Genetic programming-based self-reconfiguration planning for metamorphic robot

This paper presents a genetic programming based reconfiguration planner for metamorphic modular robots. Initially used for evolving computer programs that can solve simple problems, genetic programming (GP) has been recently used to handle various kinds of problems in the area of complex systems. This paper details how genetic programming can be used as an automatic programming tool for handling reconfiguration-planning problem. To do so, the GP evolves sequences of basic operations which are required for transforming the robot’s geometric structure from its initial configuration into the target one while the total number of modules and their connectedness are preserved. The proposed planner is intended for both Crystalline and TeleCube modules which are achieved by cubical compressible units. The target pattern of the modular robot is expressed in quantitative terms of morphogens diffused on the environment. Our work presents a solution for self reconfiguration problem with restricted and unrestricted free space available to the robot during reconfiguration. The planner outputs a near optimal explicit sequence of low-level actions that allows modules to move relative to each other in order to form the desired shape.

[1]  Rahul Kala,et al.  Multi-robot path planning using co-evolutionary genetic programming , 2012, Expert Syst. Appl..

[2]  Gregory S. Chirikjian,et al.  A useful metric for modular robot motion planning , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[3]  John R. Koza,et al.  Genetic programming 2 - automatic discovery of reusable programs , 1994, Complex Adaptive Systems.

[4]  Yves Duthen,et al.  Splittable Metamorphic Carrier Robots , 2014 .

[5]  Mark Moll,et al.  SUPERBOT: A Deployable, Multi-Functional, and Modular Self-Reconfigurable Robotic System , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  G. Chirikjian,et al.  Evaluating efficiency of self-reconfiguration in a class of modular robots , 1996 .

[7]  Hitoshi Iba,et al.  Genetic Programming for Classifying Cancer Data and Controlling Humanoid Robots , 2007 .

[8]  Tad Hogg,et al.  Agent-Based Control for Object Manipulation with Modular Self-reconfigurable Robots , 2001, IJCAI.

[9]  Bernhard Sendhoff,et al.  Global shape with morphogen gradients and motile polarized cells , 2009, 2009 IEEE Congress on Evolutionary Computation.

[10]  Tad Hogg,et al.  Complex behaviors from local rules in modular self-reconfigurable robots , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[11]  Marsette Vona,et al.  A physical implementation of the self-reconfiguring crystalline robot , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[12]  Marsette Vona,et al.  Crystalline Robots: Self-Reconfiguration with Compressible Unit Modules , 2001, Auton. Robots.

[13]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[14]  Gregory S. Chirikjian,et al.  Modular Self-Reconfigurable Robot Systems [Grand Challenges of Robotics] , 2007, IEEE Robotics & Automation Magazine.

[15]  Gregory S. Chirikjian,et al.  Useful metrics for modular robot motion planning , 1997, IEEE Trans. Robotics Autom..

[16]  Subramanian Ramamoorthy,et al.  An efficient algorithm for self-reconfiguration planning in a modular robot , 2010, 2010 IEEE International Conference on Robotics and Automation.

[17]  Zack J. Butler,et al.  Distributed Planning and Control for Modular Robots with Unit-Compressible Modules , 2003, Int. J. Robotics Res..

[18]  Yunpeng Wang,et al.  Optimal Formation of Multirobot Systems Based on a Recurrent Neural Network , 2016, IEEE Transactions on Neural Networks and Learning Systems.