Dedicated to defining measures and methodologies of evaluating performance of intelligent systems
Covers a wide range of subject areas related to intelligent system
Written by leading experts from their presentations at workshop held at the National Institute of Standards and Technology (NIST)
Dedicated to defining measures and methodologies of evaluating performance of intelligent systems
Covers a wide range of subject areas related to intelligent system
Written by leading experts from their presentations at workshop held at the National Institute of Standards and Technology (NIST)
Includes supplementary material: sn.pub/extras
To design and develop capable, dependable, and affordable intelligent systems, their performance must be measurable. Scienti?c methodologies for standardization and benchmarking are crucial for quantitatively evaluating the performance of eme- ing robotic and intelligent systems´ technologies. There is currently no accepted standard for quantitatively measuring the performance of these systems against user-de?ned requirements; and furthermore, there is no consensus on what obj- tive evaluation procedures need to be followed to understand the performance of these systems. The lack of reproducible and repeatable test methods has precluded researchers working towards a common goal from exchanging and communic- ing results, inter-comparing system performance, and leveraging previous work that could otherwise avoid duplication and expedite technology transfer. Currently, this lack of cohesion in the community hinders progress in many domains, such as m- ufacturing, service, healthcare, and security. By providing the research community with access to standardized tools, reference data sets, and open source libraries of solutions, researchers and consumers will be able to evaluate the cost and be- ?ts associated with intelligent systems and associated technologies. In this vein, the edited book volume addresses performance evaluation and metrics for intel- gent systems, in general, while emphasizing the need and solutions for standardized methods. To the knowledge of the editors, there is not a single book on the market that is solely dedicated to the subject of performance evaluation and benchmarking of intelligent systems.
Metrics for Multiagent Systems.- Evaluation Criteria for Human-Automation Performance Metrics.- Performance Evaluation Methods for Assistive Robotic Technology.- Issues in Applying Bio-Inspiration, Cognitive Critical Mass and Developmental-Inspired Principles to Advanced Intelligent Systems.- Evaluating Situation Awareness of Autonomous Systems.- From Simulation to Real Robots with Predictable Results: Methods and Examples.- Cognitive Systems Platforms using Open Source.- Assessing Coordination Demand in Cooperating Robots.- Measurements to Support Performance Evaluation of Wireless Communications in Tunnels for Urban Search and Rescue Robots.- Quantitative Assessment of Robot-Generated Maps.- Mobile Robotic Surveying Performance for Planetary Surface Site Characterization.- Performance Evaluation and Metrics for Perception in Intelligent Manufacturing.- Quantification of Line Tracking Solutions for Automotive Applications.
Performance Evaluation and Benchmarking of Intelligent Systems presents research dedicated to the subject of performance evaluation and benchmarking of intelligent systems by drawing from the experiences and insights of leading experts gained both through theoretical development and practical implementation of intelligent systems in a variety of diverse application domains. This contributed volume offers a detailed and coherent picture of state-of-the-art, recent developments, and further research areas in intelligent systems.
The chapters cover a broad range of applications, such as assistive robotics, planetary surveying, urban search and rescue, and line tracking for automotive assembly. Subsystems or components described in this book include human-robot interaction, multi-robot coordination, communications, perception, and mapping. Chapters are also devoted to simulation support and open source software for cognitive platforms, providing examples of the type of enabling underlying technologies that can help intelligent systems to propagate and increase in capabilities.
Performance Evaluation and Benchmarking of Intelligent Systems serves as a professional reference for researchers and practitioners in the field. This book is also applicable to advanced courses for graduate level students and robotics professionals in a wide range of engineering and related disciplines including computer science, automotive, healthcare, manufacturing, and service robotics.
From the reviews:"This book is the result of the 2008 performance Metrics for Intelligent Systems Workshop at the National Institute of Standards and Technology (NIST). It investigates intelligent systems, starting with multiagent systems ... . presents an impressive quantity of data, diagrams, proposals, experimental methods, and open topics, and also includes current solutions and relevant literature. ... Intelligent systems developers and users will be able to build on this book´s material.” (G. Gini, ACM Computing Reviews, December, 2009)
To design and develop capable, dependable, and affordable intelligent systems, their performance must be measurable. Scienti?c methodologies for standardization and benchmarking are crucial for quantitatively evaluating the performance of eme- ing robotic and intelligent systems' technologies. There is currently no accepted standard for quantitatively measuring the performance of these systems against user-de?ned requirements; and furthermore, there is no consensus on what obj- tive evaluation procedures need to be followed to understand the performance of these systems. The lack of reproducible and repeatable test methods has precluded researchers working towards a common goal from exchanging and communic- ing results, inter-comparing system performance, and leveraging previous work that could otherwise avoid duplication and expedite technology transfer. Currently, this lack of cohesion in the community hinders progress in many domains, such as m- ufacturing, service, healthcare, and security. By providing the research community with access to standardized tools, reference data sets, and open source libraries of solutions, researchers and consumers will be able to evaluate the cost and be- ?ts associated with intelligent systems and associated technologies. In this vein, the edited book volume addresses performance evaluation and metrics for intel- gent systems, in general, while emphasizing the need and solutions for standardized methods. To the knowledge of the editors, there is not a single book on the market that is solely dedicated to the subject of performance evaluation and benchmarking of intelligent systems.
From the reviews: "This book is the result of the 2008 performance Metrics for Intelligent Systems Workshop at the National Institute of Standards and Technology (NIST). It investigates intelligent systems, starting with multiagent systems ... . presents an impressive quantity of data, diagrams, proposals, experimental methods, and open topics, and also includes current solutions and relevant literature. ... Intelligent systems developers and users will be able to build on this book's material." (G. Gini, ACM Computing Reviews, December, 2009)
Inhaltsverzeichnis
Metrics for Multiagent Systems.- Evaluation Criteria for Human-Automation Performance Metrics.- Performance Evaluation Methods for Assistive Robotic Technology.- Issues in Applying Bio-Inspiration, Cognitive Critical Mass and Developmental-Inspired Principles to Advanced Intelligent Systems.- Evaluating Situation Awareness of Autonomous Systems.- From Simulation to Real Robots with Predictable Results: Methods and Examples.- Cognitive Systems Platforms using Open Source.- Assessing Coordination Demand in Cooperating Robots.- Measurements to Support Performance Evaluation of Wireless Communications in Tunnels for Urban Search and Rescue Robots.- Quantitative Assessment of Robot-Generated Maps.- Mobile Robotic Surveying Performance for Planetary Surface Site Characterization.- Performance Evaluation and Metrics for Perception in Intelligent Manufacturing.- Quantification of Line Tracking Solutions for Automotive Applications.
Klappentext
Performance Evaluation and Benchmarking of Intelligent Systems presents research dedicated to the subject of performance evaluation and benchmarking of intelligent systems by drawing from the experiences and insights of leading experts gained both through theoretical development and practical implementation of intelligent systems in a variety of diverse application domains. This contributed volume offers a detailed and coherent picture of state-of-the-art, recent developments, and further research areas in intelligent systems.
The chapters cover a broad range of applications, such as assistive robotics, planetary surveying, urban search and rescue, and line tracking for automotive assembly. Subsystems or components described in this book include human-robot interaction, multi-robot coordination, communications, perception, and mapping. Chapters are also devoted to simulation support and open source software for cognitive platforms, providing examples of the type of enabling underlying technologies that can help intelligent systems to propagate and increase in capabilities.
Performance Evaluation and Benchmarking of Intelligent Systems serves as a professional reference for researchers and practitioners in the field. This book is also applicable to advanced courses for graduate level students and robotics professionals in a wide range of engineering and related disciplines including computer science, automotive, healthcare, manufacturing, and service robotics.
Dedicated to defining measures and methodologies of evaluating performance of intelligent systems
Covers a wide range of subject areas related to intelligent system
Written by leading experts from their presentations at workshop held at the National Institute of Standards and Technology (NIST)
Includes supplementary material: sn.pub/extras
