Human Responsibility for Autonomous Agents

Automated or autonomous systems can sometimes fail harmlessly, but they can also destroy data, compromise privacy, and consume resources, such as bandwidth or server capacity. What's more troubling is that automated systems embedded in vital systems can cause financial losses, destruction of property, and loss of life. Controlling these dangers will increase trust while enabling broader use of these systems with higher degrees of safety. Obvious threats stem from design errors and software bugs, but we can't overlook mistaken assumptions by designers, unanticipated actions by humans, and interference from other computerized systems. This article is part of a special issue on Interacting with Autonomy.     

Guest Editors' Introduction: Pervasive Computing in Healthcare

Pervasive computing has great potential to improve healthcare, from enriching data collection and distribution to virtually bringing experts to an emergency site. This special issue samples this developing area through five theme articles that go beyond current applications to find a wider range of applicability. This article is part of a special issue on Healthcare.     

Designing with Care: The Future of Pervasive Healthcare

Humane care—which is an important design paradigm relevant for pervasive healthcare—means designing systems with care, keeping in mind both users and other stakeholders. Understanding human values is a key factor in creating any successful healthcare application and is essential to avoid dehumanizing and stigmatizing users. By considering human values, designers and developers can create pervasive healthcare applications that better fit users' needs and desires. The Designing with Care 09 workshop aimed to bring together researchers, designers, and practitioners to share their experiences with incorporating values into the design of pervasive healthcare systems and to help understand the sensitive issues involved in designing for healthcare. Based on the findings from the workshop, the present state of the art is discussed, and a research agenda is presented.     

智能机器人的自适应自主Agents的建模

在问题求解期间及穿越动态的、不可预测的环境的过程中 ,真实世界的问题需要自适应的求解方法来‘裁剪’Agent的行为 ,并使其落入任务域 ,否则不完备的知识、不确定性、不确定的Agents及过程的存在、硬件失灵和不精确性都会引发不确定事件的发生。自适应自主Agents是一种存在于动态的、不可预测的环境中 ,并试图满足一系列随时间变化的目标或动机的系统 ,而且此类Agents在处理这些目标的过程中 ,能基于已有的经验改进其能力。自适应自主Agents为智能机器人实现这一目标提供了一种新的途径。主要讨论了智能机器人的自适应自主Agents的建模问题 ,并指出它的局限性和开问题     

Real-Time Search for Autonomous Agents and Multiagent Systems

Since real-time search provides an attractive framework for resource-bounded problem solving, this paper extends the framework for autonomous agents and for a multiagent world. To adaptively control search processes, we propose -search which allows suboptimal solutions with error, and -search which balances the tradeoff between exploration and exploitation. We then consider search in uncertain situations, where the goal may change during the course of the search, and propose a moving target search (MTS) algorithm. We also investigate real-time bidirectional search (RTBS) algorithms, where two problem solvers cooperatively achieve a shared goal. Finally, we introduce a new problem solving paradigm, called organizational problem solving, for multiagent systems.     

Creating Real-Time Embodied Autonomous Agents

A challenging research area for computer graphics and virtual environments (VE) is training interpersonal interactions. In such a system, at least one person is the VE participant, while several more virtual human agents (represented by human-like, embodied models) are engaged in activities in the same virtual space. The participants, whether live or virtual, should interact as if all were real. This means that the virtual agents must have several characteristics afforded to real people, including the following:     

自主体的创现行为

创现行为是人工生命系统研究的关键目标之一．作为组成人工生命系统的个体，本文研究了自主体创现行为实现的方法．文中以二维平面环境内的自主体为例，探讨了自主体的行为学习和行为选择机制，并给出了创现行为的实验结果．     

Privacy-Aware Collaborative Spam Filtering

While the concept of collaboration provides a natural defense against massive spam e-mails directed at large numbers of recipients, designing effective collaborative anti-spam systems raises several important research challenges. First and foremost, since e-mails may contain confidential information, any collaborative anti-spam approach has to guarantee strong privacy protection to the participating entities. Second, the continuously evolving nature of spam demands the collaborative techniques to be resilient to various kinds of camouflage attacks. Third, the collaboration has to be lightweight, efficient, and scalable. Toward addressing these challenges, this paper presents ALPACAS-a privacy-aware framework for collaborative spam filtering. In designing the ALPACAS framework, we make two unique contributions. The first is a feature-preserving message transformation technique that is highly resilient against the latest kinds of spam attacks. The second is a privacy-preserving protocol that provides enhanced privacy guarantees to the participating entities. Our experimental results conducted on a real e-mail data set shows that the proposed framework provides a 10 fold improvement in the false negative rate over the Bayesian-based Bogofilter when faced with one of the recent kinds of spam attacks. Further, the privacy breaches are extremely rare. This demonstrates the strong privacy protection provided by the ALPACAS system.     

Games That Agents Play: A Formal Framework for Dialogues between Autonomous Agents

We present a logic-based formalism for modeling ofdialogues between intelligent and autonomous software agents,building on a theory of abstract dialogue games which we present.The formalism enables representation of complex dialogues assequences of moves in a combination of dialogue games, and allowsdialogues to be embedded inside one another. The formalism iscomputational and its modular nature enables different types ofdialogues to be represented.     

Autonomous Adaptive Agents for Single Seller Sealed Bid Auctions

In developing open, heterogeneous and distributed multi-agent systems researchers often face a problem of facilitating negotiation and bargaining amongst agents. It is increasingly common to use auction mechanisms for negotiation in multi-agent systems. The choice of auction mechanism and the bidding strategy of an agent are of central importance to the success of the agent model. Our aim is to determine the best agent learning algorithm for bidding in a variety of single seller auction structures in both static environments where a known optimal strategy exists and in complex environments where the optimal strategy may be constantly changing. In this paper we present a model of single seller auctions and describe three adaptive agent algorithms to learn strategies through repeated competition. We experiment in a range of auction environments of increasing complexity to determine how well each agent performs, in relation to an optimal strategy in cases where one can be deduced, or in relation to each other in other cases. We find that, with a uniform value distribution, a purely reactive agent based on Cliff’s ZIP algorithm for continuous double auctions (CDA) performs well, although is outperformed in some cases by a memory based agent based on the Gjerstad Dickhaut agent for CDA.     

An Efficient and Flexible Perception Pipeline for Autonomous Agents

Agents in virtual environments require a combination of perception and action to behave in an autonomous way. We extend a software architecture for the management of actions blending, called AGENTlib, with a perception mechanism. The perception system provides a uniform interface to various techniques in the field of virtual perception, including synthetic vision, database access and perception persistency. We describe the framework we designed to efficiently filter valuable information from the scene and we address concerns about computation redundancy and data propagation through multiple filtering modules.     

基于自主代理的入侵检测

文中分析了一般入侵检测系统在可配置性、可伸缩性和效率等方面的弱点，描述了自主代理技术在入侵检测的数据采集和数据分析方面的优势，介绍了一种基于自主代理的入侵检测方法及其实现部件，并提出了其存在的不足和几点改进意见     

Privacy-Aware Role-Based Access Control

A privacy-aware role-based access control model extends RBAC to express highly complex privacy-related policies, including consideration of such features as conditions and obligations. Because it's based on the RBAC model, the full-fledged P-RBAC solution is easy to deploy in systems already adopting RBAC, thus allowing seamless integration of access control and privacy policies.     

Multiresolution Motion Planning for Autonomous Agents via Wavelet-Based Cell Decompositions

We present a path- and motion-planning scheme that is "multiresolution" both in the sense of representing the environment with high accuracy only locally and in the sense of addressing the vehicle kinematic and dynamic constraints only locally. The proposed scheme uses rectangular multiresolution cell decompositions, efficiently generated using the wavelet transform. The wavelet transform is widely used in signal and image processing, with emerging applications in autonomous sensing and perception systems. The proposed motion planner enables the simultaneous use of the wavelet transform in both the perception and in the motion-planning layers of vehicle autonomy, thus potentially reducing online computations. We rigorously prove the completeness of the proposed path-planning scheme, and we provide numerical simulation results to illustrate its efficacy.     

基于多自主智能体的群体动画创作

群体动画一直是计算机动画界一个具有挑战性的研究方向,提出了一个基于多自主智能体的群体动画创作框架：群体中的各角色作为自主智能体,能感知环境信息,产生意图,规划行为,最后通过运动系统产生运动来完成行为和实现意图,与传统的角色运动生成机理不同,首先采用运动捕获系统建立基本运动库,然后通过运动编辑技术对基本运动进行处理以最终得到角色运动,应用本技术,动画师只需“拍摄”角色群体的运动就能创作群体动画,极大地提高了制作效率。     

自治Agents的面向服务的协商模型

提出了一个基于自治Agents的面向服务的协商模型。模型主要包括两大模块：首先定义了一系列的战略和战术过程，使得Agents可以产生初始建议，评价对方的建议，以及在此基础上做出反建议；其次，定义了两个层次的Agent通信机制。二者相辅相成，实现了Agents间合作的动态形成和随机协调，使得Agents可以承担因环境的不确定性而需动态协作的复杂任务。     

Autonomous Agents that Learn to Better Coordinate

A fundamental difficulty faced by groups of agents that work together is how to efficiently coordinate their efforts. This coordination problem is both ubiquitous and challenging, especially in environments where autonomous agents are motivated by personal goals.Previous AI research on coordination has developed techniques that allow agents to act efficiently from the outset based on common built-in knowledge or to learn to act efficiently when the agents are not autonomous. The research described in this paper builds on those efforts by developing distributed learning techniques that improve coordination among autonomous agents.The techniques presented in this work encompass agents who are heterogeneous, who do not have complete built-in common knowledge, and who cannot coordinate solely by observation. An agent learns from her experiences so that her future behavior more accurately reflects what works (or does not work) in practice. Each agent stores past successes (both planned and unplanned) in their individual casebase. Entries in a casebase are represented as coordinated procedures and are organized around learned expectations about other agents.It is a novel approach for individuals to learn procedures as a means for the group to coordinate more efficiently. Empirical results validate the utility of this approach. Whether or not the agents have initial expertise in solving coordination problems, the distributed learning of the individual agents significantly improves the overall performance of the community, including reducing planning and communication costs.     

QUIET: A Methodology for Autonomous Software Deployment using Mobile Agents

Every software setup has an installation wizard that helps the user to install/un-install the software on PCs. Typically user interaction is required and the process cannot proceed without user input. Silent Unattended Installation Package Manager (SUIPM) automates the process of software installation/un-installation and can be used to deploy any software silently without user interaction. In this paper, we have proposed A Methodology for Autonomous Software Deployment using Mobile Agents, which deploys silent unattended installation/un-installation packages efficiently and smartly on networks without user interaction or intervention, suitable for network of networks, commonly known as CAN (campus area network). The system once initialized is fully autonomous and deployment of the software(s) is performed efficiently and autonomously with the help of mobile agents. We have evaluated this architecture on the university campus having 7 laboratories equipped with 20–300 PCs in various laboratories. Results are very promising and support the implementation of the solution.