Floreano, D. and Mondada, F., "Hardware Solutions for Evolutionary Robotics", In: P.Husbands and JA. Meyer, editors, Proceedings of the first European Workshop on Evolutionary Robotics. Springer Verlag, Berlin, pp. 137-151, 1998.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....function against which, say, a complex circuit is evolved) over time, with the aim of minimizing the overall time spent evolving a circuit that achieves the prescribed task. Incremental evolution consists of gradually evolving one complex task in a series of tasks of increasing complexity [15], 16] Bidirectional incremental evolution consists in gradually decomposing a complex task into a series of tasks of decreasing complexity and in gradually evolving a complex task into a series of tasks of increasing complexity. In bidirectional incremental evolution, the scaling of the fitness ....

Floreano D. and Mondada F. Hardware solutions for evolutionary robotics. In Husbands P. and Meyer JA. , editors, Proc. of the First European Workshop on Evolutionary Robotics. Berlin: Springer-Verlag, 1998.

....controllers are automatically downloaded on the microcontrollers of the robots through the serial link. In the predator, an additional microprocessor on the vision module performs visual pre processing and sends data at 15 Hz frequency to the main microcontroller. the K213 vision turret (see [11] for more details of this modular architecture) At the beginning of a co evolutionary run, the two neurocontrollers, with the connection strengths initialized to zero, were downloaded into the corresponding robots. Two genetic algorithms (with the same parameters in these experiments) were then ....

D. Floreano and F. Mondada. Hardware Solutions for Evolutionary Robotics. In P. Husbands and J-A. Meyer, editors, Proceedings of the first European Workshop on Evolutionary Robotics. Springer Verlag, Berlin, 1998.

.... The fitness function Phi i for species i was based only on the average time to contact over K tournaments, Phi py = 1 K K X k=1 x k 500 ; Phi pr = 1 K K X k=1 i 1 Gamma x k 500 j ; 2 More details on this architecture and its relevance for evolutionary robotics are given in (Floreano and Mondada, 1998). that is the number x k of sensorimotor cycles performed in tournament k normalized by the maximum number of sensorimotor cycles available (500) in the case of the prey py, and the complement in the case of the predator pr, further averaged over the number of tournaments K. This fitness ....

....hint at the computational advantages of competitive coevolution. In a companion paper, we report results showing that predators evolved against a fixed co evolved prey (from another run) do not reach the same performance levels obtained when both prey and predators are co evolved (Nolfi and Floreano, 1998). It has also been shown that, by including all the best opponents evolved so far as test cases for each individual (Hall of Fame method) co evolution becomes very similar to a very robust optimization technique (Rosin and Belew, 1997) However, the basic issue that the results presented above ....

[Article contains additional citation context not shown here]

Floreano, D. and Mondada, F. (1998). Hardware Solutions for Evolutionary Robotics. In Husbands, P. and Meyer, J., editors, Proceedings of the first European Workshop on Evolutionary Robotics. Springer Verlag, Berlin.

....robot will operate, and save money in terms of dedicated equipment and man hours for developing a particular application. Although in this manuscript I will concentrate mainly on control problems, it is important to stress that a new approach requires also a different way of building robots (e.g. [13]) In the traditional approach, robots are often closed systems (they cannot be easily expanded or modified) tailored for a specific task and operating condition, and rely on precise, costly, and fragile components. These are consequences of a Cartesian approach that attempts to fit a mathematical ....

D. Floreano and F. Mondada. Hardware Solutions for Evolutionary Robotics. In P. Husbands and J-A. Meyer, editors, Proceedings of the first European Workshop on Evolutionary Robotics. Springer Verlag, Berlin, 1998.

No context found.

Floreano, D. and Mondada, F., "Hardware Solutions for Evolutionary Robotics", In: P.Husbands and JA. Meyer, editors, Proceedings of the first European Workshop on Evolutionary Robotics. Springer Verlag, Berlin, pp. 137-151, 1998.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC