Which position do I pick, if I don't know how to do the task?

A model to predict advantageous base poses for semi-autonomous robots.

More Info
expand_more

Abstract

In our aging society, the demand for care is increasing. Therefore, it is foreseen that robots will assist elderly. However, human assistance will often be required by the robot, which thus should be at a position advantageous for telemanipulation. For autonomous manipulation, methods have been developed that position a robot. But for telemanipulation, human capabilities and master limitations change the positions suitability. In this research, a positioning model -- Inverse Telemanipulation Capability Map (ITCM) -- is designed which take these into account. The goal of this research is to find if the ITCM can be used to replace manual robot placement and if telemanipulation is influenced by the base pose. Six participants have done a pick-and-place task with the robot positioned in the lowest (ITCM-low) and the highest scoring base pose (ITCM-high) and a base pose selected by an expert (Expert). The results show no difference between the ITCM-high and Expert conditions. Participants also reported that the task was less or equally difficult in the ITCM-high condition. From the base pose of the ITCM-high to the ITCM-low condition, the task execution time increases with 71 % and effort metrics are around one and a half times as high. Moreover, participants reported that task was more difficult from the ITCM-low base pose. It is concluded that the base pose influences performance and effort and that the base pose can be succesfully selected with the presented model.