Getting it right the first time: Robot mission guarantees in the presence of uncertainty

Abstract

Certain robot missions need to perform predictably in a physical environment that may only be poorly characterized in advance. We have previously developed an approach to establishing performance guarantees for behavior-based controllers in a process-algebra framework. We extend that work here to include random variables, and we show how our prior results can be used to generate a Dynamic Bayesian Network for the coupled system of program and environment model. Verification is reduced to a filtering problem for this network. Finally, we present validation results that demonstrate the effectiveness of the verification of a multiple waypoint robot mission using this approach.

DOI: 10.1109/IROS.2013.6697122

Extracted Key Phrases

9 Figures and Tables

Cite this paper

@article{Lyons2013GettingIR, title={Getting it right the first time: Robot mission guarantees in the presence of uncertainty}, author={Damian M. Lyons and Ronald C. Arkin and P. Nirmal and Shu Jiang and Tsung-Ming Liu and J. Deeb}, journal={2013 IEEE/RSJ International Conference on Intelligent Robots and Systems}, year={2013}, pages={5292-5299} }