Master’s in Swarm and Multi-Agent Cooperation Engineering with an Ethical and Regulatory Focus
Online master's programme of 1,900 hours in swarm and multi-agent cooperation engineering with an ethical and regulatory focus. 12 modules covering Regulation (EU) 2024/1689 (AI Act), Additional Protocol I to the Geneva Conventions, Implementing Regulation (EU) 2019/947, collective dynamics, formation control, task allocation, multi-agent learning and formal verification, using ROS 2, Gazebo and PettingZoo, 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
Model the dynamics of multi-agent systems and swarms.
Design formation control and consensus algorithms.
Implement distributed task allocation strategies.
Apply multi-agent reinforcement learning.
Assess human-swarm interaction and meaningful human control.
Analyse the ethical and legal framework of collective autonomy.
Formally verify properties of collective systems.
Who it's for
- Multi-agent systems engineers designing coordination and consensus algorithms.
- Swarm robotics researchers working on collective behaviours.
- Reinforcement learning engineers applying MARL to robotic teams.
- Autonomy ethics specialists assessing collective systems against legal frameworks.
- Autonomous systems verification engineers using model checking and large-scale simulation.
- Robotics simulation developers working with ROS 2 and Gazebo.
- Engineering or science graduates aiming to enter robotics and automation.
What you'll work with
- Regulation (EU) 2024/1689 (Artificial Intelligence Act)
- Additional Protocol I to the Geneva Conventions (protection of victims of armed conflict)
- Implementing Regulation (EU) 2019/947 (UAS operations)
- ISO 10218 (safety of industrial robots)
- IEEE 7000 (addressing ethical concerns during system design)
- ISO/IEC 23894 (AI risk management)
- NATO Principles of Responsible Use of AI (defence AI governance)
- ROS 2
- Gazebo
- PettingZoo
- PRISM
- Mesa
12 modules · 1900 h
1.1Definition of a swarm and emergent properties1.2Biological inspiration: flocks, colonies and shoals1.3Classification by homogeneity and hierarchy1.4Scalability, robustness and flexibility1.5Civil applications: agriculture, rescue and inspection1.6Life cycle of a swarm system1.7Levels of collective autonomy1.8Certification challenges for collective systems1.9Ethical debate on collective autonomy1.10Case study: analysis of an agricultural inspection swarm
2.1Reynolds models: separation, alignment and cohesion2.2Vicsek model and phase transitions2.3Graph theory for agent networks2.4Distributed consensus and convergence2.5Particle systems and potential fields2.6Lyapunov stability in formations2.7Stochastic and Markov models2.8Order and cohesion metrics2.9Agent-based simulation2.10Practical exercise: flocking simulation in Python with Mesa
3.1Leader-follower formations3.2Virtual structures and behaviour-based control3.3Distance- and bearing-based formation control3.4Graph rigidity and formations3.5Dynamic reconfiguration of formations3.6Distributed control with limited communication3.7Inter-agent collision avoidance3.8Robust control against disturbances3.9Heterogeneous air-ground formations3.10Lab: formation control with Crazyflie in simulation
4.1The multi-robot task allocation problem4.2Auction algorithms: CBBA4.3Combinatorial optimisation and heuristics4.4Mixed-integer programming for allocation4.5Area coverage and Voronoi partitions4.6Collaborative search for civil targets4.7Conflict-based multi-agent planning4.8Coordination with temporal constraints4.9Replanning in the event of agent failures4.10Practical exercise: auction-based allocation in ROS 2
5.1Network topologies in swarms5.2Mesh networks and lightweight protocols5.3Implicit communication and stigmergy5.4Consensus with losses and delays5.5Collective bandwidth management5.6Distributed time synchronisation5.7Security of inter-agent communications5.8Resilience against network partitions5.9Joint network-robotics simulation5.10Workshop: evaluation of topologies with ns-3 and Gazebo
6.1Multi-agent reinforcement learning6.2Centralised training and decentralised execution6.3MADDPG, QMIX and MAPPO algorithms6.4Learning emergent communication6.5Simulation-to-reality transfer6.6Robustness and generalisation of policies6.7Explainability of learned policies6.8Safety during training6.9PettingZoo and SMAC environments6.10Lab: MAPPO training in PettingZoo
7.1Distributed information fusion7.2Collaborative mapping and multi-robot SLAM7.3Cooperative target tracking7.4Distributed estimation consensus7.5Management of shared uncertainty7.6Multi-agent data association7.7Heterogeneous sensors in the collective7.8Reducing perceptual redundancy7.9Bandwidth and map compression7.10Practical exercise: multi-robot SLAM with simulated data
8.1Human supervision of collective systems8.2Swarm-level command interfaces8.3Cognitive load and situational awareness8.4Meaningful human control8.5Levels of intervention and delegation8.6Visualisation of collective states8.7Calibrated trust in autonomy8.8Human factors in decision-making8.9Usability evaluation8.10Case study: design of a supervision interface
9.1International humanitarian law and new technologies9.2Article 36 of Additional Protocol I9.3CCW debate on autonomous systems9.4NATO principles of responsible use of AI9.5European AI Regulation (EU) 2024/16899.6Responsibility and accountability9.7Civil regulations for multi-UAS operations9.8Privacy and data protection9.9Design ethics and values9.10Workshop: ethical compliance review of a case
10.1Formal verification of emergent properties10.2Model checking with PRISM and UPPAAL10.3Testing through large-scale simulation10.4Analysis of collective failure modes10.5Detection of anomalous behaviour10.6Agent cybersecurity and spoofing10.7Safety arguments for collectives10.8Staged field testing10.9Collective performance metrics10.10Lab: consensus verification with PRISM
11.1Precision agriculture with swarms11.2Search and rescue in disasters11.3Inspection of extensive infrastructure11.4Distributed environmental monitoring11.5Drone light shows11.6Autonomous logistics in warehouses11.7Cooperative planetary exploration11.8Transfer of dual-use technologies11.9European robotics roadmaps11.10Case study: design of a search and rescue mission
12.1Definition of the collective mission12.2State-of-the-art review12.3Modelling the multi-agent system12.4Design of coordination algorithms12.5Implementation in simulation12.6Ethical and regulatory assessment12.7Analysis of results and scalability12.8Conclusions and future work12.9Master's Thesis report12.10Master's Thesis: defence before a panel
How you'll learn
100% online training 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 the intake, so the programme can be combined with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is ROS 2, Gazebo, PettingZoo, PRISM and Mesa, in free, academic or evaluation versions. Practical work is based on real procedures for large-scale simulation of collective behaviours, training of multi-agent policies and formal verification of emergent properties. Assessment is continuous by module, plus the final Master's Thesis.
Standards covered: Regulation (EU) 2024/1689 (AI Act), Additional Protocol I to the Geneva Conventions, Implementing Regulation (EU) 2019/947, ISO 10218, IEEE 7000, ISO/IEC 23894, NATO Principles of Responsible Use of AI.
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 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, PettingZoo, PRISM and Mesa, 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 degree in engineering, science or architecture (or equivalent professional experience), a suitable computer 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 Data Governance, Classification and Information Security Engineering (NATO/EU/US)
Online master's programme of 1,900 hours in data governance, classification and information security engineering (NATO/EU/US). 12 modules covering C-M(2002)49, Council Decision 2013/488/EU, NIST SP 800-171, CMMC,…
Master’s in COMSEC/CRYPTO and Secure Defence Communications Engineering
Online master's programme of 1,900 hours in COMSEC/CRYPTO and secure defence communications engineering, structured in 12 modules covering the mathematics of cryptography, symmetric, asymmetric and post-quantum…
Master’s in Land Fleet MRO and Sustainment Engineering
Online master's programme of 1,900 hours in MRO and land fleet sustainment engineering, with 12 modules covering logistic support analysis (ASD S3000L), reliability-centred maintenance (SAE JA1011),…
More in Defense, Military Engineering & Land Systems
All Defense, Military Engineering & Land Systems programmes → · How to apply · Fees & financing · Scholarships