Long-Horizon Prediction and Uncertainty Propagation with Residual Point Contact Learners
Name
2009.03994.pdf
Description
Accepted version
Size
1.06 MB
Format
Unknown
Checksum (MD5)
3aa52bb81efe159ad54c262044106b42
Author(s)
Fazeli, Nima
Ajay, Anurag
Rodriguez Garcia, Alberto
Date Issued
2020
Journal
Proceedings - IEEE International Conference on Robotics and Automation
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Fazeli, Nima, Ajay, Anurag and Rodriguez, Alberto. 2020. "Long-Horizon Prediction and Uncertainty Propagation with Residual Point Contact Learners." Proceedings - IEEE International Conference on Robotics and Automation.
Version
Author's final manuscript
Abstract
The ability to simulate and predict the outcome of contacts is paramount to the successful execution of many robotic tasks. Simulators are powerful tools for the design of robots and their behaviors, yet the discrepancy between their predictions and observed data limit their usability. In this paper, we propose a self-supervised approach to learning residual models for rigid-body simulators that exploits corrections of contact models to refine predictive performance and propagate uncertainty. We empirically evaluate the framework by predicting the outcomes of planar dice rolls and compare it's performance to state-of-the-art techniques.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/ICRA40945.2020.9196511
