Filter

  • Trusted test suites for safe agent-based simulations

    Project ID: STAI-CDT-2020-KCL-11
    Themes: AI Planning, Verification
    Supervisor: Steffen Zschaler

    Agent-based models (ABMs) are an AI technique to help improve our understanding of complex real-world interactions and their ”emergent behaviour”. ABMs are used to develop and test theories or to explore how...

    Read more

  • Correct-by-construction domain-specific AI planners

    Project ID: STAI-CDT-2020-KCL-10
    Themes: AI Planning, Verification
    Supervisor: Steffen Zschaler

    When using complex algorithms to make decisions within autonomous systems, the weak link is the abstract model used by the algorithms: any errors in the model may lead to unanticipated behaviour potentially risking...

    Read more

  • Digital twins for the verification of learning and adaptive software

    Project ID: STAI-CDT-2020-IC-41
    Themes: AI Planning, Verification
    Supervisor: Antonio Filieri

    Learning and decision-making AI components are gaining popularity as enablers of modern adaptive software. Common uses include, for example, the classification or regression of incoming data (e.g., face recognition), the...

    Read more

  • Neural-symbolic learning: a solution for generalisable and explainable AI

    Project ID: STAI-CDT-2020-IC-43
    Themes: AI Planning, Logic
    Supervisor: Alessandra Russo

    This research proposal focuses on developing a novel hybrid neural-symbolic learning approach that combines the capabilities of deep learning methods in extracting features from unstructured data with the ability of...

    Read more

  • Abstract Interpretation for Safe Machine Learning

    Project ID: STAI-CDT-2020-IC-7
    Themes: AI Planning, Verification
    Supervisor: Sergio Maffeis

    Machine learning (ML) techniques such as Support Vector Machines, Random Forests and Neural Networks are being applied with great success to a wide range of complex and sometimes safety-critical tasks. Recent research in...

    Read more

  • A model-based verification for safe and trusted concurrent robotics systems

    Project ID: STAI-CDT-2020-IC-21
    Themes: AI Planning, Logic, Verification
    Supervisor: Nobuko Yoshida

    SUMMARY Robotics applications involve programming concurrent components synchronising through messages while simultaneously executing motion actions that control the state of the physical world. Today, these applications...

    Read more

  • A Novel Model-driven AI Paradigm for Intrusion Detection

    Project ID: STAI-CDT-2020-KCL-26
    Themes: AI Planning, Logic, Verification
    Supervisor: Fabio Pierazzi

    Intrusion Detection Systems (IDSs) are commonly deployed in networks and hosts to identify malicious activities representing misuse of computer systems. The numbers and types of attacks have been constantly increasing, and...

    Read more

  • Probabilistic Abstract Interpretation of Deep Neural Networks

    Project ID: STAI-CDT-2020-IC-30
    Themes: AI Planning, Verification
    Supervisor: Herbert Wiklicky

    The extraction of (symbolic) rules which describe the operation of (deep) neural networks which have been trained to perform a certain task is central to explaining their inner workings in order to judge their correctness,...

    Read more

  • Verifying Emergence Properties of Robotic Swarms

    Project ID: STAI-CDT-2020-IC-31
    Themes: AI Planning, Logic, Verification
    Supervisor: Alessio Lomuscio

    The effective development and deployment of single-robot systems is increasingly shown to be problematic in a variety of application domains including search and rescue, remote exploration, de-mining, etc. These and other...

    Read more

  • Discrete-continuous hybrid planning for adaptive cyber-physical systems

    Project ID: STAI-CDT-2020-IC-35
    Themes: AI Planning, Verification
    Supervisor: Antonio Filieri

    Adaptive cyber-physical systems rely on the composition and coordinated interaction of different decision-making procedures. Cyber components capabilities and semantics are usually captured by operational models (such as...

    Read more