Collaboration is essential for effective performance by groups
of robots in disaster response settings. Here we are particularly
interested in heterogeneous robots that collaborate in
complex scenarios with incomplete, dynamically changing
information. In detail, we consider a search and rescue setting,
where robots with different capabilities work together
to accomplish tasks (rescue) and find information about further
tasks (search) at the same time. The state of the art
for such collaboration is robot control based on independent
planning for robots with different capabilities and typically
incorporates uncertainty with only a limited scope. In contrast,
in this paper, we create a joint plan to optimise all
robots’ actions incorporating uncertainty about the future
information gain of the robots. We evaluate our planner’s
performance in settings based on real disasters and find that
our approach decreases the response time by 20-25% compared
to state-of-the-art approaches. In addition, practical
constraints are met in terms of time and resource utilisation.