Teaching multiple robots by a human — Teaching data generation

In this paper we propose a service system composed of small robots. These robots are able to do tasks executed by a single human in environments like homes or offices. The goal is that a user will be capable of teaching multiple small robots how to perform tasks. We use kinematic data during the teaching process like the motion and force applied by the hands of the subject during task execution. Based on the analysis of the data generated vs the physical capabilities of the robots, the system determines how many robots will execute the task and how to split it into subtasks for each robot. In the experiments, we generated the teaching data using a foldable chair, along with specific hand set triggers for the robots to use in the task.