Autonomous Tool Research Articles

Using Case-Based Reasoning and Principled Negotiation to provide decision support for dispute resolution

The growing use of Information Technology in the commercial arena leads to an urgent need to find alternatives to traditional dispute resolution. New tools from fields such as artificial intelligence (AI) should be considered in the process of developing novel online dispute resolution (ODR) platforms, in order to make the ligation process simpler, faster and conform with the new virtual environments. In this work, we describe UMCourt, a project built around two sub-fields of AI research: Multi-agent Systems and Case-Based Reasoning, aimed at fostering the development of tools for ODR. This is then used to accomplish several objectives, from suggesting solutions to new disputes based on the observation of past similar disputes, to the improvement of the negotiation and mediation processes that may follow. The main objective of this work is to develop autonomous tools that can increase the effectiveness of the dispute resolution processes, namely by increasing the amount of meaningful information that is available for the parties.

Autonomous Perforating Tool Works Without Umbilicals and Self-Destructs During Process

This article, written by Editorial Manager Adam Wilson, contains highlights of paper SPE 147296, ’Autonomous Perforating System for Multizone Completions,’ by Pavlin B. Entchev, SPE, and Renzo Angeles, SPE, ExxonMobil Upstream Research Company; Krishnan Kumaran and Niranjan Subrahmanya, ExxonMobil Corporate Strategic Research; and Randy Tolman, SPE, RC Tolman, prepared for the 2011 SPE Annual Technical Conference and Exhibition, Denver, 30 October-2 November. The paper has not been peer reviewed. Autonomous downhole tools offer a range of advantages over conventional tools controlled manually through umbilicals. For instance, perforating guns or bridge plugs could be dropped or pumped downhole without the use of wireline, coiled tubing, or tractors. Because umbilical intervention is no longer required, the tools may perform an action automatically (e.g., perforate a desired interval), with substantial cost reduction and enhanced safety. An autonomous perforating system currently being developed is based on using a self-destructing disposable perforating tool that is run without a wireline. To accomplish this, the tool has three frangible components: a logging device, an onboard navigation system, and friable perforating guns. Introduction The autonomous system presented here enables individual stimulation of each zone in a multizone completion interval without the use of wireline or other conventional umbilicals. Because of such critical step elimination, the proposed system eliminates much of the crane work and lubricator exposure within the drilling footprint. More important, no additional wireline trips are required to change perforating-tool assemblies and pumping rate is no longer limited to the breaking strength of the cable. Fracturing operations can be continuous, as with the case of ball-actuated openhole technology, but with the additional advantage of being able to complete and treat individual zones as opposed to an entire range of perforation clusters that can lead to suboptimal stimulations. In addition, safety is improved by the reduction of equipment at surface, which could enable simultaneous operations such as completion while drilling, where wells are completed while the drilling rig continues to operate on the same pad. Thus, the system presented here has the potential to accelerate the production startup in pad development and improve the economics of the project. Objectives The overarching goal was to develop a prototype autonomous perforating system that meets and exceeds the current industry safety standards and requirements while using industry standard hardware such as perforating charges. With this goal in mind, the design of the autonomous perforating system should satisfy a number of specific objectives. One of the main objectives was to have a disposable tool that destroys itself downhole without obstructing future operations of the well. In addition, the system should not require any changes during the well-construction phase and should be usable in both newly drilled and previously drilled wells. This requirement eliminated several design possibilities, such as putting tags or markers in specific casing points.

A hybrid approach for personalized recommendation of news on the Web

A hybrid method for personalized recommendation of news on the Web is presented, which provides Web users with an autonomous tool that is able to minimize repetitive and tedious Web surfing. The proposed approach classifies Web pages by calculating the respective weights of terms. A user’s interest and preference models are generated by analyzing the user’s navigational history. Based on the content of the Web pages and on a user’s interest and preference models, the recommender system suggests news Web pages to the user who is likely interested in the related topics. Moreover, the technique of collaborative filtering, which aims to choose the trusted users, is employed to improve the performance of the recommender system. Experiments are carried out in order to demonstrate the effectiveness of the proposed method. In the experiments, Web news items are classified and recommended to Web users by matching the users’ interests with the contents of the news.

What do numerical (climate) models really represent?

The translation of a mathematical model into a numerical one employs various modifications in order to make the model accessible for computation. Such modifications include discretizations, approximations, heuristic assumptions, and other methods. The paper investigates the divergent styles of mathematical and numerical models in the case of a specific piece of code in a current atmospheric model. Cognizance of these modifications means that the question of the role and function of scientific models has to be reworked. Neither are numerical models pure intermediaries between theory and data, nor are they autonomous tools of inquiry. Instead, theory and data are transformed into a new symbolic form of research due to the fact that computation has become an essential requirement for every scientific practice. Therefore the question is posed: What do numerical (climate) models really represent?

Full Autonomous Monitoring Tools Inside Nuclear Reactor Building

In this paper, we define, design and test a radiation tolerant full autonomous monitoring tool for Nuclear embedded applications. The goal of the instrumentation system was to record the values of some parameters such as dose, temperature or vibrations appearing inside the containment building of nuclear power plants (NPPs) during periods of electricity generation. The analysis of these data will be done to later define with confidence the ageing management policy useful for life-time extension of NPPs. For the design of the modules, we rely on commercial-off-theshelf (COTS) low power electronic components to use battery-supplied power. When the degradation of these components induced by irradiated environments is expected, tolerance is to be considered by components selection, by characterisation as near as possible to nominal environments to assess parameters drifts with working conditions and, finally, by rules and adapted design rules to reach the goals of the applications. A large amount of components starting from discrete transistors or logic units to memories and microcontrollers was associated to define and design a prototype. We then confirm the environment conditions tolerance estimated to up to 2 kGy of total dose and 80°C (176°F) by on-line irradiation experiments for individual components and functions and prototypes. Two different sets of about 60 systems were realised as industrial products and then installed on EDF facilities. They were exploited during NPPs activities of about eighteen months. This large scale experiment was concluded with the inspection of some withdrawn systems. No major degradations were observed showing the efficiency of the hardening method allowing regular use of COTS. Recorded data were thoroughly analysed with the goal to later decide to extend the instrument to a larger number of sites.

Seven tools for creating adaptive policies

Experience demonstrates that policies crafted to operate within a certain range of conditions are often faced with unexpected challenges outside of that range. The result is that many policies have unintended impacts and do not accomplish their goals. Adaptive policies are designed to function more effectively in complex, dynamic, and uncertain conditions. Based on over a dozen case studies on public policies relating to agriculture and water resources management in Canada and India, we conclude that there are seven tools policymakers should follow to create adaptive policies. Adaptive policies anticipate and plan for the array of conditions that lie ahead: (#1) using integrated and forward-looking analysis; (#2) monitoring key performance indicators to trigger built-in policy adjustments; (#3) undertaking formal policy review and continuous learning; and (#4) using multi-stakeholder deliberation. But not all situations can be anticipated. Unknown unknowns and deep uncertainty will always be part of policymaking. Adaptive policies are able to navigate toward successful outcomes in settings that cannot be anticipated in advance. This can be done by working in concert with certain characteristics of complex adaptive systems and thereby facilitating autonomous actions among stakeholders on the ground. To a degree, adaptive policy tools #3 and #4 can be used toward this purpose, but most directly, such autonomous tools include: (#5) enabling self-organization and social networking; (#6) decentralizing decisionmaking to the lowest and most effective jurisdictional level; and (#7) promoting variation in policy responses. This paper elaborates on these seven tools as a pragmatic guide for policymakers who find themselves working in highly complex, dynamic, and uncertain settings.

Some Basic Principles of Developmental Robotics

This paper formulates five basic principles of developmental robotics. These principles are formulated based on some of the recurring themes in the developmental learning literature and in the author's own research. The five principles follow logically from the verification principle (postulated by Richard Sutton) which is assumed to be self-evident. This paper also gives an example of how these principles can be applied to the problem of autonomous tool use in robots.

The Doppler wheel revisited

Millimeter-wave radar returns from cylindrical targets, such as artillery shells or helicopter rotor shafts, can be experimentally evaluated with the classic Doppler wheel. This also is a simple autonomous calibration tool for radar development and field testing. However, the less-apparent wheel-return characteristics found in practice must be taken into account. Doppler spectra for speeds up to 3000 rpm measured with a Ka-band radar against a 100 mm-diameter flat cylinder are presented, showing a frequency range from 200 to 4200 Hz. Meaningful signal amplitudes were measured up to the rim-speed Doppler. Frequency components beyond the range defined by the local radial velocity of the illuminated portion were observed up to 2500 Hz. Miniature surface deformations increased the amplitude of the highest frequencies by 5-10 dB. Simulated spectra agreed with measurement results at the higher Doppler frequencies, but a model based on Physical and Geometrical Optics failed to explain the low-frequency components.

An autonomic tool for building self-organizing Grid-enabled applications

In this paper we present CAMELotGrid, a tool to manage Grid computations of Cellular Automata that support the efficient simulation of complex systems modeled by a very large number of simple elements (cells) with local interaction only. The study of these systems has generated great interest over the years because of their ability to generate a rich spectrum of very complex patterns of behavior out of sets of relatively simple underlying rules. Moreover, they appear to capture many essential features of complex self-organizing cooperative behavior observed in real systems. The middleware architecture of CAMELotGrid is designed according to an autonomic approach on top of the existing Grid middleware and supports dynamic performance adaptation of the cellular application without any user intervention. The user must only specify, by global criteria, the high level policies and submit the application for execution over the Grid.

The development and application of wireless capsule endoscopy

The introduction of the Video Capsule Endoscope (VCE) by Given Imaging Ltd. (Yoqneam, Israel) in 2001, and its subsequent approval by the FDA as a first line tool in the detection of abnormalities of the small bowel, is indicative of the rapid acceptance of capsule endoscopy by the practicing gastroenterological community. An extensive clinical trials program consistently revealed a high diagnostic yield of the VCE when compared to other diagnostic modalities of the small intestine. The capsule endoscope contains a miniature color video camera, illumination sources, lens, transmitter/controller, antenna, and a power source. It is small enough to easily swallow (11 x 26 mm), and it is propelled through the gastrointestinal (GI) tract by peristalsis. Its development was enabled by a series of technological breakthroughs that occurred at the close of the 20th century. The VCE is one of the most exciting examples of the recent trend for minimally invasive autonomous medical tools in diagnostic, monitoring, and therapeutic applications. Expanding applications of the VCE to additional parts of the GI tract, adding physiological sensors, and--in the more remote future--addition of therapeutic capabilities will likely occur as this new branch of endoscopy develops.

Development of an innovative autonomous machine tool for dynamic product planning

In the area of machining, laborsaving and automation are comparatively realized mainly by the contribution of NC machine tools so far. However, conventional NC machine tools are not autonomous and intelligent because they don’t have any feedback mechanisms during machining operations. Therefore, in order to realize dynamic product planning for an innovative autonomous machine tool, it is indispensable that machine tools have feedback mechanism to adapt cutting parameters to monitoring information. As a matter of course, it is needed for the mechanism to include a function of tool path generation in real time. Because the real time tool path generation can perform to change not only feed speed but also depth of cut during an operation. In this paper, digital copy milling system that can generate tool paths in real time is developed by applying the traditional copy milling principle. And also, machining strategy is proposed to adapt cutting parameters considering cutting load, and integrated into the digital copy milling. Feedback machining control can be realized using the digital copy milling system with the proposed machining strategy. Furthermore, in order to achieve dynamic product planning, an automatic function of product planning is added by customizing commercial CAD software. By using this automatic planning system, even in case of a cutting trouble, it is possible to reschedule product planning immediately. Autonomous machining based on dynamic product planning can enable to realize high flexibility and high durability in machining operations.

The Shoreline Environment Aerosol Study (SEAS): A Context for Marine Aerosol Measurements Influenced by a Coastal Environment and Long-Range Transport*

The Shoreline Environment Aerosol Study (SEAS) was carried out in Hawaii on the southeast coast of Oahu in an area exposed to relatively steady onshore flow. This location provided favorable opportunities to test and evaluate new instrumentation designed to improve measurements of marine aerosol and its physical, chemical, and optical properties, including the remote sensing (lidar) of coastal aerosol fields. Data acquired from the diverse instruments deployed before and during SEAS demonstrate that environmental and meteorological features actively influence aerosol measurements at this location. Both a ceilometer and a visibility sensor were operated continuously and found to be effective autonomous tools for characterizing mixed-layer aerosol conditions. These instruments also helped demonstrate that changes in physical and optical properties measured during SEAS were also linked to volcanic aerosol transported across the Pacific in the free troposphere from Japan and later entrained into the marine boundary layer. This and various local effects of wind direction, wind speed, tides, and sampling altitude were superimposed on the variations in offshore marine aerosol. Characterization of these site-specific effects provides a context and guidance for the interpretation of coastal aerosol data and evaluation of SEAS data.

Autonomous Tool Path Generation in Robotic Polishing of an Aluminum Alloy

Autonomous Tool Path Generation in Robotic Polishing of an Aluminum Alloy

Il Tesoro della Lingua Italiana delle Origini

The Tesoro della Lingua Italiana delle Origini (TLIO) is the main project of the Institute of Italian Research Council “Opera del Vocabolario Italiano” (OVI). TLIO is a historical dictionary of Old Italian; its most important characteristic is that of having been founded on a huge database (around 19 million words in 1581 texts), consisting of texts written in any variety of mediaeval Italian and dated within 1375. The database is available in internet thanks to the international consortium ItalNet (http://www.italnet.nd.edu). The TLIO database not only allows the writing out of dictionary entries, but is also an autonomous tool, useful for the research on Old Italian.

Autonomous tool adjustment in robotic grinding

The work presented here is concerned with acquiring knowledge that allows a robot to adjust a rubber abrasive disk in the grinding process. The experiments performed in this work were conducted using a six-axis articulated robot. A rotary hand grinding system with a cup-shaped rubber abrasive disk is held by a robot actuator to perform the grinding task. The workpiece is an aluminum alloy block fixed onto a piezo-electric type dynamometer. The authors propose a method where by the robot can frequently reduce errors by using external cutting force data in order to adjust the tool to the workpiece surface. This adjustment is effective in finding the optimal tool angle to obtain the best ground surface. The effects of grinding strokes on the surface roughness and depth of machining have been found also. With the aid of the experiments performed in this work, it is possible to find good machining conditions in an autonomous robotic grinding system.

Real-time cutting simulation system of a milling operation for autonomous and intelligent machine tools

The conceptual architecture of autonomous and intelligent machine tools has been proposed not only to generate flexibly the process and operation plan but also to utilize the machine tools and cutting tools' performance while satisfying the requirements of the products and avoiding unexpected machining trouble. In order to realize the autonomous milling, machining strategy such as tool paths and cutting conditions must be decided, not in advance like current NC machining, but in a real-time manner. The objective of this research is to develop a real time machining optimization with machining simulation. Consequently, a cutting simulation system called a virtual machining simulator has been developed for this purpose. This simulator can calculate the changing geometry of the workpiece and estimate the instantaneous cutting force, torque, etc using the physical model. This estimated information enables the system to decide the suitable cutting conditions according to the machinability evaluated. In this paper, the machining status is evaluated and the cutting conditions are modified in real time so that the requirement of the machining operation is satisfied by referring to the physical model. The reliable and safe machining operation is carried out by maintaining the cutting force and torque desired value.

Agent-Mediated Electronic Commerce: An MIT Media Laboratory Perspective

:Software agents, semi-intelligent autonomous tools, will play an increasing role in electronic commerce applications. This paper gives an overview of the work at MIT’s Media Laboratory on several types of agents for electronic commerce, ranging from consumer-to-consumer “smart” classified-ad systems to merchant agents that provide integrative negotiation capabilities, from agents that facilitate expertise brokering to distributed reputation facilities, and from point-of-sale comparison-shopping agents to mobile shopping systems.

Why Mission Control Works: Supporting Cognition and Collaboration in Distributed, Dynamic Worlds

Studies of failures have dominated human factors research in complex, dynamic domains. The goal of this panel, however, is to use a case study of success - space shuttle mission control - to explore how robust problem-solving and effective collaboration among distributed, functionally distinct agents can be facilitated. This panel brings together human factors researchers and systems designers who are familiar with mission control to discuss the cognitive factors, organizational practices, and technological innovations that contribute to the success of space shuttle missions. As with other complex domains, economic and technological pressures are threatening mission control's bases for success. These pressures (e.g., budget/staff reductions, more complex technology, and longer, more remote missions) are intensifying demands for “smarter”, more autonomous computer support tools. Therefore, this panel explores approaches for designing intelligent systems and automation that perform as “team players” in challenging operational environments - where effective collaboration constitutes the key to success.

Research Environment for Data Analysis Tool Allocators

Intelligent data analysis implies the reasoned application of autonomous or semi-autonomous tools to data sets drawn from problem domains. Automation of this process of reasoning about analysis (based on factors such as available computational resources, cost of analysis, risk of failure, lessons learned from past errors, and tentative structural models of problem domains) is highly non-trivial. By casting the problem of reasoning about analysis (MetaReasoning) as yet another data analysis problem domain, we have previously [R. Levinson and J. Wilkinson, in Advances in Intelligent Data Analysis, edited by X. Liu, P. Cohen, and M. Berthold, volume LNCS 1280, Springer-Verlag, Berlin, pp. 89–100, 1997] presented a design framework, MetaReasoning for Data Analysis Tool Allocation (MRDATA). Crucial to this framework is the ability of a Tool Allocator to track resource consumption (i.e. processor time and memory usage) by the Tools it employs, as well as the ability to allocate measured quantities of resources to these Tools. In order to test implementations of the MRDATA design, we now implement a Runtime Environment for Data Analysis Tool Allocation, RE:DATA. Tool Allocators run as processes under RE:DATA, are allotted system resources, and may use these resources to run their Tools as spawned sub-processes. We also present designs of native RE:DATA implementations of analysis tools used by MRDATA: K-Nearest Neighbor Tables, Regression Trees, Interruptible (“Any-Time”) Regression Trees, and “Hierarchy Diffusion” Temporal Difference Learners. Preliminary results are discussed and techniques for integration with non-native tools are explored.

A CORBA-based agent-driven design for distributed intelligent manufacturing systems

An agent-oriented methodology is presented for representation, acquisition, and processing of manufacturing knowledge along with analysis and modeling of an intelligent manufacturing system (IMS). An intelligent manufacturing system adopts heterarchical and collaborative control as its information system architecture. The behavior of the entire manufacturing system is collaboratively determined by many interacting subsystems that may have their own independent interests, values, and modes of operation. The subsystems are represented as agents. An agent's architecture and task decomposition method are presented. The agent-oriented methodology is used to analyze and model an intelligent machine cell. An intelligent machine center is considered as an autonomous, modular, reconfigurable and fault-tolerant machine tool with self-perception, decision making, and self-process planning, able to cooperate with other machines through communication. The common object request broker architecture (CORBA) distributed software control system was developed as a simple prototype. A case study illustrates an intelligent machine center.