Tools

Personal Experiments & Tools

I build these tools to test new AI capabilities and rapid prototyping workflows (often using Claude or Gemini). It keeps me hands-on with the tech stack I manage professionally, allowing me to experiment with UI/UX and agentic flows outside of a production environment.

Note: For my professional work on simulation systems, see Publications and Medium article.

Research Chat (RAG)

AI Chat with My Publications

What it does: Chat interface powered by Retrieval-Augmented Generation (RAG) that answers questions about my PhD thesis and publications. Uses embeddings to find relevant content and provides cited answers grounded in my actual research. Try asking about cooperative robotics, POMCP, or urban search and tracking.
Tech: Next.js 14, Supabase (PostgreSQL + pgvector), Google Gemini 2.5 Flash, Python ingestion pipeline with pypdf and bibtexparser.
💬 Try the Chat | 📖 How it Works (RAG Architecture)

Career Knowledge Graph

Interactive Skill Timeline

What it does: Force-directed graph visualization showing my career evolution from 1999 to 2025. Explore 100+ skills, technologies, and research areas with an interactive timeline, search, and zoom controls. Watch skills appear year by year and discover how concepts connect across robotics, logistics optimization, and LLM agents.
Tech: React, SVG, Custom Physics Simulation, Force-Directed Graph Layout.
📖 About the Graph - Learn about the 10 skill categories and how to navigate the visualization.

ALV Homing Simulation

Bio-Inspired Robot Navigation

What it does: Interactive visualization of the Average Landmark Vector (ALV) homing method inspired by desert ant navigation. Click to add landmarks, set home and robot positions, and watch the robot autonomously navigate home using only the average direction to visible landmarks. Test robustness with different scenarios and compare unit vector vs. distance-weighted approaches.
Tech: Vanilla JavaScript, Canvas API, Real-time vector mathematics, MathJax for equations.
Research: Based on my Master's research (2007) on biologically-inspired navigation methods.
📖 About the Method - Learn about the theory, biological inspiration, and applications of ALV homing.

Route Optimizer

TSP Algorithm Playground

What it does: Interactive visualization of Traveling Salesman Problem (TSP) algorithms. Click to add cities, select an algorithm (Nearest Neighbor, 2-Opt, Simulated Annealing, Genetic Algorithm, etc.), and watch it optimize routes in real-time. Compare all algorithms to see which performs best for your scenario.
Tech: React, Canvas API, Async JavaScript with time-slicing for responsive UI.
📖 Algorithm Documentation - Deep dive into how each algorithm works with pseudocode and complexity analysis.

CVRP Visualizer

Vehicle Routing on Real Maps

What it does: Interactive visualization of the Capacitated Vehicle Routing Problem (CVRP) on a map of Barcelona. Compare three algorithms (Nearest Neighbor, Polar Sweep, Clarke-Wright Savings) as they optimize delivery routes for a fleet of trucks with capacity constraints. Watch routes form in real-time and see performance metrics.
Tech: React, Leaflet.js for maps, Real-time algorithm visualization.
Context: Core problem in logistics optimization, directly related to my work at Glovo on delivery platform simulation.
📖 About CVRP - Learn about the algorithms and the vehicle routing problem.

GNG-SLAM Simulator

Neural Network-Based Mapping

What it does: Watch a robot build a map of its environment using Growing Neural Gas (GNG), a self-organizing neural network. The simulation shows how the network dynamically adapts its structure to represent obstacles, automatically allocating more nodes to complex regions and learning topology through lidar data.
Tech: Vanilla JavaScript, Canvas API, Real-time neural network visualization.
Research: Based on my Bachelor's thesis (2006) on SLAM using self-organizing neural networks.
📖 About GNG-SLAM - Deep dive into the algorithm, parameters, and how it compares to traditional SLAM.

Financial Simulator

Interactive Portfolio Modeling

What it does: Runs Monte Carlo simulations to visualize the probability distributions of future portfolio values. It allows users to stress-test contribution strategies and asset allocations against various risk scenarios over time.
Tech: React, Chart.js, Probabilistic Modeling.

DS Cheat Sheet

Personal Reference Library

What it does: My personal cheat sheet for Data Science workflows covering optimization algorithms, LLM agent patterns, Python snippets, Vim commands, and more. Features AI-assisted card generation via Google's Gemini API to quickly transform code snippets into searchable reference cards. Useful for any DS building their own knowledge base.
Tech: React, Google Gemini API, JSON data storage.
📄 Raw data (JSON) - Download or fork the complete card collection.

VitalDecision

AI-Assisted Health Triage

What it does: A symptom tracking tool designed to improve doctor-patient communication. It uses AI to structure health data over time and provides preliminary guidance on symptom severity and care urgency.
Tech: AI-assisted decision support.

Contact: alex (at) goldhoorn.net