Optimization algorithms, artificial intelligence & robotics (AI)

Prototype of one of the robots of the robotic choral

This research pole deals with optimization algorithms, evolutionary computing, artificial intelligence and robotics.

Our goal is to develop evolutionary algorithms to address medium to large-scale computationally expensive optimization problems. These algorithms are based on natural selection strategies and take advantage of the computational resources of high-performance computing systems.

We also develop machine-learning algorithms for the analysis, classification or visualization of high-dimensional data. An objective is to achieve a better understanding of the roots of their functioning. We adopt here an interdisciplinary approach by enforcing the cross fertilisation among the involved disciplines.

We also carry out research activity in the domain of Evolutionary and Swarm Robotics. We have a lab equipped with Kilobots, E-pucks and other robotic platforms.

We use evolutionary computation techniques as well as other bio-inspired control design algorithms to the synthesis of neurocontrollers for robots required to cooperate to execute tasks that are beyond the capabilities of single agents.

Keywords: Optimization Algorithms, Evolutionary Computing, Neural Networks, Artificial Intelligence, Evolutionary and Swarm Robotics

Contact: Alexandre Mayer, Timoteo Carletti and Elio Tuci

Robotics Lab

Relevant references:

  • Blanchard, C. Beauthier and T. Carletti, A surrogate-assisted cooperative co-evolutionary algorithm using recursive differential grouping as decomposition strategy, IEEE Congress on Evolutionary Computation (Piscataway, New Jersey, USA), p. 689-696 (2019).
  • Delchevalerie, A. Mayer, A. Bibal and B. Frenay, Accelerating t-SNE using Fast Fourier Transforms and the Particle-Mesh Algorithm from Physics, International Joint Conference on Neural Networks (IJCNN), in press (2021).
  • Giambagli, L. Buffoni, T. Carletti, W. Nocentini and D. Fanelli, Machine learning in spectral domain, Nature Communications 12, p. 1330 (2021).
  • Giagkos, E. Tuci, M.S. Wilson and P.B. Charlesworth, “UAV Flight Coordination for Communication Networks: Genetic Algorithms versus Game Theory”, Soft Computing Journal, Springer, in press (2021).
  • Alkilabi, T. Carletti and E. Tuci, Odometry during object transport: a study with a swarm of physical robots, the 12th International Conference on Swarm Intelligence (ICSI’2021), in press (2021).
  • Firat, E. Ferrante, Y. Gillet and E. Tuci, On Self-organised Aggregation Dynamics in Swarms of Robots with Informed Robots, Neural Computing and Applications, 32(17), p. 13825-13841 (2020) doi:10.1007/s00521-020-04791-0