Abstract

Through the use of autonomy Unmanned Aerial Vehicles (UAVs) can be used to solve a range of of multi-agent problems that exist in the real world, for example search and rescue or surveillance. Within these scenarios the global objective might often be better achieved if aspects of the problem can be optimally shared amongst its agents. However, in uncertain, dynamic and often partially observable environments centralised global-optimisation techniques are not achievable. Instead, agents may have to act on their own belief of the world, making the best decisions independently and potentially myopically. With multiple agents acting in a decentralised manner how can we discourage competitive behaviour and instead facilitate cooperation. This paper focuses on the specific problem of multiple UAVs simultaneously searching for tasks in an environment whilst efficiently routing between them and ultimately visiting them. This paper is motivated by this idea that collaboration can be simple and achieved without the need for a dialogue but instead through the design of the individual agent’s behaviour. By focusing on what is communicated we expand the use of a single agent behaviour. Which through minor modifications can produce distinct agents demonstrating independent, collaborative and competitive behaviour. In particular by investigating the role of sensor and communication ranges this paper will show that increased sensor ranges can be detrimental to system performance, and instead the simple modelling of nearby agents’ intent is a far better approach.

Highlights

  • Unmanned Aerial Vehicles (UAVs) are a potential and exciting solution to a number of real-world problems such as reconnaissance and surveillance [1,2,3,4,5,6,7], search and rescue [8,9,10], and package delivery [11,12]

  • The Multi-Agent Simultaneous Searching and Routing Problem (MSSRP) explored in this paper can be summarised as the problem of simultaneously searching for tasks in an environment whilst simultaneously routing between them

  • We will start by defining the global co-operative routing problem of multiple UAVs with full observably, i.e., the searching part of the problem is solved and we know ahead of time the entire set of tasks to visit

Read more

Summary

Introduction

Unmanned Aerial Vehicles (UAVs) are a potential and exciting solution to a number of real-world problems such as reconnaissance and surveillance [1,2,3,4,5,6,7], search and rescue [8,9,10], and package delivery [11,12]. Modelling and planning for multi-agent problems can often be difficult due to a rapidly growing decision space, made increasing complex through agents interactions with each other and the environment. This can result in a need for coordination and communication that may not be possible in many situations [14,15]. In particular focusing on what is communicated between agents or what agents think about other agents actions can produce distinct results These can demonstrate independent, collaborative and competitive behaviour.

The Multi-Agent Simultaneous Searching and Routing Problem
The Routing Problem Statement
Partial-Observability of Task Locations
Decentralised Agents
Non-Stationarity
No Fixed Depot
Heuristic Solution Process
UAV Agent Behaviours
Modelling Other Agents Intent
Multi-Agent System Simulation Environment
The Environment
Task Agents
UAV Agents
Get Visible
Get Communicable
Optimise Route
Simulation Assumptions
Example of Single Simulation Run
Results and Discussion
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call