Evolutionary Optimization of Mechanical and Control Design Application to Active Endoscopes
Simultaneous structure/control optimization in a robotic system design is addressed through Evolutionary Algorithms (including genetic algorithms and genetic programming). Both aspects are evolved in the same evolutionary algorithm through dynamic simulations and simulation approximations for continuous and task oriented evaluations. Here, we investigate a specific adaptation of these principles to the design of smart active endoscopes for minimally invasive diagnosis or surgery. The design of such mini-robotic systems is based on a serial arrangement of articulated rings with associated antagonist SMA micro-actuators which configuration have to be adapted to the surgical operation constraints. The control strategies for adaptation of the system geometry to the environmental constraints are based on a multi-agent approach to minimize the inter-module communication requirements. The results obtained from the developed Genetic Algorithm-based design software for the particular application of colonoscopy show the consistency of the solutions. Moreover, the proposed technique for synthesis of approximated evaluation functions significantly speedup the design process while leading to robust fitness representations.
KeywordsShape Memory Alloy Evolutionary Optimization Symbolic Regression Evolution Graph Shape Memory Alloy Actuator
Unable to display preview. Download preview PDF.
- [ADAM 94]A.P. Fraser, Genetic programming in C++, Technical report, University of Salford, Cybernetic Research Institute, 1994.Google Scholar
- [BACK 96]J. Barthelemy and R.Haffka — Approximation concepts for optimum structural design — Structural Optimization, vol 5 —129–144 1993Google Scholar
- [CHAP 01]F. Chapelle, Ph. Bidaud — A closed form for inverse kinematics approximation of general 6R manipulators using genetic programming — in Proc. IEEE Int. Conf. on Robotics and Automation — Seoul 2001.Google Scholar
- [CHOC 99]O. Chocron, Ph. Bidaud — An Evolutionary Algorithm for Global Design of locomotion systems — Proc. of Congress on Evolutionary Computation, vol 3 pages 1068–1075, Washington 1999.Google Scholar
- [GOLD 89]Davis E. Goldberg — GeneticAlgorithms in Search, Optimization and Machine Learning — Addison Wesley 1989.Google Scholar
- [KINN 94]K.E. Kinnar — Advances in Genetic Programming — MIT Press 1994.Google Scholar
- [KOZA 92]John R. Koza — Genetic Programming: On the Programming of Computers by Natural Selection — MIT Press 1992.Google Scholar
- [LIAN 2000]K.H. Hsin Liang and al. — Evolutionary search of approximated n-dimensional landscape — Int. Journal of Knowledge-Based Intelligent Eng System, pages 172–183, July 2000.Google Scholar
- [MICH 92]Z. Michalewicz - Genetic Algorithms + data structures = Evolution programs — Springer Verla 1992Google Scholar
- [NAIR 98]P.B. Nair, A.J. Keane, R.P. Shimpi — Combining Approximation Concepts with Genetic Algorithm-Based Structural Optimization Procedures, Tech. Report, American Institute of Aeronautics and Astronautics, 1998.Google Scholar
- [RATL 99]A. Ratle — Optimal sampling strategies for learning a fitness model — Proc. of Congress on Evolutionary Computation, vol 3 pages 2078–2085, Washington 1999.Google Scholar
- [SZEW 00]J. Szewczyk, N. Troisfontaine, Ph. Bidaud — An active steering device for endocopes — Proc. of DETC2000, ASME Design Technical Conferences, Baltimore — USA — 2000.Google Scholar