Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “agent”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
NASA NTRS1975

Development of high temperature resistant graphite fiber coupling agents

Surface treatments were investigated as potential coupling agents to improve the elevated temperature shear strength retention of polyimide/graphite and polyphenylquinoxaline/graphite composites. The potential coupling agents were evaluated by fiber strand tensile tests, fiber and composite weight losses at 533 and 588K, and by interlaminar shear strength retention at 533 and 588K. The two surface treatments selected for more extensive evaluation were a coating of Ventromer T-1, a complex organometallic reaction product of titanium tetrachloride and trimethyl borate, and a polyphenylquinoxaline (PPQ) sizing which was pyrolyzed in nitrogen to form a carbonaceous layer on the fiber. Pyrolyzed polyphenylquinoxaline is a satisfactory coupling agent for polyimide/Thornel 300 graphite fiber composites. During 1000 hours aging at 588K such composites lose a little over half their transverse tensile strength, and suffer a slight loss in flexural modulus. No degradation of flexural strength or interlaminar shear strength occured during 1000 hours aging at 588K. None of the coupling agents examined had a markedly beneficial effect with polyphenylquinoxaline composites.

Griffin, R. N.↗
NASA NTRS1977

Spacecraft disinfectant/cleansing agent development

The sanitation agent container, which was selected in a trade off study, employs two chambers, a rigid outer container and an inner flexible bladder. The bladder contains the sanitation agent formulation and its release is controlled by a manually operated valve. The outer container holds a high pressure vapor. There is no void in the bladder which makes the package operation independent of orientation and therefore usable in zero gravity. Foam is developed by a low boiling point fluid or dissolved in the product. When the product is dispensed at atmospheric presure, the evolved gas or vapor whips up a goam in the valve. The sanitation agents were initially formulated with freons which produces an excellent foam. However freon is incompatible with the life support system and was replaced with carbon dioxide dissolved at high pressure. The CO2 system may limit high temperature exposure to prevent leakage or package distortion. The sanitation agents have been shown to be effective in cleaning soils from personnel and material.

Abbate, M.↗
NASA NTRS1994

Agent oriented programming

The goal of our research is a methodology for creating robust software in distributed and dynamic environments. The approach taken is to endow software objects with explicit information about one another, to have them interact through a commitment mechanism, and to equip them with a speech-acty communication language. System-level applications include software interoperation and compositionality. A government application of specific interest is an infrastructure for coordination among multiple planners. Daily activity applications include personal software assistants, such as programmable email, scheduling, and new group agents. Research topics include definition of mental state of agents, design of agent languages as well as interpreters for those languages, and mechanisms for coordination within agent societies such as artificial social laws and conventions.

Shoham, Yoav↗
NASA NTRS1998

Research and Development for an Operational Information Ecology: The User-System Interface Agent Project

The User System Interface Agent (USIA) is a special type of software agent which acts as the "middle man" between a human user and an information processing environment. USIA consists of a group of cooperating agents which are responsible for assisting users in obtaining information processing services intuitively and efficiently. Some of the main features of USIA include: (1) multiple interaction modes and (2) user-specific and stereotype modeling and adaptation. This prototype system provides us with a development platform towards the realization of an operational information ecology. In the first phase of this project we focus on the design and implementation of prototype system of the User-System Interface Agent (USIA). The second face of USIA allows user interaction via a restricted query language as well as through a taxonomy of windows. In third phase the USIA system architecture was revised.

Srivastava, Sadanand↗
NASA NTRS2000

Emergent Aerospace Designs Using Negotiating Autonomous Agents

This paper presents a distributed design methodology where designs emerge as a result of the negotiations between different stake holders in the process, such as cost, performance, reliability, etc. The proposed methodology uses autonomous agents to represent design decision makers. Each agent influences specific design parameters in order to maximize their utility. Since the design parameters depend on the aggregate demand of all the agents in the system, design agents need to negotiate with others in the market economy in order to reach an acceptable utility value. This paper addresses several interesting research issues related to distributed design architectures. First, we present a flexible framework which facilitates decomposition of the design problem. Second, we present overview of a market mechanism for generating acceptable design configurations. Finally, we integrate learning mechanisms in the design process to reduce the computational overhead.

Deshmukh, Abhijit↗
NASA NTRS2000

Multi-Agent Diagnosis and Control of an Air Revitalization System for Life Support in Space

An architecture of interoperating agents has been developed to provide control and fault management for advanced life support systems in space. In this adjustable autonomy architecture, software agents coordinate with human agents and provide support in novel fault management situations. This architecture combines the Livingstone model-based mode identification and reconfiguration (MIR) system with the 3T architecture for autonomous flexible command and control. The MIR software agent performs model-based state identification and diagnosis. MIR identifies novel recovery configurations and the set of commands required for the recovery. The AZT procedural executive and the human operator use the diagnoses and recovery recommendations, and provide command sequencing. User interface extensions have been developed to support human monitoring of both AZT and MIR data and activities. This architecture has been demonstrated performing control and fault management for an oxygen production system for air revitalization in space. The software operates in a dynamic simulation testbed.

Malin, Jane T.↗
NASA NTRS1998

Collaborative Information Agents on the World Wide Web

In this paper, we present DIAMS, a system of distributed, collaborative information agents which help users access, collect, organize, and exchange information on the World Wide Web. Personal agents provide their owners dynamic displays of well organized information collections, as well as friendly information management utilities. Personal agents exchange information with one another. They also work with other types of information agents such as matchmakers and knowledge experts to facilitate collaboration and communication.

Chen, James R.↗
NASA NTRS2001

Designing Agent Collectives For Systems With Markovian Dynamics

The "Collective Intelligence" (COIN) framework concerns the design of collectives of agents so that as those agents strive to maximize their individual utility functions, their interaction causes a provided "world" utility function concerning the entire collective to be also maximized. Here we show how to extend that framework to scenarios having Markovian dynamics when no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. Our approach transforms the (time-extended) argument of each agent's utility function before evaluating that function. This transformation has benefits in scenarios not involving Markovian dynamics, in particular scenarios where not all of the arguments of an agent's utility function are observable. We investigate this transformation in simulations involving both linear and quadratic (nonlinear) dynamics. In addition, we find that a certain subset of these transformations, which result in utilities that have low "opacity (analogous to having high signal to noise) but are not "factored" (analogous to not being incentive compatible), reliably improve performance over that arising with factored utilities. We also present a Taylor Series method for the fully general nonlinear case.

Wolpert, David H.↗
NASA NTRS2002

The Design of Collectives of Agents to Control Non-Markovian Systems

The 'Collective Intelligence' (COIN) framework concerns the design of collectives of reinforcement-learning agents such that their interaction causes a provided 'world' utility function concerning the entire collective to be maximized. Previously, we applied that framework to scenarios involving Markovian dynamics where no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. This approach sets the individual utility function of each agent to be both aligned with the world utility, and at the same time, easy for the associated agents to optimize. Here we extend that approach to systems involving non-Markovian dynamics. In computer simulations, we compare our techniques with each other and with conventional-'team games'. We show whereas in team games performance often degrades badly with time, it steadily improves when our techniques are used. We also investigate situations where the system's dimensionality is effectively reduced. We show that this leads to difficulties in the agents' ability to learn. The implication is that 'learning' is a property only of high-enough dimensional systems.

Lawson, John W.↗
NASA NTRS2001

Design and Control of Large Collections of Learning Agents

The intelligent control of multiple autonomous agents is an important yet difficult task. Previous methods used to address this problem have proved to be either too brittle, too hard to use, or not scalable to large systems. The 'Collective Intelligence' project at NASA/Ames provides an elegant, machine-learning approach to address these problems. This approach mathematically defines some essential properties that a reward system should have to promote coordinated behavior among reinforcement learners. This work has focused on creating additional key properties and algorithms within the mathematics of the Collective Intelligence framework. One of the additions will allow agents to learn more quickly, in a more coordinated manner. The other will let agents learn with less knowledge of their environment. These additions will allow the framework to be applied more easily, to a much larger domain of multi-agent problems.

Agogino, Adrian↗
NASA NTRS2004

Adaptive, Distributed Control of Constrained Multi-Agent Systems

Product Distribution (PO) theory was recently developed as a broad framework for analyzing and optimizing distributed systems. Here we demonstrate its use for adaptive distributed control of Multi-Agent Systems (MASS), i.e., for distributed stochastic optimization using MAS s. First we review one motivation of PD theory, as the information-theoretic extension of conventional full-rationality game theory to the case of bounded rational agents. In this extension the equilibrium of the game is the optimizer of a Lagrangian of the (Probability dist&&on on the joint state of the agents. When the game in question is a team game with constraints, that equilibrium optimizes the expected value of the team game utility, subject to those constraints. One common way to find that equilibrium is to have each agent run a Reinforcement Learning (E) algorithm. PD theory reveals this to be a particular type of search algorithm for minimizing the Lagrangian. Typically that algorithm i s quite inefficient. A more principled alternative is to use a variant of Newton's method to minimize the Lagrangian. Here we compare this alternative to RL-based search in three sets of computer experiments. These are the N Queen s problem and bin-packing problem from the optimization literature, and the Bar problem from the distributed RL literature. Our results confirm that the PD-theory-based approach outperforms the RL-based scheme in all three domains.

Bieniawski, Stefan↗
NASA NTRS2004

Approach for Autonomous Control of Unmanned Aerial Vehicle Using Intelligent Agents for Knowledge Creation

This paper describes the development of a planned approach for Autonomous operation of an Unmanned Aerial Vehicle (UAV). A Hybrid approach will seek to provide Knowledge Generation thru the application of Artificial Intelligence (AI) and Intelligent Agents (IA) for UAV control. The application of many different types of AI techniques for flight will be explored during this research effort. The research concentration will be directed to the application of different AI methods within the UAV arena. By evaluating AI approaches, which will include Expert Systems, Neural Networks, Intelligent Agents, Fuzzy Logic, and Complex Adaptive Systems, a new insight may be gained into the benefits of AI techniques applied to achieving true autonomous operation of these systems thus providing new intellectual merit to this research field. The major area of discussion will be limited to the UAV. The systems of interest include small aircraft, insects, and miniature aircraft. Although flight systems will be explored, the benefits should apply to many Unmanned Vehicles such as: Rovers, Ocean Explorers, Robots, and autonomous operation systems. The flight system will be broken down into control agents that will represent the intelligent agent approach used in AI. After the completion of a successful approach, a framework of applying a Security Overseer will be added in an attempt to address errors, emergencies, failures, damage, or over dynamic environment. The chosen control problem was the landing phase of UAV operation. The initial results from simulation in FlightGear are presented.

Dufrene, Warren R., Jr.↗
NASA NTRS2004

Designing Agent Collectives For Systems With Markovian Dynamics

The Collective Intelligence (COIN) framework concerns the design of collectives of agents so that as those agents strive to maximize their individual utility functions, their interaction causes a provided world utility function concerning the entire collective to be also maximized. Here we show how to extend that framework to scenarios having Markovian dynamics when no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. Our approach transforms the (time-extended) argument of each agent's utility function before evaluating that function. This transformation has benefits in scenarios not involving Markovian dynamics of an agent's utility function are observable. We investigate this transformation in simulations involving both hear and quadratic (nonlinear) dynamics. In addition, we find that a certain subset of these transformations, which result in utilities that have low opacity (analogous to having high signal to noise) but are not factored (analogous to not being incentive compatible), reliably improve performance over that arising with factored utilities. We also present a Taylor Series method for the fully general nonlinear case.

Wolpert, David H.↗
NASA NTRS2004

The Design of Collectives of Agents to Control Non-Markovian Systems

The Collective Intelligence (COIN) framework concerns the design of collectives of reinforcement-learning agents such that their interaction causes a provided "world" utility function concerning the entire collective to be maximized. Previously, we applied that framework to scenarios involving Markovian dynamics where no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. This approach sets the individual utility function of each agent to be both aligned with the world utility, and at the same time, easy for the associated agents to optimize. Here we extend that approach to systems involving non-Markovian dynamics. In computer simulations, we compare our techniques with each other and with conventional "team games". We show whereas in team games performance often degrades badly with time, it steadily improves when our techniques are used. We also investigate situations where the system's dimensionality is effectively reduced. We show that this leads to difficulties in the agents ability to learn. The implication is that learning is a property only of high-enough dimensional systems.

Lawson, John W.↗
NASA NTRS2004

Evaluation of CO2, N2 and He as Fire Suppression Agents in Microgravity

The U.S. modules of the International Space Station use gaseous CO2 as the fire extinguishing agent. This was selected as a result of extensive experience with CO2 as a fire suppressant in terrestrial applications, trade studies on various suppressants, and experiments. The selection of fire suppressants and suppression strategies for NASA s Lunar and Martian exploration missions will be based on the same studies and normal-gravity data unless reduced gravity fire suppression data is obtained. In this study, the suppressant agent concentrations required to extinguish a flame in low velocity convective flows within the 20-sec of low gravity on the KC-135 aircraft were investigated. Suppressant gas mixtures of CO2, N2, and He with the balance being oxygen/nitrogen mixtures with either 21% or 25% O2 were used to suppress flames on a 19-mm diameter PMMA cylinder in reduced gravity. For each of the suppressant mixtures, limiting concentrations were established that would extinguish the flame at any velocity. Similarly, concentrations were established that would not extinguish the flame. The limiting concentrations were generally consistent with previous studies but did suggest that geometry had an effect on the limiting conditions. Between the extinction and non-extinction limits, the suppression characteristics depended on the extinguishing agent, flow velocity, and O2 concentration. The limiting velocity data from the CO2, He, and N2 suppressants were well correlated using an effective mixture enthalpy per mole of O2, indicating that all act via O2 displacement and cooling mechanisms. In reduced gravity, the agent concentration required to suppress the flames increased as the velocity increased, up to approximately 10 cm/s (the maximum velocity evaluated in this experiment). The effective enthalpy required to extinguish flames at velocities of 10 cm/s is approximately the same as the concentrations in normal gravity. A computational study is underway to further evaluate these findings.

Ruff, Gary A.↗
NASA NTRS2004

Using Ontologies to Formalize Services Specifications in Multi-Agent Systems

One key issue in multi-agent systems (MAS) is their ability to interact and exchange information autonomously across applications. To secure agent interoperability, designers must rely on a communication protocol that allows software agents to exchange meaningful information. In this paper we propose using ontologies as such communication protocol. Ontologies capture the semantics of the operations and services provided by agents, allowing interoperability and information exchange in a MAS. Ontologies are a formal, machine processable, representation that allows to capture the semantics of a domain and, to derive meaningful information by way of logical inference. In our proposal we use a formal knowledge representation language (OWL) that translates into Description Logics (a subset of first order logic), thus eliminating ambiguities and providing a solid base for machine based inference. The main contribution of this approach is to make the requirements explicit, centralize the specification in a single document (the ontology itself), at the same that it provides a formal, unambiguous representation that can be processed by automated inference machines.

Breitman, Karin Koogan↗
NASA NTRS2006

Adjustably Autonomous Multi-agent Plan Execution with an Internal Spacecraft Free-Flying Robot Prototype

We present an multi-agent model-based autonomy architecture with monitoring, planning, diagnosis, and execution elements. We discuss an internal spacecraft free-flying robot prototype controlled by an implementation of this architecture and a ground test facility used for development. In addition, we discuss a simplified environment control life support system for the spacecraft domain also controlled by an implementation of this architecture. We discuss adjustable autonomy and how it applies to this architecture. We describe an interface that provides the user situation awareness of both autonomous systems and enables the user to dynamically edit the plans prior to and during execution as well as control these agents at various levels of autonomy. This interface also permits the agents to query the user or request the user to perform tasks to help achieve the commanded goals. We conclude by describing a scenario where these two agents and a human interact to cooperatively detect, diagnose and recover from a simulated spacecraft fault.

Dorais, Gregory A.↗
NASA NTRS2006

QUICR-learning for Multi-Agent Coordination

Coordinating multiple agents that need to perform a sequence of actions to maximize a system level reward requires solving two distinct credit assignment problems. First, credit must be assigned for an action taken at time step t that results in a reward at time step t > t. Second, credit must be assigned for the contribution of agent i to the overall system performance. The first credit assignment problem is typically addressed with temporal difference methods such as Q-learning. The second credit assignment problem is typically addressed by creating custom reward functions. To address both credit assignment problems simultaneously, we propose the "Q Updates with Immediate Counterfactual Rewards-learning" (QUICR-learning) designed to improve both the convergence properties and performance of Q-learning in large multi-agent problems. QUICR-learning is based on previous work on single-time-step counterfactual rewards described by the collectives framework. Results on a traffic congestion problem shows that QUICR-learning is significantly better than a Q-learner using collectives-based (single-time-step counterfactual) rewards. In addition QUICR-learning provides significant gains over conventional and local Q-learning. Additional results on a multi-agent grid-world problem show that the improvements due to QUICR-learning are not domain specific and can provide up to a ten fold increase in performance over existing methods.

Agogino, Adrian K.↗