Task Allocation for Spatially and Temporally Distributed Tasks

In multi robot task allocation, a set of tasks has to be allocated to a group of robots while optimizing some measure (for example, fuel or time). In order to find the optimal allocation, an exponential number of possibilities must be explored. In this work, we extend the Consensus Based Bundle Algorithm, to improve its support for tasks with time constraints. The modified algorithm is compared with the original one in order to show how strategic modifications to the algorithm increase the number of tasks successfully completed. 1 Description of Problem Multi robot task allocation addresses the problem of matching tasks to robots in a way that satisfies a certain criterion or optimization function. The criterion is usually to minimize the distance traveled, or to minimize the time to complete all the tasks, or maximize the number of completed tasks. Real problems often have additional constraints. For example, in a post-disaster scenario, tasks location and their magnitude may be initially unknown, so robots should first explore the environment and dynamically allocate tasks as they find them. Also, the amount of time to reach tasks might be limited, after which some of them may no longer be available (for example, a wounded civilian may have died), or may be too complex to complete (for example, a fire may be too big to put off). There might be obstacles in the predicted path to a task, and some tasks may need a minimum number of robots allocated in order to be completed. We build upon a decentralized auction algorithm, the Consensus Based Bundle Algorithm [1], and modify it in order to incorporate stronger temporal constraints. This is useful for scenarios where, for example, the lives of wounded civilians depend on how fast ambulances can reach them. Department of Computer Science and Engineering, University of Minnesota, 200 Union St SE, Minneapolis, MN 55455, USA e-mail: [email protected],[email protected]