Task Allocation Strategy for Heterogeneous Robot Teams in Offshore Missions

Heterogeneous robot fleets are capable of supporting dynamic and resource-constrained missions. While current temporal AI planners are able to deal with multi-robot planning problems by producing plans that take into account the individual robot capabilities and task requirements, these approaches deal with the high-dimensionality of the state space inefficiently, leading to multi-robot plans with poor plan quality. This paper proposes a novel task allocation strategy called Multi-Role Goal Assignment (MRGA) which enables for more efficient computation of plans using temporal planners. The approach allocates a mission's goals based on robot capabilities, the redundancy of the sensor system, the spatial distribution of the goals and task implementation time, avoiding the need to compute a large number of possible assignments. We demonstrate the applicability of the strategy with multiple robots operating jointly in an offshore platform. Experiments demonstrate that our approach allows for more robust solutions and improved plan quality while significantly reducing planning time.