Bayesian-inferred Flexible Path Generation in Human-Robot Collaborative Networks.

Abstract

This paper presents a novel method for generating the trajectory of a robot assisting a human in servicing a set of tasks embedded in a convex 2-D domain. This method makes use of Bayesian inference to predict human intent in task selection. Rather than following optimal trajectory towards a single task, the robot computes a set of potentially optimal tasks each weighted by the human's posterior probability and superimposes them into a cost function that is designed to minimize the weighted Euclidean distance relative to set. The effect is a flexible path human-robot collaborative network that is shown in simulation to complete all tasks in a given domain in less time than existing methods for a certain class of highly impulsive humans, i.e., humans that tend to randomly switch tasks at times generated by a Poisson counting process. The algorithm is also illustrated through an experimental demonstration.

Bib

@inproceedings{DBLP:conf/iros/BentzP18,
  author       = {William Bentz and
                  Dimitra Panagou},
  title        = {Bayesian-inferred Flexible Path Generation in Human-Robot Collaborative
                  Networks},
  booktitle    = {2018 {IEEE/RSJ} International Conference on Intelligent Robots and
                  Systems, {IROS} 2018, Madrid, Spain, October 1-5, 2018},
  pages        = {1816--1822},
  publisher    = {{IEEE}},
  year         = {2018},
  url          = {https://doi.org/10.1109/IROS.2018.8593611},
  doi          = {10.1109/IROS.2018.8593611},
  timestamp    = {Wed, 16 Oct 2019 14:14:51 +0200},
  biburl       = {https://dblp.org/rec/conf/iros/BentzP18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}