Abstract-Neuromorphic computing is a promising solution for reducing the size, weight and power of mobile embedded systems. In this paper, we introduce a realization of such a system by creating the first closed-loop battery-powered communication system between an IBM TrueNorth NS1e and an autonomous Android-Based Robotics platform. Using this system, we constructed a dataset of path following behavior by manually driving the Android-Based robot along steep mountain trails and recording video frames from the camera mounted on the robot along with the corresponding motor commands. We used this dataset to train a deep convolutional neural network implemented on the TrueNorth NS1e. The NS1e, which was mounted on the robot and powered by the robot's battery, resulted in a selfdriving robot that could successfully traverse a steep mountain path in real time. To our knowledge, this represents the first time the TrueNorth NS1e neuromorphic chip has been embedded on a mobile platform under closed-loop control.
Abstract. We created a simple evolutionary system, sexyloop, on a deterministic ten-state five-neighbour cellular automaton (CA) where self-reproducing loops have the capability of sex. With this ability, the loops are capable of transferring genetic material into other loops. This work was based on Sayama's evoloop which was transformed by adding a new state and new rules. The evoloop model showed an emergent evolutionary process only due to an adaptation of the loops to interaction in the environment; and after a certain time, all the individuals capable of self-reproduction belonged to the smallest species 4 which reproduced the fastest. We created two different models of self-reproducing loops with sex, Sexyloop M1 and M2, in order to study the possibility of sex in self-reproducing automata and to assess the impact of sex on the evolutionary process via comparing between the evoloop and the sexyloop variants. In the sexyloop M1 and M2, the diversity of the whole population was different from that found in the evoloop and the evolutionary process was quite different too. The sexyloops also created smaller and bigger species than the evoloops, and exhibited greater diversity and faster evolution than their non-sexual counterparts. The most interesting model was the sexyloop M2 whose evolutionary dynamics had a very different longterm behaviour than the evoloop and sexyloop M1. The most surprising and intriguing phenomenon in the sexyloop M2 was that the evolutionary process was selecting quickly a bigger species than in the evoloop and sexyloop M1: the species 5. In fact, the individuals from this species needed more time to reproduce than those from the species 4. So it appears that in the sexyloop M2, the fittest individual was not one that could reproduce the fastest but surely one that reproduced fast and which was more adapted to propagate in an environment where sex with individuals of the same and other types could occur. These results give the first examples in cellular automata of evolution in a population of self-replicators where sex plays an important role.
Game theory is commonly used to study social behavior in cooperative or competitive situations. One socioeconomic game, Stag Hunt, involves the trade-off between social and individual benefit by offering the option to hunt a low-payoff hare alone or a high-payoff stag cooperatively. Stag Hunt encourages the creation of social contracts as a result of the payoff matrix, which favors cooperation. By playing Stag Hunt with set-strategy computer agents, the social component is degraded because of the inability of subjects to dynamically affect the outcomes of iterated games, as would be the case when playing against another subject. However, playing with an adapting agent has the potential to evoke unique and complex reactions in subjects because of its ability to change its own strategy based on its experience over time, both within and between games. In the present study, 40 subjects played the iterated Stag Hunt with five agents differing in strategy: exclusive hare hunting, exclusive stag hunting, random, Win-Stay-Lose-Shift, and adapting. The results indicated that the adapting agent caused subjects to spend more time and effort in each game, exhibiting a more complicated path to their destination. This suggests that adapting agents exhibit behavior similar to human opponents, evoking more natural social responses in subjects.
Humans and other terrestrial animals use vision to traverse novel cluttered environments with apparent ease. On one hand, although much is known about the behavioral dynamics of steering in humans, it remains unclear how relevant perceptual variables might be represented in the brain. On the other hand, although a wealth of data exists about the neural circuitry that is concerned with the perception of self-motion variables such as the current direction of travel, little research has been devoted to investigating how this neural circuitry may relate to active steering control. Here we present a cortical neural network model for visually guided navigation that has been embodied on a physical robot exploring a real-world environment. The model includes a rate based motion energy model for area V1, and a spiking neural network model for cortical area MT. The model generates a cortical representation of optic flow, determines the position of objects based on motion discontinuities, and combines these signals with the representation of a goal location to produce motor commands that successfully steer the robot around obstacles toward the goal. The model produces robot trajectories that closely match human behavioral data. This study demonstrates how neural signals in a model of cortical area MT might provide sufficient motion information to steer a physical robot on human-like paths around obstacles in a real-world environment, and exemplifies the importance of embodiment, as behavior is deeply coupled not only with the underlying model of brain function, but also with the anatomical constraints of the physical body it controls.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.