Unconstrained Evolution and Hard Consequences

Artificial evolution as a design methodology for hardware frees many of the simplifying constraints normally imposed to make design by humans tractable. However, this freedom comes at some cost, and a whole fresh set of issues must be considered. Standard genetic algorithms are not generally appropriate for hardware evolution when the number of components need not be predetermined. The use of simulations is problematic, and robustness in the presence of noise or hardware faults is important. We present theoretical arguments, and illustrate with a physical piece of hardware evolved in the real-world (‘intrinsically evolved’ hardware). A simple asynchronous digital circuit controls a real robot, using a minimal sensorimotor control system of 32 bits of RAM and a few flip-flops to co-ordinate sonar pulses and motor pulses with no further processing. This circuit is tolerant to single-stuck-at faults in the RAM. The methodology is applicable to many types of hardware, including Field-Programmable Gate Arrays (FPGA's).

[1]  J. G. Elias,et al.  Evolving synaptic connections for a silicon neuromorph , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[2]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[3]  Geoffrey E. Hinton,et al.  How Learning Can Guide Evolution , 1996, Complex Syst..

[4]  Adrian Thompson.  Evolving fault tolerant systems , 1995 .

[5]  Inman Harvey,et al.  Explorations in Evolutionary Robotics , 1993, Adapt. Behav..

[6]  M. Eigen.  New concepts for dealing with the evolution of nucleic acids. , 1987, Cold Spring Harbor symposia on quantitative biology.

[7]  V. Braitenberg.  Vehicles, Experiments in Synthetic Psychology , 1984 .

[8]  M. Nowak,et al.  Error thresholds of replication in finite populations mutation frequencies and the onset of Muller's ratchet. , 1989, Journal of theoretical biology.

[9]  Adrian Thompson,et al.  Evolving Electronic Robot Controller that Exploit Hardware Resources , 1995, ECAL.

[10]  Alan F. Murray,et al.  PULSED SILICON NEURAL NETWORKS - FOLLOWING THE BIOLOGICAL LEADER - , 1991 .

[11]  Trevor A. York.  Survey of field programmable logic devices , 1993, Microprocess. Microsystems.

[12]  M. Eigen,et al.  Molecular quasi-species. , 1988 .

[13]  Inman Harvey,et al.  Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics , 1995, ECAL.

[14]  Günter P. Wagner,et al.  Adaptation and the Modular Design of Organisms , 1995, ECAL.

[15]  Inman Harvey,et al.  Genetic Convergence in a Species of Evolved Robot Control Architectures , 1993, ICGA.

[16]  Inman Harvey,et al.  Seeing the Light: Artiicial Evolution, Real Vision Seeing the Light: Artiicial Evolution, Real Vision , 1994 .

[17]  R. A. Brooks,et al.  Intelligence without Representation , 1991, Artif. Intell..

[18]  M. Eigen,et al.  The Hypercycle: A principle of natural self-organization , 2009 .

[19]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[20]  Hugo de Garis,et al.  EVOLVABLE HARDWARE Genetic Programming of a Darwin Machine , 1993 .

[21]  Peter R. Kinget,et al.  Full analog CMOS integration of very large time constants for synaptic transfer in neural networks , 1992 .

[22]  Alexander Miczo,et al.  Digital logic testing and simulation , 1986 .

[23]  Stuart A. Kauffman,et al.  ORIGINS OF ORDER , 2019, Origins of Order.