Use of Human Computation for Coordinating Robotic Mobility Aids Based on User Impairments *

Abstract

The users impairments are one of the most important factors for how a robotic mobility aid device is used. However, this has not been addressed in existing solutions. In this paper, we propose using information about the users’ disabilities and impairments to create a navigation prioritization layer for solving multi-robot navigation situations. To deal with the deep subjectivity inherent to assigning these priorities, we propose using human computation to create a navigation solution that will be aligned with humans’ personal value systems, increasing the perceived fairness and trustworthiness of the system. This paper covers the background, methodology, initial experiments and discusses the results, limitations, and future potential of the proposed approach.