IkerAzurmendi/act-pick-v3-chunk60-4800

robotics model by IkerAzurmendi

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Earlier source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Same data as the 1-2 piece v3 run, but with a shorter chunk of 60 targets (a 2 s plan instead of 3 s): checkpoint at 4,800 steps of a 12,000-step run. ACT policy for the SO-101 "pick a piece from the crate and hold it up to the camera" task. Inputs: front camera, wrist camera and the six joint positions; output: a chunk of 60 future joint targets at 30 fps. This is the checkpoint at 4,800 steps. 331 training episodes, same selection as act-pick-v3-1-2-pieces-18000 (30 fps, one or two pieces, quality filter). Recipe: LeRobot train(), batch 8, chunk 60, 30 action steps per replan, learning rate 1e-5, LeRobot default image augmentation (colour, sharpness, small affine), seed 1000. Held out: 16 episodes, 12 from so101-pick-cube20261024181939 (one piece, varied positions) and 4 from so101-pick-cube20261024144537 (two pieces). Mean absolute joint error over the predicted chunk (lower is better) against a "stay…

IkerAzurmendi/act-pick-v3-chunk60-4800 on Hugging Face A short preview, not the full document.

The latest refresh did not succeed. This is the last available preview; check the original for changes.

Read the full model card ↗ · Preview checked 2026-10-25T07:54:40.488Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

IkerAzurmendi/act-pick-v3-chunk60-4800 is a robotics model repository published by IkerAzurmendi on Hugging Face. The source reports the lerobot library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: robotics
Library: lerobot
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: 51,627,654
Architecture: Not reported
License: apache-2.0
Access: Not gated by Hugging Face
Created: 2026-10-25T06:18:38.000Z
Last modified: 2026-10-25T06:18:45.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion