Intelligence distribuée | EPFL Graph Search

L'intelligence distribuée, appelée aussi intelligence en essaim, désigne l'apparition de phénomènes cohérents à l'échelle d'une population dont les individus agissent selon des règles simples. L'interaction ou la synergie entre actions individuelles simples peut de façons variées permettre l'émergence de formes, organisations, ou comportements collectifs, complexes ou cohérents, tandis que les individus eux se comportent à leur échelle indépendamment de toute règle globale. C'est l'indépendance entre d'une part les actions et règles qui régissent les individus et de l'autre la forme ou la dynamique collective, qui est au cœur du concept d'intelligence distribuée : comment cette cohérence globale apparaît-elle alors qu'elle n'est ni inscrite au niveau de l'individu, ni le résultat de "décisions communes", ni encore "commandée" par une "intelligence" centrale? Un cas flagrant est le fonctionnement collectif d'une colonie de fourmis, par exemple dans le cas de la découverte d'une sour

Model Predictive Control of Aerial Swarms

Enrica Soria

Aerial robot swarms can have a large socio-economic impact. They can perform time-critical missions faster than a single robot and access dangerous environments without compromising human safety. However, swarm deployment is often limited to free environments where no obstacle interferes with the robots' flight. Their trajectories are computed before the flight in many applications, and the robots are perceptually blind to one another. In these cases, all decisions are taken by a central computer that is informed about all robots' states, thus increasing their chance of failure in case of signal interruptions, limiting their robustness to failure, and preventing their scalability in size. Drones should have the autonomy to make their own decisions based on local information, and they should integrate a safe obstacle avoidance behavior to offer more versatility for their application in real-world environments.We propose a predictive approach to swarm control inspired by flocking birds to address these limitations. In particular, we develop methods that enable drones to coordinate their motion by predicting their future trajectory and coordinating with their neighbors based on local information. We first propose a centralized predictive algorithm that computes the trajectories of the drones in real-time and improves the synchronization and order of the swarm flight compared to current state-of-the-art algorithms. We show in extensive simulations that our algorithm is robust to different obstacle densities, swarm speeds, and inter-agent distances. Then, we formulate a distributed predictive algorithm with the same qualitative advantages as its centralized counterpart but scalable in the swarm size. We also show that our approach is tolerant to a wide range of sensor noise. Finally, we extend and analyze the usage of this algorithm also for pure sensor-based swarms that cannot use explicit communication. We validate the algorithms in extensive simulation and in the real world with a fleet of hand-sized quadcopters in controlled indoor environments with obstacles.

EPFL2022

Montreux Co-Operative Culturelle. Une architecture de l'intelligence collective

Benoît Meugniot

L'architecte est pris au piège dans son système de pensées d'expert. Dès lors, le travail vise à introduire des outils conviviaux au workflow architectural pour faciliter l'intervention et la discussion des utilisateurs profanes, promulguant une architecture plus inclusive et durable. Le projet s'appuie sur les idéaux de l'association, « la 17ème », résidant à Montreux. Son idéologie, articulée autour de notions de participativité, d'inventivité et d'exploration, favorise un environnement propice à la vérification du processus « par et pour l'utilisateur ». L'expérience s'appuie sur le logiciel « Minecraft », base de nos interactions projectuelles. Ces dernières, collectées, nous permettent de comprendre les différentes itérations et l'improvisation architecturale qui mènent à la solution concertée. Situé dans un bâtiment désaffecté derrière le Montreux Palace, en aplomb sur le lac, le programme tente de répondre au besoin d'un « Incubateur culturel ». Ce choix questionne le rapport de la culture amatrice, qui nécessite des espaces d'expressions et de performances, avec celui d'une dynamique de logement coopératif. Ainsi, l'emphase sur l'intelligence collective rend intelligible, d'une part le fonctionnement du processus de création collective et d'autre part, solidifie les préceptes coopératifs.

2021

Evolutionary Synthesis of Communication-Based Aerial Swarms

Sabine Hauert

Aerial swarms have the potential to search for forest fires, chemical plumes or victims and serve as communication and sensor networks in the sky. Flying robots are interesting for such applications because they are fast, can easily overcome difficult terrain and provide line-of-sight communication or aerial perspectives. However, swarms of flying robots have so far only been demonstrated in simulation or in few examples in reality. Current simulators typically rely on unrealistic assumptions concerning robot sensing capabilities and motion. To bridge this reality gap we propose to address two key challenges. The first challenge consists in discovering swarm controllers that do not use position information. Swarm controllers in the literature rely on global or relative position information which can be obtained using GPS, cameras or range and bearing sensors. However, position requirements typically entail robots that are complex, heavy and expensive or that rely on specific environmental conditions to function. Lifting the need for position could instead lead to swarm controllers that can be deployed in a variety of environments and using very simple robots. The second challenge addressed consists in developing swarm controllers that can accommodate motion constraints of flying robots. In particular, we consider fixed-wing robots that can not stop or turn on the spot like ground robots or rotor crafts. Instead they must fly at relatively high speeds to avoid stalling. Therefore, making the robots advance slowly in average can only be done by having them turn. To address these challenges, we consider robot controllers that continuously react to wireless communication with neighboring robots or people by changing their turn rate (communication-based behaviors). Using communication as a sensor for flying robots is interesting because most robots are equipped with off-the-shelf radio modules that are low-cost, light-weight and relatively long-range. The design of robot controllers that can lead to desired swarm behaviors is done following a systematic approach. First, artificial evolution is used to automatically discover simple and unthought-of controllers for swarms of flying robots. Evolved controllers are then reverse engineered to obtain basic behaviors that can be modeled and used in a variety of swarm applications. In order to discover a range of basic behaviors, we consider a challenging swarm application that requires robots to direct themselves in their environment, move in groups, cover an area, and maintain a communication relay. Discovered behaviors are then extended to scenarios with wind. Overall, this thesis presents the evolutionary synthesis of communication-based behaviors for swarms of fixed-wing flying robots.

EPFL2010