DC3 - Monitoring and Self-Adaptation Capabilities for Uncertainty-Informed Resilient Robotics

Objectives

1. To conduct research on rigorous and mathematically-based techniques for empowering monitoring and self-adaptation in autonomous systems by considering uncertainty as a first class entity.
2. To develop techniques that learn and revise the developed monitors based on runtime data, hence enabling the more accurate representation and analysis of the target system and leading to robust self-adaptation.

Expected Results

1. Techniques for monitoring and efficient decision-making under uncertainty which combine compositionally heterogeneous stochastic models that also consider partial observability and non-determinism.
2. Techniques for learning and refinement of the developed monitors, thus enabling both the structural and behavioral improvement of the stochastic models underpinning these monitors based on operational data.

Planned Secondment(s)

S5: ITU, Prof. Varshosaz, 2 months in M14-15
S6: EIVA, Dr. Brodsky, 2 months in M26-27

Required Skills

Essential

• Degree in Computer Science, Applied Mathematics or related field
• Excellent programming skills (C++, Python, etc.)

Desirable

• Knowledge in ROS and robot simulators (e.g. Gazebo, IsaacSim, etc.)
• Practical experience with Domain-Specific Language Engineering, Model-Driven Engineering or LLMs