Artificial Life Simulation

Ever wondered by nearly impromptu making decisions you end up being so awesome? How the sight of a question paper can invalidate all pre-decided cheating chains and dynamically make new ones without easy communication? What gives the capability to see a new dangerous assignment and stand tall united within no time? And what gives the capability to the institution to foresee any such attempts and tactically drop surprises which are hard to combat? In this beautiful journey we see how innocent, small and week looking lives otherwise end up giving a display of the most majestic nature, whether in your favor or against you is a matter of discretion. Taking an inspiration, we see the mechanisms to simulate and engineer the artificial systems of the future that will do something amazing, while still be so simple to look, to develop and (to some extent) to cost.

The course takes a deeper looks into all micro and macro beings around, all cool looking natural mechanisms and everything that you'd been doing so far, to assess the fundamental working mechanisms behind these and thereafter to see if the same can be injected into artificial systems and robots for some amazing capabilities. The course talks about the intelligent paradigms of search and evolutionary behaviors of animals (and animal-like humans), exhibition of characteristics behaviors that you love or hate, and creation of a simulation setup to get a full view of the amazing world of chaos all around, and the mechanisms to make robots exhibit the same characteristics.


Part I: Introduction
Introduction to the course
Introduction to Artificial Life and Artificial Intelligence

Part II Agent Behaviors
Reinforcement Learning
Centre of area Method, Potential Field, Velocity Obstacles
Finite State Machine based Modelling
Cellular Automata

Part III Simulation Systems, Software
Basics of Robot Simulation Software
Robot Operating System
Traffic Simulation
Crowd Simulation

Part IV Collective Behaviors
Swarm Robotics
Game Theory, Adversarial Search
Mechanism Design
Pursuit Evasion

Part V Evolution
Particle Swarm Optimization
Differential Evolution
Diversity Preservation
Multi-Objective Optimization
Memetic Computing
Cooperative Co-evolution
Competitive Co-evolution
Parallel Genetic Algorithms
Artificial Immune System
Adaptive Systems and Self-Adaptation
Evolutionary Strategies

Part VI Evolutionary Robotics
Recurrent Neural Networks
Grammatical Evolution
Evolutionary Robotics
Embodied Robotics

Lab Syllabus

Simple graphics and animation
Simple Stochastic Simulations
Simple Behaviors
ROS Basic
ROS Turtlebot lab

Term Papers based on the topics covered in class and use of any simulation software


There is no major prerequisite. A basic understanding of Artificial Intelligence or Computational Intelligence can be very useful, although the relevant topics are discussed in the course. Even though some basics of evolution and Genetic Algorithm is covered prior to the start of the specific topics, knowledge of Genetic Algorithm is preferred, which can also be done independently by the candidate after taking the course. The lab component also assumes the student to be sufficiently proficient in Programming and the Linux Operating System.

Text/Reference Material

Myself on:

And also on:


Dr. Rahul Kala
Assistant Professor,
IIIT Allahabad,

Phone: +91 532 299 2117
Mobile: +91 7054 292 063