Evolutionary Robotics and Open-Ended Design Automation - Biomimetics: Biologically Inspired Technologies - page 153

4.8. CONCLUSIONS

We have followed through a number of cases where principles of biological evolution have been
used to automate the design of machines — from relatively simple examples in controller design to
design and fabrication of complete functional machines in physical reality, sometimes outperform-
ing the human designs. Unlike other forms of biomimicry, however, we are not seeking to imitate
the solutions that present themselves in nature — like the gecko's feet, a bird's wing, or a human's
muscle — because these solutions were optimized for very specific needs and circumstances that
may not reflect our requirements and unique capabilities. Instead, we chose to imitate the process
that led to these solutions, as biology's design process has shown time and again its ability to
discover new opportunities.
It is clear that the complexity of engineering products is increasing to the point where traditional
design processes are reaching their limits. More manpower is being invested in managing
and maintaining large systems than designing them, and this ratio is likely to increase because
no single person can fathom the complexities involved. Alexander's quote (above) is truer today than
it was in the 1960s. Engineering and science are moving into scales and dimensions where people
have little or no intuitions and the complexities involved are overwhelming. One way out of this
conundrum is to design machines that can design for us — this is the future of engineering.

4.9 FURTHER READING

Digital Biology , Peter Bentley, Simon and Schuster, 2004.
Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines , Stefano Nolfi
and Dario Floreano, Bradford Books, 2004.
Out of Control: The New Biology of Machines, Social Systems and the Economic World , Kevin Kelly, Perseus
Books Group, 1995.

REFERENCES

Alexander, C. A. (1964) Notes on the Synthesis of Form , Harvard University Press, Cambridge, Massachusetts.
Basalla, G. (1989) The Evolution of Technology , Cambridge University Press, Cambridge, Massachusetts.
Beer, R. D., Gallagher, J. C. (1992) Evolving dynamical neural networks for adaptive behavior, Adaptive
Behavior , 1(1), 91-122.
Bongard, J. C. (2002) Evolved Sensor Fusion and Dissociation in an Embodied Agent, Proceedings of the
EPSRC/BBSRC International Workshop Biologically-Inspired Robotics: The Legacy of W. Grey
Walter , pp. 102-109.
Bongard, J. C., Lipson, H. (2004a) Once more unto the breach: automated tuning of robot simulation using an
inverse evolutionary algorithm, Proceedings of the Ninth International Conference on Artificial Life
(ALIFE IX) , pp. 57-62.
Bongard, J. C., Lipson, H. (2004b) Automated damage diagnosis and recovery for remote robotics, IEEE
International Conference on Robotics and Automation (ICRA04) , pp. 3545-3550.
Bongard, J. C., Lipson, H. (2004c) Integrated design, deployment and inference for robot ecologies, Pro-
ceedings of Robosphere 2004 , November 2004, NASA Ames Research Center, Moffett Field,
California.
Bongard, J. C., Pfeifer, R. (2003) Evolving complete agents using artificial ontogeny. In: Hara, F., Pfeifer, R.,
(eds), Morpho-Functional Machines: the New Species (Designing Embodied Intelligence) , Springer-
Verlag, New York, New York, pp. 237-258.
Bonner, J. T. (1988) The Evolution of Complexity by Means of Natural Selection , Princeton University Press,
Princeton, New Jersey.
Floreano, D., Urzelai, J. (2001) Evolution of plastic control networks, Autonomous Robots , 11, 311-317.