A framework for cooperative work: An approach based on the intentionality

The aim of this work is to elaborate rational interaction between intelligent systems, particularly when these systems have to resolve together a given task.Firstly, inherent problems of distributed problem solving are discussed. In the centre of these problems emerges on one hand, the difficulty in building an organizational structure and its dynamic for cooperative intelligent systems, and on the other hand the difficulty for the intelligent systems to know what is their degree of cooperation and what is their information exchange policy.To resolve these problems, the first part of this paper explores basic principles governing the rational balance among an agent's beliefs, actions, and intentions. Then, the second part treats the planning in the multi-agent environment. In this case, a plan is not considered as a sequence of actions executed by an agent in order to achieve his goal, but as a mental frame including his beliefs, his commitments, and his intentions. Then this planning method serves as rational interaction between intelligent systems in which the communicative acts expressed in formal language take place. Finally, the formulation of cooperative strategies between intelligent systems complete this work. These strategies are simulated and valued in the concrete environment of air traffic control.     

Cross‐platform management of intelligent objects behaviors in serious virtual environments

In this paper, we present a generic interaction framework that controls intelligent objects' actions in different virtual world (VW) platforms. These actions are based on the state of external platform‐independent artificial intelligence‐based systems such as multi‐agent and rule‐based systems. We have evaluated the proposed framework by means of two intelligent objects, a door and a noticeboard, incorporating them in Second Life and OpenWonderland VWs. These objects allow to work along three advanced aspects of a serious virtual environment: it is a dynamic space where participants are synchronously informed about activities evolution inside the virtual space, it can integrate processes and information coming from the real world, and it needs norms to organize participants actions, to define actions consequences, and to prevent undesired participants behaviors. Copyright © 2011 John Wiley & Sons, Ltd.     

Using planning techniques in intelligent tutoring systems

This paper proposes an architecture for building better Computer-Assisted Instruction (CAI) programs by applying and extending Artificial Intelligence (AI) techniques which were developed for planning and controlling the actions of robots. A detailed example shows how programs built according to this architecture are able to plan global teaching strategies using local information. Since the student's behavior can never be accurately predicted, the pre-planned teaching strategies may be foiled by sudden surprises and obstacles. In such cases, the planning component of the program is dynamically reinvoked to revise the unsuccessful strategy, often by recognizing student misconceptions and planning a means to correct them. This plan-based teaching strategy scheme makes use of global course knowledge in a flexible way that avoids the rigidity of earlier CAI systems. It also allows larger courses to be built than has been possible in most AI-based “intelligent tutoring systems” (ITSs), which seldom address the problem of global teaching strategies.     

Autonomous construction using scarce resources in unknown environments

The goal of creating machines that autonomously perform useful work in a safe, robust and intelligent manner continues to motivate robotics research. Achieving this autonomy requires capabilities for understanding the environment, physically interacting with it, predicting the outcomes of actions and reasoning with this knowledge. Such intelligent physical interaction was at the centre of early robotic investigations and remains an open topic. In this paper, we build on the fruit of decades of research to explore further this question in the context of autonomous construction in unknown environments with scarce resources. Our scenario involves a miniature mobile robot that autonomously maps an environment and uses cubes to bridge ditches and build vertical structures according to high-level goals given by a human. Based on a “real but contrived” experimental design, our results encompass practical insights for future applications that also need to integrate complex behaviours under hardware constraints, and shed light on the broader question of the capabilities required for intelligent physical interaction with the real world.     

Self-organization based on nonlinear nonequilibrium. Dynamics of autonomous agents

This paper discusses a study on the mechanism of self-organization. A global order is organized by the simple and locally coordinated actions of autonomous agents using only local information, so complex or globally coordinated actions which use global communication and high-level strategies are not necessary. The fundamental factors for establishing a global order using self-organization are a “dissipative structure,” an “autocatalysis mechanism,” and “intentional fluctuations.” If an environment where there are agents has a dissipative structure and those agents have some sort of autocatalysis and intentional fluctuation mechanisms within themselves, it is possible to form a global order for them using only their simple and locally coordinated actions. “The blind-hunger dilemma” is used as an example to simulate the self-organization and coordinated actions of agents. In this simulation environment, there are many ant-like agents which must get energy. However, there is only one small energy supply base, so either an efficient method or the coordinated actions of agents is needed. As a result, the agents using our approach could move and get energy more efficiently than agents using conventional coordination mechanisms involving global communication and high-level strategies. Real World Computing Partnership This work was presented, in part, at the Second International Symposium on Artificial Life and Robotics, Oita, Japan, February 18–20, 1997     

Using schedulers to test probabilistic distributed systems

Formal methods are one of the most important approaches to increasing the confidence in the correctness of software systems. A formal specification can be used as an oracle in testing since one can determine whether an observed behaviour is allowed by the specification. This is an important feature of formal testing: behaviours of the system observed in testing are compared with the specification and ideally this comparison is automated. In this paper we study a formal testing framework to deal with systems that interact with their environment at physically distributed interfaces, called ports, and where choices between different possibilities are probabilistically quantified. Building on previous work, we introduce two families of schedulers to resolve nondeterministic choices among different actions of the system. The first type of schedulers, which we call global schedulers, resolves nondeterministic choices by representing the environment as a single global scheduler. The second type, which we call localised schedulers, models the environment as a set of schedulers with there being one scheduler for each port. We formally define the application of schedulers to systems and provide and study different implementation relations in this setting.     

Rosen's modelling relations via categorical adjunctions

Rosen's modelling relations constitute a conceptual schema for the understanding of the bidirectional process of correspondence between natural systems and formal symbolic systems. The notion of formal systems used in this study refers to information structures constructed as algebraic rings of observable attributes of natural systems, in which the notion of observable signifies a physical attribute that, in principle, can be measured. Due to the fact that modelling relations are bidirectional by construction, they admit a precise categorical formulation in terms of the category-theoretic syntactic language of adjoint functors, representing the inverse processes of information encoding/decoding via adjunctions. As an application, we construct a topological modelling schema of complex systems. The crucial distinguishing requirement between simple and complex systems in this schema is reflected with respect to their rings of observables by the property of global commutativity. The global information structure representing the behaviour of a complex system is modelled functorially in terms of its spectrum functor. An exact modelling relation is obtained by means of a complex encoding/decoding adjunction restricted to an equivalence between the category of complex information structures and the category of sheaves over a base category of partial or local information carriers equipped with an appropriate topology.     

Overview of multidatabase transaction management

A multidatabase system (MDBS) is a facility that allows users access to data located in multiple autonomous database management systems (DBMSs). In such a system,global transactions are executed under the control of the MDBS. Independently,local transactions are executed under the control of the local DBMSs. Each local DBMS integrated by the MDBS may employ a different transaction management scheme. In addition, each local DBMS has complete control over all transactions (global and local) executing at its site, including the ability to abort at any point any of the transactions executing at its site. Typically, no design or internal DBMS structure changes are allowed in order to accommodate the MDBS. Furthermore, the local DBMSs may not be aware of each other and, as a consequence, cannot coordinate their actions. Thus, traditional techniques for ensuring transaction atomicity and consistency in homogeneous distributed database systems may not be appropriate for an MDBS environment. The objective of this article is to provide a brief review of the most current work in the area of multidatabase transaction management. We first define the problem and argue that the multidatabase research will become increasingly important in the coming years. We then outline basic research issues in multidatabase transaction management and review recent results in the area. We conclude with a discussion of open problems and practical implications of this research.     

An intelligent agent-based collaborative information security framework

In this paper we proposed a framework for collaborative intelligent agents in a distributed environment to execute sound security strategies for protecting information resources. First, the intelligent agent-based Duty Reliable Center (DRC) in the model uses the group decision method to determine a global information threat level. With the threat level, local agent employs the Bayes’ decision procedure to calculate the expected loss of its all-possible actions, and then chooses an action among them with the minimum expected loss to protect its information resources. The proposed framework enables an agent to choose among alternatives in an optimal fashion, taking into account the worth of acquiring prior information to reduce uncertainty. Because system operations are distributed, hackers are unlikely to wreck the whole system. Thus, it is expected to yield information security cost-effective solutions.     

IVVI 2.0: An intelligent vehicle based on computational perception

This paper presents the IVVI 2.0 a smart research platform to foster intelligent systems in vehicles. Computational perception in intelligent transportation systems applications has advantages, such as huge data from vehicle environment, among others, so computer vision systems and laser scanners are the main devices that accomplish this task. Both have been integrated in our intelligent vehicle to develop cutting-edge applications to cope with perception difficulties, data processing algorithms, expert knowledge, and decision-making. The long-term in-vehicle applications, that are presented in this paper, outperform the most significant and fundamental technical limitations, such as, robustness in the face of changing environmental conditions. Our intelligent vehicle operates outdoors with pedestrians and others vehicles, and outperforms illumination variation, i.e.: shadows, low lighting conditions, night vision, among others. So, our applications ensure the suitable robustness and safety in case of a large variety of lighting conditions and complex perception tasks. Some of these complex tasks are overcome by the improvement of other devices, such as, inertial measurement units or differential global positioning systems, or perception architectures that accomplish sensor fusion processes in an efficient and safe manner. Both extra devices and architectures enhance the accuracy of computational perception and outreach the properties of each device separately.     

Q-学习及其在智能机器人局部路径规划中的应用研究

强化学习一词来自于行为心理学,这门学科把行为学习看成反复试验的过程,从而把环境状态映射成相应的动作．在设计智能机器人过程中,如何来实现行为主义的思想、在与环境的交互中学习行为动作？ 文中把机器人在未知环境中为躲避障碍所采取的动作看作一种行为,采用强化学习方法来实现智能机器人避碰行为学习．Ｑ－学习算法是类似于动态规划的一种强化学习方法,文中在介绍了Ｑ－学习的基本算法之后,提出了具有竞争思想和自组织机制的Ｑ－学习神经网络学习算法;然后研究了该算法在智能机器人局部路径规划中的应用,在文中的最后给出了详细的仿真结果     

Application Specific Transaction Management in Multidatabase Systems

We present a transaction model for multidatabase systems with autonomous component systems, coined heterogeneous 3-level transactions. It has become evident that in such a system the requirements of guaranteeing full ACID properties and full local autonomy can not be reconciled. In the heterogeneous 3-level transaction model, semantics of actions and specific properties of the architecture of multidatabase systems and of applications are utilized to define application specific compromises between these competing goals. We consider different definitions of conflicts between actions together with application specific sets of allowed (autonomous) local transactions and global subtransactions. A formal model for serializability is given. It is proven that heterogeneous 3-level transactions guarantee all consistency constraints that are ensured in serial executions. In contrast to most other models, we do not require data to be partitioned into global and local data. In particular, heterogeneous 3-level transactions even allow the same data to be updated by local and global transactions in parallel, if these updates are found to be semantically non-conflicting. Recovery is handled by inverse actions. We present a formal framework for this approach which is fully integrated into serializability theory by considering inverse actions as ordinary actions. This has an important impact on the relationship of concurrency control and recovery in our model: By changing the definition of conflicts between actions in order to tailor the model according to application needs, recovery is implicitly affected and no further explicit adaptation of recovery algorithms is necessary. The heterogeneous 3-level transaction model assumes component database systems to support ACID transaction properties. Further properties of local transactions or interfaces of the component database systems are not required. We describe a prototype implementation of heterogeneous 3-level transactions in the object-oriented database system VODAK.     

AFFECT IN TUTORING DIALOGUES

ABSTRACT

This paper is about INES, an intelligent, multimodal tutoring environment, and how we build a tutor agent in the environment that tries to be sensitive to the mental state of the student that interacts with it. The environment was primarily designed to help students practice nursing tasks. For example, one of the implemented tasks is to give a virtual patient a subcutaneous injection. The students can interact multimodally using speech and a haptic device under the guidance of the virtual embodied tutor. INES takes into account elements of the student's character and an appraisal of the student's actions to estimate the mental state of the student. This information is used to plan and execute the actions and responses of the tutor agent.     

Operator Performance and Intelligent Aiding in Unmanned Aerial Vehicle Scheduling

Unmanned vehicles (UVs) are quickly becoming ubiquitous in almost every aspect of hostile-environment operations. A key challenge in designing futuristic one-controlling-many systems will be minimizing periods of excessive operator workload that can arise when critical tasks for several UVs occur simultaneously. To a certain degree, you can predict and mitigate such periods in advance. However, actions that mitigate a particular period of high workload in the short term might create long-term episodes of high workload that were previously nonexistent. So, we need decision support that helps an operator evaluate alternative actions for managing a mission schedule in real time. To this end, we present an iterative design cycle that tries to leverage intelligent, predictive aiding together with human judgment and pattern recognition to maximize both system and human performance in the supervision of four UAVs. Automated decision support tools that provide more local, as opposed to global, visual recommendations can produce better performance in multiple UAV scheduling     

基于自注意力机制的局部与全局特征融合的评分预测算法

为了完全挖掘异质信息网络中节点的特征并且更好地融合这些特征,提高推荐算法的性能,提出一种基于自注意力机制的局部与全局特征融合的评分预测算法（rating prediction algorithm based on self-attention mechanism and fusion of local & global features,AMFL&GRec）。首先基于LeaderRank算法提取目标节点的全局序列,基于元路径带偏置的随机游走算法提取节点的局部序列,通过skip-gram模型分别学习节点的全局特征与局部特征;通过自注意力机制学习目标节点对局部与全局特征的偏好,从而得到在单一元路径下节点的特征表示;再通过自注意力机制融合不同元路径下同一节点的表示,从而得到节点在不同元路径下的最终的特征表示;最后基于多层感知器实现评分预测任务。在两个真实数据集进行了大量实验,实验结果验证了AMFL&GRec算法不仅能够捕获具有密集连通节点的微观（局部）结构,而且还能够捕获该节点在网络中的全局结构,从而使其得到的节点特征得以体现节点的整体（局部+全局）特征。同时,实验结果也证明了AMFL&GRec算法评分预测性能优于对比算法,从而证明利用自注意力机制考虑异质信息网络中节点对于局部、全局特征以及元路径的偏好能够提高评分预测的准确性。     

Towards probabilistic synchronisation of local controllers

The traditional use of global and centralised control methods fails for large, complex, noisy and highly connected systems, which typify many real-world industrial and commercial systems. This paper provides an efficient bottom-up design of distributed control in which many simple components communicate and cooperate to achieve a joint system goal. Each component acts individually so as to maximise personal utility whilst obtaining probabilistic information on the global system merely through local message-passing. This leads to an implied scalable and collective control strategy for complex dynamical systems, without the problems of global centralised control. Robustness is addressed by employing a fully probabilistic design, which can cope with inherent uncertainties, can be implemented adaptively and opens a systematic rich way to information sharing. This paper opens the foreseen direction and inspects the proposed design on a linearised version of coupled map lattice with spatio-temporal chaos. A version close to linear quadratic design gives an initial insight into possible behaviours of such networks.     

Bacterial colonies as complex adaptive systems

The present work explores bacterial colonies and their individual and social behaviours under the lens of complex adaptive systems. We initially provide a background on the biology of bacteria to describe important phenomena, such as quorum-sensing, individual and collective behaviours, adaptation, evolution and self-organization over the influence of mechanical effects on bacterial systems and connecting scales. We then explore some associations between bacterial colonies and complex adaptive systems by considering components and ownerships of self-organization. The main contribution of this paper places emphasis on individual decision-making and behaviour as a cause of bacterial colonies’ actions, i.e., how self-organization and collective behaviours impact the ability of a bacterial colony to address an environmental stimulus and maintain itself as an open biological and fault-tolerant system. Finally, we conclude the work and provide some comments regarding future research.     

On Resource Arc for Petri Net Modelling of Complex Resource Sharing System

PFS-R – Production Flow Schema with Resources – is a novel graphical representation for complex resource sharing discrete production systems proposed in this paper. The PFS-R is an augmented version of the PFS (Production Flow Schema, previously proposed by the authors) which includes correspondences of system resources at each production step. The PFS-R is able to model system structures as well as system behaviours in a more simplified and transparent manner than ordinary Petri net representations. That is, the PFS-R solves an important drawback when actually adopting Petri nets as a design technique for intelligent manufacturing systems. First, the paper introduces the basic elements of PFS-R, and the equivalent transformations of PFS-R model into hybrid nets and Petri nets, taking into account the net conservativeness. Next, examples of discrete production systems to illustrate the effectiveness of PFS-R are presented. In addition, it is shown, using an example, that the correspondence between resources and production steps in the process flow has a tree structure, which is an effective way to evaluate whether or not the objects designed have a well-defined structure.