Multi-Robot Systems can succeed at tasks that may not be possible with a single robot alone. However, they also introduce several challenges. I have worked on two main aspects of a multi-robot system consisting of several defender robots that protect an important resource. This work was performed mostly at the Navy Center for Applied Research in Artificial Intelligence.
I extended an approach called Anytime Learning (later renamed to Continuous and Embedded Learning) to multi-robots systems. This work allowed the team to adapt to changing situations such as individual robot failures. For example, the experiments showed that the team could switch from generalists to specialists depending on the number of members in the team.