Student opportunities

Evolutionary Robotics

  • Voxel-based soft robots (VSRs)
    • Co-evolution of body and brain of VSRs
    • Learning techniques for the controllers of VSRs: reinforcement learning
    • Auto-assembly of VSRs
    • Resolution-agnostic representation for evolution of closed-loop controllers of VSRs
    • Improving scalability of VSR controller learning with Covariance Matrix Adaptation Evolutionary Strategies (CMA-ES)
    • Learning and pruning techniques for improving robustness to damages of VSR controllers
    • Modularity of VSRs as robotic tissue
    • Human control of VSRs with a brain-computer interface
    • Novelty in perception for driving optimization of VSRs controller
  • Real robots
    • Design and development of an sw framework for experimenting with learning techniques
    • Hybrid (real vs. simulated) controller learning for addressing the reality gap
    • Reality-gap in multi-agent systems with communication
    • PushGP on mobile robots (Thymio-II): a machine-friendly representation for robotic agents controllers

Artificial Life

  • Multi-agent systems
    • Evolution of behavioral rules for multi-agent systems: the case of self-driving cars
  • Development of an Artificial Life simulator for investigating the Alife-Human interactions

See also the student opportunities at the Machine Learning Lab.