kiteml / dual-openyam-close-box-diffusion

Diffusion Policy · dual OpenYAM, "close the box"

A Diffusion Policy policy for a bimanual OpenYAM robot, trained on kiteml/dual-openyam-close-box to close the box . Diffusion Policy is a visuomotor policy that generates action sequences by iterative denoising. Trained from scratch.

Trained with Kite on LeRobot v0.6.0.

Training

Inputs and outputs

Each inference call predicts 64 actions (2.1 s at 30 fps) and executes 32 of them, conditioned on the last 2 observations.

Usage

Requires LeRobot v0.6.0 or later.

import torch
from lerobot.policies.factory import get_policy_class, make_pre_post_processors

repo_id = "kiteml/dual-openyam-close-box-diffusion"
policy = get_policy_class("diffusion").from_pretrained(repo_id)
preprocessor, postprocessor = make_pre_post_processors(policy.config, pretrained_path=repo_id)

# observation: the input features above, formatted like a LeRobotDataset frame
# (images as float tensors in [0, 1], channels first)
observation["task"] = "close the box"
with torch.inference_mode():
    action = postprocessor(policy.select_action(preprocessor(observation)))

To run it with LeRobot's CLI tools, pass --policy.path=kiteml/dual-openyam-close-box-diffusion to lerobot-record or lerobot-eval .

Evaluation

Not evaluated yet. The loss above is the final training loss, and no rollouts on the robot or in simulation have been scored.

Other policies trained on this dataset

ACT · π₀ · π₀.₅ · π₀-FAST · SmolVLA · VLA-JEPA · X-VLA