tags:
- microduck-academy-policy
- microduck-policy
- academy
- official
- family:ballkick
- kind:episodic
- tier:1
- microduck
- robotics
- reinforcement-learning
- onnx
license: apache-2.0
library_name: onnx
Kick (right foot)
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.