Sit and stand

Sit and stand (poster)

An official Microduck move: Pollen Robotics' sit and stand, retrained from scratch by Microduck Academy with the upstream recipe as-is (task Mjlab-SitStand-Flat-MicroDuck of pollen-robotics/microduck_rl at 2b25a48, 5999 iterations, 4096 envs, no reward edit), so that it carries the base/model.pt checkpoint the Academy needs to remix it. The policy Pollen ships is alpha_sitstand.onnx.

Pollen Robotics' sit and stand: one policy, a posture flag in the twist slot (1 = sit, 0 = stand), gentle both ways.

Fidelity check (this move vs Pollen's policy, same scene, same command, take flag)

number this move Pollen's alpha_sitstand.onnx
final_upright True True
max_tilt 0.265 0.536
base_z_mean 0.0938 0.0911
base_z_min 0.0593 0.056
z_stand 0.1155 0.1107
z_sit 0.0597 0.0595
z_stand_after 0.1156 0.1159
t_to_sit_s 0.58 0.28
t_to_rise_s 0.24 0.26

Recorded with space/payload/render/rollout.py on the upstream robot MJCF (spikes/base_moves/fidelity.py).

Run it on a robot

robotctl policy load sitstand tfrere/microduck-move-base-sitstand

This move takes a posture flag (command.encoding: posture_flag on twist.vx: 1.0 = sit, 0.0 = stand). robotctl policy add refuses it: policy load puts it in the sitstand slot, the daemon's sit / stand button drives the flag.

Files

policy.onnx (play it, normalizer baked in), base/model.pt + base/agent.yaml + base/env.yaml (the rsl_rl checkpoint and configs: remix = fine-tune from it), rollouts/0.traj (trajectory.v1 showcase take, with the commands), video.mp4 + poster.jpg (the card clip), manifest.json (schema 2 + academy block: origin, source task and policy, training facts, fidelity numbers), fidelity.json, train.json.

Credits and license

The task, the reward design, the robot model and the training recipe are Pollen Robotics' work (pollen-robotics/microduck_rl, Apache-2.0). This repo republishes a retrained policy of that recipe under the same Apache-2.0 license, with the checkpoint, so the Academy's users can start from it.

Downloads last month

-

Downloads are not tracked for this model. How to track
Video Preview
loading