1 / 28

Trained NeuroAnimator Demo

NeuroAnimator. Physical Model. Trained NeuroAnimator Demo. Which one is the physical model?. Example NeuroAnimators. Inputs: 12 Outputs: 6 Hidden Units: 20 Training set: 3K. Inputs: 8 Outputs: 6 Hidden Units: 40 Training set: 5K. Inputs: 17 Outputs: 13 Hidden Units: 50

Download Presentation

Trained NeuroAnimator Demo

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. NeuroAnimator Physical Model Trained NeuroAnimator Demo • Which one is the physical model?

  2. Example NeuroAnimators Inputs: 12 Outputs: 6 Hidden Units: 20 Training set: 3K Inputs: 8 Outputs: 6 Hidden Units: 40 Training set: 5K Inputs: 17 Outputs: 13 Hidden Units: 50 Training set: 13K Inputs: 84 / 76 Outputs: 78 / 36 Hidden Units: 50 / 40 Training set: 64K / 32K

  3. Multi-Link Pendulum Emulation • Passive pendulum in gravity

  4. Multi-Link Pendulum Emulation • Active pendulum (motor torques) in gravity

  5. Multi-Link Pendulum Emulation • Passive pendulum driven by external force

  6. Biomechanical Dolphin Emulation • 50-timestep emulator is in foreground

  7. Lunar Lander Emulation

  8. Pendulum Control Learning • Iteration 1

  9. Pendulum Control Learning • Iteration 3

  10. Pendulum Control Learning • Iteration 6

  11. Pendulum Control Learning • Iteration 9

  12. Pendulum Control Learning • Iteration 12

  13. Pendulum Control Learning • Iteration 15

  14. Controlling the Physical Model • Physical pendulum model is purple

  15. Dolphin Locomotion Learning • Iteration 1

  16. Dolphin Locomotion Learning • Iteration 3

  17. Dolphin Locomotion Learning • Iteration 5

  18. Dolphin Locomotion Learning • Iteration 8

  19. Dolphin Locomotion Learning • Iteration 11

  20. Dolphin Locomotion Learning • Iteration 14

  21. Controlling the Physical Model

  22. Lander Control Learning • Iteration 1

  23. Lander Control Learning • Iteration 3

  24. Lander Control Learning • Iteration 6

  25. Lander Control Learning • Iteration 9

  26. Lander Control Learning • Iteration 12

  27. Lander Control Learning • Iteration 15

  28. Controlling The Physical Model

More Related