Online learning for characterizing unknown environments in ground robotic vehicle models

Alec Koppel, Jonathan Fink, Garrett Warnell, Ethan Stump, Alejandro Ribeiro

Abstract

In pursuit of increasing the operational tempo of a ground robotics platform in unknown domains, we consider the problem of predicting the distribution of structural state-estimation error due to poorly-modeled platform dynamics as well as environmental effects. Such predictions are a critical component of any modern control approach that utilizes uncertainty information to provide robustness in control design. We use an online learning algorithm based on matrix factorization techniques to fit a statistical model of error that provides enough expressive power to enable prediction directly from motion control signals and low-level visual features. Moreover, we empirically demonstrate that this technique compares favorably to predictors that do not incorporate this information.
BibTeX
@inproceedings{koppel2016online,
  author = {Alec Koppel and Jonathan Fink and Garrett Warnell and Ethan Stump and Alejandro Ribeiro},
  title = {{Online learning for characterizing unknown environments in ground robotic vehicle models}},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
  year = {2016},
  doi = {10.1109/iros.2016.7759118},
}

Loading related content...

Figure