Swarmlab Projects

The general research line of the lab focuses on how to build bio-inspired autonomous systems capable of learning from their environment and peers in order to solve complex tasks. For this purpose we draw inspirations from nature and investigate bio-inspired techniques such as swarm intelligence (social insect behavior as found in honeybees and ants), reinforcement learning and evolutionary algorithms.

Currently our research focus includes following topics.

  1. We are particularly interested in how to design large-scale distributed, self-organizing systems capable of solving complex coordination tasks, such as foraging for food. These tasks find direct applications in areas as automated patrolling, localization of danger and localization of victims in rescue management scenarios.
  2. We focus on developing and implementing new learning and filtering algorithms to build individual robots capable of facilitating human tasks, such as for instance adaptive tele-presence robotics.

Projects (List of our projects will be updated soon)

BRON_introPic

BROM: Brain-Robot Operation platform

A pilot project on the use of functional near-infrared spectroscopy (fNIRS) based brain-computer interface (BCI) applied to control physical robots. fNIRS is a quite novel technique, which bears such advantages as portability, reliable signal generation and electromagnetic noise resistance. The goal of the project is to build a platform for future BCI research.

For further information click HERE. (Coming soon)

StiCo: Stigmergic Coverage

StiCo is a novel approach for multi-robot coverage based on the principle of pheromone-based communication. According to this approach, the robots communicate indirectly via depositing/detecting markers in the environment to be covered. Although the motion policies of each robot are very simple, complex and yet very efficient coverage behavior is achieved at the team level.

For further information click HERE.

MiSS: Mining Social Structures from Real World Complex Networks

This project addresses the problem of how to derive identities of persons and social structures from large sets of genealogical data available as text and photographs with incomplete information. In order to do so we want to investigate and deploy a combination of techniques from data mining, machine learning and human computation. One of the project goals is providing automatic tools for supporting large scale prosopographical and demographic research.

For further information click HERE.

Analytical Study of Co-Evolution in Complex Networks

Aiming at a broad theoretical understanding of the co-evolution in complex/social networks, this project develops a formal analysis of network structure, behaviors and interactions among individuals in complex social networks.

Behavioral Robotics

In this project we use swarm robotics to study the network emergence, self-organisation, coordination and the co-evolution in social networks. Our results show that robots can be used to study various concepts from economy and sociology where the physical environment is likely to influence the outcome of social interactions (See this VIDEO).