Learning effects in variable autonomy human-robot systems: how much training is enough?

The article explores the impact of learning and training on the performance of human-robot systems with variable autonomy. It presents the findings from an experiment inspired by a search and rescue scenario. The operators remotely controlled a mobile robot with either Human-Initiative (HI) or Mixed-Initiative (MI) control. The study found evidence of learning in terms of primary navigation task and secondary task performance. It also concluded that MI and HI performance in a pure navigation task is equal.

Publication date: 17 Nov 2023
Project Page: Not provided
Paper: https://arxiv.org/pdf/2311.09803