Heterogeneous Agents Situated in Heterogeneous Spaces

This paper introduces the Multi-layered Multi-Agent Situated System model (MMASS), a model for Multi-Agent Systems (MAS) situated in an environment. The main feature of the MMASS model is to give an explicit definition of the spatial structure of the environment in which the system of situated agents are acting and interacting. Moreover, the presented model allows the representation of the heterogeneity that characterizes both agent types and interactions, and the spatial structures of the environment in which they are situated. The MMASS model allows the representaton of both open and closed systems: examples of its application (one for each class of systems) will be shown.     

GPS Navigation Using Adaptive Kalman Filter for Maneuvering Vehicle

Several filter techniques were available for the GPS position estimation problem of maneuvering vehicle ranging from using different process noises to Interactive Multiple Model (IMM). The limitation of using standard Kalman filters is listed.The performance of proposed adaptive filter is compared with that of the standard ones,two types of dynamic modeling of the maneuvering vehicle are used.The simulation is based on the almanac data of the GPS satellites to compute its feasibility during the simulation t...     

Interactive Control of Large-Crowd Navigation in Virtual Environments Using Vector Fields

Providing interactive control is a hot topic in crowd-navigation research. Here, the authors propose a simple but effective way for authoring a crowd scene. With their governing tool, users can easily drive the flow of crowds by sketching velocities on anchor points in the scene. This approach is fast enough to allow on-the-fly modification of vector fields.     

Improving Performance of Heterogeneous Agents

Agents provide services not only to humans users but also to agents in one or more multiagent systems. When agents are confronted with multiple tasks to perform (or requests to satisfy), the agent can reduce load on itself by attempting to take advantage of commonalities between the tasks that need to be performed. In this paper, we develop a logical theory by which such “heavily loaded” agents can merge commonalities amongst such tasks. In our framework, agents can be built on top of legacy codebases. We propose a logical formalism called invariants using which agent developers may specify known commonalities between tasks – after this, we propose a sound and complete mechanism to derive all possible derived commonalities. An obvious A ^*-based algorithm may be used to merge a set of tasks in a way that minimised expected execution cost. Unfortunately the execution time of this algorithm is prohibitive, even when only 10 tasks need to be merged, thus making it unusable in practice. We develop heuristic algorithms for this problem that take much less time to execute and produce almost as good ways of merging tasks.     

Internet-Based Smart-Space Navigation of a Car-Like Wheeled Robot Using Fuzzy-Neural Adaptive Control

In this paper, a navigation system is developed. The system includes path tracking and obstacle avoidance apparatus for a car-like wheeled robot (CLWR) within an Internet-based smart-space (IBSS) using fuzzy-neural adaptive control (FNAC). Two distributed charge-coupled device (CCD) cameras are installed to capture both the dynamic pose of the CLWR and the obstacle. Based on the control authority of these two CCD cameras, a suitable reference command that contains the desired steering angle and angular velocity for the FNAC built into the client computer is planned. Because of the delay encountered by the transmission through the Internet network (IN) and the wireless local area network (WLAN) and the nonlinear coupling features of the CLWR, a weighted combination of $N$ linear subsystems that are described by a state-space model with average-delay is implemented to approximate the dynamics of an IBSS-CLWR. The proposed FNAC contains a neural network consisting of a radial basis function (RBFNN) to learn the uncertainties due to the fuzzy-model error (e.g., the random time-varying delays and the slippage of the CLWR) and the interactions caused by other subsystems. The stability of the overall system is then investigated by adopting the Lyapunov stability theory. Finally, a sequence of experiments including the control of the off-ground CLWR (i.e., the CLWR does not make contact with the ground) and the navigation of the IBSS-CLWR as compared with the conventional proportional-integral-derivative (PID) control is performed to demonstrate the advantage of the proposed control system.      

Adaptive Web Site Agents

We discuss the design and evaluation of a class of agents that we call adaptive web site agents. The goal of such an agent is to help a user find additional information at a particular web site, adapting its behavior in response to the actions of the individual user and the actions of other visitors to the web site. The agent recommends related documents to visitors and we show that these recommendations result in increased information read at the site. It integrates and coordinates among different reasons for making recommendations including user preference for subject area, similarity between documents, frequency of citation, frequency of access, and patterns of access by visitors to the web site. We argue that this information is best used not to change the structure or content of the web site but rather to change the behavior of an animated agent that assists the user.     

Intelligent Adaptive Information Agents

Adaptation in open, multi-agent information gathering systems isimportant for several reasons. These reasons include the inability toaccurately predict future problem-solving workloads, future changes inexisting information requests, future failures and additions of agents anddata supply resources, and other future task environment characteristicchanges that require system reorganization. We have developed a multi-agentdistributed system infrastructure, RETSINA (REusable Task Structure-based Intelligent Network Agents) that handles adaptation in an open Internetenvironment. Adaptation occurs both at the individual agent level as well asat the overall agent organization level. The RETSINA system has three typesof agents. Interface agents interact with the userreceiving user specifications and delivering results. They acquire, model,and utilize user preferences to guide system coordination in support of theusers tasks. Task agents help users perform tasks byformulating problem solving plans and carrying out these plans throughquerying and exchanging information with other software agents. Information agents provide intelligent access to a heterogeneouscollection of information sources. In this paper, we concentrate on theadaptive architecture of the information agents. We use as the domain ofapplication WARREN, a multi-agent financial portfolio management system thatwe have implemented within the RETSINA framework.     

A Simulation Framework for Heterogeneous Agents

We introduce a generic simulation framework suitable for agent-based simulations featuring the support of heterogeneous agents, hierarchical scheduling, and flexible specification of design parameters. One key aspect of this framework is the design specification: we use a format based on the Extendible Markup Language (XML) that is simple-structured yet still enables the design of flexible models. Another issue in agent-based simulations, especially when ready-made components are used, is the heterogeneity arising from both the agents' implementations and the underlying platforms. To tackle such obstacles, we introduce a wrapper technique for mapping the functionality of agents living in an interpreter-based environment to a standardized JAVA interface, thus facilitating the task for any control mechanism (like a simulation manager) because it has to handle only one set of commands for all agents involved. Again, this mapping is made by an XML-based definition format. We demonstrate the technique by applying it to a simple sample simulation of two mass marketing firms operating in an artificial consumer environment.     

Interactive Critiquing forCatalog Navigation in E-Commerce

E-commerce sites can have large, essentiallyunbounded, catalogs. With large catalogs comesincreasing difficulty for buyers in making useof standard search and browsing facilities.Particularly in the case of casual oroccasional buyers and in the case of complexproducts, the gap between a product'sspecifications and the buyer's understanding ofneed can be hard to bridge. An effectivee-commerce catalog must map user needs toproducts that can fulfill them. This paperdescribes an interactive, incremental,case-based, critiquing approach to solving thisproblem. The approach is interactive andincremental, so it does not require that theuser have a completely specified need at thestart. The system is case-based in that itemphasizes products over features orconstraints, and uses case-based reasoningtechniques for its product retrieval. Finally,the approach is based on the critiquing ofpresented examples, each critique redirectingthe search to home in on appropriate products.     

A Formal Framework for Interactive Agents

This paper proposes a formal framework and architecture for specification and analysis of interactive agents. The framework can be used to explore the design space, study features of different points in the design space, and to develop executable specifications of specific agents and study their interactions with the environment. A long term goal is development of reasoning principles specialized to different regions of the design space.     

Intelligent Adaptive Mobile Robot Navigation

This paper deals with the application of a neuro-fuzzy inference system to a mobile robot navigation in an unknown, or partially unknown environment. The final aim of the robot is to reach some pre-defined goal. For this purpose, a sort of a co-operation between three main sub-modules is performed. These sub-modules consist in three elementary robot tasks: following a wall, avoiding an obstacle and running towards the goal. Each module acts as a Sugeno–Takagi fuzzy controller where the inputs are the different sensor information and the output corresponds to the orientation of the robot. The rule-base is generated by the controller after some learning process based on a neural architecture close to that used by Wang and Menger. This leads to adaptive neuro-fuzzy inference systems (ANFIS) (one for each module). The adaptive navigation system (ANFIS), based on integrated reactive-cognitive parts, learns and generates the required knowledge for achieving the desired task. However, the generated rule-base suffers from redundancy and abundance of data, most of which are less useful. This makes the assignment of a linguistic label to the associated variable difficult and sometimes counter-intuitive. Consequently, a simplification phase allowing elimination of redundancy is required. For this purpose, an algorithm based on the class of fuzzy c-means algorithm introduced by Bezdek and we have developed an inclusion structure. Experimental results confirm the meaningfulness of the elaborated methodology when dealing with navigation of a mobile robot in unknown, or partially unknown environment.     

自适应GHPF及其在组合导航中的应用

研究组合导航系统精度优化问题,针对粒子滤波存在重要性密度函数难以选取的问题,提出一种新的自适应GHPF算法,通过高斯-厄米特滤波来获取状态均值和协方差阵,计算自适应因子并利用自适应因子调节均值和方差,得到一种参数可调节的重要性密度函数.重要性密度函数考虑了最新量测的影响,提高了滤波精度,使滤波性能明显改善,能更好地解决非线性非高斯系统模型的滤波问题.将提出的算法应用于SINS/SAR组合导航系统中,仿真结果表明,提出的滤波算法能提高导航计算的精度,定位性能明显优于与扩展Kalman滤波、粒子滤波以及高斯-厄米特粒子滤波.     

交互式智能体体系结构应用研究

介绍和分析了目前关于智能体体系结构的研究,重点以无人作战武器防御系统为背景,深入研究交互式智能体体系结构的应用,并对智能体的协调机制、通信机制、不完全全局规划方法等作了较深入的阐述。     

Using RTT Variability for Adaptive Cross-Layer Approach to Multimedia Delivery in Heterogeneous Networks

A holistic approach should be made for a wider adoption of a cross-layer approach. A cross-layer design on a wireless network assumed with a certain network condition, for instance, can have a limited usage in heterogeneous environments with diverse access network technologies and time varying network performance. The first step toward a cross-layer approach is an automatic detection of the underlying access network type, so that appropriate schemes can be applied without manual configurations. To address the issue, we investigate the characteristics of round-trip time (RTT) on wireless and wired networks. We conduct extensive experiments from diverse network environments and perform quantitative analyses on RTT variability. We show that RTT variability on a wireless network exhibits greatly larger mean, standard deviation, and min-to-high percentiles at least 10 ms bigger than those of wired networks due to the MAC layer retransmissions. We also find that the impact of packet size on wireless channel is particularly significant. Thus through a simple set of testing, one can accurately classify whether or not there has been a wireless network involved. We then propose effective adaptive cross-layer schemes for multimedia delivery over error-prone links. They include limiting the MAC layer retransmissions, controlling the application layer forward error correction (FEC) level, and selecting an optimal packet size. We conduct an analysis on the interplay of those adaptive parameters given a network condition. It enables us to find optimal cross-layer adaptive parameters when they are used concurrently.     

Asset Price Dynamics among Heterogeneous Interacting Agents

In this paper, we investigate the presence of rationalherding on asset price dynamics during the intra-day trading withheterogeneous interacting agents, whose information set is notcomplete. In the model, individual probability measures offinancial investment strategies are defined using statisticalmechanics concepts. In addition, there is a learning processtoward the best strategy, implemented as a geneticalgorithm. Simulations show that imitative behavior can be arational strategy, since it allows an investor to gain excessreturns on an asset by exploiting information regarding pricedynamics not strictly contained in the fundamental solution. Herdbehavior is rational in the sense that it produces profits at theexpense of increasing the complexity of the system.     

交互式虚拟导航技术研究

研究基于体单元的交互式导航技术,是一具有虚拟现实特征的交互式方法可用于带空腔的人体器官的疾病疹断。其内容涉及虚拟相机的概念设计,受控运动的特性研究,潜在可见表面集的缩减技术和交互式演示技术。     

自适应高斯粒子滤波在导航中的应用

针对粒子滤波中重要性密度函数难以选取和粒子退化导致的计算精度下降的问题,提出一种新的自适应高斯粒子滤波算法。通过高斯混合密度函数和UT变换来获取状态均值和协方差阵,选择并计算合适的自适应因子来调节均值和方差,在迭代过程中可动态调节重要性密度函数,并用WEM和EM步骤代替重采样,上述滤波算法考虑了最新量测信息的影响,使滤波性能明显改善,能更好地解决非线性非高斯系统模型的抗干扰问题。将提出的算法应用于SINS/GPS组合导航系统跑车试验中,结果表明上述滤波算法能提高导航解算的精度,其性能明显优于已有滤波,同时验证了当系统出现噪声干扰突然变化时提出算法的有效性。     

Multiple Adaptive Agents for Tactical Driving

Recent research in automated highway systems has ranged from low-level vision-based controllers to high-level route-guidance software. However, there is currently no system for tactical-level reasoning. Such a system should address tasks such as passing cars, making exits on time, and merging into a traffic stream. Many previous approaches have attempted to hand construct large rule-based systems which capture the interactions between multiple input sensors, dynamic and potentially conflicting subgoals, and changing roadway conditions. However, these systems are extremely difficult to design due to the large number of rules, the manual tuning of parameters within the rules, and the complex interactions between the rules. Our approach to this intermediate-level planning is a system which consists of a collection of autonomous agents, each of which specializes in a particular aspect of tactical driving. Each agent examines a subset of the intelligent vehicle's sensors and independently recommends driving decisions based on their local assessment of the tactical situation. This distributed framework allows different reasoning agents to be implemented using different algorithms.When using a collection of agents to solve a single task, it is vital to carefully consider the interactions between the agents. Since each reasoning object contains several internal parameters, manually finding values for these parameters while accounting for the agents' possible interactions is a tedious and error-prone task. In our system, these parameters, and the system's overall dependence on each agent, is automatically tuned using a novel evolutionary optimization strategy, termed Population-Based Incremental Learning (PBIL).Our system, which employs multiple automatically trained agents, can competently drive a vehicle, both in terms of the user-defined evaluation metric, and as measured by their behavior on several driving situations culled from real-life experience. In this article, we describe a method for multiple agent integration which is applied to the automated highway system domain. However, it also generalizes to many complex robotics tasks where multiple interacting modules must simultaneously be configured without individual module feedback.