[Tweets]

10/12/2018 7:08pm
RT @karpathy: Incredible NeurIPS talk from @drmichaellevin on "Bioelectric Computation Outside the Nervous System" [LINK]
06/12/2018 6:39pm
We are looking for 2x part-time Java developers to work on an awesome editor for a multi-agent systems modelling la… [LINK]
06/12/2018 5:12pm
Excited to announce that we have been awarded the @EPSRC Impact Accelerator Kickstarter Award in collaboration with… [LINK]
03/12/2018 8:39pm
RT @BristolRobotLab: Cafe opens in Tokyo staffed by robots controlled by paralyzed people [LINK] via @RocketNews24En

[Task Allocation in Foraging Robot Swarms]

Multi-agent systems C++ Project: Designing Robot Swarms
Date: Apr 2016

DOWNLOAD PAPERDOWNLOAD TALK SLIDESDOWNLOAD CODE
Publication:
Pitonakova, L., Crowder R. & Bullock, S. (2016). Task allocation in foraging robot swarms: The role of information sharing. In Gershenson, C. et al. (eds.), Proceedings of the Fifteenth International Conference on the Synthesis and Simulation of Living Systems (ALIFE XV), MIT Press, 306-313.

Autonomous task allocation is a desirable feature of robot swarms that collect and deliver items. When there are many robots in the swarm, or when collected items accumulate quickly in a drop-off location, congestion can prevent the swarm from working effectively. In such scenarios, self-regulation of workforce can prevent unnecessary energy consumption.

In this paper, we analyse bee-inspired self-regulation algorithms for robot swarms that deliver items into a single drop-off location.

We explore two types of self-regulation:
  • Non-social, where robots go to rest when they experience congestion
  • Social, where robots broadcast information about congestion to their team mates to tell them that they should rest

Robots foragingPerformance of the swarms in various environments

Outcome:
We show that both types of self-regulation can lead to improved energy efficiency and increase the amount of resource collected. More importantly, the rate at which information about congestion spreads through a swarm affects the scalability of the explored robot control strategies.

A slow information flow, characteristic for non-social self-regulation, leads to behaviour suitable for a larger number of experimental scenarios. On the other hand, fast information flow, achieved by social self-regulation, causes more extreme difference in performance across scenarios. Using swarms with faster information flow thus requires us to be more certain about the environmental conditions we employ our swarms in.



{Please enable JavaScript in order to post comments}

How Coding in Python Might Be Bad For You

7 reasons why coding in Python is like writing a really bad essay and getting away with it

Are Robot Swarms Like Brains?

I have recently explored a way of measuring how information flows within a robot swarm. I think that there is something intriguing behind this idea - a swarm's resemblance to the human brain.

Information Flow Principles for Plasticity in Robot Swarms

An important characteristic of a robot swarm that must operate in the real world is the ability to cope with changeable environments by exhibiting behavioural plasticity at the collective level. In this paper, we report on simulation experiments with homogeneous foraging robot teams and show that analysing swarm behaviour in terms of information flow can help us to identify whether a particular behavioural strategy is likely to exhibit useful swarm plasticity in response to dynamic environments.

Top 5 Things I Wish I Knew When I Started a PhD

In a short moment self-reflection, I made a list of the five most important things that doing research with a lot of data has taught me. And I learned the hard way - wasting a lot of time and energy re-doing things instead of being smart about it at the beginning. Note to self: I should read this once a year or so.

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.