Downloads · 30 days
20
100% of all-time downloads
Bigenlight/flow_matching_carrot_in_pot_ee
flow_matching_carrot_in_pot_ee is a robotics model from Bigenlight. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for lerobot. The card lists the license as cc-by-nc-4.0.
Text-conditioned flow-matching policy (multitaskdit, CLIP text encoder, Euler ODE) trained on the real UR7e "Put carrot in pot" demonstrations (54 GELLO-teleop takes, 30 fps) in the EEF-delta action space (eefdeltav1)…
Downloads · 30 days
20
100% of all-time downloads
All-time downloads
20
Public
Parameters
249M
997 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors997 MB · 100%
From the Hugging Face model README
Text-conditioned flow-matching policy (multi_task_dit, CLIP text encoder, Euler ODE) trained on
the real UR7e "Put carrot in pot" demonstrations (54 GELLO-teleop takes, 30 fps) in the
EEF-delta action space (eef_delta_v1). This is the 60k-step checkpoint (best open-loop
chunk-30 error of 10k..100k; kanu kept only 100k).
eef_delta_v1)observation.state 16-D = [q1..q6 (rad, UR order), tcp_x, tcp_y, tcp_z (m, base_link), r11, r21, r31, r12, r22, r32 (first two columns of the TCP rotation), grip_pos (0=open..1=closed)].
TCP = ur_kin.fk(q) + 0.174 m along flange +Z.action 7-D = [dx, dy, dz, drx, dry, drz, grip_cmd] — achieved per-frame TCP motion
(dp = p_{t+1}-p_t, drot = so3_log(R_{t+1} R_t^T), base frame), gripper absolute 0..1.
Deploy: p_target = p_live + dp, R_target = so3_exp(drot) R_live, analytic IK, branch locking.cam1 (scene), cam2 (wrist), native 720×1280 fed in; the policy resizes internally
to image_resize_shape = [224, 224] — do not pre-resize (double-resize silently degrades)."Put carrot in pot" (CLIP-conditioned; send it every tick).chunk_size 32, n_action_steps 24, n_obs_steps 2, num_integration_steps 100 at train
time (10 is the usual serving override), DiT hidden 512 × 6 layers.carrot_in_pot_eef_lerobot_v3 — local LeRobot v3 re-export of
Bigenlight/carrot_in_pot_lerobot_v3
(54 ep / 17,085 frames; joints de-lagged by per-take τ≈0.90 s + linear re-interpolation).
Not yet on the Hub.lerobot-train, batch 8, seed 1000, 100k steps (10 h 15 m on one RTX A4000, kanu), job fm_carrot_eef.| 10k | 20k | 30k | 60k (this) | 100k | zero-motion |
|---|---|---|---|---|---|
| 34.8 mm | 32.8 mm | ~33 mm | 32.0 mm | 32.6 mm | 65.6 mm |
lerobot's eval_loss rose monotonically 0.096→0.233 over the run while the open-loop metric
kept improving — it was ignored for checkpoint selection.
Real-robot closed-loop evaluation: not yet run. The shipped ZMQ servers
(gello_policy/policy_server/fm_server.py) are joint-space 7/7 and refuse this checkpoint's
16-D state; serving needs the EEF-mode deploy node from branch feat/carrot-eef-il.