Fast Motion Prediction for Collaborative Robotics
Abstract
The efficient and safe performance of collaborative robots requires advancements in perception, control, design and algorithms, among other factors. With regard to algorithms, representing the structure of collaborative tasks and reasoning about progress toward task completion in an on-line fashion enables a robot to be a fluent and safe collaborator based on its ability to predict the next actions of a human agent. With this goal in mind, we focus on real-time target prediction of human reaching motion and present an algorithm based on time series classification. Results from on-line testing involving a tabletop task with a PR2 robot yielded 70% prediction accuracy with 400 msec of observed trajectory. PDF
Cite
Text
Pérez-D'Arpino and Shah. "Fast Motion Prediction for Collaborative Robotics." International Joint Conference on Artificial Intelligence, 2016.Markdown
[Pérez-D'Arpino and Shah. "Fast Motion Prediction for Collaborative Robotics." International Joint Conference on Artificial Intelligence, 2016.](https://mlanthology.org/ijcai/2016/perezdaposarpino2016ijcai-fast/)BibTeX
@inproceedings{perezdaposarpino2016ijcai-fast,
title = {{Fast Motion Prediction for Collaborative Robotics}},
author = {Pérez-D'Arpino, Claudia and Shah, Julie A.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2016},
pages = {3988-3989},
url = {https://mlanthology.org/ijcai/2016/perezdaposarpino2016ijcai-fast/}
}