[Search by tag: Simulation models]

Novelty detection with robots using the Grow-When-Required Neural Network

Simulation models C++ Bash script Date: 12/09/2018 :: 0 comments

The Grow-When-Required Neural Network implementation in simulated robot experiments using the ARGoS robot simulator.

A Highly Customisable Multi-Robot Foraging Simulation

Simulation models C++ Bash script Date: 20/02/2017 :: 0 comments

An ARGoS simulation of robot swarm foraging using various robot controllers and environments. This code has been used in various papers (see References) and thus allows to run different types of simulations.

Controlling Ant-Based Construction

Multi-agent systems Java Simulation models Date: 02/04/2013 :: 0 comments

Stigmergy allows insect colonies to collectively build structures that no single individual is fully aware of. Since relatively minimal sensory and reasoning capabilities are required of the agents, such building activity could be utilised by robotic swarms if we could learn how to control the shape of the final structures.

Boid Game-Playing through Randomised Movement

Multi-agent systems Java AI Simulation models Date: 22/10/2012 :: 0 comments

The original boid flocking algorithm is extended by adding randomised movement to the flock members. This approach is a light-weight alternative to other ‘follow the leader’ techniques implemented in order to create a ‘game-playing’ behaviour during which a flock changes its movement direction as observed in real birds.

Ultrastable Neuroendocrine Robot Controller

Neural networks Java AI Simulation models Date: 15/08/2011 :: 0 comments

Attributes of ultrastability as an adaption mechanism in a hormone-modulated neural robot controller were investigated in a simulation. Action-selection based on hormone-driven utilities of memory items was used to alternate between mineral gathering and recharging.

Neural Networks and the Evolution of Cooperation

Neural networks Java AI Simulation models Date: 16/01/2011 :: 0 comments

The paper investigates artificial evolution of cooperation in the Iterated Prisoner's Dilemma using a number of player implementations. Existing strategy encoding and neural network models are compared with action-discriminating neural network created during writing of this paper.