TR2017-176
Learning to Regulate Rolling Ball Motion
-
- "Learning to Regulate Rolling Ball Motion", IEEE Symposium on Computational Intelligence in Engineering Solutions, DOI: 10.1109/SSCI.2017.8285376, November 2017.BibTeX TR2017-176 PDF
- @inproceedings{Jha2017nov,
- author = {Jha, Devesh K. and Yerazunis, William S. and Nikovski, Daniel N. and Farahmand, Amir-massoud},
- title = {Learning to Regulate Rolling Ball Motion},
- booktitle = {IEEE Symposium on Computational Intelligence in Engineering Solutions},
- year = 2017,
- month = nov,
- doi = {10.1109/SSCI.2017.8285376},
- url = {https://www.merl.com/publications/TR2017-176}
- }
,
- "Learning to Regulate Rolling Ball Motion", IEEE Symposium on Computational Intelligence in Engineering Solutions, DOI: 10.1109/SSCI.2017.8285376, November 2017.
-
MERL Contacts:
-
Research Areas:
Artificial Intelligence, Data Analytics, Optimization, Robotics
Abstract:
In this paper, we present a problem of regulating the motion of a rolling ball in a one-dimensional space in the presence of non-linear effects of friction and contact. The regulation problem is solved using a model-based reinforcement learning technique. A Gaussian process model is learned to make predictions on the motion of the ball and then, the predictive model is used to solve for the control policy using dynamic programming by estimating the value functions. Several results are shown to demonstrate the simple, yet interesting motion dynamics for the ball. Our hope is that the proposed system will serve as a simple benchmark system for reinforcement and robot learning.
Related News & Events
-
NEWS MERL Researchers Demonstrate New Model-Based AI Learning Technology for Equipment Control Date: February 14, 2018
Where: Tokyo, Japan
MERL Contacts: Devesh K. Jha; Daniel N. Nikovski; Diego Romeres; William S. Yerazunis
Research Areas: Optimization, Computer VisionBrief- New technology for model-based AI learning for equipment control was demonstrated by MERL researchers at a recent press release event in Tokyo. The AI learning method constructs predictive models of the equipment through repeated trial and error, and then learns control rules based on these models. The new technology is expected to significantly reduce the cost and time needed to develop control programs in the future. Please see the link below for the full text of the Mitsubishi Electric press release.