摘要翻譯:
動力系統(tǒng)理論和復(fù)雜性科學(xué)為分析人工智能體和機(jī)器人提供了強(qiáng)有力的工具。此外,它們最近也被提議作為設(shè)計原則和指導(dǎo)方針的來源。布爾網(wǎng)絡(luò)是復(fù)雜動力系統(tǒng)的一個突出例子,已被證明能有效地捕捉基因調(diào)控中的重要現(xiàn)象。從工程的角度來看,這些模型非常引人注目,因為它們可以展示豐富而復(fù)雜的行為,盡管它們的描述很緊湊。本文提出用布爾網(wǎng)絡(luò)來控制機(jī)器人的行為。該網(wǎng)絡(luò)是通過基于隨機(jī)局部搜索技術(shù)的自動過程來設(shè)計的。我們表明,這種方法使得設(shè)計一個網(wǎng)絡(luò)成為可能,使機(jī)器人能夠完成一個需要使用光刺激的空間導(dǎo)航能力的任務(wù),以及形成和使用內(nèi)部存儲器。
---
英文標(biāo)題:
《Boolean network robotics: a proof of concept》
---
作者:
Andrea Roli and Mattia Manfroni and Carlo Pinciroli and Mauro
Birattari
---
最新提交年份:
2011
---
分類信息:
一級分類:Computer Science 計算機(jī)科學(xué)
二級分類:Artificial Intelligence 人工智能
分類描述:Covers all areas of AI except Vision, Robotics, Machine Learning, Multiagent Systems, and Computation and Language (Natural Language Processing), which have separate subject areas. In particular, includes Expert Systems, Theorem Proving (although this may overlap with Logic in Computer Science), Knowledge Representation, Planning, and Uncertainty in AI. Roughly includes material in ACM Subject Classes I.2.0, I.2.1, I.2.3, I.2.4, I.2.8, and I.2.11.
涵蓋了人工智能的所有領(lǐng)域,除了視覺、機(jī)器人、機(jī)器學(xué)習(xí)、多智能體系統(tǒng)以及計算和語言(自然語言處理),這些領(lǐng)域有獨立的學(xué)科領(lǐng)域。特別地,包括專家系統(tǒng),定理證明(盡管這可能與計算機(jī)科學(xué)中的邏輯重疊),知識表示,規(guī)劃,和人工智能中的不確定性。大致包括ACM學(xué)科類I.2.0、I.2.1、I.2.3、I.2.4、I.2.8和I.2.11中的材料。
--
一級分類:Computer Science 計算機(jī)科學(xué)
二級分類:Neural and Evolutionary Computing 神經(jīng)與進(jìn)化計算
分類描述:Covers neural networks, connectionism, genetic algorithms, artificial life, adaptive behavior. Roughly includes some material in ACM Subject Class C.1.3, I.2.6, I.5.
涵蓋神經(jīng)網(wǎng)絡(luò),連接主義,遺傳算法,人工生命,自適應(yīng)行為。大致包括ACM學(xué)科類C.1.3、I.2.6、I.5中的一些材料。
--
一級分類:Computer Science 計算機(jī)科學(xué)
二級分類:Robotics 機(jī)器人學(xué)
分類描述:Roughly includes material in ACM Subject Class I.2.9.
大致包括ACM科目I.2.9類的材料。
--
---
英文摘要:
Dynamical systems theory and complexity science provide powerful tools for analysing artificial agents and robots. Furthermore, they have been recently proposed also as a source of design principles and guidelines. Boolean networks are a prominent example of complex dynamical systems and they have been shown to effectively capture important phenomena in gene regulation. From an engineering perspective, these models are very compelling, because they can exhibit rich and complex behaviours, in spite of the compactness of their description. In this paper, we propose the use of Boolean networks for controlling robots' behaviour. The network is designed by means of an automatic procedure based on stochastic local search techniques. We show that this approach makes it possible to design a network which enables the robot to accomplish a task that requires the capability of navigating the space using a light stimulus, as well as the formation and use of an internal memory.
---
PDF鏈接:
https://arxiv.org/pdf/1101.6001