Kick (right foot)

Kick (right foot) (poster)

An official Microduck move: Pollen Robotics' kick (right foot), retrained from scratch by Microduck Academy with the upstream recipe as-is (task Mjlab-BallKick-Flat-MicroDuck of pollen-robotics/microduck_rl at 2b25a48, 3999 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 ball_kick_right.onnx.

Pollen Robotics' kick: a 0.5 s right-foot kick at a ball placed in front of the foot, then back to the walk.

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

number this move Pollen's ball_kick_right.onnx
final_upright True True
max_tilt 0.261 0.261
base_z_mean 0.1149 0.1141
base_z_min 0.1106 0.1125
ball_travel_m 0.338 0.326
ball_travel_x_m 0.338 0.326
ball_travel_y_m -0.017 0.018
ball_peak_speed_m_s 0.477 0.503
upright_at_0_5s True True
tilt_at_0_5s 0.027 0.008

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

Run it on a robot

sudo robotctl policy add kick-right-foot tfrere/microduck-move-base-kick-right
robotctl robot do kick-right-foot

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