Master’s in UAS Swarm and Multi-Agent Cooperation Engineering
Online master's programme of 1,900 hours in swarm UAS and multi-agent cooperation engineering, structured in 12 modules covering multi-agent systems, graph theory and consensus, formation control, multi-agent path planning, task allocation, swarm communications, cooperative perception, multi-agent learning, simulation, civil applications and regulation, with an assigned technical tutor.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Understand the fundamentals of multi-agent systems applied to UAS.
Apply consensus and formation control algorithms.
Design path planning and task allocation strategies.
Implement networked communications for swarms.
Develop cooperative perception and localisation.
Simulate swarms in SITL environments and validate them.
Analyse the ethical, regulatory and safety aspects of swarms.
Who it's for
- Autonomous systems engineers.
- Multi-agent robotics researchers.
- Drone software engineers working with ROS 2 and PX4.
- Mission planning specialists.
- Wireless communications engineers designing mesh and FANET networks.
- Drone light-show developers.
- Engineering or science graduates seeking to enter robotics.
What you'll work with
- Implementing Regulation (EU) 2019/947 (rules and procedures for the operation of unmanned aircraft)
- Delegated Regulation (EU) 2019/945 (UAS classes and third-country operators)
- JARUS SORA (specific operations risk assessment)
- Regulation (EU) 2024/1689 (EU Artificial Intelligence Act)
- IEEE 802.11s (wireless mesh networking)
- ISO 21384-3 (UAS operational procedures)
- EUROCAE ED-270 (geo-awareness and geofencing requirements)
- ROS 2
- Gazebo
- PX4
- AirSim
- Python
12 modules · 1900 h
1.1Definition of agent and environment1.2Reactive and deliberative architectures1.3Emergent behaviour and self-organisation1.4Swarm intelligence1.5Reynolds models1.6Communication topologies1.7Taxonomy of UAS swarms1.8Civil applications of swarms1.9Scalability challenges1.10Case study: analysis of a light-show swarm demonstration
2.1Communication graphs2.2Graph Laplacian matrix2.3Consensus algorithms2.4Consensus with delays2.5Switching communication topologies2.6Algebraic connectivity and the Fiedler value2.7Clock and state synchronisation2.8Distributed estimation of common parameters2.9Robustness to node failures2.10Lab: consensus simulation on a 10-agent graph
3.1Leader–follower formation3.2Formation using virtual structures3.3Behaviour-based control3.4Distance-based formation3.5Consensus-based formation control3.6Formation switching3.7Inter-agent collision avoidance3.8Potential functions3.9Lyapunov stability3.10Practical exercise: triangle formation control
4.1Centralised and decentralised planning4.2Multi-agent A* and RRT*4.3Conflict-based search (CBS) algorithm4.4Planning with dynamic constraints4.5Velocity obstacles and ORCA4.6Distributed model predictive control (MPC)4.7Coverage trajectories4.8Planning in uncertain environments4.9Real-time replanning4.10Lab: ORCA navigation in an environment with obstacles
5.1The assignment problem5.2Auctions and CBBA5.3Hungarian assignment algorithm5.4Allocation with time constraints5.5Vehicle routing problems5.6Dynamic reallocation after failures5.7Load balancing5.8Multi-objective optimisation of allocations5.9Heuristics and metaheuristics5.10Practical exercise: task allocation with CBBA
6.1Ad hoc networks (FANET)6.2Routing protocols6.3Mesh and topologies6.4Latency and bandwidth6.5Packet loss6.6Implicit communication through stigmergy6.7Communication security6.8ROS 2 and DDS6.9Spectrum management6.10Case study: mesh network design for 20 UAS
7.1Cooperative SLAM between vehicles7.2Relative localisation between agents7.3UWB and range estimation7.4Map fusion7.5Neighbour detection7.6Cooperative vision with multiple cameras7.7Distributed estimation with filters7.8GNSS-denied localisation7.9Inter-agent calibration7.10Lab: relative localisation with UWB
8.1Multi-agent reinforcement learning8.2Centralised training and decentralised execution8.3Shared policies between agents8.4Sim-to-real transfer8.5Imitation learning8.6Graph neural networks8.7Robustness and generalisation8.8Safety in learning8.9Simulation environments8.10Practical exercise: MARL training in a coverage environment
9.1Gazebo and PX4 SITL9.2AirSim simulator and Unreal Engine9.3Crazyswarm and laboratory platforms9.4Scaling simulations9.5Hardware-in-the-loop testing of the swarm9.6Motion capture9.7Performance metrics9.8Reproducibility of experiments9.9Field testing9.10Lab: SITL simulation of 5 multirotors
10.1Search and rescue10.2Cooperative mapping of large areas10.3Agriculture with drone fleets10.4Environmental monitoring with swarms10.5Light shows10.6Cooperative logistics and delivery10.7Infrastructure inspection10.8Wildfire fighting10.9Emergency communications10.10Case study: search mission design with a swarm
11.1Regulatory framework for multiple operations11.2SORA for swarms11.3Meaningful human oversight11.4Ethics of autonomous systems11.5EU AI Act11.6Reliability and certification11.7Swarm cybersecurity11.8Legal liability of autonomous systems11.9Social acceptance of swarms11.10Workshop: risk assessment of a swarm show
12.1Definition of the cooperative mission12.2Agent modelling12.3Design of coordination algorithms12.4Communications design12.5Swarm simulation12.6Robustness assessment12.7Safety and regulatory analysis12.8Experimental validation with real vehicles12.9Master's Thesis report12.10Master's Thesis: defence before a panel
How you'll learn
The programme is delivered 100% online on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so you can combine it with your job.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is ROS 2, Gazebo, PX4, AirSim and Python, in free, academic or evaluation versions. Exercises are based on real procedures: SITL simulations of multiple UAS, motion-capture experiments and training of multi-agent policies. Assessment is continuous for each module, plus the final Master's Thesis.
Standards covered: Implementing Regulation (EU) 2019/947, Delegated Regulation (EU) 2019/945, JARUS SORA, Regulation (EU) 2024/1689 on Artificial Intelligence, IEEE 802.11s, ISO 21384-3, EUROCAE ED-270.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
Requirements
- University degree in engineering, science or architecture, or equivalent demonstrable professional experience.
- Internet connection and a computer capable of running the programme's software.
- English sufficient to read technical standards.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme totals 1,900 hours over 12–14 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with ROS 2, Gazebo, PX4, AirSim and Python, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.
A SEIUM Institute diploma, awarded on passing the continuous assessment and the Master's Thesis. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.
Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Ask about the recognition policy when you enrol.
A university degree in engineering, science or architecture (or equivalent professional experience), a computer able to run the software, and English sufficient to read technical standards.
Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.
Related programmes
Master’s in Aerospace Acoustics and Noise Reduction Engineering
Online master's programme of 1,900 hours in aerospace acoustics and noise reduction engineering, with 12 modules covering physical acoustics and psychoacoustics, aeroacoustic theory, engine and airframe…
Master’s in Regulation, Continuing Airworthiness & Business Engineering
Online master's programme of 1,900 hours in aviation regulation, continuing airworthiness and business engineering. 12 modules covering the EASA Basic Regulation, Part 21, Regulation (EU) 1321/2014,…
Master’s in Rotorcraft Aeromechanics
Online master's programme of 1,900 hours in rotorcraft aeromechanics. 12 modules covering rotor aerodynamics, blade dynamics, flight controls, performance, loads, noise and certification to CS-29, CS-27…
More in Aerospace, UAM, Drones & Space
All Aerospace, UAM, Drones & Space programmes → · How to apply · Fees & financing · Scholarships