JoVe-FL - A Joint-embedding Vertical Federated Learning Framework

Presentation (2023)

MO-Gym: A Library of Multi-Objective Reinforcement Learning Environments

Scientific Conference (2022, November)

Optimising Autonomous Robot Swarm Parameters for Stable Formation Design

in Proceedings of the Genetic and Evolutionary Computation Conference (2022, July 08)

Autonomous robot swarm systems allow to address many inherent limitations of single robot systems, such as scalability and reliability. As a consequence, these have found their way into numerous ... [more ▼]

Autonomous robot swarm systems allow to address many inherent limitations of single robot systems, such as scalability and reliability. As a consequence, these have found their way into numerous applications including in the space and aerospace domains like swarm-based asteroid observation or counter-drone systems. However, achieving stable formations around a point of interest using different number of robots and diverse initial conditions can be challenging. In this article we propose a novel method for autonomous robots swarms self-organisation solely relying on their relative position (angle and distance). This work focuses on an evolutionary optimisation approach to calculate the parameters of the swarm, e.g. inter-robot distance, to achieve a reliable formation under different initial conditions. Experiments are conducted using realistic simulations and considering four case studies. The results observed after testing the optimal configurations on 72 unseen scenarios per case study showed the high robustness of our proposal since the desired formation was always achieved. The ability of self-organise around a point of interest maintaining a predefined fixed distance was also validated using real robots. [less ▲]

A Framework of Hyper-Heuristics based on Q-Learning

in International Conference in Optimization and Learning (OLA2022) (2022)

Learning to Optimise a Swarm of UAVs

in Applied Sciences (2022), 12(19 9587),

The use of Unmanned Aerial Vehicles (UAVs) has shown a drastic increase in interest in the past few years. Current applications mainly depend on single UAV operations, which face critical limitations such ... [more ▼]

The use of Unmanned Aerial Vehicles (UAVs) has shown a drastic increase in interest in the past few years. Current applications mainly depend on single UAV operations, which face critical limitations such as mission range or resilience. Using several autonomous UAVs as a swarm is a promising approach to overcome these. However, designing an efficient swarm is a challenging task, since its global behaviour emerges solely from local decisions and interactions. These properties make classical multirobot design techniques not applicable, while evolutionary swarm robotics is typically limited to a single use case. This work, thus, proposes an automated swarming algorithm design approach, and more precisely, a generative hyper-heuristic relying on multi-objective reinforcement learning, that permits us to obtain not only efficient but also reusable swarming behaviours. Experimental results on a three-objective variant of the Coverage of a Connected UAV Swarm problem demonstrate that it not only permits one to generate swarming heuristics that outperform the state-of-the-art in terms of coverage by a swarm of UAVs but also provides high stability. Indeed, it is empirically demonstrated that the model trained on a certain class of instances generates heuristics and is capable of performing well on instances with a different size or swarm density. [less ▲]

A RNN-Based Hyper-Heuristic for Combinatorial Problems

in A RNN-Based Hyper-Heuristic for Combinatorial Problems (2022)

Designing efficient heuristics is a laborious and tedious task that generally requires a full understanding and knowledge of a given optimization problem. Hyper-heuristics have been mainly introduced to ... [more ▼]

Designing efficient heuristics is a laborious and tedious task that generally requires a full understanding and knowledge of a given optimization problem. Hyper-heuristics have been mainly introduced to tackle this issue and are mostly relying on Genetic Programming and its variants. Many attempts in the literature have shown that an automatic training mechanism for heuristic learning is possible and can challenge human-based heuristics in terms of gap to optimality. In this work, we introduce a novel approach based on a recent work on Deep Symbolic Regression. We demonstrate that scoring functions can be trained using Recurrent Neural Networks to tackle a well-know combinatorial problem, i.e., the Multi-dimensional Knapsack. Experiments have been conducted on instances from the OR-Library and results show that the proposed modus operandi is an alternative and promising approach to human- based heuristics and classical heuristic generation approaches. [less ▲]

Swarm-based counter UAV defense system

in Discover Internet of Things (2021), 1(1),

Unmanned Aerial Vehicles (UAVs) have quickly become one of the promising Internet-of-Things (IoT) devices for smart cities. Thanks to their mobility, agility, and onboard sensors'customizability, UAVs ... [more ▼]

Unmanned Aerial Vehicles (UAVs) have quickly become one of the promising Internet-of-Things (IoT) devices for smart cities. Thanks to their mobility, agility, and onboard sensors'customizability, UAVs have already demonstrated immense potential for numerous commercial applications. The UAVs expansion will come at the price of a dense, high-speed and dynamic traffic prone to UAVs going rogue or deployed with malicious intent. Counter UAV systems (C-UAS) are thus required to ensure their operations are safe. Existing C-UAS, which for the majority come from the military domain, lack scalability or induce collateral damages. This paper proposes a C-UAS able to intercept and escort intruders. It relies on an autonomous defense UAV swarm, capable of self-organizing their defense formation and to intercept the malicious UAV. This fully localized and GPS-free approach follows a modular design regarding the defense phases and it uses a newly developed balanced clustering to realize the intercept- and capture-formation. The resulting networked defense UAV swarm is resilient to communication losses. Finally, a prototype UAV simulator has been implemented. Through extensive simulations, we demonstrate the feasibility and performance of our approach. [less ▲]

A Distributed Pareto-based Path Planning Algorithm for Autonomous Unmanned Aerial Vehicles (Extended Abstract)

Scientific Conference (2021, January 07)

Autonomous Unmanned Aerial Vehicles (UAVs) are in increasing demand thanks to their applicability in a wide range of domains. However, to fully exploit such potential, UAVs should be capable of ... [more ▼]

Autonomous Unmanned Aerial Vehicles (UAVs) are in increasing demand thanks to their applicability in a wide range of domains. However, to fully exploit such potential, UAVs should be capable of intelligently planning their collision-free paths as that impacts greatly the execution quality of their applications. While being a problem well addressed in literature, most presented solutions are either computationally complex centralised approaches or ones not suitable for the multiobjective requirements of most UAV use-cases. This extended abstract introduces ongoing research on a novel distributed Pareto path planning algorithm incorporating a dynamic multi-criteria decision matrix allowing each UAV to plan its collision-free path relying on local knowledge gained via digital stigmergy. The article presents some initial simulations results of a distributed UAV Traffic Management system (UTM) on a weighted multilayer network. [less ▲]

A competitive Predator–Prey approach to enhance surveillance by UAV swarms

in Applied Soft Computing (2021), 111

In this paper we present the competitive optimisation of a swarm of Unmanned Aerial Vehicles (UAV) protecting a restricted area from a number of intruders following a Predator–Prey approach. We propose a ... [more ▼]

In this paper we present the competitive optimisation of a swarm of Unmanned Aerial Vehicles (UAV) protecting a restricted area from a number of intruders following a Predator–Prey approach. We propose a Competitive Coevolutionary Genetic Algorithm (CompCGA) which optimises the parameters of the UAVs (i.e. predators) to maximise the detection of intruders, while the parameters of the intruders (i.e. preys) are optimised to maximise their intrusion success rate. Having chosen the CACOC (Chaotic Ant Colony Optimisation for Coverage) as the base mobility model for the UAVs, we propose an improved new version, where its behaviour is modified by identifying and optimising new parameters to improve the overall success rate when detecting intruders. Six case studies have been optimised using simulations by performing 30 independent runs (180 in total) of our CompCGA. Finally, we conducted a series of master tournaments (1,800,000 evaluations) using the best specimens obtained from each run and case study to test the robustness of our proposed approach against unexpected intruders. Our surveillance system improved the average percentage of intruders detected with respect to CACOC by a maximum of 126%. More than 90% of intruders were detected on average when using a swarm of 16 UAVs while CACOC’s detection rates are always under 80% in all cases. [less ▲]

Improving Pheromone Communication for UAV Swarm Mobility Management

in 13th International Conference on Computational Collective Intelligence (ICCCI 2021) (2021)