UAV Team Operation based on Artificial Intelligence approach.

Lead Research Organisation: Cranfield University
Department Name: Sch of Aerospace, Transport & Manufact

Abstract

Unmanned Aerial Vehicles (UAV) have become more popular for usage due to the low cost of deployment and maintenance. Single UAV employment allows remote area monitoring and transferring different payloads to inaccessible or dangerous zones for human. In order to deal with flight tasks that are more complex, UAV swarms are applied. The main challenge of UAV swarm formation and flight control is to avoid vehicle collisions. In this case, artificial intelligence is responsible for flight performance in the airspace in such way that collision is avoided. The main requirements to the method, which will provide conflict-free manoeuvres, are safety (collision avoidance), liveness (decentralized control, destination area reachability) and flyability (UAV flight performance constraints are satisfied).

Publications

10 25 50
publication icon
Skaltsis G (2022) Self play with parameter sharing in n-player mixed competitive-cooperative games

publication icon
Skaltsis G (2021) A survey of task allocation techniques in MAS

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/N509450/1 01/10/2016 30/09/2021
2279290 Studentship EP/N509450/1 01/10/2019 31/05/2023 George Skaltis
EP/R513027/1 01/10/2018 30/09/2023
2279290 Studentship EP/R513027/1 01/10/2019 31/05/2023 George Skaltis
 
Description The achievements of this work include, a state of the art review of the techniques of task allocation in multi-agent systems, an improved self-play based multiagent reinforcement learning method for cooperative and competitive UAVs task allocation and an improved centralised critic method multiagent reinforcement learning for cooperative UAVs task allocation. The specific research outcomes have been submitted to conference and journal papers.
Exploitation Route The outcomes can help research impovement in the fields of reinforcement learning and multiagent systems like UAVs, as well as task allocation methods of UAvs.
Sectors Aerospace, Defence and Marine,Digital/Communication/Information Technologies (including Software),Transport