dp-blockpick-yaw45-2k

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-yaw45-2k")); 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-topdown-yaw45-2k-full-dr2-3cam (not on HF yet): 2,000 successful sim demos, 343,765 frames, same task, full reachable region and dr2 randomization as padiredd/pick-cube-topdown-region10k-full-dr2-3cam, but the block yaw is uniform in
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 4090 24 GB (lab225), shared by the two yaw45-2k runs trained at the same time

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