Motion-generation system for violin-playing robot using reinforcement learning differences in bowing parameters due to changes in learning conditions and sound pressure values
Kenzo Horigome, Koji Shibuya · 2024
Read Motion-generation system for violin-playing robot using reinforcement learning differences in bowing parameters due to changes in learning conditions and sound pressure values by Kenzo Horigome, Koji Shibuya (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11634750.txt.
Description
Kenzo Horigome and Koji Shibuya build a learning system that teaches a robot how to bow a violin from a printed score, in a 2024 paper. Their system reads each note's loudness from the score and chooses bow speed and direction to match it, aiming for expressive sound. It learns by reinforcement, using Q-learning with a neural network standing in for the value table.
Simulations on phrases from a folk tune varied the learning settings and the target loudness per note. As the settings improved, penalties fell and rewards rose, and the robot kept up even when target loudness changed. The authors conclude that expressive automated bowing is achievable this way.
Catalog record
| CREATOR | Kenzo Horigome, Koji Shibuya |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 26 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |