Extended neglect tolerance model & human robot teams

Estimating robot performance in human robot teams is a vital problem in human robot interaction community. In previous work, we presented extended neglect tolerance model for estimation of robot performance, where the human operator switches control between robots sequentially based on low degree of minimum acceptable performance level set at 50% of peak performance, taking into account any false alarms in human robot interactions. In this paper, we validate the extended neglect tolerance model for an assistive walking task with high degree of minimum acceptable performance levels set at 80% of peak performance. Experiments were performed with Robo-Erectus@Home, a service robot across tele-operation, and semi-autonomous modes of autonomy where a human operator controlled the robot to perform a walking assistant task. Measured false alarm demands and robot performances were largely consistent with the extended neglect tolerance model predictions for both autonomy modes. We also compared traditionally adopted neglect tolerance and extended neglect tolerance model for the same experimental design. The results showed that the latter offers better estimates of robot performance and attention demands, due to the inclusion of false alarms into the model.