Search Results

< Back Dr Jozef Kulik University of York iGGi Alum Jozef’s first study has focused on developing a better understanding of the challenges and barriers to making accessible games. This identified a vast array of personal, organisational, and external factors which contribute to the difficulties that developers experience when seeking to make their games more accessible, and also identifies avenues which might be helpful. One key finding in this research was that one of the biggest challenges that developers experience relates to a lack of lived experience with disability, or knowledge of the player experience with disabilities. My most recent research is focused on how to effectively extract that knowledge from players with disabilities, then insert it into a large studio within the UK. This research takes a multi-pronged approach to assisting developers in making more accessible games. First by directly assisting a studio with knowledge about their games, second generating potentially transferable knowledge on accessibility issues and player experience for the rest of the industry, and exploring how research methods such as diary study methodology can be valuable in extracting data from natural play environments with people with disabilities. Email joe.kulik@york.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisors: Prof. Paul Cairns Dr Jen Beeston Featured Publication(s): Understanding how we make accessible games: Perspectives from the games industry and players with disabilities A Qualitative Investigation of Real World Accessible Design Experiences within a Large Scale Commercial Game Development Studio Grounded theory of accessible game development What makes icons appealing? The role of processing fluency in predicting icon appeal in different task contexts Themes Accessibility Player Research - Previous Next

< Back Evgenii Kashin University of York iGGi Alum Evgenii, a Computer Science enthusiast, began crafting games in school using the Warcraft3 editor. He spent five years as a Machine Learning Engineer, excelling in computer vision and graphics. His work at Snap included creating engaging lenses and researching 3D object capturing. An ECCV2020 article on face manipulation, with over 100 citations, is a testament to his prowess. Away from work, he enjoys bouldering, hiking, racing, and gaming. My research is dedicated to establishing a cost-effective approach for creating and generating 3D scenes for game development, a critical aspect of modern VR/AR applications. Harnessing the potential of generative visual content, I aim to develop algorithms capable of realistically completing 3D scenes from a few images. This could revolutionize the entertainment and creative industries, particularly game development. Picture having only a couple of images from your favourite film and envisioning the entire scene. Such technology can enhance the efficiency of 3D artists, democratize game development, and serve as entertainment in itself. Currently, I am developing an algorithm to achieve this goal. The proposed solution employs a general pretrained text-to-image model for supervision, with a NeRF 3D representation of the scene. The central concept involves iterative outpainting, where each iteration updates the NeRF weights. Email evgenii.kashin@york.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisor Dr William Smith Featured Publication(s): The Sky's the Limit: Relightable Outdoor Scenes via a Sky-Pixel Constrained Illumination Prior and Outside-In Visibility Stylegan2 distillation for feed-forward image manipulation Themes Creative Computing - Previous Next

< Back Younès Rabii Queen Mary University of London iGGi PG Researcher Available for post-PhD position Younès is an awarded game designer and generative AI researcher. Their current research is concerned with the relationship between a game's rules, its narrative, and how to build AI systems that can understand these relationships, manipulate them, and invent new ones. Younès also has been a game developer for the past 10 years. They specialize in crafting new forms of play and making it accessible for their peers. Their work has been previously exposed in the French embassies and international conferences like the Game Developers Conference, the Gamedevs of Color Expo and the A MAZE Festival. A description of Younès' research: Younès' research goal is to bring to video games some of the most interesting properties of roleplaying games: their ability to trust every player with building a part of the game, and their ability to generate both new narrative and gameplay on the fly. Younès is working both on the AI techniques needed to allow that, and how to design the social spaces around those games in a way that won't hurt players or abuse creators. For the end of their PhD, Younès is designing a prototype in that new genre, counting among the first games to contain a form of Live Automated Game Design. Email yrabii.eggs@gmail.com Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisor(s): Dr Mike Cook Dr Jeremy Gow Featured Publication(s): "Hunt Takes Hare": Theming Games Through Game-Word Vector Translation " Hunt Takes Hare": Theming Games Through Game-Word Vector Translation Why Oatmeal is Cheap: Kolmogorov Complexity and Procedural Generation Revealing game dynamics via word embeddings of gameplay data Themes Creative Computing Design & Development Game AI - Previous Next

< Back Prakriti Nayak Queen Mary University of London iGGi PG Researcher Available for placement Prakriti is a neuroscientist passionate about pushing boundaries at the intersection of technology and biological research. Her journey began with a deep dive into neuroscience during her master’s program, where she explored large-scale imaging data and mastered statistical modelling techniques. Afterward, she pursued a career in scientific editing. She views gaming as an excellent platform to connect different fields, such as computational modelling and behaviour. Prakriti plans to develop a model of player uncertainty to enhance the gaming experience by setting difficulty levels that are enjoyable for each player, making games more accessible for people with limited cognitive capabilities. Additionally, her work has diagnostic applications. A description of Prakriti's research: Navigation and spatial memory are essential cognitive processes that enable individuals to orient themselves in complex environments. Amid the inherent uncertainty of environmental noise and cognitive variability, the brain employs sophisticated strategies to make navigational decisions. This project aims to elucidate the cognitive underpinnings of spatial navigation performance by leveraging gaming data to understand how individuals manage spatial uncertainty. The plan is to adapt a Bayesian ideal-observer model based on visual simultaneous localization and mapping. The model will fit and predict the player’s moment-by-moment movement decisions, given the first-person view and the map of the game environment. Fitting the model to the players' gameplay trajectories will yield parameters indicating each individual's levels of visual, motor, and memory noise. The combination of parameters that best differentiate between players will then be examined. This research has the potential to enhance our understanding of spatial navigation and its underlying mechanisms, as well as improve spatial navigation in games, offering an adaptive gaming experience tailored to individual spatial uncertainty levels. Email p.nayak@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisors: Dr Guifen Chen Dr Yul HR Kang Themes Accessibility Applied Games Player Research - Previous Next

< Back Dr Adam Katona University of York iGGi Alum Adam did his MSc in mechatronics at Budapest University of Technology and Economics. After graduation, he spent two years working on automated driving at Robert Bosch GmbH, during which he got exposed to both the classical and the machine learning approach of creating intelligent agents. Evolutionary computation continues to surprise us by producing creative and efficient designs. However despite our best efforts, artificial evolution had not produced anything ascomplex and interesting as natural evolution. As our hardware is becoming faster and number of cores in our chips increase, the lack of computational power is becoming less of an excuse. It is starting to become more and more obvious that some fundamental component of natural evolution is missing from our simulations. One possible candidate is the evolution of evolvability. Evolution seems to produce organisms which are well suited for further evolution. The goal of my research is to find mechanisms which allows evolution to increase evolvability, and incorporate these in the design of more efficient neuroevolution algorithms.This research is in the intersection of evolutionary computation, evolutionary developmental biology and neural networks. Email mail.adamkatona@gmail.com Website LinkedIn Mastodon BlueSky GitHub Other Link Featured Publication(s): Complex computation from developmental priors Utilizing the Untapped Potential of Indirect Encoding for Neural Networks with Meta Learning Quality Evolvability ES: Evolving Individuals With a Distribution of Well Performing and Diverse Offspring Growing 3d artefacts and functional machines with neural cellular automata Time to die: Death prediction in dota 2 using deep learning Themes Game AI - Previous Next

< Back Janet Gibbs Goldsmiths iGGi Alum Janet is exploring how multi-modal perceptual feedback contributes to a player's sense of presence in the virtual world. Jaron Lanier described Virtual Reality (VR) as the substitution of the interface between a person and their physical environment with an interface to a simulated environment. This interface is of particular significance in understanding how presence depends on the nature, extent and veridicality of our sensorimotor interaction with the virtual environment, and how that relates to our normal engagement with the real world. In practice, only selected parts of the interface are substituted - we are never fully removed from our physical environment. Our perceptual apparatus evolved to make sense of changing sensations in multiple modalities originating naturally and coherently from the same event or percept. By contrast, in VR, individually crafted feedback using different technologies for each modality are coordinated to appear as if from a single source. VR benefits from a long history of visual and audio technologies, developed in harness for virtual experiences from cinema to computer games. Haptics is a relative newcomer that must be blended with them to create coherent multimodal perceptual experiences. Additionally, haptics is closely related to proprioception, and to the wide range of tactile senses—texture, heat, pain etc—that current VR systems do not address. Building on sensorimotor theory of perception, Janet aims to establish how our perceptual system responds to multi-modal feedback that almost, but not quite, matches what we are used to, in making sense of the simulated environment of VR. Email JGIBB016@gold.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Featured Publication(s): Investigating Sensorimotor Contingencies in the Enactive Interface A comparison of the effects of haptic and visual feedback on presence in virtual reality Novel Player Experience with Sensory Substitution and Augmentation Investigating sensorimotor contingencies in the enactive interface Themes - Previous Next

< Back Dominik Jeurissen Queen Mary University of London iGGi PG Researcher Dominik holds an MSc in Artificial Intelligence from Maastricht University and a BSc in Computer Science with a focus on Applied Mathematics from RWTH Aachen. During his undergraduate studies, he worked for 3 years as a software engineer at INFORM GmbH, contributing to their supply management software, add*ONE. His long-term goal is to develop fully autonomous agents that can act in complex environments while continually improving themselves. As a result, he is familiar with many related fields, including reinforcement learning, continual learning, large language models (LLMs), and imitation learning. A description of Dominik's research: "My PhD is a collaboration with Creative Assembly , focusing on researching AI for complex strategy games, such as Total War. With the recent rise of Large Language Models (LLMs), I'm exploring their potential to enhance game-playing agents. LLMs can instantly recall knowledge on almost any topic, perform basic reasoning, and are easily configured for a wide range of text-based tasks. These abilities make them especially promising for game development, where machine learning agents often struggle due to constantly changing game environments. During an internship at Creative Assembly, I worked together with the Creative Assembly's R&D team and NVIDIA to develop a prototype for an Onboarding Assistant that aims to help players when they are stuck in the game. My current research aims to improve the assistant by exploring systems for retrieving dynamic gamestate information." Email d.jeurissen@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisors: Dr Diego Pérez-Liébana Dr Jeremy Gow Featured Publication(s): Exploration with Foundation Models: Capabilities, Limitations, and Hybrid Approaches Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds Playing nethack with llms: Potential & limitations as zero-shot agents Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents PyTAG: Challenges and Opportunities for Reinforcement Learning in Tabletop Games Generating Diverse and Competitive Play-Styles for Strategy Games Automatic Goal Discovery in Subgoal Monte Carlo Tree Search Game state and action abstracting monte carlo tree search for general strategy game-playing Portfolio search and optimization for general strategy game-playing The Design Of" Stratega": A General Strategy Games Framework Themes Design & Development Game AI Game Data - Previous Next

< Back Dr Nathan John Queen Mary University of London iGGi Alum After graduating with a MEng in Computer Science from the University of Bristol, Nathan joined the games industry as a programmer, working for Climax Studios, Gaming Corps and Freejam, before moving to a career as a general software engineer, while still developing indie games on the side. His experiences across a range of industries sparked a passion for testing, and left him wondering if there were was to improve the automated testing in game development. Borne from an experiment Nathan had performed training AIs to play his indie game WarpBall, in which he found the agents solved for exploits in the authored AI rather than playing the game well, his research project proposes a novel method for improving the quality of behaviour of human authored agents by pitting them against trained agents and observing what bad behaviours/exploits the trained agents reveal. Authored agents refer to AI agents whose actions are explicitly designed by programmers using traditional techniques such as Utility functions, Behaviour Trees and state machines; trained agents refer to agents whose behaviour is learned by playing many games against the authored agents. Email n.m.john-mcdougall@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisors: Dr Jeremy Gow Dr Laurissa Tokarchuk Themes Design & Development Game AI - Previous Next

< Back Dr Terence Broad Goldsmiths iGGi Alum Terence Broad is an artist and researcher working on developing new techniques and interfaces for the manipulation of generative models. His PhD focusses on how pre-trained generative neural networks can be repurposed and reconfigured for authoring novel multimedia content. He is completing his PhD at Goldsmiths, University of London and is also a visiting researcher at the UAL Creative Computing Institute. His research has been published in international conferences, workshops and journals such as SIGGRAPH, NeurIPS, Leonardo and xCoAx. He was acknowledged as an outstanding peer-reviewer by the journal Leonardo. Terence is a practicing artist and often uses the techniques he has developed in his research in the creation of his artworks. His art has been exhibited and screened internationally at venues such as The Whitney Museum of American Art, Ars Electronica, The Barbican and The Whitechapel Gallery. He won the Grand Prize in the ICCV 2019 Computer Vision Art Gallery. Email t.broad@gold.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Featured Publication(s): Co-Designing Fashion with AI: A Small-Data Approach to Generative Garment Design Expanding the Generative Space: Data-Free Techniques for Active Divergence with Generative Neural Networks XAIxArts Manifesto: Explainable AI for the Arts Using Generative AI as an Artistic Material: A Hacker's Guide Is computational creativity flourishing on the dead internet? Interactive Machine Learning for Generative Models Envisioning Distant Worlds: Fine-Tuning a Latent Diffusion Model with NASA's Exoplanet Data Automating Generative Deep Learning for Artistic Purposes: Challenges and Opportunities Network Bending: Expressive Manipulation of Generative Models in Multiple Domains Active Divergence with Generative Deep Learning--A Survey and Taxonomy Network Bending: Expressive Manipulation of Deep Generative Models Amplifying The Uncanny Transforming the output of GANs by fine-tuning them with features from different datasets Searching for an (un) stable equilibrium: experiments in training generative models without data Autoencoding Blade Runner: Reconstructing Films with Artificial Neural Networks Light field completion using focal stack propagation Autoencoding video frames IoT and Machine Learning for Next Generation Traffic Systems Themes Creative Computing Design & Development - Previous Next

< Back Dr Ildar Farkhatdinov Queen Mary University of London Supervisor Dr Ildar Farkhatdinov is a Lecturer in Robotics at QMUL since 11/2016 and a Turing Institute Fellow. He is an internationally leading expert in assistive robotics and human-machine interaction. He is a principle investigator of several projects on wearable robotics, mobility assistance and haptic interfaces (including funding from the UK government on supernumerary robotic limbs and assistive wheelchairs, £500k+). Several of his research works were recognised as the best paper or finalists for best paper awards at leading robotics conferences. Before joining QMUL, he was a postdoctoral research associate at the Human Robotics group of the Department of Bioengineering, Imperial College London (2013-16). He earned Ph.D. in Robotics in 2013 (Sorbonne University, UPMC, France), M.Sc. in Mechanical Engineering in 2008 (KoreaTech, South Korea) and B.Sc. in Automation and Control in 2006 (Moscow University, Russia). He has actively collaborated on a number of large-scale research projects: EPSRC NCNR to create novel robotic solutions for the nuclear industry; EU FP7 BALANCE to develop balance and robotic walking assistance for the elderly; EU FP7 SYMBITRON to develop exoskeleton control for people with spinal cord injury. My research interest relevant to CDT IGGI include serious games for medical applications, as well as using game theory to investigate human-machine interaction. Research themes: Game Design Serious games Virtual reality Game theory Email i.farkhatdinov@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Themes Design & Development Game AI Immersive Technology Player Research - Previous Next

< Back Dr Paulo Rauber Queen Mary University of London Supervisor I am a lecturer in Artificial Intelligence at Queen Mary University of London. Before becoming a lecturer, I was a postdoctoral researcher in the Swiss AI lab working on reinforcement learning under the supervision of Jürgen Schmidhuber. I believe that intelligence should be defined as a measure of the ability of an agent to achieve goals in a wide range of environments, which makes reinforcement learning an excellent framework to study many challenges that intelligent agents are bound to face. Email p.rauber@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Themes Game AI - Previous Next

< Back Tom Wells University of York iGGi PG Researcher Available for placement Tom has an interest in niche alternative and indie games which evoke strong emotions and are narratively immersive. He studied Experimental Psychology as an undergraduate in Oxford, specialising in conscious brightness perception in specific optical pigments. His Masters was in Computational Neuroscience, Cognition and AI from Nottingham, and focused on Computer Vision (specifically facial recognition) and Visual Attention. He enjoys heavy metal, strength sports and literature. A description of Tom's research: With the rise of digital art, Uncanny Valley has emerged from an esoteric robotics concept into an infectious memetic phenomenon, with specific memes such as 'Uncanny/Canny Mr. Incredible', or more generally uncanny faces being used as reaction images for humor. Critics and players will now refer to specific media being 'Uncanny' rather than using more general words as 'off-putting', demonstrating uncanniness cementing itself in the public consciousness as examples increasingly abound; ergo digital artists should be aware of evoking the uncanny even with modern rendering technology, as audiences become increasingly discerning of the Uncanny. This is most pertinent in videogames, where rendering is performed in real-time, meaning rendering constraints must be implemented. This potentially confines characters to the Uncanny Valley, as it may not be possible to increase graphical fidelity, thus artists may be left to either accept the uncanny or demaster their work (both undesirable options). This project aims to learn about the Uncanny Valley pertaining to modern skin rendering techniques, using artificial intelligence (specifically GANs) to directly map skin rendering parameters onto user assessments of uncanniness and realism. This can then be reverse engineered to provide automated tools for generatively rendering realistic non-uncanny skin, and predicting audience responses to skin realism, expediting QA testing. The primary experimental stage is to generate a face database with photorealistic skin to be assessed using psychometrics by participants. This is additionally one of few studies looking into the novel phenomena of training AI's to generate human-oriented psychologically salient content. Email tw1700@york.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Themes - Previous Next