Generalizing Over Uncertain Dynamics for Online Trajectory Generation
Name
kim-isrr15.pdf
Description
Accepted version
Size
799.67 KB
Format
Adobe PDF
Checksum (MD5)
27975ee3d6172db8a811c6349002360c
Author(s)
Kim, Beomjoon
Kim, Albert
Dai, Hongkai
Kaelbling, Leslie
Lozano-Perez, Tomas
Date Issued
July 2017
Publisher
Springer Nature
Citation
Kim, Beomjoon, Kim, Albert, Dai, Hongkai, Kaelbling, Leslie and Lozano-Perez, Tomas. 2017. "Generalizing Over Uncertain Dynamics for Online Trajectory Generation."
Version
Author's final manuscript
Abstract
We present an algorithm which learns an online trajectory generator that can generalize over varying and uncertain dynamics. When the dynamics is certain,the algorithm generalizes across model parameters. When the dynamics is partially observable, the algorithm generalizes across different observations. To do this, we employ recent advances in supervised imitation learning to learn a trajectory generator from a set of example trajectories computed by a trajectory optimizer. In experiments in two simulated domains, it finds solutions that are nearly as good as, and sometimes better than, those obtained by calling the trajectory optimizer online. The online execution time is dramatically decreased, and the off-line training time is reasonable.
MIT Department
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/10.1007/978-3-319-60916-4_3
