This paper introduces a new type of artificial neural network (GasNets) and shows that it is possible to use evolutionary computing techniques to find robot controllers based on them. The controllers are built from networks inspired by the modulatory effects of freely diffusing gases, especially nitric oxide, in real neuronal networks. Evolutionary robotics techniques were used to develop control networks and visual morphologies to enable a robot to achieve a target discrimination task under very noisy lighting conditions. A series of evolutionary runs with and without the gas modulation active demonstrated that networks incorporating modulation by diffusing gases evolved to produce successful controllers considerably faster than networks without this mechanism. GasNets also consistently achieved evolutionary success in far fewer evaluations than were needed when using more conventional connectionist style networks.2
In this paper, we develop techniques based on evolvability statistics of the fitness land-scape surrounding sampled solutions. Averaging the measures over a sample of equal fitness solutions allows us to build up fitness evolvability portraits of the fitness land-scape, which we show can be used to compare both the ruggedness and neutrality in a set of tunably rugged and tunably neutral landscapes. We further show that the tech-niques can be used with solution samples collected through both random sampling of the landscapes and online sampling during optimization. Finally, we apply the techniques to two real evolutionary electronics search spaces and highlight differences between the two search spaces, comparing with the time taken to find good solutions through search.
We have recently shown that glucose and glucosamine regulate the transcription of transforming growth factor-alpha (TGF alpha) in rat aortic smooth muscle (RASM) cells. Based on the increased potency of glucosamine compared to glucose, we hypothesized that stimulation of TGF alpha transcription by glucose is mediated through the hexosamine biosynthesis pathway. The yeast cDNA for the rate-limiting enzyme of this pathway, glutamine:fructose-6-phosphate amidotransferase (GFA), was therefore expressed in RASM cells. GFA-transfected cells showed an increase in GFA activity, exhibiting a 2.2-fold increase in the synthesis of glucosamine-6-phosphate, the first product of the hexosamine biosynthetic pathway. To test the effect of GFA overexpression on TGF alpha transcriptional activity, cells were transiently cotransfected with GFA along with a reporter plasmid containing the firefly luciferase gene under control of the TGF alpha promoter. GFA-transfected cells exhibited a glucose-dependent 2-fold increase in TGF alpha activity compared to control cells. Maximal stimulation of TGF alpha-luciferase activity by glucosamine, however, was equivalent in GFA-and control-transfected cells, confirming that the stimulation observed by both agents operated through the same pathway. This increase in TGF alpha activity was inhibited (85% at 0.5 mM glucose and 69% at 30 mM glucose) by the glutamine analog and inhibitor of GFA, 6-diazo-5-oxonorleucine (10 microM). Control studies confirmed that the increased TGF alpha-luciferase activity in the GFA-expressing cells was not an artifact of altered growth, survival, or transfection efficiency.(ABSTRACT TRUNCATED AT 250 WORDS)
Recent years have seen the discovery of freely diffusing gaseous neurotransmitters, such as nitric oxide (NO), in biological nervous systems. A type of artificial neural network (ANN) inspired by such gaseous signaling, the GasNet, has previously been shown to be more evolvable than traditional ANNs when used as an artificial nervous system in an evolutionary robotics setting, where evolvability means consistent speed to very good solutions--here, appropriate sensorimotor behavior-generating systems. We present two new versions of the GasNet, which take further inspiration from the properties of neuronal gaseous signaling. The plexus model is inspired by the extraordinary NO-producing cortical plexus structure of neural fibers and the properties of the diffusing NO signal it generates. The receptor model is inspired by the mediating action of eurotransmitter receptors. Both models are shown to significantly further improve evolvability. We describe a series of analyses suggesting that the reasons for the increase in evolvability are related to the flexible loose coupling of distinct signaling mechanisms, one "chemical" and one "electrical."
Designing controllers for autonomous robots is not an exact science, and there are few guiding principles on what properties of control systems are useful for what kinds of task. In this article we analyze the functional operation of robot controllers developed using evolutionary computation methods, to elucidate the strengths and weaknesses of the underlying control system class. By comparing and contrasting robot controllers based on two different classes of artificial neural network, the GasNet and NoGas networks, we show that the increased evolvability of the GasNet class on a visual shape discrimination task is due to the temporally adaptive nature of the GasNet, where neuronal plasticity mediated through the concentration of virtual neuromodulatory "gases" occurs over a wide range of time courses. We argue that the availability of mechanisms operating over a wide range of potential time courses is a crucial property for controllers used to generate adaptive behavior over time, and that the design process should easily be able to adapt those time courses to the natural time scales in the environment. Keywords evolutionary robotics • artificial neural networks • GasNets • neuromodulation • neuronal plasticity A good performance, like a human life, is a temporal affair: a process in time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.