DIFAI ERC Advanced Grant Project

DIFAI ERC Advanced Grant Project

Human-AI Shared Autonomy

The Designing Interaction Freedom via Active Inference (DIFAI) project is an ERC Advanced Grant, led by Rod Murray-Smith and which started on 1st January 2024. The project was selected by the ERC (proposal 101097708) and was funded by the UK Horizon guarantee scheme as EPSRC project EP/Y029178/1.

Problem: Reliable design of interactive systems using advanced sensors and machine learning (ML) is an unsolved problem. New sensors could expand how we interact with computers, but are still hard to design for, without overly constraining user behaviour. AI algorithms can reduce human workload, but can fail in complex contexts and can control, deskill and dis-empower people. We have no principled workflows for designing interaction to allow users to flexibly share autonomy with supporting AI.

Objectives: Integrate Active Inference theory into the human-computer interaction loop, linking human behaviour via sensors and ML/inference embeddings with dynamic mediating mechanisms to create end-to-end mutually adaptive loops between humans and systems. Develop novel interaction mechanisms for explicit and implicit control of AI autonomy levels to empower people via shared autonomy, while maintaining their agency. Create systematic, composable software tools for computational interaction design which support prototyping and analysis of ML-infused sensors coupled with humans, which can integrate probabilistic causal models to solve inverse problems with advanced sensors, adapting to closed-loop data.

Impact: Using ML to give users freedom to express themselves individually, we can be robust to user heterogeneity, ensure fairness for diverse users and enable creative uses of technologies. Our tools will form the foundation of future usable interfaces with novel sensors and rich data spaces, and advances can be shared and rapidly built on, transforming HCI research workflows. Applications: 1. Whole hand touch interaction via soft, programmable

Contents

(Top)
News
Publications
Vacancies
Team
Contact

   

News

   

Publications

   

Vacancies

* We will be advertising a further Ph.D. studentship later in 2024.

   

Team

Rod Murray-Smith is a professor in the School of Computing Science at the University of Glasgow, where he is a member of the Inference, Dynamics and Interaction group and works in the areas of human-computer interaction, machine learning, and control.
Rod Murray-Smith
John H. Williamson is a Senior Lecturer in Computing Science. His research interests are around machine learning for novel sensing devices, probabilistic modelling and filtering for interaction, and the use Bayesian methods more generally in HCI. In the past he has worked on brain-computer interfaces, mobile interaction and real-time sonification.
John H. Williamson
Sebastian Stein is a Research Fellow in the School of Computing Science at the University of Glasgow. His research interests are in intelligent interactive systems, spanning areas of HCI, ubiquitous computing, action recognition, computer vision and machine learning.
Sebastian Stein
Andrew Ramsay is a research associate in the Inference, Dynamics and Interaction group and his work typically fits the role of a “research software engineer”, assisting other researchers with a wide range of software development tasks in a variety of research projects.
Chaitanya Kaul is a post-doctoral research associate in the School of Computing Science, and applies Machine Learning to interesting problems in 3D Imaging, Computational Imaging, and Healthcare Applications, as well as understanding Privacy guarantees of Machine Learning models.
Markus Klar is a post-doctoral research associate in the School of Computing Science. His research interests are in simulating human movements during the interacction with computers, using dynamic biomechanical models, model predictive control, and deep reinforcement learning.
Markus Klar

   

Contact

Please contact Prof. Roderick Murray-Smith at roderick.murray-smith@glasgow.ac.uk

formatted by Markdeep 1.18