Designing intelligent agents to support long-term partnership in two echelon e-Supply Networks

Realizing the dynamic nature of information flow and the conflicting objectives of members play vital role in effective design of e-Supply Networks (e-SN). While there are some research in the SN literature proposing different dynamic and intelligent coordination mechanisms, the impact of the proper definition of data structure and long-term relationship in modeling both coordination and negotiation mechanisms have not been addressed deeply. In this paper, we propose three overlapping services including intelligent matching of partners, proposal generations, and long-term contract management. The process begins with the selection of qualified partners based on the similarity of users profiles in a multidimensional space defined by network attributes. Then, a coordination mechanism for long-term agreements is proposed such that the generated proposals in e-SN encourage buyers to reveal their demand in advance. The proposed mechanism introduces the importance of strategic buyers for suppliers in modeling and decision making process. To illustrate the model efficiency, a prototype system has been modeled and is compared to the traditional tendering mechanism. The validation results confirm the model efficiency in providing long-term decisions in a dynamic environment.     

On the design of intelligent robotic agents for assembly

Robotic agents can greatly be benefited from the integration of perceptual learning in order to monitor and adapt to changing environments. To be effective in complex unstructured environments, robots have to perceive the environment and adapt accordingly. In this paper it is discussed a biology inspired approach based on the adaptive resonance theory (ART) and implemented on an KUKA KR15 industrial robot during real-world operations (e.g. assembly operations). The approach intends to embed naturally the skill learning capability during manufacturing operations (i.e., within a flexible manufacturing system).The integration of machine vision and force sensing has been useful to demonstrate the usefulness of the cognitive architecture to acquire knowledge and to effectively use it to improve its behaviour. Practical results are presented, showing that the robot is able to recognise a given component and to carry out the assembly. Adaptability is validated by using different component geometry during assemblies and also through skill learning which is shown by the robot’s dexterity.     

On the design of coordination diagnosis algorithms for teams of situated agents

Teamwork demands agreement among team-members in order to collaborate and coordinate effectively. When a disagreement between teammates occurs (due to failures), team-members should ideally diagnose its causes, to resolve the disagreement. Such diagnosis of social failures can be expensive in communication and computation, challenges which previous work has not addressed. We present a novel design space of diagnosis algorithms, distinguishing several phases in the diagnosis process, and providing alternative algorithms for each phase. We then combine these algorithms in different ways to empirically explore specific design choices in a complex domain, on thousands of failure cases. The results show that different phases of diagnosis affect communication and computation overhead. In particular, centralizing the diagnosis disambiguation process is a key factor in reducing communications, while runtime is affected mainly by the amount of reasoning about other agents. These results contrast with previous work in disagreement detection (without diagnosis), in which distributed algorithms reduce communications.     

基于神经网络的改进行为协调控制及其在智能轮椅路径规划中的应用

针对传统的基于行为的智能轮椅的路径规划方法在室外非结构环境下的路径规划效果差的问题,提出一种新的智能轮椅的路径规划算法.该算法利用模糊逻辑设计了基本控制行为,并在此基础上结合大量实际经验使用神经网络设计了行为协调控制器.改进的算法将仲裁机制和命令融合机制2种行为协调方法有效结合起来,并吸收了这2种行为协调方法的优点,从而改善了系统的反应速度,极大提高了控制精确;另一方面,该算法还可以识别陷阱区域并通过自主改变行为的权重方法控制轮椅逃出陷阱区域,因而具备了较强的人工智能特征.仿真和实物实验验证了该算法智能性高且实现简单,适用于室外非结构化环境下的机器人路径规划.     

INDU网络对于战场动态协同的支持

为了在多维战场上赢得胜利．我军必须做到诸作战单元之间的精确协同。本文分析了战场上动态协同的各种情况，描述了战斗动作间的时态依赖和逻辑依赖，介绍了区间代数的扩展—INDU网络，并利用它来支持战场上的动态协同。     

Agent-based web service for the design of a dynamic coordination mechanism in supply networks

The theory of network coordination presents an effective approach to improve the business processes within supply networks. The automation of the negotiation process among buyers and suppliers has become an important policy in the transactional networks. This leads to assessing the roles of both quantifiable and non-quantifiable parameters in coordination mechanisms with the aim of achieving higher performance. Here, we develop an e-based supply chain multi-agent model for the design of mass-customized on-line services. The model addresses the bullwhip effect in multi-stage supply chain and also clarifies the evaluation of inventory policies in various supply and demand uncertainties. To illustrate the feasibility of the approach, we implement a prototype system and evaluate its performance by simulation using Colored Petri Nets (CPNs). The validation results reveal the model efficiency in providing a more realistic optimization process that takes the dynamic information flow in uncertainty environments into consideration.     

智能网络磁盘通信协议研究与设计*

智能网络磁盘(IND)是一种基于ARM uClinux的新型网络存储结构,它具有成本低、易管理、高可靠性、可扩展性等优点.探讨了IND系统结构,并在此基础上分析和研究了IND实现TCP/IP协议的若干问题.提出了一种实现方案,在实际局域网运行中取得了较理想的效果.     

Artificial neural network based approach for dynamic parameter design

The Taguchi parameter design method has been recognized as an important tool for improving the quality of a product or a process. However, the statistical methods and optimization procedures proposed by Taguchi have much room for improvement. For instance, the two-step procedure proposed by Taguchi may fail to identify an optimum design condition if an adjustment parameter does not exist, the optimal setting of a design parameter is determined only among the levels included in the parameter design experiment, and, for the dynamic parameter design, the signal parameter is assumed to follow a uniform rather than a general distribution. This paper develops an artificial neural network based dynamic parameter design approach to overcome the shortcomings of the Taguchi and existing alternative approaches. First, an artificial neural network is trained to map the relationship between the characteristic, design, noise and signal parameters. Second, Latin hypercube samples of the signal and noise parameters are obtained and used to estimate the slope between the signal parameter and characteristic as well as the variance of the characteristic at each set of design parameter settings. Then, the dynamic parameter design problem is formulated as a nonlinear optimization problem and solved to find the optimal settings of the design parameters using sequential quadratic programming. The effectiveness of the proposed approach is illustrated with an example.     

Designs for explaining intelligent agents

Explanation is an important capability for usable intelligent systems, including intelligent agents and cognitive models embedded within simulations and other decision support systems. Explanation facilities help users understand how and why an intelligent system possesses a given structure and set of behaviors. Prior research has resulted in a number of approaches to provide explanation capabilities and identified some significant challenges. We describe designs that can be reused to create intelligent agents capable of explaining themselves. The designs include ways to provide ontological, mechanistic, and operational explanations. These designs inscribe lessons learned from prior research and provide guidance for incorporating explanation facilities into intelligent systems. The designs are derived from both prior research on explanation tool design and from the empirical study reported here on the questions users ask when working with an intelligent system. We demonstrate the use of these designs through examples implemented using the Herbal high-level cognitive modeling language. These designs can help build better agents—they support creating more usable and more affordable intelligent agents by encapsulating prior knowledge about how to generate explanations in concise representations that can be instantiated or adapted by agent developers.     

Preliminary design and manufacturing planning integration using web-based intelligent agents

Software agents have been increasingly used in the product and process development in industry over the past years due to the rapid evolvement of the Internet technology. This paper describes agents for the integration of conceptual design and process planning. Agents provide mechanisms to interact with each other. This mechanism is important since both of those processes involve negotiations for optimization. A set of design and planning software agents has been developed. These agents are used in a computer-based collaborative environment, called a multi-agent platform. The main purpose of developing such a platform is to support product preliminary design, optimize product form and structure, and reduce the manufacturing cost in the early design stage. The agents on the platform have access to a knowledge base that contains design and planning rules. These rules are derived from an analysis of design factors that influence process and resource planning, such as product material, form, shape complexity, features, dimension, tolerance, surface condition, production volume, and production rate. These rules are used by process planning agents to provide process planners with information regarding selecting preliminary manufacturing processes, determining manufacturing resources, and constructing feedback information to product designers. Additionally, the agents communicate with WEB servers, and they are accessible by users through Internet browsers. During performing design and planning tasks, agents access the data pertinent to design and manufacturing processes by the programming interfaces of existing computer-aided design (CAD) and manufacturing system. The agents are supported by a developed prototype agent platform. The agents and the platform enable the information exchange among agents, based on a previously developed integrated design and manufacturing process object model.     

Xml dataspaces for the coordination of internet agents

This article presents MARS-X, a programmable coordination architecture for autonomous and mobile Internet agents. In MARS-X, mobile Internet agents coordinate through programmable XML dataspaces, accessed by agents in a Linda-like fashion. Therefore, MARS-X enforces open and uncoupled interactions and, via XML, it offers a high degree of standard interoperability. These properties suit very well the characteristics of both mobile Internet agents and the Internet environment itself. In addition, coordination in MARS-X is made more flexible and secure by the capability of programming the behavior of the XML dataspaces by reaction to the agents' accesses. An application example related to the management of on-line academic courses shows the suitability and effectiveness of the MARS-X architecture.     

Modeling the dynamic interactions of agents in the provision of network infrastructure

Although next-generation information network infrastructure is prerequisite for continued economic growth, the United States is losing ground in important areas relative to peer countries. Businesses and regulators have grown concerned that the U.S. lacks the correct regulatory and business incentives to upgrade the existing network. Due to the complex and dynamic nature of the interdependencies in the ICT value network, traditional methods of public policy and management analysis have proven inadequate to fully understand the issues and possible solutions. This paper discusses a novel Genetic Programming (GP) approach to the problem. Although only a first step towards addressing the problem, the GP discovered several interesting results stemming from the complex interactions. For example, telecommunications companies would actually be hurt by the option to charge discriminatory prices but application providers would benefit.     

MARS: a programmable coordination architecture for mobile agents

Mobile agents offer much promise, but agent mobility and Internet openness make coordination more difficult. Mobile Agent Reactive Spaces (MARS), a Linda-like coordination architecture with programming features, can handle a heterogeneous network while still allowing simple and flexible application design     

Defining new markets for intelligent agents

Most agent applications are fairly straightforward: access a Web site, fetch material; in short, perform a simple fixed mission. Others do more personalized tasks such as filtering e-mail or updating legacy systems. From a programming viewpoint, agents are simply active objects that have been defined to simulate parts of a model. Agent based modeling and simulation then become a natural extension of the object oriented paradigm. Simulations of events that involve these kinds of agents (known as actors or demons) have assisted human decision making for decades in batch manufacturing, transportation, and logistics, for example. But work in complex adaptive systems (CAS) may be defining a new kind of agent: one that can actually evolve over time in response to its environment. The beginnings of these adaptive systems are already evident in more advanced agents, which can do simple negotiations on a user's behalf to secure goods and services in an auction, for example. The challenge now is to see how agents bargain and learn in a more complex environment. The Electric Power Research Institute (EPRI), for example, has funded research into agent based auctioning as a way to address the fierce competition for resources. As electric power marketers become available, wholesale electric customers are learning to shop around for the best suppliers. Like agents that represent individual human users, the agents bargaining on behalf of these suppliers and wholesalers decide things like how much to buy, which agent to buy from, how much to pay, and how to manage the exchange of power and money     

Socially intelligent reasoning for autonomous agents

Socially intelligent agents are autonomous problem solvers that have to achieve their objectives by interacting with other similarly autonomous entities. A major concern, therefore, is with the design of the decision-making mechanism that such agents employ in order to determine which actions to take to achieve their goals. We propose a framework for making socially acceptable decisions, based on social welfare functions, that combines social and individual perspectives in a unified and flexible manner. The framework is realized in an exemplar computational setting and an empirical analysis is made of the relative performance of varying sociable decision-making functions in a range of environments. This analysis is then used to design an agent that adapts its decision-making to reflect the resource constraints that it faces at any given time. A further round of empirical evaluation shows how adding such a meta-level mechanism enhances the performance of the agent by directing reasoning to adopt different strategies in different contexts. Finally, the possibility and efficacy of making the metalevel mechanism adaptive, so that experience of past encounters can be factored into the decision-making, is demonstrated     

A sub-optimal algorithm to synthesize control laws for a network of dynamic agents

We study the synthesis problem of a linear quadratic regulator (LQR) controller when the matrix describing the control law is constrained to lie in a particular vector space. Our motivation is the use of such control laws to stabilize networks of autonomous agents in decentralized fashion, with the information flow being dictated by the constraints of a pre-specified topology. In this paper, we consider the finite-horizon version of the problem and provide both a computationally intensive optimal solution and a sub-optimal solution that is computationally more tractable. Then we apply the technique to the decentralized vehicle formation control problem. It is numerically illustrated that while the loss in performance due to the use of the sub-optimal solution is not huge, the topology can have a large effect on performance.     

Open ended intelligence: the individuation of intelligent agents

Artificial general intelligence is a field of research aiming to distil the principles of intelligence that operate independently of a specific problem domain and utilise these principles in order to synthesise systems capable of performing any intellectual task a human being is capable of and beyond. While “narrow” artificial intelligence which focuses on solving specific problems such as speech recognition, text comprehension, visual pattern recognition and robotic motion has shown impressive breakthroughs lately, understanding general intelligence remains elusive. We propose a paradigm shift from intelligence perceived as a competence of individual agents defined in relation to an a priori given problem domain or a goal, to intelligence perceived as a formative process of self-organisation. We call this process open-ended intelligence. Starting with a brief introduction of the current conceptual approach, we expose a number of serious limitations that are traced back to the ontological roots of the concept of intelligence. Open-ended intelligence is then developed as an abstraction of the process of human cognitive development, so its application can be extended to general agents and systems. We introduce and discuss three facets of the idea: the philosophical concept of individuation, sense-making and the individuation of general cognitive agents. We further show how open-ended intelligence can be framed in terms of a distributed, self-organising network of interacting elements and how such process is scalable. The framework highlights an important relation between coordination and intelligence and a new understanding of values.     

Optimization of parameter design: An intelligent approach using neural network and simulated annealing

Parameter design optimization problems have found extensive industrial applications, including product development, process design and operational condition setting. The parameter design optimization problems are complex because non-linear relationships and interactions may occur among parameters. To resolve such problems, engineers commonly employ the Taguchi method. However, the Taguchi method has some limitations in practice. Therefore, in this work, we present a novel means of improving the effectiveness of the optimization of parameter design. The proposed approach employs the neural network and simulated annealing, and consists of two phases. Phase 1 formulates an objective function for a problem using a neural network method to predict the value of the response for a given parameter setting. Phase 2 applies the simulated annealing algorithm to search for the optimal parameter combination. A numerical example demonstrates the effectiveness of the proposed approach.     

卷烟厂智能计算机网络控制系统的设计

智能计算机网络控制系统在烟草行业的应用已经开始，针对烟草行业生产的特殊性，本文结合烟厂工程的设计实践，就智能计算机网络控制系统设计中涉及的设计原则、系统组成、方案确定和设备选型进行阐述，谈谈自己设计中的体会和看法。