Socially Fair Coverage: The Fairness Problem in Coverage Planning and a New Anytime-Fair Method

TY - CHAP

T1 - Socially Fair Coverage

T2 - 2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021

AU - Brandao, Martim

N1 - Publisher Copyright: © 2021 IEEE.

PY - 2021/7/8

Y1 - 2021/7/8

N2 - In this paper we investigate and characterize social fairness in the context of coverage path planning. Inspired by recent work on the fairness of goal-directed planning, and work characterizing the disparate impact of various AI algorithms, here we simulate the deployment of coverage robots to anticipate issues of fairness. We show that classical coverage algorithms, especially those that try to minimize average waiting times, will have biases related to the spatial segregation of social groups. We discuss implications in the context of disaster response, and provide a new coverage planning algorithm that minimizes cumulative unfairness at all points in time. We show that our algorithm is 200 times faster to compute than existing evolutionary algorithms-while obtaining overall-faster coverage and a fair response in terms of waiting-time and coverage-pace differences across multiple social groups.

AB - In this paper we investigate and characterize social fairness in the context of coverage path planning. Inspired by recent work on the fairness of goal-directed planning, and work characterizing the disparate impact of various AI algorithms, here we simulate the deployment of coverage robots to anticipate issues of fairness. We show that classical coverage algorithms, especially those that try to minimize average waiting times, will have biases related to the spatial segregation of social groups. We discuss implications in the context of disaster response, and provide a new coverage planning algorithm that minimizes cumulative unfairness at all points in time. We show that our algorithm is 200 times faster to compute than existing evolutionary algorithms-while obtaining overall-faster coverage and a fair response in terms of waiting-time and coverage-pace differences across multiple social groups.

UR - http://www.scopus.com/inward/record.url?scp=85116410432&partnerID=8YFLogxK

U2 - 10.1109/ARSO51874.2021.9542836

DO - 10.1109/ARSO51874.2021.9542836

M3 - Conference paper

AN - SCOPUS:85116410432

T3 - Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO

SP - 227

EP - 233

BT - 2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021

PB - IEEE Computer Society

Y2 - 8 July 2021 through 10 July 2021

ER -