A foundation model for continuous control
Project description
A Foundation Model for Continuous Control
Supports Python >= 3.6
from foundation_model import Quadrotor
import numpy as np
from scipy.spatial.transform import Rotation as R
quadrotor = Quadrotor()
position = [0, 0, 0]
orientation = [1, 0, 0, 0]
orientation_rotation_matrix = R.from_quat(np.array(orientation)[[1, 2, 3, 0]]).as_matrix().ravel().tolist()
linear_velocity = [0, 0, 0]
angular_velocity = [0, 0, 0]
previous_action = [0, 0, 0, 0]
observation = np.array([position + orientation_rotation_matrix + linear_velocity + angular_velocity + previous_action])
quadrotor.reset()
action = quadrotor.evaluate_step(observation)
print(action)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
foundation_model-0.0.10.tar.gz
(111.2 kB
view details)
File details
Details for the file foundation_model-0.0.10.tar.gz.
File metadata
- Download URL: foundation_model-0.0.10.tar.gz
- Upload date:
- Size: 111.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
920422c9b42d2a5ae0417668e29d4d41dc0866fa4025747cf5afbb86aa722903
|
|
| MD5 |
3bfac7f7d3d1c073c9cb78ec16af7ee6
|
|
| BLAKE2b-256 |
c53b29dd9d09db2dc5e38e89d50521ae65ef39a01a080dad991f9d19103155d7
|