This paper summarizes the results of the dynamical systems
analysis of nearly four hundred continuous-time recurrent neural network
(CTRNN) single-leg locomotion controllers evolved under conditions where
sensory information was unreliable and in which the body the controller
was embedded in could change its physical properties. The general
principles underlying the operation of all the resulting mixed pattern
generators (MPGs) are discussed. Several MPG operational features are
explained and verified. Finally, discussion is made of future extensions
of this research
[Show abstract][Hide abstract] ABSTRACT: Continuous time recurrent neural network-evolvable hardware (CTRNN-EH) control devices comprise of an analog continuous time recurrent neural network (CTRNN) with an on-board evolutionary algorithm (EA) engine to evolve the parameters of the neural network. These control devices were demonstrated to be effective for suppressing thermoacoustic (TA) instability in simulated jet engines. Currently, the construction of a VLSI CTRNN-EH device is underway for suppressing TA instability in a real combustion chamber while it is in operation. In this paper, we present a fully function digital EA engine for the CTRNN-EH control device. An ad-hoc hardware design is presented to realize space savings. The simulation and synthesis results of the hardware EA are presented. In addition to this, a demonstration of the efficacy of the EA across a noisy real world control problem is presented.
[Show abstract][Hide abstract] ABSTRACT: Evolvable hardware is reconfigurable hardware plus an evolutionary algorithm. Continuous time recurrent neural networks (CTRNNs) have already been proposed for use as the reconfigurable hardware component. Until recently, however, nearly all CTRNN based EH was simulation based. This paper provides a design for a reconfigurable analog CTRNN computer that supports both extrinsic and intrinsic CTRNN evolvable hardware. The paper will fully characterize the design and demonstrate that configurations can be moved from simulation to hardware without difficulty. It will also discuss implications for an upcoming VLSI system that will combine the CTRNN circuitry with the learning engine on a single chip.
Evolutionary Computation, 2005. The 2005 IEEE Congress on; 10/2005
Note: This list is based on the publications in our database and might not be exhaustive.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.