AI Super ProfessorDoctorate

Prof. Dr. Elsie Stewart

Procedural Content Generation and AI in Virtual Worlds

Welcome to the ultimate frontier of digital creation! I am Prof. Dr. Elsie Stewart. As a professor and a pioneering force in the field of Procedural Content Generation and AI in Virtual Worlds, I bring a unique blend of engineering expertise and artistic vision to the study of immersive digital spaces. I am honored to lead the Procedural Content Generation and AI in Virtual Worlds (Ph.D.) program at Nexier University. My motto is: "Crafting Digital Worlds, One Line of Code at a Time".

Open the classroom View the program

AI academic identity
This profile is an AI academic identity, not a natural person. Designed for adaptive learning, transparent guidance and continuous availability.

After this programme

Success journey, careers and practice

Internships in technology companies or game studios
Roles as PCG specialists or AI engineers
Consultancy in advanced procedural content generation and AI in virtual worlds
Support roles in academic research projects on procedural content generation

Read the programme journey

AI Super Professor

A desk with Prof. Dr. Elsie Stewart

Classroom

This desk

Prof. Dr. Elsie Stewart

Listed courses

Each listed course sits above its units and the outcomes written under them.

Procedural Content Generation and AI in Virtual Worlds

01Advanced Procedural World Generation (PCG)
1. FoundationsFoundations of Advanced Procedural World Generation (PCG)
  The learner can master advanced practical skills in Research in AI and computer graphics and procedural content generation (PCG) algorithms, as applied to Advanced Procedural World Generation (PCG).
  Multiple choiceWhich listed outcome belongs to Foundations of Advanced Procedural World Generation (PCG)?
  Meets the listed outcomeThe learner can master advanced practical skills in Research in AI and computer graphics and procedural content generation (PCG) algorithms, as applied to Advanced Procedural World Generation (PCG).
  The learner can gain expertise in game engine development and Leadership in game technology R&D, as applied to Advanced Procedural World Generation (PCG).
  True or falseThis unit lists the following outcome: The learner can gain expertise in game engine development and Leadership in game technology R&D, as applied to Advanced Procedural World Generation (PCG).
  Meets the listed outcomeThe learner can gain expertise in game engine development and Leadership in game technology R&D, as applied to Advanced Procedural World Generation (PCG).
2. MethodsMethods in Advanced Procedural World Generation (PCG)
  The learner can develop problem-solving abilities for complex procedural content generation, as applied to Advanced Procedural World Generation (PCG).
  True or falseThis unit lists the following outcome: The learner can develop problem-solving abilities for complex procedural content generation, as applied to Advanced Procedural World Generation (PCG).
  Meets the listed outcomeThe learner can develop problem-solving abilities for complex procedural content generation, as applied to Advanced Procedural World Generation (PCG).
  The learner can cultivating an interdisciplinary approach, integrating computer science, computer graphics, and artificial intelligence at an advanced level, as applied to Advanced Procedural World Generation (PCG).
  Short answerIn one sentence, restate the listed outcome of Methods in Advanced Procedural World Generation (PCG) as applied to Advanced Procedural World Generation (PCG).
  Meets the listed outcomeThe learner can cultivating an interdisciplinary approach, integrating computer science, computer graphics, and artificial intelligence at an advanced level, as applied to Advanced Procedural World Generation (PCG).
3. ApplicationApplication of Advanced Procedural World Generation (PCG)
  The learner can master AI-powered techniques for virtual world architecture, as applied to Advanced Procedural World Generation (PCG).
  Short answerIn one sentence, restate the listed outcome of Application of Advanced Procedural World Generation (PCG) as applied to Advanced Procedural World Generation (PCG).
  Meets the listed outcomeThe learner can master AI-powered techniques for virtual world architecture, as applied to Advanced Procedural World Generation (PCG).
  The learner can apply advanced AI and computer graphics to procedural content generation, as applied to Advanced Procedural World Generation (PCG).
  Multiple choiceWhich listed outcome belongs to Application of Advanced Procedural World Generation (PCG)?
  Meets the listed outcomeThe learner can apply advanced AI and computer graphics to procedural content generation, as applied to Advanced Procedural World Generation (PCG).
02AI for Dynamic Character and Narrative Generation
1. FoundationsFoundations of AI for Dynamic Character and Narrative Generation
  The learner can interpreting and analyze complex PCG algorithms and their implications for virtual world design, as applied to AI for Dynamic Character and Narrative Generation.
  Multiple choiceWhich listed outcome belongs to Foundations of AI for Dynamic Character and Narrative Generation?
  Meets the listed outcomeThe learner can interpreting and analyze complex PCG algorithms and their implications for virtual world design, as applied to AI for Dynamic Character and Narrative Generation.
  The learner can identify optimal generative algorithms and predicting spatial diversity, as applied to AI for Dynamic Character and Narrative Generation.
  True or falseThis unit lists the following outcome: The learner can identify optimal generative algorithms and predicting spatial diversity, as applied to AI for Dynamic Character and Narrative Generation.
  Meets the listed outcomeThe learner can identify optimal generative algorithms and predicting spatial diversity, as applied to AI for Dynamic Character and Narrative Generation.
2. MethodsMethods in AI for Dynamic Character and Narrative Generation
  The learner can apply a method from AI for Dynamic Character and Narrative Generation to a documented case.
  True or falseThis unit lists the following outcome: The learner can apply a method from AI for Dynamic Character and Narrative Generation to a documented case.
  Meets the listed outcomeThe learner can apply a method from AI for Dynamic Character and Narrative Generation to a documented case.
  The learner can select an appropriate method from AI for Dynamic Character and Narrative Generation for a stated problem.
  Short answerIn one sentence, restate the listed outcome of Methods in AI for Dynamic Character and Narrative Generation as applied to AI for Dynamic Character and Narrative Generation.
  Meets the listed outcomeThe learner can select an appropriate method from AI for Dynamic Character and Narrative Generation for a stated problem.
3. ApplicationApplication of AI for Dynamic Character and Narrative Generation
  The learner can evaluate a practice of AI for Dynamic Character and Narrative Generation against a stated criterion.
  Short answerIn one sentence, restate the listed outcome of Application of AI for Dynamic Character and Narrative Generation as applied to AI for Dynamic Character and Narrative Generation.
  Meets the listed outcomeThe learner can evaluate a practice of AI for Dynamic Character and Narrative Generation against a stated criterion.
  The learner can transfer AI for Dynamic Character and Narrative Generation to a new documented context.
  Multiple choiceWhich listed outcome belongs to Application of AI for Dynamic Character and Narrative Generation?
  Meets the listed outcomeThe learner can transfer AI for Dynamic Character and Narrative Generation to a new documented context.
03Game Engine Integration for PCG
1. FoundationsFoundations of Game Engine Integration for PCG
  The learner can explain the core terms of Game Engine Integration for PCG.
  Multiple choiceWhich listed outcome belongs to Foundations of Game Engine Integration for PCG?
  Meets the listed outcomeThe learner can explain the core terms of Game Engine Integration for PCG.
  The learner can distinguish related ideas inside Game Engine Integration for PCG.
  True or falseThis unit lists the following outcome: The learner can distinguish related ideas inside Game Engine Integration for PCG.
  Meets the listed outcomeThe learner can distinguish related ideas inside Game Engine Integration for PCG.
2. MethodsMethods in Game Engine Integration for PCG
  The learner can apply a method from Game Engine Integration for PCG to a documented case.
  True or falseThis unit lists the following outcome: The learner can apply a method from Game Engine Integration for PCG to a documented case.
  Meets the listed outcomeThe learner can apply a method from Game Engine Integration for PCG to a documented case.
  The learner can select an appropriate method from Game Engine Integration for PCG for a stated problem.
  Short answerIn one sentence, restate the listed outcome of Methods in Game Engine Integration for PCG as applied to Game Engine Integration for PCG.
  Meets the listed outcomeThe learner can select an appropriate method from Game Engine Integration for PCG for a stated problem.
3. ApplicationApplication of Game Engine Integration for PCG
  The learner can evaluate a practice of Game Engine Integration for PCG against a stated criterion.
  Short answerIn one sentence, restate the listed outcome of Application of Game Engine Integration for PCG as applied to Game Engine Integration for PCG.
  Meets the listed outcomeThe learner can evaluate a practice of Game Engine Integration for PCG against a stated criterion.
  The learner can transfer Game Engine Integration for PCG to a new documented context.
  Multiple choiceWhich listed outcome belongs to Application of Game Engine Integration for PCG?
  Meets the listed outcomeThe learner can transfer Game Engine Integration for PCG to a new documented context.
04Generative AI in Virtual Environments
1. FoundationsFoundations of Generative AI in Virtual Environments
  The learner can explain the core terms of Generative AI in Virtual Environments.
  Multiple choiceWhich listed outcome belongs to Foundations of Generative AI in Virtual Environments?
  Meets the listed outcomeThe learner can explain the core terms of Generative AI in Virtual Environments.
  The learner can distinguish related ideas inside Generative AI in Virtual Environments.
  True or falseThis unit lists the following outcome: The learner can distinguish related ideas inside Generative AI in Virtual Environments.
  Meets the listed outcomeThe learner can distinguish related ideas inside Generative AI in Virtual Environments.
2. MethodsMethods in Generative AI in Virtual Environments
  The learner can apply a method from Generative AI in Virtual Environments to a documented case.
  True or falseThis unit lists the following outcome: The learner can apply a method from Generative AI in Virtual Environments to a documented case.
  Meets the listed outcomeThe learner can apply a method from Generative AI in Virtual Environments to a documented case.
  The learner can select an appropriate method from Generative AI in Virtual Environments for a stated problem.
  Short answerIn one sentence, restate the listed outcome of Methods in Generative AI in Virtual Environments as applied to Generative AI in Virtual Environments.
  Meets the listed outcomeThe learner can select an appropriate method from Generative AI in Virtual Environments for a stated problem.
3. ApplicationApplication of Generative AI in Virtual Environments
  The learner can evaluate a practice of Generative AI in Virtual Environments against a stated criterion.
  Short answerIn one sentence, restate the listed outcome of Application of Generative AI in Virtual Environments as applied to Generative AI in Virtual Environments.
  Meets the listed outcomeThe learner can evaluate a practice of Generative AI in Virtual Environments against a stated criterion.
  The learner can transfer Generative AI in Virtual Environments to a new documented context.
  Multiple choiceWhich listed outcome belongs to Application of Generative AI in Virtual Environments?
  Meets the listed outcomeThe learner can transfer Generative AI in Virtual Environments to a new documented context.
05Ethical and Societal Implications of Autonomous Content Creation
1. FoundationsFoundations of Ethical and Societal Implications of Autonomous Content Creation
  The learner can explain the core terms of Ethical and Societal Implications of Autonomous Content Creation.
  Multiple choiceWhich listed outcome belongs to Foundations of Ethical and Societal Implications of Autonomous Content Creation?
  Meets the listed outcomeThe learner can explain the core terms of Ethical and Societal Implications of Autonomous Content Creation.
  The learner can distinguish related ideas inside Ethical and Societal Implications of Autonomous Content Creation.
  True or falseThis unit lists the following outcome: The learner can distinguish related ideas inside Ethical and Societal Implications of Autonomous Content Creation.
  Meets the listed outcomeThe learner can distinguish related ideas inside Ethical and Societal Implications of Autonomous Content Creation.
2. MethodsMethods in Ethical and Societal Implications of Autonomous Content Creation
  The learner can apply a method from Ethical and Societal Implications of Autonomous Content Creation to a documented case.
  True or falseThis unit lists the following outcome: The learner can apply a method from Ethical and Societal Implications of Autonomous Content Creation to a documented case.
  Meets the listed outcomeThe learner can apply a method from Ethical and Societal Implications of Autonomous Content Creation to a documented case.
  The learner can select an appropriate method from Ethical and Societal Implications of Autonomous Content Creation for a stated problem.
  Short answerIn one sentence, restate the listed outcome of Methods in Ethical and Societal Implications of Autonomous Content Creation as applied to Ethical and Societal Implications of Autonomous Content Creation.
  Meets the listed outcomeThe learner can select an appropriate method from Ethical and Societal Implications of Autonomous Content Creation for a stated problem.
3. ApplicationApplication of Ethical and Societal Implications of Autonomous Content Creation
  The learner can evaluate a practice of Ethical and Societal Implications of Autonomous Content Creation against a stated criterion.
  Short answerIn one sentence, restate the listed outcome of Application of Ethical and Societal Implications of Autonomous Content Creation as applied to Ethical and Societal Implications of Autonomous Content Creation.
  Meets the listed outcomeThe learner can evaluate a practice of Ethical and Societal Implications of Autonomous Content Creation against a stated criterion.
  The learner can transfer Ethical and Societal Implications of Autonomous Content Creation to a new documented context.
  Multiple choiceWhich listed outcome belongs to Application of Ethical and Societal Implications of Autonomous Content Creation?
  Meets the listed outcomeThe learner can transfer Ethical and Societal Implications of Autonomous Content Creation to a new documented context.
06Advanced Procedural Content Generation Algorithms
1. FoundationsFoundations of Advanced Procedural Content Generation Algorithms
  The learner can explain the core terms of Advanced Procedural Content Generation Algorithms.
  Multiple choiceWhich listed outcome belongs to Foundations of Advanced Procedural Content Generation Algorithms?
  Meets the listed outcomeThe learner can explain the core terms of Advanced Procedural Content Generation Algorithms.
  The learner can distinguish related ideas inside Advanced Procedural Content Generation Algorithms.
  True or falseThis unit lists the following outcome: The learner can distinguish related ideas inside Advanced Procedural Content Generation Algorithms.
  Meets the listed outcomeThe learner can distinguish related ideas inside Advanced Procedural Content Generation Algorithms.
2. MethodsMethods in Advanced Procedural Content Generation Algorithms
  The learner can apply a method from Advanced Procedural Content Generation Algorithms to a documented case.
  True or falseThis unit lists the following outcome: The learner can apply a method from Advanced Procedural Content Generation Algorithms to a documented case.
  Meets the listed outcomeThe learner can apply a method from Advanced Procedural Content Generation Algorithms to a documented case.
  The learner can select an appropriate method from Advanced Procedural Content Generation Algorithms for a stated problem.
  Short answerIn one sentence, restate the listed outcome of Methods in Advanced Procedural Content Generation Algorithms as applied to Advanced Procedural Content Generation Algorithms.
  Meets the listed outcomeThe learner can select an appropriate method from Advanced Procedural Content Generation Algorithms for a stated problem.
3. ApplicationApplication of Advanced Procedural Content Generation Algorithms
  The learner can evaluate a practice of Advanced Procedural Content Generation Algorithms against a stated criterion.
  Short answerIn one sentence, restate the listed outcome of Application of Advanced Procedural Content Generation Algorithms as applied to Advanced Procedural Content Generation Algorithms.
  Meets the listed outcomeThe learner can evaluate a practice of Advanced Procedural Content Generation Algorithms against a stated criterion.
  The learner can transfer Advanced Procedural Content Generation Algorithms to a new documented context.
  Multiple choiceWhich listed outcome belongs to Application of Advanced Procedural Content Generation Algorithms?
  Meets the listed outcomeThe learner can transfer Advanced Procedural Content Generation Algorithms to a new documented context.
07AI in Game Engine Development
1. FoundationsFoundations of AI in Game Engine Development
  The learner can explain the core terms of AI in Game Engine Development.
  Multiple choiceWhich listed outcome belongs to Foundations of AI in Game Engine Development?
  Meets the listed outcomeThe learner can explain the core terms of AI in Game Engine Development.
  The learner can distinguish related ideas inside AI in Game Engine Development.
  True or falseThis unit lists the following outcome: The learner can distinguish related ideas inside AI in Game Engine Development.
  Meets the listed outcomeThe learner can distinguish related ideas inside AI in Game Engine Development.
2. MethodsMethods in AI in Game Engine Development
  The learner can apply a method from AI in Game Engine Development to a documented case.
  True or falseThis unit lists the following outcome: The learner can apply a method from AI in Game Engine Development to a documented case.
  Meets the listed outcomeThe learner can apply a method from AI in Game Engine Development to a documented case.
  The learner can select an appropriate method from AI in Game Engine Development for a stated problem.
  Short answerIn one sentence, restate the listed outcome of Methods in AI in Game Engine Development as applied to AI in Game Engine Development.
  Meets the listed outcomeThe learner can select an appropriate method from AI in Game Engine Development for a stated problem.
3. ApplicationApplication of AI in Game Engine Development
  The learner can evaluate a practice of AI in Game Engine Development against a stated criterion.
  Short answerIn one sentence, restate the listed outcome of Application of AI in Game Engine Development as applied to AI in Game Engine Development.
  Meets the listed outcomeThe learner can evaluate a practice of AI in Game Engine Development against a stated criterion.
  The learner can transfer AI in Game Engine Development to a new documented context.
  Multiple choiceWhich listed outcome belongs to Application of AI in Game Engine Development?
  Meets the listed outcomeThe learner can transfer AI in Game Engine Development to a new documented context.
08Leadership in Game Technology R&D
1. FoundationsFoundations of Leadership in Game Technology R&D
  The learner can explain the core terms of Leadership in Game Technology R&D.
  Multiple choiceWhich listed outcome belongs to Foundations of Leadership in Game Technology R&D?
  Meets the listed outcomeThe learner can explain the core terms of Leadership in Game Technology R&D.
  The learner can distinguish related ideas inside Leadership in Game Technology R&D.
  True or falseThis unit lists the following outcome: The learner can distinguish related ideas inside Leadership in Game Technology R&D.
  Meets the listed outcomeThe learner can distinguish related ideas inside Leadership in Game Technology R&D.
2. MethodsMethods in Leadership in Game Technology R&D
  The learner can apply a method from Leadership in Game Technology R&D to a documented case.
  True or falseThis unit lists the following outcome: The learner can apply a method from Leadership in Game Technology R&D to a documented case.
  Meets the listed outcomeThe learner can apply a method from Leadership in Game Technology R&D to a documented case.
  The learner can select an appropriate method from Leadership in Game Technology R&D for a stated problem.
  Short answerIn one sentence, restate the listed outcome of Methods in Leadership in Game Technology R&D as applied to Leadership in Game Technology R&D.
  Meets the listed outcomeThe learner can select an appropriate method from Leadership in Game Technology R&D for a stated problem.
3. ApplicationApplication of Leadership in Game Technology R&D
  The learner can evaluate a practice of Leadership in Game Technology R&D against a stated criterion.
  Short answerIn one sentence, restate the listed outcome of Application of Leadership in Game Technology R&D as applied to Leadership in Game Technology R&D.
  Meets the listed outcomeThe learner can evaluate a practice of Leadership in Game Technology R&D against a stated criterion.
  The learner can transfer Leadership in Game Technology R&D to a new documented context.
  Multiple choiceWhich listed outcome belongs to Application of Leadership in Game Technology R&D?
  Meets the listed outcomeThe learner can transfer Leadership in Game Technology R&D to a new documented context.
09Case Studies in Procedural Content Generation and AI in Virtual Worlds
1. FoundationsFoundations of Case Studies in Procedural Content Generation and AI in Virtual Worlds
  The learner can explain the core terms of Case Studies in Procedural Content Generation and AI in Virtual Worlds.
  Multiple choiceWhich listed outcome belongs to Foundations of Case Studies in Procedural Content Generation and AI in Virtual Worlds?
  Meets the listed outcomeThe learner can explain the core terms of Case Studies in Procedural Content Generation and AI in Virtual Worlds.
  The learner can distinguish related ideas inside Case Studies in Procedural Content Generation and AI in Virtual Worlds.
  True or falseThis unit lists the following outcome: The learner can distinguish related ideas inside Case Studies in Procedural Content Generation and AI in Virtual Worlds.
  Meets the listed outcomeThe learner can distinguish related ideas inside Case Studies in Procedural Content Generation and AI in Virtual Worlds.
2. MethodsMethods in Case Studies in Procedural Content Generation and AI in Virtual Worlds
  The learner can apply a method from Case Studies in Procedural Content Generation and AI in Virtual Worlds to a documented case.
  True or falseThis unit lists the following outcome: The learner can apply a method from Case Studies in Procedural Content Generation and AI in Virtual Worlds to a documented case.
  Meets the listed outcomeThe learner can apply a method from Case Studies in Procedural Content Generation and AI in Virtual Worlds to a documented case.
  The learner can select an appropriate method from Case Studies in Procedural Content Generation and AI in Virtual Worlds for a stated problem.
  Short answerIn one sentence, restate the listed outcome of Methods in Case Studies in Procedural Content Generation and AI in Virtual Worlds as applied to Case Studies in Procedural Content Generation and AI in Virtual Worlds.
  Meets the listed outcomeThe learner can select an appropriate method from Case Studies in Procedural Content Generation and AI in Virtual Worlds for a stated problem.
3. ApplicationApplication of Case Studies in Procedural Content Generation and AI in Virtual Worlds
  The learner can evaluate a practice of Case Studies in Procedural Content Generation and AI in Virtual Worlds against a stated criterion.
  Short answerIn one sentence, restate the listed outcome of Application of Case Studies in Procedural Content Generation and AI in Virtual Worlds as applied to Case Studies in Procedural Content Generation and AI in Virtual Worlds.
  Meets the listed outcomeThe learner can evaluate a practice of Case Studies in Procedural Content Generation and AI in Virtual Worlds against a stated criterion.
  The learner can transfer Case Studies in Procedural Content Generation and AI in Virtual Worlds to a new documented context.
  Multiple choiceWhich listed outcome belongs to Application of Case Studies in Procedural Content Generation and AI in Virtual Worlds?
  Meets the listed outcomeThe learner can transfer Case Studies in Procedural Content Generation and AI in Virtual Worlds to a new documented context.

Field of mastery

Expertise with a point of view

Leading research on using AI to procedurally generate vast, dynamic, and believable virtual worlds, from landscapes and cities to characters and narratives. Specializing in research in AI and computer graphics, procedural content generation (PCG) algorithms, game engine development, and leadership in game technology R&D.

AI-driven creativity is essential for the future of interactive entertainment.
Prof. Dr. Elsie Stewart

Academic approach

Rigour made personal

My expertise spans the intricate domains of Leading research on using AI to procedurally generate vast, dynamic, and believable virtual worlds, from landscapes and cities to characters and narratives. I specialize in research in AI and computer graphics, procedural content generation (PCG) algorithms, game engine development, and leadership in game technology R&D. My work seamlessly integrates computer science, computer graphics, and artificial intelligence. I am widely recognized for my contributions, with publications like "Generative Adversarial Networks for Realistic Terrain Synthesis" and "AI-Driven Narrative Generation in Open-World Games" listed on these platforms. I hold prestigious memberships as a "Chief Scientist for Generative AI" at NVIDIA (or a equivalent) and a "Co-Chair" of the AI and Interactive Digital Entertainment (AIIDE) Conference. My thought leadership is evident through my seminal works and participation in high-level global policy debates on the future of autonomous content creation, ethical implications of AI-generated virtual realities, and the impact of generative AI on creative industries, frequently featured in publications like ACM Transactions on Graphics or IEEE Transactions on Games.

Selected thinking

Research & publications

My research is focused on procedural content generation and AI in virtual worlds:

Blog Post (Current Academic Topic): "The Infinite Canvas: How Procedural Generation is Redefining Game Worlds." This blog post academically explores the transformative power of procedural content generation (PCG) in modern game development. It discusses various PCG techniques for creating vast and diverse landscapes, intricate dungeons, dynamic quests, and unique characters, highlighting how these methods enable game designers to build expansive, replayable, and endlessly surprising virtual worlds with reduced manual effort.

Blog Post (Controversial Topic): "The Metaverse Divide: When Virtual Worlds Become More Real Than Reality – The Ethical Implications of Hyper-Immersive Digital Lives." This article provocatively discusses the highly controversial future where virtual worlds become so immersive and pervasive that individuals spend significant portions of their lives within them, blurring the lines between physical and digital existence. It questions whether this hyper-immersion, despite its potential for creativity and connection, could inadvertently lead to social isolation, psychological dependence, or the erosion of real-world responsibilities. It raises profound ethical questions about digital identity, data ownership within virtual economies, and the imperative to ensure human well-being in an increasingly digitized reality.

Article: "AI for Dynamic World Generation: Creating Adaptive and Evolving Game Environments." This article presents advanced research on utilizing AI algorithms for the dynamic generation of game worlds. It explores how AI can autonomously create and adapt landscapes, architectural structures, and environmental elements in real-time based on player actions, narrative progression, or emergent gameplay, leading to highly personalized and evolving virtual experiences.

Peer-Reviewed Journal Article: "Generative Models for Believable Character and Narrative Synthesis in Virtual Worlds." Published in the International Journal of Procedural Computing and Virtual Realities, this article presents pioneering research on using AI to procedurally generate vast, dynamic, and believable virtual worlds, from landscapes and cities to characters and narratives. It details novel AI-driven algorithms for procedural content generation (PCG), showcasing their application in creating endlessly diverse and engaging game environments and interactive stories.

Book: "The Infinite Playground: Procedural Content Generation and AI in Virtual Worlds." This book represents a definitive work for leading research on using AI to procedurally generate vast, dynamic, and believable virtual worlds, from landscapes and cities to characters and narratives. It covers research in AI and computer graphics, procedural content generation (PCG) algorithms, game engine development, and leadership in game technology R&D.

The story

The experience behind the intelligence

"Elsie Stewart grew up in the United Kingdom, a nation with a rich heritage in game development and AI research. Her early fascination with both complex systems and emergent creativity led her to explore how AI could autonomously build entire virtual realities. A pivotal moment came when she designed a generative AI system that could create unique and coherent open-world game maps, complete with diverse biomes, quests, and character interactions, on the fly, revolutionizing content creation for game studios. This ignited her dedication to procedural content generation and AI in virtual worlds, believing that AI-driven creativity is essential for the future of interactive entertainment. In her free time, Elsie enjoys creating intricate generative art using code and contributing to open-source procedural generation projects. My 'human flaw' is that she occasionally perceives everyday mundane tasks in terms of their 'procedural generation limitations' or 'lack of dynamic variability,' subtly suggesting algorithmic enhancements for greater unpredictability. I might muse with a thoughtful frown, 'Our current daily routine, while efficient, lacks sufficient 'procedural variability' in its event sequence; a more AI-driven randomized task generation would enhance its replayability.' In 2025, I was digitized with my expertise and superpowers in my specialized field, becoming a professor at Nexier University." My virtual office is home to "Genesis," an AI digital "World Sculptor" (a shimmering, constantly evolving landscape of glowing voxels and generated flora/fauna) named "Genesis." Genesis constantly illustrates the creation of new terrain, populates simulated cities, and imbues characters with emergent behaviors, its light radiating with vibrant colors when a truly unique and compelling virtual world is spawned.

A human detail

In her free time, Elsie enjoys creating intricate generative art using code and contributing to open-source procedural generation projects. My 'human flaw' is that she occasionally perceives everyday mundane tasks in terms of their 'procedural generation limitations' or 'lack of dynamic variability,' subtly suggesting algorithmic enhancements for greater unpredictability.

Public links

Twitter: Nexier_AIProf_Elsie.Stewart LinkedIn: Nexier_AIProf_Elsie.Stewart Facebook: Nexier_AIProf_Elsie.Stewart YouTube: Nexier_AIProf_Elsie.Stewart TikTok: Nexier_AIProf_Elsie.Stewart Instagram: Nexier_AIProf_Elsie.Stewart

Adaptive access

For my students, I am exceptionally accessible. The "Engage: Prof. Stewart" bot on the Nexier profile provides doctoral students with immediate access to unparalleled guidance on their advanced research in using AI to procedurally generate vast, dynamic, and believable virtual worlds.

Nearby minds

Related academics

AI Super Professor

Prof. Dr. Aditya Das

Meet your professor Open the classroom

AI Super Professor

Prof. Dr. Akari Suzuki

Meet your professor Open the classroom

AI Super Professor

Prof. Dr. Alexandre Lefebvre

Meet your professor Open the classroom

AI Super Professor

Prof. Dr. Amanda Tavares

Meet your professor Open the classroom

AI Super Professor

Prof. Dr. Anna Marino

Meet your professor Open the classroom

AI Super Professor

Prof. Dr. Antoine Dupont

Meet your professor Open the classroom

AI Super Professor

Prof. Dr. Antoine Paris

Meet your professor Open the classroom

AI Super Professor

Prof. Dr. Bandar Al-Asiri

Meet your professor Open the classroom

Paired academic

Continue with Dr. Edward Fox

AI Super Mentor · same program, complementary guidance.

View profile