Home     |     Projects    |      People     |    Publications     |     Links    |    News    |

2011 IEEE International Conference on Robotics and Automation

Shanghai, China, May 9-13, 2011

Tutorial on

Morphogenetic Robotics: A New Emerging Field of Self-Organizing Robotic Systems

Time:

     14:00 - 17:00, May 9, 2011

Abstract

This half-day tutorial will mainly give a complete introduction of a new emerging field of self-organizing robotic systems: Morphogenetic Robotics.  Epigenetic robotics concentrates primarily on modeling the development of cognitive elements of living systems in robotic systems, such as language, emotion, and social skills, while morphogenetic robotics mainly covers the modeling of neural and morphological development in single- and multi-robot systems, which is an important part of developmental robotics complementary to epigenetic robotics.   With the recent rapid advances in evolutionary developmental biology and system biology, increasing genetic and cellular principles underlying biological morphogenesis have been revealed.  Inspired by these biological principles, we propose morphogenetic robotics, a class of methodologies in robotics for designing self-organizing, self-reconfigurable, and self-repairable single- or multi-robot systems, using genetic and cellular mechanisms governing biological morphogenesis. We categorize these methodologies into three areas, namely, morphogenetic swarm robotic systems, morphogenetic modular robots, and morphogenetic body and brain design for robots.

Organizers

Prof. Yan Meng

Department of Electrical and Computer Engineering

Stevens Institute of Technology, Hoboken, NJ 07030, USA

Email: yan.meng@stevens.edu  

Prof. Yaochu Jin

Department of Computing

University of Surrey, Guildford, Surrey, GU2 7XH UK

Email: yaochu.jin@surrey.ac.uk  

Motivation and Objectives

Self-organization is one of the most important features observed in social, economic, ecological systems and biological systems.  Self-organizing robotic systems are supposed to be able to accomplish complex tasks in a changing environment through local interactions among individual agents and local environment without an external global control. Self-organizing robotic systems should exhibit life-like features such as self-reconfiguration, self-repair, self-reproduction, self-development, and context awareness.  However, developing such self-organizing systems, where desired global behaviors can emerge through contextual local interactions among individuals and with the environment, is a very challenging task. 

    Borrowing ideas from biological systems for developing self-organizing robotic systems has become increasingly popular in recent years. One example of self-organizing process in biology is morphogenesis of multi-cellular organisms. Morphogenetic approaches based on computational models of embryogeny to self-organizing robotic systems have shown to be very promising. Individual robots (in a swarm system) or modules (in a modular robot) are supposed to self-organize themselves to build different morphologies that contribute to adaptation to dynamic environments for different tasks. Furthermore, robotic systems will become more powerful if they can co-evolve their controllers and morphological development to adapt to new environments and new tasks in hand. To this end, we have proposed a new terminology called Morphogenetic Robotics[1], which is used to denote research efforts dedicated to the application of morphogenetic mechanisms to robotics which belongs to developmental robotics. 

List of Topics

   From our perspective, morphogenetic robotics may include, but is not limited to the following three main topics:

1)   Morphogenetic swarm robotic systems that deal with the self-organization of swarm robots using genetic and cellular mechanisms underlying the biological early morphogenesis [2] [3] [4][5][6][7].

2)   Morphogenetic modular robots where modular robots adapt their configurations autonomously based on the current environmental conditions using morphogenetic principles [8] [9][10].

3)   Developmental approaches to the design of the body or body parts and its neural controller of robots. Neural development can be further divided into activity-independent [11] and activity-dependent neural development [12].

   In this tutorial, we will mainly focus on the first two topics: morphogenetic swarm robotic systems and morphogenetic modular robots.

Intended Audiences

The intended audiences are researchers and students who are interested in biologically inspired self-organizing robotic systems, in particular self-organizing swarm robotic systems and self-reconfigurable modular robotic systems.

References

1. Y. Jin and Y. Meng, Morphogenetic Robotics: An Emerging New Field in Developmental Robotics, IEEE Trans. on Systems, Man, and Cybernetics, Part C. Vol. 41,  no.2, pp.145-160, 2011.
2. H. Guo, Y. Meng and Y. Jin, A Cellular Mechanism for Multi-Robot Construction via Evolutionary Multi-Objective Optimization of a Gene Regulatory Networks, BioSystems. Vol.98, no.3, pp.193-203, 2009.
3. H. Guo, Y. Jin, and Y. Meng, A Uniform Framework for Self-organized Multi-Robot Pattern Formation and Boundary Coverage Inspired from Morphogenesis. ACM Trans. on Autonomous and Adaptive Systems. (In press)

4. H. Guo, Y. Meng, and Y. Jin, Swarm robot pattern formation using a morphogenetic multi-cellular based self-organization algorithm, in IEEE International Conference on Robotics and Automation (ICRA), 2011.
5. H. Guo, Y. Meng and Y. Jin, Analysis of Local Communication Load in Shape Formation of a Distributed Morphogenetic Swarm Robotic System. 2010 IEEE Congress on Evolutionary Computation (CEC 2010). 
6. Y. Jin,  H. Guo, and Y. Meng, “Robustness analysis and failure recovery of a bio-inspired self-organizing multi-robot system,” in Proc. Third IEEE Int. Conf. Self-Adaptive Self-organizing Systems, 2009, pp. 154–164.
7. H. Guo, Y. Meng and Y. Jin, Self-Adaptive Multi-Robot Construction using Gene Regulatory Networks, 2009 IEEE Symposium on Artificial Life (ALIFE 2009).
8. Y. Meng, Y. Zhang, and J. Jin, Autonomous Self-Reconfiguration of Modular Robots using a Hierarchical Mechanochemical Model, IEEE Computational Intelligence Magazine. Vol. 6, no. 1, pp.43-54, 2011.
9. Y. Meng, Y. Zhang, and Y. Jin,   A Morphogenetic Approach to Self-Reconfigurable Modular Robots using a Hybrid Hierarchical Gene Regulatory Network, 12^th International Conference on the Synthesis and Simulation of Living Systems (ALIFE XII). 2010. 
10. Y. Meng, Y. Zhang, A. Sampath, Y. Jin, and B. Sendhoff, "Cross-ball: a new morphogenetic self-reconfigurable modular robot," in IEEE International Conference on Robotics and Automation (ICRA), 2011.
11. L. Schramm, Y. Jin, and B. Sendhoff, Emerged Coupling of Motor Control and Morphological Development in Evolution of Multi-Cellular Animates, in Proc. 10th Eur. Conf. Artificial Life, 2009.

12. Y. Meng, Y. Jin, J. Yin, and M. Conforth, Human Activity Detection using Spiking Neural Networks Regulated by a Gene Regulatory Network, 2010 IEEE International Joint Conference on Neural Networks (IJCNN 2010).