| dc.description.abstract | The rapid advancements in robotics and
artificial intelligence have driven the growth of Multi-
Robot Systems (MRS) and Teams of Robots (TOR), where
collaboration is critical in domains like manufacturing,
search and rescue, and military operations. Effective task
allocation remains a significant challenge, often addressed
via optimization techniques like Ant Colony Optimization
(ACO). However, current approaches primarily focus on
real-time availability and computational efficiency,
overlooking the historical performance of individual robots.
This paper proposes an enhanced ACO-based method that
integrates both the real-time factors and the past
experiences of each robot, to optimize task assignment. The
approach focuses on optimizing problem-solving using the
ACO by selecting the most suitable candidate for a specific
task from a given TOR while considering the agent's prior
experience with similar tasks. The approach also
addressing the possibility of using the ACO when
transferring an assigned task to another robot in the TOR.
The results validate the effectiveness, of the approach in
dynamically selecting the most suitable and available robot,
offering a significant advancement in task allocation
strategies for TOR. | en_US |
