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 1,747 records · Page 97
All sourcesNASA NTRSDOE OSTI
NASA NTRS1999

A Survey of Collective Intelligence

This chapter presents the science of "COllective INtelligence" (COIN). A COIN is a large multi-agent systems where: i) the agents each run reinforcement learning (RL) algorithms; ii) there is little to no centralized communication or control; iii) there is a provided world utility function that, rates the possible histories of tile full system. Tile conventional approach to designing large distributed systems to optimize a world utility does not use agents running RL algorithms. Rather that approach begins with explicit modeling of the overall system's dynamics, followed by detailed hand-tuning of the interactions between the components to ensure that they "cooperate" as far as the world utility is concerned. This approach is labor-intensive, often results in highly non-robust systems, and usually results in design techniques that, have limited applicability. In contrast, with COINs we wish to solve the system design problems implicitly, via the 'adaptive' character of the RL algorithms of each of the agents. This COIN approach introduces an entirely new, profound design problem: Assuming the RL algorithms are able to achieve high rewards, what reward functions for the individual agents will, when pursued by those agents, result in high world utility? In other words, what reward functions will best ensure that we do not have phenomena like the tragedy of the commons, or Braess's paradox? Although still very young, the science of COINs has already resulted in successes in artificial domains, in particular in packet-routing, the leader-follower problem, and in variants of Arthur's "El Farol bar problem". It is expected that as it matures not only will COIN science expand greatly the range of tasks addressable by human engineers, but it will also provide much insight into already established scientific fields, such as economics, game theory, or population biology.

Wolpert, David H.↗
NASA NTRS2003

Advantages of Brahms for Specifying and Implementing a Multiagent Human-Robotic Exploration System

We have developed a model-based, distributed architecture that integrates diverse components in a system designed for lunar and planetary surface operations: an astronaut's space suit, cameras, all-terrain vehicles, robotic assistant, crew in a local habitat, and mission support team. Software processes ('agents') implemented in the Brahms language, run on multiple, mobile platforms. These mobile agents interpret and transform available data to help people and robotic systems coordinate their actions to make operations more safe and efficient. The Brahms-based mobile agent architecture (MAA) uses a novel combination of agent types so the software agents may understand and facilitate communications between people and between system components. A state-of-the-art spoken dialogue interface is integrated with Brahms models, supporting a speech-driven field observation record and rover command system. An important aspect of the methodology involves first simulating the entire system in Brahms, then configuring the agents into a runtime system Thus, Brahms provides a language, engine, and system builder's toolkit for specifying and implementing multiagent systems.

Clancey, William J.↗
NASA NTRS2003

Collective Intelligence

Many systems of self-interested agents have an associated performance criterion that rates the dynamic behavior of the overall system. This chapter presents an introduction to the science of such systems. Formally, collectives are defined as any system having the following two characteristics: First, the system must contain one or more agents each of which we view as trying to maximize an associated private utility; second, the system must have an associated world utility function that rates the possible behaviors of that overall system. In practice, collectives are often very large, distributed, and support little, if any, centralized communication and control, although those characteristics are not part of their formal definition. A naturally occurring example of a collective is a human economy. One can identify the agents and their private utilities as the human individuals in the economy and the associated personal rewards they are each trying to maximize. One could then identify the world utility as the time average of the gross domestic product. ("World utility" per se is not a construction internal to a human economy, but rather something defined from the outside.) To achieve high world utility it is necessary to avoid having the agents work at cross-purposes lest phenomena like liquidity traps or the Tragedy of the Commons (TOC) occur, in which agents' individually pursuing their private utilities lowers world utility. The obvious way to avoid such phenomena is by modifying the agents utility functions to be "aligned" with the world utility. This can be done via punitive legislation. A real-world example of an attempt to do this was the creation of antitrust regulations designed to prevent monopolistic practices.

Wolpert, David H.↗
NASA NTRS2004

Planning and Execution: The Spirit of Opportunity for Robust Autonomous Systems

One of the most exciting endeavors pursued by human kind is the search for life in the Solar System and the Universe at large. NASA is leading this effort by designing, deploying and operating robotic systems that will reach planets, planet moons, asteroids and comets searching for water, organic building blocks and signs of past or present microbial life. None of these missions will be achievable without substantial advances in.the design, implementation and validation of autonomous control agents. These agents must be capable of robustly controlling a robotic explorer in a hostile environment with very limited or no communication with Earth. The talk focuses on work pursued at the NASA Ames Research center ranging from basic research on algorithm to deployed mission support systems. We will start by discussing how planning and scheduling technology derived from the Remote Agent experiment is being used daily in the operations of the Spirit and Opportunity rovers. Planning and scheduling is also used as the fundamental paradigm at the core of our research in real-time autonomous agents. In particular, we will describe our efforts in the Intelligent Distributed Execution Architecture (IDEA), a multi-agent real-time architecture that exploits artificial intelligence planning as the core reasoning engine of an autonomous agent. We will also describe how the issue of plan robustness at execution can be addressed by novel constraint propagation algorithms capable of giving the tightest exact bounds on resource consumption or all possible executions of a flexible plan.

Muscettola, Nicola↗
NASA NTRS2005

Distributed Adaptive Control: Beyond Single-Instant, Discrete Variables

In extensive form noncooperative game theory, at each instant t, each agent i sets its state x, independently of the other agents, by sampling an associated distribution, q(sub i)(x(sub i)). The coupling between the agents arises in the joint evolution of those distributions. Distributed control problems can be cast the same way. In those problems the system designer sets aspects of the joint evolution of the distributions to try to optimize the goal for the overall system. Now information theory tells us what the separate q(sub i) of the agents are most likely to be if the system were to have a particular expected value of the objective function G(x(sub 1),x(sub 2), ...). So one can view the job of the system designer as speeding an iterative process. Each step of that process starts with a specified value of E(G), and the convergence of the q(sub i) to the most likely set of distributions consistent with that value. After this the target value for E(sub q)(G) is lowered, and then the process repeats. Previous work has elaborated many schemes for implementing this process when the underlying variables x(sub i) all have a finite number of possible values and G does not extend to multiple instants in time. That work also is based on a fixed mapping from agents to control devices, so that the the statistical independence of the agents' moves means independence of the device states. This paper also extends that work to relax all of these restrictions. This extends the applicability of that work to include continuous spaces and Reinforcement Learning. This paper also elaborates how some of that earlier work can be viewed as a first-principles justification of evolution-based search algorithms.

Wolpert, David H.↗
NASA NTRS2006

Distributed Constrained Optimization with Semicoordinate Transformations

Recent work has shown how information theory extends conventional full-rationality game theory to allow bounded rational agents. The associated mathematical framework can be used to solve constrained optimization problems. This is done by translating the problem into an iterated game, where each agent controls a different variable of the problem, so that the joint probability distribution across the agents moves gives an expected value of the objective function. The dynamics of the agents is designed to minimize a Lagrangian function of that joint distribution. Here we illustrate how the updating of the Lagrange parameters in the Lagrangian is a form of automated annealing, which focuses the joint distribution more and more tightly about the joint moves that optimize the objective function. We then investigate the use of "semicoordinate" variable transformations. These separate the joint state of the agents from the variables of the optimization problem, with the two connected by an onto mapping. We present experiments illustrating the ability of such transformations to facilitate optimization. We focus on the special kind of transformation in which the statistically independent states of the agents induces a mixture distribution over the optimization variables. Computer experiment illustrate this for &sat constraint satisfaction problems and for unconstrained minimization of NK functions.

Macready, William↗
NASA NTRS2011

Method for Selective Cleaning of Mold Release from Composite Honeycomb Surfaces

Honeycomb structures are commonly employed as load- and force-bearing structures as they are structurally strong and lightweight. Manufacturing processes for heat-molded composite honeycomb structures commence with the placement of pre-impregnated composite layups over metal mandrels. To prevent permanent bonding between the composite layup and the metal mandrels, an agent, known as a mold release agent, is used. Mold release agents allow the molded composite material to be removed from mandrels after a heat-forming process. Without a specific removal process, mold release agents may continue to adhere to the surface of the composite material, thereby affecting the bonding of other materials that may come into contact with the composite surface in later stages of processing A constituent common to commercially available household cleaning agents is employed for the removal of mold release agents common to the manufacturing of heat-formed composite materials. The reliability of the solvent has been proven by the longevity and reliability of commercial household cleaners. At the time of this reporting, no one has attempted using constituent for this purpose. The material to be cleaned is immersed in the solution, vertically removed so that the solution is allowed to drain along cell walls and into a solvent bath, and then placed on a compressed airflow table for drying.

Pugel, Diane↗
NASA NTRS2003

Software for Sharing and Management of Information

DIAMS is a set of computer programs that implements a system of collaborative agents that serve multiple, geographically distributed users communicating via the Internet. DIAMS provides a user interface as a Java applet that runs on each user s computer and that works within the context of the user s Internet-browser software. DIAMS helps all its users to manage, gain access to, share, and exchange information in databases that they maintain on their computers. One of the DIAMS agents is a personal agent that helps its owner find information most relevant to current needs. It provides software tools and utilities for users to manage their information repositories with dynamic organization and virtual views. Capabilities for generating flexible hierarchical displays are integrated with capabilities for indexed- query searching to support effective access to information. Automatic indexing methods are employed to support users queries and communication between agents. The catalog of a repository is kept in object-oriented storage to facilitate sharing of information. Collaboration between users is aided by matchmaker agents and by automated exchange of information. The matchmaker agents are designed to establish connections between users who have similar interests and expertise.

Chen, James R.↗
NASA NTRS2014

CLEANing the Reward: Counterfactual Actions to Remove Exploratory Action Noise in Multiagent Learning

Learning in multiagent systems can be slow because agents must learn both how to behave in a complex environment and how to account for the actions of other agents. The inability of an agent to distinguish between the true environmental dynamics and those caused by the stochastic exploratory actions of other agents creates noise in each agent's reward signal. This learning noise can have unforeseen and often undesirable effects on the resultant system performance. We define such noise as exploratory action noise, demonstrate the critical impact it can have on the learning process in multiagent settings, and introduce a reward structure to effectively remove such noise from each agent's reward signal. In particular, we introduce Coordinated Learning without Exploratory Action Noise (CLEAN) rewards and empirically demonstrate their benefits

Reinforcement Learning↗
NASA NTRS2018

Serious Gaming for Building a Basis of Certification via Trust and Trustworthiness of Autonomous Systems

Autonomous systems governed by a variety of adaptive and nondeterministic algorithms are being planned for inclusion into safety-critical environments, such as unmanned aircraft and space systems in both civilian and military applications. However, until autonomous systems are proven and perceived to be capable and resilient in the face of unanticipated conditions, humans will be reluctant or unable to delegate authority, remaining in control aided by machine-based information and decision support. Proving capability, or trustworthiness, is a necessary component of certification. Perceived capability is a component of trust. Trustworthiness is an attribute of a cyber-physical system that requires context-driven metrics to prove and certify. Trust is an attribute of the agents participating in the system and is gained over time and multiple interactions through trustworthy behavior and transparency. Historically, artificial intelligence and machine learning systems provide answers without explanation - without a rationale or insight into the machine “thinking”. In order to function as trusted teammates, machines must be able to explain their decisions and actions. This transparency is a product of both content and communication. NASA’s Autonomy Teaming & TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project seeks to build a basis for certification of autonomous systems via establishing metrics for trustworthiness and trust in multi-agent team interactions, using AI (Artificial Intelligence) explainability and persistent modeling and simulation, in the context of mission planning and execution, with analyzable trajectories. Inspired by Massively Multiplayer Online Role Playing Games (MMORPG) and Serious Gaming, the proposed ATTRACTOR modeling and simulation environment is similar to online gaming environments in which player (aka agent) participants interact with each other, affect their environment, and expect the simulation to persist and change regardless of any individual agent’s active participation. This persistent simulation environment will accommodate individual agents, groups of self-organizing agents, and large-scale infrastructure behavior. The effects of the emerging adaptation and coevolution can be observed and measured to building a basis of measurable trustworthiness and trust, toward certification of safety-critical autonomous systems.

Allen, B. Danette↗
NASA NTRS2017

Distributed Fast Motion Planning for Spacecraft Swarms in Cluttered Environments using Spherical Expansions and Sequence of Convex Optimization Problems

This paper presents a novel guidance algorithm for spacecraft swarms in an environment cluttered with many obstacles like a debris field or the asteroid belt. The objective of this algorithm is to reconfigure the swarm to a desired formation in a distributed manner while minimizing fuel and avoiding collisions among themselves and with the obstacles. The agents first use a spherical-expansion-based sampling algorithm to cooperatively explore the workspace and find paths to the desired terminal positions. Using a distributed assignment algorithm, the agents converge on an optimal assignment of the target locations in the desired formation. Then each agent generates a locally optimal trajectory from its current location to its terminal position by solving a sequence of convex optimization problems. As the agent moves along this trajectory, it receives the position of other agents and updates its trajectory to avoid collisions with other agents and the obstacles. Thus the swarm achieves the desired formation in a distributed manner while avoiding collisions. Moreover, this algorithm is computationally efficient, therefore it can be implemented onboard resource-constrained spacecraft. Simulations results show that the proposed distributed algorithm can be used by a spacecraft swarm to reconfigure a desired formation around an asteroid in a collision-free manner.

Bandyopadhyay, Saptarshi↗
NASA NTRS2019

Advancing Aircraft Operations in a Net-Centric Environment with the Incorporation of Increasingly Autonomous Systems and Human Teaming

NextGen has begun the modernization of the nation’s air transportation system, with goals to improve system safety, increase operation efficiency and capacity, provide enhanced predictability, resilience and robustness. With these improvements, NextGen is poised to handle significant increases in air traffic operations, more than twice the number recorded in 2016, by 2025.1 NextGen is evolving toward collaborative decision-making across many agents, including automation, by use of a Net-Centric architecture, which in itself creates a very complex environment in which the navigation and operation of aircraft are to take place. An intricate environment such as this, coupled with the expected upsurge of air traffic operations generates concern respecting the ability of the human-agent to both fly and manage aircraft within. Therefore, it is both necessary and practical to begin the process of increasingly autonomous systems within the cockpit that will act independently to assist the human-agent achieve the overall goal of NextGen. However, the straightforward technological development and implementation of intelligent machines into the cockpit is only part of what is necessary to maintain, at minimum, or improve human-agent functionality, as desired, while operating in NextGen. The full integration of Increasingly Autonomous Systems (IAS) within the cockpit can only be accomplished when the IAS works in concert with the human, formulating trust between the two, thereby establishing a team atmosphere. Imperative to cockpit implementation is ensuring the proper performance of the IAS by the development team and the human-agent with which it will be paired when given a specific piloting, navigation, or observational task. Described in this paper are the steps taken, at NASA Langley Research Center, during the second and third phases of the development of an IAS, the Traffic Data Manager (TDM), its verification and validation by human-agents, and the foundational development of Human Autonomy Teaming (HAT) between the two.

Houston, Vincent E.↗
NASA NTRSDate not supplied

Collision Avoidance Approach Using Deep Reinforcement Learning

A method to enable autonomous robots moving in a 2D space collision free motivates the purposed approach for collision avoidance for autonomous UAM vehicles. Challenges of autonomous collision free navigation for both problems are similar. Agents in each environment do not know the intent, or goal, of the other. Finding the time efficient paths require some level of anticipation with neighboring agents which is computationally expensive. In the original work, these obstacles were overcome with a novel application of deep reinforcement learning which offloads the online computation to an offline learning algorithm. A value network that encodes the estimated time to the goal given the agent’s state and the observable portion of the other agent’s state is trained on a baseline policy and further refined with reinforcement learning to promote time efficient collision free navigation. Online, the value network efficiently informs the agent’s decision making in the face of uncertainty of the other agent’s next move. In this paper, challenges extending this methodology to the 3D environment of autonomous UAM vehicles with kinematic constraints are discussed and initial results shown.

Collision Avoidance↗
NASA NTRSDate not supplied

Collision Avoidance Approach Using Deep Reinforcement Learning

A method to enable autonomous robots moving in a 2D space collision free motivates the purposed approach for collision avoidance for autonomous UAM vehicles. Challenges of autonomous collision free navigation for both problems are similar. Agents in each environment do not know the intent, or goal, of the other. Finding the time efficient paths require some level of anticipation with neighboring agents which is computationally expensive. In the original work, these obstacles were overcome with a novel application of deep reinforcement learning which offloads the online computation to an offline learning algorithm. A value network that encodes the estimated time to the goal given the agent’s state and the observable portion of the other agent’s state is trained on a baseline policy and further refined with reinforcement learning to promote time efficient collision free navigation. Online, the value network efficiently informs the agent’s decision making in the face of uncertainty of the other agent’s next move. In this paper, challenges extending this methodology to the 3D environment of autonomous UAM vehicles with kinematic constraints are discussed and initial results shown.

Collision Avoidance↗
DOE OSTI2016

Method, apparatus and system for managing queue operations of a test bench environment

Techniques and mechanisms for performing dequeue operations for agents of a test bench environment. In an embodiment, a first group of agents are each allocated a respective ripe reservation and a second set of agents are each allocated a respective unripe reservation. Over time, queue management logic allocates respective reservations to agents and variously changes one or more such reservations from unripe to ripe. In another embodiment, an order of servicing agents allocated unripe reservations is based on relative priorities of the unripe reservations with respect to one another. An order of servicing agents allocated ripe reservations is on a first come, first served basis.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Transactive Energy Systems: The Market-based Coordination of Distributed Energy Resources

This paper synthesizes a unifying framework that captures a large class of transactive energy systems studied in the literature. The framework consists of four key elements: agent preferences, control decisions, information structure, and solution concept. Among them, agent preference specifies the preferred outcome by each agent and models the conflict of interest in decision making. Control decision specifies the set of decisions for each agent to maximize its payoff. Information structure describes the information available to each agent before it makes a decision. Solution concept encodes the rationality assumptions of each agent in the system. These elements are important in identifying and distinguishing different transactive energy systems. In this paper, we use them to analyze a number of important ones, including the competitive equilibrium, Stackelberg game, reverse Stackelberg game, and mechanism design. Each class of these problems is formulated as a special case of the proposed transactive energy systems. Their connections and differences are discussed. Available tools and results for each category of problems are surveyed.

Li, Sen↗
DOE OSTI2023

Data exchange and processing synchronization in distributed systems

Systems, methods, techniques and apparatuses of asynchronous communication is distributed systems are disclosed. One exemplary embodiment is a method determining, with a plurality of agent nodes structured to communicate asynchronously in a distributed system, a first set of iterations including an iteration determined by each of the plurality of agent nodes; determining, with a first agent node of the plurality of agent nodes, a local vector clock; receiving, with the first agent node, a first iteration of the first set of iterations and a remote vector clock determined based on the first iteration; updating, with the first agent node, the local vector clock based on the received remote vector clock; and determining a first iteration of a second set of iterations based on the first set of iterations after determining all iterations of the first set of iterations have been received based on the local vector clock.

Cintuglu, Mehmet H.↗
DOE OSTI2020

Novel Foaming Solutions for High Level Waste (HLW) Processing - 20195

Foaming occurs during treatment of high level waste (HLW) at Savannah River Site's Defense Waste Processing Facility (DWPF) in the Chemical Process Cell (CPC) due to high gas generation from process steam and chemical offgas products [1]. The presence of amphiphilic particles in the waste slurry stabilizes the foam [2], [3]. Efficient processing of HLW requires foam control, as foam-overs lead to lower productivity and potential radioactive contamination of condensate streams. DWPF currently employs Siovation Antifoam 747, a surfactant produced by Momentive Performance Materials, as an antifoaming agent during waste treatment. Despite its ability to control foam generation, processing issues have arisen from its use [4]. During DWPF chemical processing, a chemical antifoam agent must be effective at temperatures up to 103 deg. C between pH 3-13. Antifoam 747 is effective at pH 7 but degrades as pH deviates [5]. Antifoam 747 is 90% by weight Momentive{sup TM} L77 and 10% by weight Momentive{sup TM} Y-17580. These ingredients are trisiloxane products, which are especially vulnerable to attack in acidic and caustic environments. Since Antifoam 747 readily degrades, periodic addition is required. Several processing concerns related to Antifoam 747 have affected DWPF operation. Its overuse warranted concern of potential flammable melter offgas under upset conditions due to the generation of carbon dioxide and hydrogen. As a result, a Potential Inadequacy in the Safety Analysis (PISA) was declared [6]. Antifoam contribution has been included in the melter offgas flammability strategy and the quantity of antifoam is monitored to ensure limits are not exceeded. Testing at Savannah River National Laboratory (SRNL) determined that propanal, tri-methylsilanol, and hexamethyldisiloxane are generated as Antifoam 747 degrades, leading to a second PISA [7]. The formation of these byproducts poses additional flammability risks. Furthermore, the methyl and ethyl groups of these compounds may be responsible for the formation of the methyl and ethyl mercury discovered in DWPF [8], [9]. The formation of organomercury has specifically been called out by DOE as a need for increased research. The effectiveness of non-chemical methods for foam control and the efficiency of alternative antifoam agents were evaluated as part of an effort to improve HLW treatment operations at DWPF and to reduce, or eliminate, the flammability hazards associated with Antifoam 747 currently in use. Foaming of high-level waste (HLW) slurries is an issue at the Defense Waste Processing Facility (DWPF) Chemical Process Cell (CPC) which is currently mitigated with a chemical antifoam agent. The effectiveness of non-chemical methods for foam control and the efficiency of alternative antifoams were examined to improve HLW treatment at DWPF and to eliminate the flammability hazards associated with Siovation Antifoam 747 currently in use. Non-chemical foam control methods were deemed unviable for chemical processing at DWPF, as the spray/mist technique requires too much water and space limitations make installation and implementation of headspace agitators unfeasible. The use of ultrasonic energy thickened and further stabilized the foam. Two suitable alternative defoaming agents, Momentive{sup TM} Y- 17112 and Evonik Surfynol{sup R} MD-20, were identified. Both defoamers control foam over a pH range of 4- 13 at boiling, with no flammable degradation products, and only minimal quantities (100-200 mg/kg) are required under glycolic acid conditions. In order to validate the effectiveness of these defoaming agents, SRNL recommends irradiation testing and laboratory scale SRAT/SME experiments with actual radioactive waste. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗