An MIT news release highlights recent research from the Interactive Robot Group at MIT's Computer Science and Artificial Intelligence Lab (CSAIL). The researchers look at the best strategy for ensuring that humans and robots can work side-by-side in manufacturing environments. Not surprisingly, the biggest problem is that people have trouble doing things in the same way each time, which can confuse robots. Various techniques have been tried in the past to solve this problem, most of which involve trying to train the humans. A new approach was needed. From the news release:
So Shah and PhD student Stefanos Nikolaidis began to investigate whether techniques that have been shown to work well in training people could also be applied to mixed teams of humans and robots. One such technique, known as cross-training, sees team members swap roles with each other on given days. “This allows people to form a better idea of how their role affects their partner and how their partner’s role affects them.”
The researchers concluded that the cross-training approach was "an extremely effective team-building tool" when dealing with teams of robots and humans working together. The details of their research can be found in a paper that will be presented soon at the International Conference on Human-Robot Interaction, titled "Human-Robot Cross-Training: Computational Formulation, Modeling and Evaluation of a Human Team Training Strategy" (PDF format).