Rami S. Abielmona

Robotic sensor agents: a new generation of intelligent agents for complex environment monitoring

Monitoring environment parameters is a complex task of great importance in many areas, such as the natural living environment; homeland security; industrial or laboratory hazardous environments (biologically, radioactively, or chemically contaminated); polluted/toxic natural environments; water treatment plants; nuclear stations; war zones; or remote, difficult-to-reach environments, such as the deep space or underwater. This article will discuss a new generation of intelligent, autonomous, wireless robotic sensor agents (RSAs) for complex environment monitoring. Shown in this article is the architecture of an RSA system under development in our laboratory at the University of Ottawa (see Petriu et al., p14-19, May 2002). Monitoring is done by continuously collecting sensory data from stationary and mobile RSAs deployed in the field.

An evolving risk management framework for wireless sensor networks

Individual units in a wireless sensor network (WSN) are exposed to multiple risks, either during or after their deployment. The identification of the risk sources and their watchful monitoring in dynamic, unpredictable environments is pivotal to ensure a smooth, long-term functioning of the WSN. We introduce an evolving risk management framework for WSNs that captures multiple risk features and provides both a visual depiction of the corporate network threats at any time and a numerical assessment of any sensors overall risk. The visualization module is embodied through an evolving clustering architecture which heavily relies on shadowed sets. The risk assessment module embraces fuzzy and shadowed evaluations of the risk sources and incorporates a simple adaptive learning process that weights the risk sources proportionally to their observed impact on failed sensors. A distinctive trait of the proposed framework is its highly automated yet still human-centric nature. Experiments utilizing different sensor models and deployment scenarios confirm the feasibility of the risk management platform under consideration.

Mission-Driven Robotic Intelligent Sensor Agents for Territorial Security

Territorial security deals with the prevention, detection and response to unauthorized persons and/or goods from crossing a perimeter. It deals with large territories of strategic importance, such as international borders, transportation and critical infrastructure. Multi-agent systems provide flexibility, fault-tolerance, high sensing fidelity, low-cost and rapid deployment. In this paper, we concentrate on the challenges presented in applying the concepts of multi-agent systems to those presented by territorial security. We first introduce the overall system as well as prevalent agent architectures. We then briefly present our novel agent architecture, its experimental embodiment and the virtualized reality model that accepts physical sensor data and updates a global model of the environment in real-time.

Risk management with hard-soft data fusion in maritime domain awareness

Enhanced situational awareness is integral to risk management and response evaluation. Dynamic systems that incorporate both hard and soft data sources allow for comprehensive situational frameworks which can supplement physical models with conceptual notions of risk. The processing of widely available semi-structured textual data sources can produce soft information that is readily consumable by such a framework. In this paper, we augment the situational awareness capabilities of a recently proposed risk management framework (RMF) with the incorporation of soft data. We illustrate the beneficial role of the hard-soft data fusion in the characterization and evaluation of potential vessels in distress within Maritime Domain Awareness (MDA) scenarios. Risk features pertaining to maritime vessels are defined a priori and then quantified in real time using both hard (e.g., Automatic Identification System, Douglas Sea Scale) as well as soft (e.g., historical records of worldwide maritime incidents) data sources. A risk-aware metric to quantify the effectiveness of the hard-soft fusion process is also proposed. Though illustrated with MDA scenarios, the proposed hard-soft fusion methodology within the RMF can be readily applied to other domains.

A response-aware risk management framework for search-and-rescue operations

Efficient coordination among all assets participating in a response to a search-and-rescue (SAR) incident has long been a focus of many governments and organizations. Finding innovative solutions that guarantee a swift reaction to the distressed entity with a rational use of the available resources is pivotal to the success of the SAR operation. In spite of the plethora of successfully deployed SAR systems, we witness a substantial gap when it comes to the integration of risk-driven analyses into the underlying machinery of any decision support platform that leans upon the in-field SAR assets. This paper extends a recently proposed risk management framework [1] by adding automated modules for risk monitoring and response selection. An evolutionary multi-objective optimization algorithm is used to navigate across the discrete space of all available assets and their set of actions in order to present a limited number of promising responses to a SAR operator, who will ultimately decide what action must be carried out. The proposed methodology was validated in the context of a simulated nautical SAR scenario in the Canadian Atlantic coastline with nine different types of ground, maritime and aerial assets.

Distributed intelligent sensor agent system for environment mapping

This paper discusses a multi-agent system consisting of a limited set of mobile intelligent sensor agents that are exploring an environment with the goal of minimizing the environment mapping uncertainty, i.e. the entropy. A novel tree in-motion mapping method combining simplicity and speed of computation with low storage and communications requirements is proposed for the management of a network of robotic agents, each possessing limited sensing, processing and communicating operational entities. Simulation and experimental results demonstrate the efficiency of the proposed system architecture and mapping method.

A Self-Reconfigurable Platform for Built-In Self-Test Applications

This paper introduces a novel architecture that is targeted for digital core testing and built-in-self test (BIST) algorithm development. This reconfigurable architecture is validated by an application that implements the novel idea of verifying algorithms for testing digital circuits by using runtime reconfigurable techniques in order to minimize the circuit area, as well as the test generation and application time. The idea revolves around the dynamic partial reconfiguration of circuits under test in order to inject stuck-at faults at different locations of the circuit and uncover both detectable and undetectable faults. Four testing strategies are presented, and two are experimentally compared, namely, the sequential compile-time reconfiguration and runtime reconfiguration strategies.

Can an intelligent society of robots survive in a hostile environment

In this paper, we introduce a distributed intelligent system capable of adapting to a possibly hostile environment, by learning and applying task solution strategies as a society. The system is composed of intelligent architectures, that interact with each other, to resolve a common objective. The intelligent entities, themselves, are robotic platforms, equipped with static (microcontrollers/microprocessors) and dynamic (FPGAs) computational resources, proprio-(internal) and extero-ceptor (external) capabilities, as well as various on-board actuators. The result is a society of mobile and stationary intelligent architectures, that are able to utilize a hardware-based genetic algorithm (GA) as an evolutionary computational paradigm, and reconfigurable computing approaches to handle the real-time issues in the entire system. The presented work is part of the ongoing research in the concept of intelligent systems and agents, first presented by Rami Abielmona and Voicu Groza in (2001) and (2002). The distributed intelligent system provides four main services, namely the communications, tracking, monitoring and exploring services. Along with these services, three levels of intelligence will be discussed: local, network and coupled intelligence. Local intelligence describes the know-how of each architecture, network intelligence describes the know-how of cliques of architectures, while coupled intelligence describes the know-how of architectures currently working together. It is envisioned that the architectures will be able to develop human-like instincts, while competing for limited resources in the environment that they reside in.

Agent-based control for a dynamically reconfigurable mobile robotic structure

This work discusses an agent-based control system utilized for target tracking by clusters of basic mobile robotic sensor agents coupled to form complex reconfigurable mobile structures. Coupling and de-coupling mobile agents are controlled using an adaptive algorithm, which does not initially know the physical constraints tying the agents together, but is able to navigate the structure as if it were a single entity.

Circuit synthesis evolution using a hardware-based genetic algorithm

We propose a scheme based on a hardware implementation of a genetic algorithm, to evolve the minimized logic solution of a defined input function. The minimization will be one of resource usage, more precisely of look-up tables (LUTs). The design aids in the difficult issue of technology mapping, as well as multi-level logic synthesis. The approach undertaken in this research involves intrinsic hardware evolution, where the circuit solution is evolved online, and the output is a minimized structure of the circuit. Our architecture is outlined and discussed, while our current results are presented and analyzed.