Build and test various high level control and coordination techniques for autonomous robotic boats for monitoring water conditions in lakes and rivers. This is the main research focus of the INTCATCH H2020 project.
Possible ideas for projects in this area: i) intelligent exploration implementation and evaluation of approaches for intelligent water sampling; ii) HRI study of Human Robot Interaction approaches for controlling a team of autonomous boats; iii) perception and situation assessment using techniques for multisensor time-series analysis and computer vision to detect relevant features and situations.
Possible ideas: i) Collective Energy purchasing Complete or approximate algorithms to solve coalition formation problem in the energy domain, where users join coalitions to buy more energy in the forward market. Test the method on real consumption data. ii) Ridesharing Design and implement techniques for managing ridesharing requests from a bunch of commuters (i.e., form groups, decide payments, compute best routes). iii) Use of GPUs for efficient implementation Implement and evaluate solution approaches to the above combinatorial problems using GPUs to speed-up solution process and scale up to larger systems.
Perform active malware analysis by using reinforcement learning approaches that interact with the malware in a sandbox. Design action selection strategies to learn malware models representing behaviors triggered by specific actions on the infected system. Compare learned models with machine learning approaches (e.g. clustering, classification etc...)
Implement and evaluate coordination approaches for Multi-robot systems. Possible ideas: i) design exploration and patrolling approaches for robotic agents (UAVs or UGVs). Test the solution on a widely used simulation environment (ROS + stage); ii) develop coordination strategies for heterogeneous agents (i.e., UAV + UGV) using team plan languanges
Design and evaluate high level modeling and control approaches for greenhouse system to maximizes crop yield and minimizes infection based on real time data acquired though a sensor network. Focus on: i) regression and other modeling techniques to analyse real data collected from a greenhouse; ii) devising the best actions (e.g., control light intensity and temperature) to avoid disease infections (e.g., peronospera). In collaboration with the EXPO-AGRI Project.