Differences in Learning from Complex Versus Simple Visual Interfaces When Operating a Model Excavator

Abstract

The goal of this study was to test two visual co-robot interfaces (one simple and one more complex) and their effectiveness in teaching a novice participant to operate a complex machine at a later date without assistance. Participants (N = 113) were randomly assigned to one of three groups (one with a basic user interface, one with a more complex guidance interface, and one without an interface) to test the teaching ability of the co-robot in training the user to perform a task with a remote-controlled excavator. Each group was asked to load dirt from a bin into a small model dump truck (in scale with the excavator) with the help of the robot instructor and were asked to return a few days later to complete the task again without the robot instructor. Trials were monitored for completion time and errors and compared to those of an expert operator. The result was that the simple interface was slightly more effective than the more complex version at teaching humans a complicated task. This suggests that novices may learn better and retain more information when given basic feedback (using operant conditioning principles) and less guidance from robot teachers. As robots are increasingly used to help humans learn skills, industries may benefit from simpler guided instructions rather than more complex versions. Such changes in training may result in improved situational awareness and increased safety in the workplace.