k-dr2")); step-10000/, step-20000/, step-30000/, step-40000/, step-50000/, step-60000/, step-70000/, step-80000/, step-90000/ = intermediate checkpoints (every 10k steps).

data	pick-cube-cap1k-retry-dr2-3cam (not on HF yet): 1,000 successful sim demos, 196,577 frames, generated by a code-as-policy program (data_collection/cap, block_pick_retry.py: per-episode drawn grasp/approach/timing parameters, 30 % induced first-grasp misses followed by a retreat and regrasp, executed-only joint pushes with clean labels) over the left arm's region with the region10k dr2 recipe (start pose, gripper, spotlights, cameras, table height)
sampling	uniform over all frames (LeRobot default EpisodeAwareSampler)
inputs / outputs	head + left wrist + right wrist cameras, each 240x240, + 22-dim joint state; action = 16 joint targets, 15 Hz
image augmentation	heavy, random order, up to 5 of: brightness 0.6-1.4, contrast 0.6-1.4, saturation 0.3-1.7, hue +-0.1, sharpness 0.3-2.0, affine +-10 deg / 10 % / 0.9-1.1, perspective 0.2, blur, random erasing, grayscale
state noise	none
recipe	100k steps, batch 32, ResNet18 per camera, Adam 1e-4, cosine, DDPM 100 steps, horizon 64 / 32 executed, n_obs_steps 1, seed 1000
hardware	one NVIDIA RTX A5000 24 GB, ~5.7 steps/s

Task string: "pick up the lime green block with the left arm". Evaluation results are added once they are run.