Evolutionary conditions for the emergence of communication in robots Dario Floreano, Sara Mitri, Stephane Magnenat, and Laurent Keller Current Biology,

Slides:



Advertisements
Similar presentations
Learning School of Computing, University of Leeds, UK AI23 – 2004/05 – demo 2.
Advertisements

Higher Coordination with Less Control – A Result of Information Maximization in the Sensorimotor Loop Keyan Zahedi, Nihat Ay, Ralf Der (Published on: May.
NVIS: An Interactive Visualization Tool for Neural Networks Matt Streeter Prof. Matthew O. Ward by Prof. Sergio A. Alvarez advised by and.
1 November 2005 Stefano Nolfi* Dario Floreano~ *Institute of Psychology, National Research Council Viale Marx 15, Roma, Italy ~LAMI - Laboratory of Microcomputing.
The Dominance Tournament Method of Monitoring Progress in Coevolution Speaker: Lin, Wei-Kai (2009/04/30) 1.
1 Lecture 8: Genetic Algorithms Contents : Miming nature The steps of the algorithm –Coosing parents –Reproduction –Mutation Deeper in GA –Stochastic Universal.
1 Autonomous Controller Design for Unmanned Aerial Vehicles using Multi-objective Genetic Programming Choong K. Oh and Gregory J. Barlow U.S. Naval Research.
Tracking a moving object with real-time obstacle avoidance Chung-Hao Chen, Chang Cheng, David Page, Andreas Koschan and Mongi Abidi Imaging, Robotics and.
Evolutionary Computation Introduction Peter Andras s.
Introduction to Genetic Algorithms Yonatan Shichel.
1 Incremental Evolution of Autonomous Controllers for Unmanned Aerial Vehicles using Multi-objective Genetic Programming Gregory J. Barlow, Choong K. Oh,
Network Motifs Zach Saul CS 289 Network Motifs: Simple Building Blocks of Complex Networks R. Milo et al.
Design of Autonomous Navigation Controllers for Unmanned Aerial Vehicles using Multi-objective Genetic Programming Gregory J. Barlow March 19, 2004.
1 Autonomous Controller Design for Unmanned Aerial Vehicles using Multi-objective Genetic Programming Gregory J. Barlow North Carolina State University.
Chapter 16 Evolution Of Populations.
October 7, 2010Neural Networks Lecture 10: Setting Backpropagation Parameters 1 Creating Data Representations On the other hand, sets of orthogonal vectors.
1 Robustness Analysis of Genetic Programming Controllers for Unmanned Aerial Vehicles Gregory J. Barlow 1,2 and Choong K. Oh 2 1 The Robotics Institute,
Evolutionary Robotics Evolutionary Robotics for Swarms.
Coordinative Behavior in Evolutionary Multi-agent System by Genetic Algorithm Chuan-Kang Ting – Page: 1 International Graduate School of Dynamic Intelligent.
Marcus Gallagher and Mark Ledwich School of Information Technology and Electrical Engineering University of Queensland, Australia Sumaira Saeed Evolving.
컴퓨터 그래픽스 분야의 캐릭터 자동생성을 위하여 인공생명의 여러 가지 방법론이 어떻게 적용될 수 있는지 이해
Introduction Due to the recent advances in smart grid as well as the increasing dissemination of smart meters, the electricity usage of every moment in.
Genetic Algorithms and Ant Colony Optimisation
Evolving a Sigma-Pi Network as a Network Simulator by Justin Basilico.
Introduction to Genetic Algorithms and Evolutionary Computation
The Evolution of Populations.  Emphasizes the extensive genetic variation within populations and recognizes the importance of quantitative characteristics.
Genetic algorithms Prof Kang Li
Study on Genetic Network Programming (GNP) with Learning and Evolution Hirasawa laboratory, Artificial Intelligence section Information architecture field.
More on coevolution and learning Jing Xiao April, 2008.
CP Biology Ms. Morrison. Genes and Variation  Gene pool = combined genetic information of all members of a particular population  Relative frequency.
Clustering of protein networks: Graph theory and terminology Scale-free architecture Modularity Robustness Reading: Barabasi and Oltvai 2004, Milo et al.
Boltzmann Machine (BM) (§6.4) Hopfield model + hidden nodes + simulated annealing BM Architecture –a set of visible nodes: nodes can be accessed from outside.
Chih-Ming Chen, Student Member, IEEE, Ying-ping Chen, Member, IEEE, Tzu-Ching Shen, and John K. Zao, Senior Member, IEEE Evolutionary Computation (CEC),
FRE 2672 TFG Self-Organization - 01/07/2004 Engineering Self-Organization in MAS Complex adaptive systems using situated MAS Salima Hassas LIRIS-CNRS Lyon.
Evolutionary Computation Dean F. Hougen w/ contributions from Pedro Diaz-Gomez & Brent Eskridge Robotics, Evolution, Adaptation, and Learning Laboratory.
A New Evolutionary Approach for the Optimal Communication Spanning Tree Problem Sang-Moon Soak Speaker: 洪嘉涓、陳麗徽、李振宇、黃怡靜.
Evolving Virtual Creatures by Karl Sims (1995) Adelein Rodriguez.
Escape Behavior of Flesh-Fly (Sarcophagidae): Verifying the mechanism of escape initiation Dae-eun Kim School of Biological Sciences.
Technical Seminar Presentation Presented By:- Prasanna Kumar Misra(EI ) Under the guidance of Ms. Suchilipi Nepak Presented By Prasanna.
1. Genetic Algorithms: An Overview  Objectives - Studying basic principle of GA - Understanding applications in prisoner’s dilemma & sorting network.
Biologically inspired algorithms BY: Andy Garrett YE Ziyu.
2/29/20121 Optimizing LCLS2 taper profile with genetic algorithms: preliminary results X. Huang, J. Wu, T. Raubenhaimer, Y. Jiao, S. Spampinati, A. Mandlekar,
1 Danny Hillis and Co-evolution Between Hosts and Parasites I 590 4/11/2005 Pu-Wen(Bruce) Chang.
CITS7212: Computational Intelligence An Overview of Core CI Technologies Lyndon While.
CAP6938 Neuroevolution and Developmental Encoding Evolving Adaptive Neural Networks Dr. Kenneth Stanley October 23, 2006.
제 6 주. 응용 -2: Graphics Evolving L-systems to Generate Virtual Creatures G.S. Hornby and J.B. Pollack, Computers & Graphics, vol. 25, pp. 1041~1048, 2001.
Implicit Active Shape Models for 3D Segmentation in MR Imaging M. Rousson 1, N. Paragio s 2, R. Deriche 1 1 Odyssée Lab., INRIA Sophia Antipolis, France.
제 9 주. 응용 -4: Robotics Synthesis of Autonomous Robots through Evolution S. Nolfi and D. Floreano, Trends in Cognitive Science, vol. 6, no. 1, pp. 31~37,
Lesson # 7: Evolution (Processes + Patterns of Evolution)
Robot Intelligence Technology Lab. 10. Complex Hardware Morphologies: Walking Machines Presented by In-Won Park
CAP6938 Neuroevolution and Artificial Embryogeny Real-time NEAT Dr. Kenneth Stanley February 22, 2006.
Robot Intelligence Technology Lab. Evolutionary Robotics Chapter 3. How to Evolve Robots Chi-Ho Lee.
An application of the genetic programming technique to strategy development Presented By PREMKUMAR.B M.Tech(CSE) PONDICHERRY UNIVERSITY.
An Evolutionary Algorithm for Neural Network Learning using Direct Encoding Paul Batchis Department of Computer Science Rutgers University.
Evolving robot brains using vision Lisa Meeden Computer Science Department Swarthmore College.
Robot Intelligence Technology Lab. 8. Competitive co-evolution From ‘Evolutionary Robotics’ Presented by Jeongki, Yoo `
March 1, 2016Introduction to Artificial Intelligence Lecture 11: Machine Evolution 1 Let’s look at… Machine Evolution.
Presented By: Farid, Alidoust Vahid, Akbari 18 th May IAUT University – Faculty.
Evolution, Self-organization and Swarm Robotics Minsu Kim.
Robot Intelligence Technology Lab. Evolution of simple navigation Chapter 4 of Evolutionary Robotics Jan. 12, 2007 YongDuk Kim.
Evolutionary Algorithms Jim Whitehead
Creative Evolution of Flying Objects
Dr. Kenneth Stanley September 25, 2006
Ch 14. Active Vision for Goal-Oriented Humanoid Robot Walking (1/2) Creating Brain-Like Intelligence, Sendhoff et al. (eds), Robots Learning from.
Self-Adjusting Jacket ECE 445 SP2017
Power and limits of reactive intelligence
Example: Applying EC to the TSP Problem
Dr. Kenneth Stanley February 6, 2006
Evolutionary Conditions for the Emergence of Communication in Robots
CHAPTER I. of EVOLUTIONARY ROBOTICS Stefano Nolfi and Dario Floreano
Presentation transcript:

Evolutionary conditions for the emergence of communication in robots Dario Floreano, Sara Mitri, Stephane Magnenat, and Laurent Keller Current Biology, vol. 17, no. 6, pp , Jongwon Yoon

Contents Introduction Evolution of multiagent systems in robotics Overview Experimental setup –Robots –Foraging arena –Neural controller –Evolution process Data analysis Experimental results Conclusion 1/13

Introduction Information transfer & communication systems –Plays a central role in the biology of most organisms, particularly social species –Extremely sophisticated in large and complex societies –Key component ensuring the ecological success of highly social species Evolution of communication –Efficient communication requires tight coevolution between the signal emitted and the response elicited –Conditions and paths remain largely unknown Contributions of this study –Predict about the evolutionary conditions conductive to the emergence of communication –Provide guidelines for designing artificial evolutionary systems 2/13

Evolution of multiagent systems in robotics AuthorTargetYear Team compositionLevel of selection Hetero -geneous Homo -geneous IndividualTeam S. Raik and B. DurnotaBehavior1994OO S. Luke and L. SpectorBehavior1996OO S. G. Ficicici et al.Behavior1999OO A. S. Wu et al.Behavior1999OO A. MartinoliBehavior1999OO M. QuinnBehavior2001OOO E. Simoes and D. BaroneBehavior2002OO L. SteelsCommunication2003OO L. Spector et al.Behavior2005OO M. Mirolli and D. ParisiCommunication2005OO V. Trianni et al.Communication2006OO 3/13

Overview Purpose –Studying the evolution of communication Consideration of the kin structure of groups (Relatedness) The scale at which cooperation and competition occur (Level of selection) Experiments overview –Colonies of robots forage in an environment Containing a food and a poison –Use 100 colonies of 10 robots –Selection experiments over 500 generations By using physics-based simulations 4/13

Robots Experimental setup Equipments –Two tracks : Independently rotate in both directions –Translucent ring : Emit blue light –360 degree vision camera –Infrared ground sensors Sensory-motor cycle –Length : 50ms Use a neural controller to process visual information and ground-sensor input Set direction and speed of the two tracks Control the emission of blue light Performance unit –Gain one unit : if it detected food –Lost one unit : if it detected poison 1 Trial = 1200 sensory-motor cycles * 50ms = 1min 5/13

Foraging arena Experimental setup Size : 300cm x 300cm (Robots are placed randomly) A food and a poison source –Radius : 10cm –Placed at 100cm from one of two opposite corners –Constantly emit red light –Circular gray and black papers Placed under the food and the poison Robots detect by infrared ground sensors 6/13

Neural controller Experimental setup Evolutionary Neural network –Feed-forward neural network –Ten inputs & three outputs Genetic encoding –Encoded the synaptic weights of 30 neural connections –Each weight was encoded in 8bits, giving 256 values mapped onto the interval [-1, 1] –Total length : 8bits x 3 inputs x 10 outputs = 240 bits 7/13

Evolutionary process Experimental setup Population –100 colonies x 10 robots in each colony = Total 1000 robots –20 independent selection lines (replicates) Selection –Four treatments Colony-level / High relatedness Individual-level / High relatedness Colony-level / Low relatedness Individual-level / High relatedness Recombination –Crossover rate : 0.05 (5%) –Mutation rate : 0.01 (1%) 8/13

Data analysis Performance –Average performance of the 100 colonies over the last 50 generations –Compared with nonparametric (Kruskal-Wallis and Mann-Whitney) tests Some of the data did not follow a normal distribution Signaling strategy –N F / N P : Total number of cycles spent near the food / the poison –b F rn / b P rn : Whether robot r was emmiting light at cycle n near the food or poison Tendency –The tendency of robots to be attracted by light –a r : Decrease in the distance as attraction –v r : Increase in the distance as avoidance 9/13

Experimental results Performance Performance comparison 10/13

Experimental results (cont.) Strategy comparison –Produce light in the vicinity of the food : 12 / 20 –Produce light in the vicinity of the poison : 8 / 20 –The communication strategy where robots signaled near the food resulted in higher performance (259.6 ± 29.5) than the strategy of producing light near the poison (197.0 ± 16.8) Signaling near the food while they feed Food signal can easily be detected by other robots Tendency comparison –Attracted to the light : 12 / 12 –Repelled by the light : 7 / 8 11/13

Experimental results (cont.) 12/13

Conclusion Cooperative communication and deceptive signaling can evolve Communication readily evolves when.. –Colonies consist of genetically similar individuals –Selection acts at the colony level May constrain the evolution of more efficient communication system –Communication between signalers and receivers can be perturbed –Evolved biological systems can be maintained despite their suboptimal nature Evolutionary principles are demonstrated –Can be useful for designing efficient groups of cooperative robots 13/13