17/10/2018 12:47pm
RT @GTheraulaz: Introducing the new Cuboids: a concentrate of high-techology to study flocking behavior. I will present this swarm robotic…
12/10/2018 7:28pm
RT @andy_adamatzky: Fantastic position is open to work in groundbreaking H2020 Project @evo_nano The successful candidate will work in an…
12/10/2018 7:19pm
RT @AutomatonBlog: Boston Dynamics' Atlas Robot Shows Off Parkour Skills [LINK]

[Robustness of Foraging E-puck Swarms]

Robots Multi-agent systems Project: Designing Robot Swarms
Date: Aug 2018

Publication: Pitonakova, L., Winfield, A. F. T. & Crowder, R. (in press). Recruitment near worksites facilitates the robustness of foraging e-puck swarms to global positioning noise. Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018), IEEE.

We compare the ability of two different robot controllers for collective foraging to cope with noise in robot global positioning data and show how recruitment, in the form of broadcast messages near worksites, can make swarms more robust. Swarms of five e-puck robots are used in a semi-virtual environment, facilitated by the VICON positioning system. This setup allows us to control the amount of noise in the robot positioning data, as well as to generate pseudo-random environments. The effect of inherent noise in the robot infra-red sensors, used for obstacle avoidance, is also noted and the importance of modeling such noise in agent-based simulations is highlighted.

Experimental setup with e-puck robots and the VICON system The experimental setup consisting of the e-puck arena, a Server and a VICON system. Worksites are drawn on the arena floor for visualisation purposes only. The robots communicated with the Server in order to obtain positional, worksite and recruitment data. The Server maintained a virtual representation of the world, keeping track of base, worksite and robot locations and the amount of resource units in each worksite.

Results summary

Basic foraging loop

Congestion formation

{Please enable JavaScript in order to post comments}


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.