[Tweets]

19/09/2020 10:14pm
Proud to announce after a LOT of work, drawing and sound making, demo for my #iOS #arcade style #indiegame Zirthian… [LINK]
15/09/2020 4:18pm
Weapon 4 in my game #Zirthian: Seeker Missile: Destroys the first target in sight - great against strong enemies… [LINK]
12/09/2020 8:42pm
RT @DoctorJosh: Our metamorphosing #robot was featured on Video Friday: thank you @IEEESpectrum! Joint work with Dylan Shah, Josh Powers,…
11/09/2020 5:06am
Weapon 3 in my game #Zirthian: Gamma Ray: Stream of pure power that obliterates everything in your path - great aga… [LINK]

[My First Journal Publication]

Multi-agent systems Robots Neural networks Added on 06/09/2012

After working on it for quite a long time, my paper titled Ultrastable Neuroendocrine Robot Controller was finally accepted for publication in Adaptive Behaviour. It is now available on OnlineFirst.

I put together one of my Masters courseworks and my Masters dissertation and have done some extra work over the last year or so. The paper describes a neural network controller modulated by hormones where behaviour of both neurons and hormone-producing glands is ultrastable, meaning that the parts self-reconfigure in order to achieve low activation. I show that this type of mechanism allows for both behaviour self-organisation and adaptation to perturbations during tasks like obstacle avoidance, action selection and targeted navigation.

Based on the journal terms and conditions, I will be able to put the paper on my web site next year. For now, I will post updates on Twitter regarding when it should be published.



{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

To Vote or Not To Vote: A Swarm Approach

 I’ve never voted. I am not sure why, I perhaps don't care enough. People always tell me: 'Imagine everybody would decide not to vote! You have to vote because every small opinion counts towards the final results'. I've never agreed with it, although I couldn't express why...

Ultrastable Neuroendocrine Robot Controller

 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.

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.