Decentralized Learning-aware Communication and Communication-aware Mobility Control for the Target Assignment Problem
- View All
We consider a team of mobile autonomous agents with the aim to cover a given set of targets. Each agent aims to determine a target to select and physically reach by the final time in coordination with other agents given locations of targets. Agents are unaware of which targets other agents intend to cover. Each agent can control its mobility and who to send information to. We assume communication happens over a wireless channel that is subject to failures. Given the setup, we propose a decentralized algorithm based on the distributed fictitious play algorithm in which agents reason about the selections and locations of other agents to decide which target to select, whether to communicate or not, who to communicate with, and where to move. Specifically, the communication actions of the agents are learning-aware, and their mobility actions are sensitive to the communication success probability. We show that the decentralized algorithm guarantees that agents will cover their targets in finite time. Numerical experiments show that mobility control for communication and learning-aware voluntary communication protocols reduce the number of communication attempts in comparison to a benchmark distributed algorithm that relies on sustained communication.
author list (cited authors)