受生物群体智能启发的多机器人系统研究

首先,介绍了生物社会中的群体智能．接着,讨论了群体机器人技术中的群体控制、群体通信和群体形态等主要研究内容及其发展趋势,并介绍了群体机器人系统的几个典型任务环境．最后,通过一个物体搜集任务的仿真实例来说明群体智能设计原则在多机器人系统中的应用．     

Towards a Theoretical Framework of Autonomous Systems Underpinned by Intelligence and Systems Sciences

Autonomous systems are an emerging AI technology functioning without human intervention underpinned by the latest advances in intelligence,cognition,computer,and systems sciences.This paper explores the intelligent and mathematical foundations of autonomous systems.It focuses on structural and behavioral properties that constitute the intelligent power of autonomous systems.It explains how system intelligence aggregates from reflexive,imperative,adaptive intelligence to autonomous and cognitive intelligence.A hierarchical intelligence model(HIM)is introduced to elaborate the evolution of human and system intelligence as an inductive process.The properties of system autonomy are formally analyzed towards a wide range of applications in computational intelligence and systems engineering.Emerging paradigms of autonomous systems including brain-inspired systems,cognitive robots,and autonomous knowledge learning systems are described.Advances in autonomous systems will pave a way towards highly intelligent machines for augmenting human capabilities.     

Intelligent Collectives: Theory,Applications, and Research Challenges

ABSTRACT

Nowadays, along with the rapid development of information technologies, very often solving a common problem is entrusted to many autonomous units (people, systems). With such an approach, one can tap into the so-called collective intelligence (CI)—emerging from the collaboration and competition of many individuals. In this paper, we present recent research on CI related to the effectiveness of using the wisdom of crowds to perform a wide range of problems. For this aim, we first introduce a general framework of CI involving key characteristics of intelligent collectives. Next, we focus on the problem of how diversity and collective cardinality influence collective performance. Then, its applications, which are widely used such as prediction markets and Delphi method, will be presented. Furthermore, some research challenges on the capacity of combining CI with other research fields such as machine learning and social networks are also discussed.     

Artificial intelligence: New jobs from old

The age of artificial intelligence (AI) is upon us, and its effect upon society in the coming years will be noteworthy. Artificial intelligence is a field that encompasses such applications as robotics, expert systems, natural language understanding, speech recognition, and computer vision. The effect of these AI systems upon existing and future job occupations will be important. This paper takes a look at artificial intelligence in terms of the creation of new job categories. Also, the introduction of AI into the organization to better familiarize the employees about AI will be discussed.     

Evolutionary computing in robotics

Intelligent systems are required in knowledge engineering, computer science, mechatronics, and robotics. This article discusses machine (system) intelligence from the viewpoints of the learning and adaptation of living things. We then introduce computational intelligence, including neural networks, fuzzy systems, and genetic algorithms, and end with a discussion of recent work on computational intelligence in robotics. This work was presented, in part, at the Sixth International Symposium on Artificial Life and Robotics, Tokyo, Japan, January 15–17, 2001     

Robots, insects and swarm intelligence

The aim of this paper is to consider the relationships between robots and insects. To this end, an overview is provided of the two main areas in which insects have been implicated in robotics research. First, robots have been used to provide working models of mechanisms underlying insect behaviour. Second, there are developments in robotics that have been inspired by our understanding of insect behaviour; in particular the approach of swarm robotics. In the final section of the paper, the possibility of achieving “strong swarm intelligence” is discussed. Two possible interpretations of strong swarm intelligence are raised: (1) the emergence of a group mind from a natural, or robot swarm, and (2) that behaviours could emerge from a swarm of artificial robots in the same way as they emerge from a biological swarm. Both interpretations are dismissed as being unachievable in principle. It is concluded that bio-robotic modelling and biological inspiration have made important contributions to both insect and robot research, but insects and robots remain separated by the divide between the living and the purely mechanical.     

Search and tracking algorithms for swarms of robots: A survey

Target search and tracking is a classical but difficult problem in many research domains, including computer vision, wireless sensor networks and robotics. We review the seminal works that addressed this problem in the area of swarm robotics, which is the application of swarm intelligence principles to the control of multi-robot systems. Robustness, scalability and flexibility, as well as distributed sensing, make swarm robotic systems well suited for the problem of target search and tracking in real-world applications. We classify the works we review according to the variations and aspects of the search and tracking problems they addressed. As this is a particularly application-driven research area, the adopted taxonomy makes this review serve as a quick reference guide to our readers in identifying related works and approaches according to their problem at hand. By no means is this an exhaustive review, but an overview for researchers who are new to the swarm robotics field, to help them easily start off their research.     

基于对抗样本的人工智能反制技术研究进展与趋势

随着基于深度学习的人工智能技术的快速发展及其广泛应用,人们对其安全性的关注也日益凸显。特别是,最近一系列研究表明基于深度学习模型的人工智能系统容易受到对抗样本的攻击。对抗样本通过向正常样本中添加精心设计、人类难以察觉的微小扰动,可导致深度学习模型的严重误判。本文回顾基于对抗性图像和音频两类人工智能反制技术最新进展,并对这些研究成果进行分类和综合比较,最后对现有挑战与未来研究趋势进行了讨论和展望。     

Modeling development process of skill-based system for human-like manipulation robot

The importance of system integration is widely recognized in robotics. This motivates the application of Model-Based Systems Engineering (MBSE) approaches to improve the development process of robot systems. This paper models a development process to achieve given task goals using a human-like upper body robot based on MBSE approach. For this purpose, we focus on the domain knowledge of tasks and skills in robotics. Since MBSE is a general methodology, there is a lot of flexibility on the way of proceeding with the analysis and design, and how to utilize models there. Using the concept of tasks and skills is helpful for better uderstanding of the development process. Our process is based on three main concepts: (1) stakeholders of User and Developer, (2) coordination between User and Developer using skills as communication interface, (3) extension development. Making the process explicit helps many stakeholders such as robot makers, system integrators, and engineers in various application domains to join the system development. It is also effective for accumulating experiences and work products of the development. In addition, we can expect that better understanding of the engineering process results in the improvement of the process performed by automation tools and humans cooperatively.     

面向人工智能和大数据的高效能计算

【目的】本文主要分析人工智能和大数据应用随着迅速增大的数据规模,给计算机系统带来的主要挑战,并针对计算机系统的发展趋势给出了一些面向人工智能和大数据亟待解决的高效能计算的若干研究方向。【文献范围】本文广泛查阅国内外在超级计算和高性能计算平台进行大数据和人工智能计算的最新研究成果及解决的挑战性问题。【方法】大数据既为人工智能提供了日益丰富的训练数据集合,但也给计算机系统的算力提出了更高的要求。近年来我国超级计算机处于世界的前列,为大数据和人工智能的大规模应用提供了强有力的计算平台支撑。【结果】而目前以超级计算机为代表的高性能计算平台大多采用CPU+加速器构成的异构并行计算系统,其数量众多的计算核心能够为人工智能和大数据应用提供强大的计算能力。【局限性】由于体系结构复杂,在充分发挥计算能力和提高计算效率方面存在较大挑战。尤其针对有别于科学计算的人工智能和大数据领域,其并行计算效率的提升更为困难。【结论】因此需要从底层的资源管理、任务调度、以及基础算法设计、通信优化,到上层的模型并行化和并行编程等方面展开高效能计算的研究,全面提升人工智能和大数据应用在高性能计算平台上的计算能效。     

集群机器人研究综述

首先,给出了集群机器人的定义与基本特征,概括了相对于传统多机器人控制方法的优势.然后,总结了集群机器人的主要设计与分析方法.将集群机器人研究归纳为空间组织、集群导航、集群决策以及其他集群行为等4类,综述了各类别近十年的主要研究成果.最后,分析总结了当前集群机器人研究面临的挑战与关键科学问题,并对未来发展方向进行了展望.     

Cooperative Mobile Robotics: Antecedents and Directions

There has been increased research interest in systems composed of multiple autonomous mobile robots exhibiting cooperative behavior. Groups of mobile robots are constructed, with an aim to studying such issues as group architecture, resource conflict, origin of cooperation, learning, and geometric problems. As yet, few applications of cooperative robotics have been reported, and supporting theory is still in its formative stages. In this paper, we give a critical survey of existing works and discuss open problems in this field, emphasizing the various theoretical issues that arise in the study of cooperative robotics. We describe the intellectual heritages that have guided early research, as well as possible additions to the set of existing motivations.     

Integration framework for intelligent manufacturing processes

In this article, we describe a new approach to applying distributed artificial intelligence techniques to manufacturing processes. The construction of intelligent systems is one of the most important techniques among artificial intelligence research. Our goal is to develop an integrated intelligent system for real time manufacturing processes. An integrated intelligent system is a large knowledge integration environment that consists of several symbolic reasoning systems (expert systems) and numerical computation packages. These software programs are controlled by a meta-system which manages the selection, operation and communication of these programs. A meta-system can be implemented in different language environments and applied to many disciplines. This new architecture can serve as a universal configuration to develop high performance intelligent systems for many complicated industrial applications in real world domains.To whom all correspondence should be addressed.     

Knowledge acquisition for expert systems in accounting and financial problem domains

Since the mid-1980s, expert systems have been developed for a variety of problems in accounting and finance. The most commonly cited problems in developing these systems are the unavailability of the experts and knowledge engineers and difficulties with the rule extraction process. Within the field of artificial intelligence, this has been called the ‘knowledge acquisition’ (KA) problem and has been identified as a major bottleneck in the expert system development process. Recent empirical research reveals that certain KA techniques are significantly more efficient than others in helping to extract certain types of knowledge within specific problem domains. This paper presents a mapping between these empirical studies and a generic taxonomy of expert system problem domains. To accomplish this, we first examine the range of problem domains and suggest a mapping of accounting and finance tasks to a generic problem domain taxonomy. We then identify and describe the most prominent KA techniques employed in developing expert systems in accounting and finance. After examining and summarizing the existing empirical KA work, we conclude by showing how the empirical KA research in the various problem domains can be used to provide guidance to developers of expert systems in the fields of accounting and finance.     

Component Specifications for Robotics Integration

Robotics researchers have been unable to capitalize easily on existing software components to speed up their development efforts and maximize their system's capabilities. A component-based approach for building the software for robotics systems can provide reuse and sharing abilities to the research community. The software engineering community has been studying reuse techniques for three decades. We present several results from those efforts that are applicable to the robotics software integration problem. We describe how to specify a software component so that a potential user may understand its capabilities and facilitate its application to his or her system. At the National Institute of Standards and Technology, we have developed a three-stage, component-specification approach. We illustrate this approach for a component that is relevant to robotics.     

Structure evolving systems and control in integrated design

Existing methods in Systems and Control deal predominantly with Fixed Systems, that have been designed in the past, and for which the control design has to be performed. The new paradigm of Structure Evolving Systems (SES), expresses a new form of system complexity where the components, interconnection topology, measurement-actuation schemes may not be fixed, the control scheme also may vary within the system-lifecycle and different views of the system of varying complexity may be required by the designer. Such systems emerge in many application domains and in the engineering context in problems such as integrated system design, integrated operations, re-engineering, lifecycle design issues, networks, etc. The paper focuses on the Integrated Engineering Design (IED), which is revealed as a typical structure evolution process that is strongly linked to Control Theory and Design type problems. It is shown, that the formation of the system, which is finally used for control design evolves during the earlier design stages and that process synthesis and overall instrumentation are critical stages of this evolutionary process that shapes the final system structure and thus the potential for control design. The paper aims at revealing the control theory context of the evolutionary mechanism in overall system design by defining a number of generic clusters of system structure evolution problems and by establishing links with existing areas of control theory. Different aspects of model evolution during the overall design are identified which include cases such as: (i) Time-dependent evolution of system models from “early” to “late” stages of design. (ii) Design stage-dependent evolution from conceptualisation to process synthesis and to overall instrumentation. (iii) Redesign of given systems and constrained system evolution. Within each cluster a number of well defined new Control Theory problems are introduced, which may be studied within the structural methodologies framework of Linear Systems. The problems posed have a general systems character, but the emphasis here is on Linear Systems; an overview of relevant results is given and links with existing research topics are established. The paper defines the Structural Control Theoretic context of an important family of complex systems emerging in engineering design and defines a new research agenda for structural methods of Control Theory. Copyright ©2002 IFAC     

A cognitivist model for decision support: COGITA project, a problem formulation assistant

The formulation of a problem may be defined as a process of acquisition and organization of knowledge related to a given situation, on which a decision maker projects some action. The assistance in the problem formulation that we may expect within decision support systems is difficult to design and to implement. This is mainly due to the frequent lack of attention to a sufficiently formalized conceptual framework which would consider the decision with a more cognition sciences oriented approach. In the first part, we will present an instrumental model for the study of decision processes as an attempt to simulate the cognitive process of knowledge acquisition and organization carried out by a decision maker facing a problematic situation. Considering its epistemological foundations, this model can be named “cognitivist model”. Within this model, the decision is defined as a cognitive construction which we call “decisional construct”. It consists of the elaboration of one or several abstract representations of the problematic situation (formulation phase), and the design of operational models (solving phase). In the second part, we will present the COGITA project, which consists of the design and realization of an environment for the development of problem formulation assistance systems. The modelization and simulation of cognitive processes call for relevant techniques originating either in artificial intelligence or in connectionism. We will show which are the main characteristics, potentials, limits and complementarity of these techniques and why their integration is fundamental and necessary to the simulation of the cognitive process associated with the formulation. COGITA is a hybrid system currently under development which tends to integrate symbolic artificial intelligence techniques and connectionist models in a cooperative hybridation the general architecture of which is presented.     

人工智能软件系统的非功能属性及其质量保障方法综述

随着神经网络等技术的快速发展,人工智能被越来越多地应用到安全关键或任务关键系统中,例如汽车自动驾驶系统、疾病诊断系统和恶意软件检测系统等.由于缺乏对人工智能软件系统全面和深入的了解,导致系统时常发生严重错误.人工智能软件系统的功能属性和非功能属性被提出以加强对人工智能软件系统的充分认识和质量保障.经调研,有大量研究者致力于功能属性的研究,但人们越来越关注于人工智能软件系统的非功能属性.为此,专注于人工智能软件系统的非功能属性,调研了138篇相关领域的论文,从属性定义、属性必要性、属性示例和常见质量保障方法几个方面对目前已有的研究工作进行系统的梳理和详细的总结,同时重新定义和分析了非功能属性之间的关系并介绍了人工智能软件系统研究中可以用到的开源工具.最后,展望了人工智能软件系统非功能属性的未来研究方向和挑战,以期为该领域的研究人员提供参考.     

Using the cassiopeia method to design a robot soccer team

We have defined the Cassiopeia method, whose specificity is to focus the analysis and design of a multiagent system on the notion of organization. This article reports the use of this methodological framework for designing and implementing the organization of a robot soccer team in the context of a research project on collective robotics. We show why we chose this application, and we discuss its interest and inherent difficulties, in order to clearly express the needs for a design methodology dedicated to distributed artificial intelligence.     

Integration and control of intelligence in distributed manufacturing

The area of intelligent systems has generated a considerable amount of interest—occasionally verging on controversy—within both the research community and the industrial sector. This paper aims to present a unified framework for integrating the methods and techniques related to intelligent systems in the context of design and control of modern manufacturing systems. Particular emphasis is placed on the methodologies relevant to distributed processing over the Internet. Following presentation of a spectrum of intelligent techniques, a framework for integrated analysis of these techniques at different levels in the context of intelligent manufacturing systems is discussed. Integration of methods of artificial intelligence is investigated primarily along two dimensions: the manufacturing product life-cycle dimension, and the organizational complexity dimension. It is shown that at different stages of the product life-cycle, different intelligent and knowledge-oriented techniques are used, mainly because of the varied levels of complexity associated with those stages. Distribution of the system architecture or system control is the most important factor in terms of demanding the use of the most up-to-date distributed intelligence technologies. A tool set for web-enabled design of distributed intelligent systems is presented. Finally, the issue of intelligence control is addressed. It is argued that the dominant criterion according to which the level of intelligence is selected in technological tasks is the required precision of the resulting operation, related to the degree of generalization required by the particular task. The control of knowledge in higher-level tasks has to be executed with a strong involvement of the human component in the feedback loop. In order to facilitate the human intervention, there is a need for readily available, user-transparent computing and telecommunications infrastructure. In its final part, the paper discusses currently emerging ubiquitous systems, which combine this type of infrastructure with new intelligent control systems based on a multi-sensory perception of the state of the controlled process and its environment to give us tools to manage information in a way that would be most natural and easy for the human operator.