[Tweets]

18/10/2021 10:24pm
RT @petitegeek: “If we could understand what information the predictive models were using, we could ask for feedback that improved our whol…
16/10/2021 6:43am
This week ends with a finished design for a prototype electric car website. What do you think? Would you buy the ca… [LINK]
05/10/2021 4:14am
RT @vitotrianni: Two PhD positions in collaboration between @cnr_istc and @SapienzaRoma will open soon. The research focuses on #robotics a…
04/10/2021 9:14am
A new office pet has arrived :) [LINK]
01/10/2021 10:46pm
Just published: A new case study about a website that I made for my research project about robot swarms.… [LINK]

[Ultrastable Neuroendocrine Robot Controller]

Neural networks Java AI Simulation models Date: Aug 2011

DOWNLOAD PAPER DOWNLOAD CODE RUN JAVA APPLET
Technologies used: Java, JFreeChart, Model-View-Controller, Git

Publication:
Pitonakova, L. (2013). Ultrastable neuroendocrine robot controller. Adaptive Behaviour, 21(1), 47-63.

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 resource gathering and recharging tasks.

The network schema

The implemented ultrastability mechanism was applied on two different time scales, to regulate fast-operating neurons and slowly-operating glands. The main limitation of the algorithm was that the adaptation was unstable when a task required an unexpectedly varied satisfaction time.


{Please enable JavaScript in order to post comments}

Ultrastable Neuroendocrine Robot is born

I have finally put a beginning of an artificial brain to my Ultrastable Neuroendocrine Robot - UNER... my lego robot can now measure inputs from its 3 front proximity sensors and individual cells in its brain get activated when it sees something

Adaptive Robot Controller

A robot neural controller where obstacle-avoidance and random-walk neurons observe level of their irritation and randomly reconfigure their connections to motors when the irritation reaches a specified threshold is presented and tested.

pyCreeper

The main purpose of pyCreeper is to wrap tens of lines of python code, required to produce graphs that look good for a publication, into functions. It takes away your need to understand various quirks of matplotlib and gives you back ready-to-use and well-documented code.

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

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

Fast Data Analysis Using C++ and Python

C++ code that processes data and makes it available to Python, significantly improving the execution speed.

Designing Robot Swarms

This project looks at the challenges involved in modeling, understanding and designing of multi-robot systems.