Environment-driven evolutionary adaptation with 20 autonomous robots

This video shows a fully autonomous artificial evolution within a population of ~20 completely autonomous real (e-puck) robots. Each robot is driven by its "genome" and genomes are spread whenever robots are close enough (range: 25cm). The most "efficient" genomes end up being those that successfully drive robots to meet with each other while avoiding getting stuck in a corner.

There is no human-defined pressure on robot behavior. There is no human-defined objective to perform.

The environment alone puts pressure upon which genomes will survive (ie. the better the spread, the higher the survival rate). Then again, the ability for a genome to encode an efficient behavioral strategy first results from pure chance, then from environmental pressure.

In this video, you can observe how going towards the sun naturally emerges as a good strategy to meet/mate with other (it is used as a convenient "compass") and how changing the sun location affect robots behavior.

=-=-=

AUTHORS:

- Nicolas Bredeche and Jean-Marc Montanier (Univ. Paris-Sud, CNRS, INRIA)
- Alan Winfield and Wenguo Liu (BRL, Univ. West England)

The research shown here was performed within the EU-funded Symbrion project (Symbiotic Evolutionary Robot Organisms. funded by: FET Proactive Intiative: PERVASIVE ADAPTATION)

=-=-=

TECHNICAL NOTES:

- there are ~20 robots, and one inactive robot that is referred to as "the sun"
- each robot have 8 IR sensors, and knows its direction (angle) and distance to the "sun"
- the controller is a simple multi-layered perceptrons (starting with random weights)
- being close to or away from the sun a priori provides NO advantages
- the algorithm running is loosely inspired from Dawkins' selfish gene metaphor: the more a genome spread, the higher the survival rate.
- whenever robots are closer than ~15cm, genome are exchanged (automaticaly). Incoming genomes are stored for future use.
- one genome controls a robot during a full generation
- a generation lasts for one minute - at the end of a generation, one random genome is picked among the list of received genomes, and mutated.
- in the video, the last footage example ("full run") is in fact the continuation of the very first footage (emergence of consensus #1) - ie. the beginning of the video in not shown as it was shown before.

=-=-=

More details in:

Bredeche, Montanier, Liu, Winfield. Environment-driven Distributed Evolutionary Adaptation in a Population of Autonomous Robotic Agents (journal: MCMDS, 2011)

Bredeche, Montanier. Environment-driven Embodied Evolution in a Population of Autonomous Agents. 11th International Conference on Parallel Problem Solving From Nature (Conference Proceedings: PPSN 2010).

=-=-=

Category:

Science & Technology

Tags:

• artificial
• evolution
• symbrion
• robots
• life
• swarm

[CamBoxer51]

cool