What is Swarm Intelligence? - Swarm AI Explained
summary
C++ implementations use SFML to draw agents and a simple game loop, demonstrating particle swarm, ant colony and bee heuristics and a paper‑bag cat swarm demo that actually gets agents out of the bag. Code uses a velocity vector per agent, a global best plus personal best, RNG-backed updates, discrete_distribution for weighted choice and a seeking memory pool (5) for seeking mode. Demos show cats escape and also solve a 2D Rosenbrock surface, but single‑mode setups get stuck so both seeking and tracing modes plus parameter tuning are needed.
AI-written summary · about
chapters (12)
- 0:00Introduction to swarm AI
- 3:42Particle swarm optimization
- 16:33Ant colony optimization
- 17:45Bee colony algorithms
- 19:58Cat swarm optimization intro
- 22:33Implementing seeking mode
- 37:35Implementing tracing mode
- 40:37Collaborative swarm update
- 43:34Handling local minima
- 46:35Benchmarking optimization
- 50:55Final thoughts and resources
- 55:05Closing and book resources
related talks
01h 15mAn Introduction to Swarm Intelligence Algorithms
52mAn Introduction to Swarm Intelligence Algorithms
54mAmazing Algorithms for Solving Problems in Software
23mA Swarm of Processes — Simulating Ant Foraging Behavior...
44mSwarmfare - When the shit hits a thousand fans
25mDirecting a Swarm of Agents for Fun and Profit
10mWhat Alien Invaders, Birds, and Computer Simulations have in Common: Flocking!!
49mMonitoring global events with AI-driven satellite swarms