Author:
Boddhu Sanjay K.,Gallagher John C.
Abstract
PurposeThe purpose of this paper is to present an approach to employ evolvable hardware concepts, to effectively construct flapping‐wing mechanism controllers for micro robots, with the evolved dynamically complex controllers embedded in a, physically realizable, micro‐scale reconfigurable substrate.Design/methodology/approachIn this paper, a continuous time recurrent neural network (CTRNN)‐evolvable hardware (a neuromorphic variant of evolvable hardware) framework and methodologies are employed in the process of designing the evolution experiments. CTRNN is selected as the neuromorphic reconfigurable substrate with most efficient Minipop Evolutionary Algorithm, configured to drive the evolution process. The uniqueness of the reconfigurable CTRNN substrate preferred for this study is perceived from its universal dynamics approximation capabilities and prospective to realize the same in small area and low power chips, the properties which are very much a basic requirement for flapping‐wing based micro robot control. A simulated micro mechanical flapping insect model is employed to conduct the feasibility study of evolving neuromorphic controllers using the above‐mentioned methodology.FindingsIt has been demonstrated that the presented neuromorphic evolvable hardware approach can be effectively used to evolve controllers, to produce various flight dynamics like cruising, steering, and altitude gain in a simulated micro mechanical insect. Moreover, an appropriate feasibility is presented, to realize the evolved controllers in small area and lower power chips, with available fabrication techniques and as well as utilizing the complex dynamics nature of CTRNNs to encompass various controls ability in a architecturally static hardware circuit, which are more pertinent to meet the constraints of micro robot construction and control.Originality/valueThe proposed neuromorphic evolvable hardware approach along with its modules intact (CTRNNs and Minipop) can provide a general mechanism to construct/evolve dynamically complex and optimal controllers for flapping‐wing mechanism based micro robots for various environments with least human intervention. Further, the evolved neuromorphic controllers in simulation study can be successfully transferred to its hardware counterpart without sacrificing its anticipated functionality and realized within a predictable area and power ranges.
Reference34 articles.
1. Augustsson, P., Wolff, K. and Nordin, P. (2002), “Creation of a learning flying robot by means of evolution”, The Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 02), Morgan Kaufmann, San Francisco, CA, pp. 1279‐85.
2. Beer, R.D. (1995), “On the dynamics of small continuous‐time recurrent neural networks”, Adaptive Behavior, Vol. 3 No. 4, pp. 469‐509.
3. Beer, R.D., Chiel, H.J. and Gallagher, J.C. (1999), “Evolution and analysis of model CPGs for walking II. General principles and individual variability”, Journal of Computational Neuroscience, Vol. 7 No. 2, pp. 119‐47.
4. Boddhu, S.K. and Gallagher, J.C. (2009), “Evolving non‐autonomous neuromorphic flight control for a flapping‐wing mechanical insect model”, paper presented at IEEE Workshop on Evolvable and Adaptive Hardware – 2009, Nashvile, TN.
5. Boddhu, S.K., Gallagher, J.C. and Vigraham, S.A. (2006), “A reconfigurable continuous time recurrent neural network for evolvable hardware applications: intrinsic evolution and extrinsic verification”, The Congress on Evolutionary Computation – 2006, IEEE Press, Vancouver.
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献