Property:OneLineSummary
From ISLAB/CAISR
"
A robot which can detect faults on itself and try to mark or fix them +
A
Compare different solutions for building a decentralised IoT platform +
A Meta-Learning Approach for Preserving and Transferring Beneficial Behaviors in Asynchronous Multi-Agent Reinforcement Learning +
Develop a meta-learning system that preserves beneficial behaviors discovered by individual agents and adapts them for transfer across a population in asynchronous reinforcement learning. +
In this project, we will modify the well-known IoT protocol, i.e., MQTT to consider a topic-based reliability strategy between the broker and subscribers. +
Developing a clinical decision support system using machine learning and biomedical signal analysis techniques for an ICU setting. +
Feasibility study on bioimplants in humans. +
This project allows the MSc student(s) to study and experiment on Agentic AI methods for the generation of trustworthy ML-pipelines +
Develop a toolkit for a successful implementation of an AI application for Service Market Logistics, with a working AI in a pilot environment and an implementation process evaluation as an output. +
Reinforcement learning +
Connect AI models to sustainability / ESG (social, environmental, and governance) to enable automated processing related to EU sustainability regulations. +
To develop and evaluate an AI-based semantic encoding model capable of transforming raw data into compact, structured representations. +
This project, in collaboration with Volvo Logistics, focuses on using state-of-the-art methods based on meta-learning to improve demand forecasting, inventory management and spare parts availability at Volvo dealers and warehouses. +
Action Library for Robot Execution +
Tracking of more than one person in a smart environment using fixed sensors and a mobile robot +
Build a series of increasingly sophisticated robot models in Acumen, to (1) explore mathematical formulations and (2) create tutorials and didactic examples. +
LoCoMotif is a novel TSMD method able to discover motifs that have different lengths (variable-length motifs), exhibit slight temporal differences (time-warped motifs), and span multiple dimensions (multivariate motifs) +
Develop an adaptive method to combine knowledge from multiple reinforcement learning agents more efficiently in asynchronous setups. +
This master thesis project focuses on developing an adaptive obfuscation frame- work for protecting multi-modal data in resource-constrained IoT environments. +
Adaptive warning field system +
