Search NASA⌕ Search

SEARCH · Search NASA

Results for “agentic systems”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
NASA NTRS2005

Situation Awareness of Onboard System Autonomy

We have developed intelligent agent software for onboard system autonomy. Our approach is to provide control agents that automate crew and vehicle systems, and operations assistants that aid humans in working with these autonomous systems. We use the 3 Tier control architecture to develop the control agent software that automates system reconfiguration and routine fault management. We use the Distributed Collaboration and Interaction (DCI) System to develop the operations assistants that provide human services, including situation summarization, event notification, activity management, and support for manual commanding of autonomous system. In this paper we describe how the operations assistants aid situation awareness of the autonomous control agents. We also describe our evaluation of the DCI System to support control engineers during a ground test at Johnson Space Center (JSC) of the Post Processing System (PPS) for regenerative water recovery.

Schreckenghost, Debra↗
NASA NTRS2002

CATS-based Agents That Err

This report describes preliminary research on intelligent agents that make errors. Such agents are crucial to the development of novel agent-based techniques for assessing system safety. The agents extend an agent architecture derived from the Crew Activity Tracking System that has been used as the basis for air traffic controller agents. The report first reviews several error taxonomies. Next, it presents an overview of the air traffic controller agents, then details several mechanisms for causing the agents to err in realistic ways. The report presents a performance assessment of the error-generating agents, and identifies directions for further research. The research was supported by the System-Wide Accident Prevention element of the FAA/NASA Aviation Safety Program.

Callantine, Todd J.↗
NASA NTRS1994

Reflexive reasoning for distributed real-time systems

This paper discusses the implementation and use of reflexive reasoning in real-time, distributed knowledge-based applications. Recently there has been a great deal of interest in agent-oriented systems. Implementing such systems implies a mechanism for sharing knowledge, goals and other state information among the agents. Our techniques facilitate an agent examining both state information about other agents and the parameters of the knowledge-based system shell implementing its reasoning algorithms. The shell implementing the reasoning is the Distributed Artificial Intelligence Toolkit, which is a derivative of CLIPS.

Goldstein, David↗
NASA NTRS2004

Hybrid Exploration Agent Platform and Sensor Web System

A sensor web to collect the scientific data needed to further exploration is a major and efficient asset to any exploration effort. This is true not only for lunar and planetary environments, but also for interplanetary and liquid environments. Such a system would also have myriad direct commercial spin-off applications. The Hybrid Exploration Agent Platform and Sensor Web or HEAP-SW like the ANTS concept is a Sensor Web concept. The HEAP-SW is conceptually and practically a very different system. HEAP-SW is applicable to any environment and a huge range of exploration tasks. It is a very robust, low cost, high return, solution to a complex problem. All of the technology for initial development and implementation is currently available. The HEAP Sensor Web or HEAP-SW consists of three major parts, The Hybrid Exploration Agent Platforms or HEAP, the Sensor Web or SW and the immobile Data collection and Uplink units or DU. The HEAP-SW as a whole will refer to any group of mobile agents or robots where each robot is a mobile data collection unit that spends most of its time acting in concert with all other robots, DUs in the web, and the HEAP-SWs overall Command and Control (CC) system. Each DU and robot is, however, capable of acting independently. The three parts of the HEAP-SW system are discussed in this paper. The Goals of the HEAP-SW system are: 1) To maximize the amount of exploration enhancing science data collected; 2) To minimize data loss due to system malfunctions; 3) To minimize or, possibly, eliminate the risk of total system failure; 4) To minimize the size, weight, and power requirements of each HEAP robot; 5) To minimize HEAP-SW system costs. The rest of this paper discusses how these goals are attained.

Stoffel, A. William↗
NASA NTRS2003

A Real-Time Rover Executive based On Model-Based Reactive Planning

This paper reports on the experimental verification of the ability of IDEA (Intelligent Distributed Execution Architecture) effectively operate at multiple levels of abstraction in an autonomous control system. The basic hypothesis of IDEA is that a large control system can be structured as a collection of interacting control agents, each organized around the same fundamental structure. Two IDEA agents, a system-level agent and a mission-level agent, are designed and implemented to autonomously control the K9 rover in real-time. The system is evaluated in the scenario where the rover must acquire images from a specified set of locations. The IDEA agents are responsible for enabling the rover to achieve its goals while monitoring the execution and safety of the rover and recovering from dangerous states when necessary. Experiments carried out both in simulation and on the physical rover, produced highly promising results.

Bias, M. Bernardine↗
NASA NTRS1994

DYNACLIPS (DYNAmic CLIPS): A dynamic knowledge exchange tool for intelligent agents

In a dynamic environment, intelligent agents must be responsive to unanticipated conditions. When such conditions occur, an intelligent agent may have to stop a previously planned and scheduled course of actions and replan, reschedule, start new activities and initiate a new problem solving process to successfully respond to the new conditions. Problems occur when an intelligent agent does not have enough knowledge to properly respond to the new situation. DYNACLIPS is an implementation of a framework for dynamic knowledge exchange among intelligent agents. Each intelligent agent is a CLIPS shell and runs a separate process under SunOS operating system. Intelligent agents can exchange facts, rules, and CLIPS commands at run time. Knowledge exchange among intelligent agents at run times does not effect execution of either sender and receiver intelligent agent. Intelligent agents can keep the knowledge temporarily or permanently. In other words, knowledge exchange among intelligent agents would allow for a form of learning to be accomplished.

Cengeloglu, Yilmaz↗
NASA NTRS2005

Distributed Evaluation Functions for Fault Tolerant Multi-Rover Systems

The ability to evolve fault tolerant control strategies for large collections of agents is critical to the successful application of evolutionary strategies to domains where failures are common. Furthermore, while evolutionary algorithms have been highly successful in discovering single-agent control strategies, extending such algorithms to multiagent domains has proven to be difficult. In this paper we present a method for shaping evaluation functions for agents that provide control strategies that both are tolerant to different types of failures and lead to coordinated behavior in a multi-agent setting. This method neither relies of a centralized strategy (susceptible to single point of failures) nor a distributed strategy where each agent uses a system wide evaluation function (severe credit assignment problem). In a multi-rover problem, we show that agents using our agent-specific evaluation perform up to 500% better than agents using the system evaluation. In addition we show that agents are still able to maintain a high level of performance when up to 60% of the agents fail due to actuator, communication or controller faults.

Agogino, Adrian↗
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 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 NTRS2005

Automating CapCom Using Mobile Agents and Robotic Assistants

We have developed and tested an advanced EVA communications and computing system to increase astronaut self-reliance and safety, reducing dependence on continuous monitoring and advising from mission control on Earth. This system, called Mobile Agents (MA), is voice controlled and provides information verbally to the astronauts through programs called personal agents. The system partly automates the role of CapCom in Apollo-including monitoring and managing EVA navigation, scheduling, equipment deployment, telemetry, health tracking, and scientific data collection. EVA data are stored automatically in a shared database in the habitat/vehicle and mirrored to a site accessible by a remote science team. The program has been developed iteratively in the context of use, including six years of ethnographic observation of field geology. Our approach is to develop automation that supports the human work practices, allowing people to do what they do well, and to work in ways they are most familiar. Field experiments in Utah have enabled empirically discovering requirements and testing alternative technologies and protocols. This paper reports on the 2004 system configuration, experiments, and results, in which an EVA robotic assistant (ERA) followed geologists approximately 150 m through a winding, narrow canyon. On voice command, the ERA took photographs and panoramas and was directed to move and wait in various locations to serve as a relay on the wireless network. The MA system is applicable to many space work situations that involve creating and navigating from maps (including configuring equipment for local topology), interacting with piloted and unpiloted rovers, adapting to environmental conditions, and remote team collaboration involving people and robots.

Clancey, William J.↗
NASA NTRS2013

Predicting Pilot Behavior in Medium Scale Scenarios Using Game Theory and Reinforcement Learning

Effective automation is critical in achieving the capacity and safety goals of the Next Generation Air Traffic System. Unfortunately creating integration and validation tools for such automation is difficult as the interactions between automation and their human counterparts is complex and unpredictable. This validation becomes even more difficult as we integrate wide-reaching technologies that affect the behavior of different decision makers in the system such as pilots, controllers and airlines. While overt short-term behavior changes can be explicitly modeled with traditional agent modeling systems, subtle behavior changes caused by the integration of new technologies may snowball into larger problems and be very hard to detect. To overcome these obstacles, we show how integration of new technologies can be validated by learning behavior models based on goals. In this framework, human participants are not modeled explicitly. Instead, their goals are modeled and through reinforcement learning their actions are predicted. The main advantage to this approach is that modeling is done within the context of the entire system allowing for accurate modeling of all participants as they interact as a whole. In addition such an approach allows for efficient trade studies and feasibility testing on a wide range of automation scenarios. The goal of this paper is to test that such an approach is feasible. To do this we implement this approach using a simple discrete-state learning system on a scenario where 50 aircraft need to self-navigate using Automatic Dependent Surveillance-Broadcast (ADS-B) information. In this scenario, we show how the approach can be used to predict the ability of pilots to adequately balance aircraft separation and fly efficient paths. We present results with several levels of complexity and airspace congestion.

Game Theory↗
NASA NTRS2000

Agent Building Software

AgentBuilder is a software component developed under an SBIR contract between Reticular Systems, Inc., and Goddard Space Flight Center. AgentBuilder allows software developers without experience in intelligent agent technologies to easily build software applications using intelligent agents. Agents are components of software that will perform tasks automatically, with no intervention or command from a user. AgentBuilder reduces the time and cost of developing agent systems and provides a simple mechanism for implementing high-performance agent systems.

Source record↗
NASA NTRS2001

Autonomy for SOHO Ground Operations

The SOLAR and HELIOSPHERIC OBSERVATORY (SOHO) project [SOHO Web Page] is being carried out by the European Space Agency (ESA) and the US National Aeronautics and Space Administration (NASA) as a cooperative effort between the two agencies in the framework of the Solar Terrestrial Science Program (STSP) comprising SOHO and other missions. SOHO was launched on December 2, 1995. The SOHO spacecraft was built in Europe by an industry team led by Matra, and instruments were provided by European and American scientists. There are nine European Principal Investigators (PI's) and three American ones. Large engineering teams and more than 200 co-investigators from many institutions support the PI's in the development of the instruments and in the preparation of their operations and data analysis. NASA is responsible for the launch and mission operations. Large radio dishes around the world, which form NASA's Deep Space Network (DSN), are used to track the spacecraft beyond the Earths orbit. Mission control is based at Goddard Space Flight Center in Maryland. The agent group at the NASA Goddard Space Flight Center, in collaboration with JPL, is currently involved with the design and development of an agent-based system to provide intelligent interactions with the control center personnel for SOHO. The basic approach that is being taken is to develop a sub-community of agents for each major subsystem of SOHO and to integrate these sub-communities into an overall SOHO community. Agents in all sub-communities will be capable of advanced understanding (deep reasoning) of the associated spacecraft subsystem.

Truszkowski, Walt↗
NASA NTRS1990

A distributed agent architecture for real-time knowledge-based systems: Real-time expert systems project, phase 1

We propose a distributed agent architecture (DAA) that can support a variety of paradigms based on both traditional real-time computing and artificial intelligence. DAA consists of distributed agents that are classified into two categories: reactive and cognitive. Reactive agents can be implemented directly in Ada to meet hard real-time requirements and be deployed on on-board embedded processors. A traditional real-time computing methodology under consideration is the rate monotonic theory that can guarantee schedulability based on analytical methods. AI techniques under consideration for reactive agents are approximate or anytime reasoning that can be implemented using Bayesian belief networks as in Guardian. Cognitive agents are traditional expert systems that can be implemented in ART-Ada to meet soft real-time requirements. During the initial design of cognitive agents, it is critical to consider the migration path that would allow initial deployment on ground-based workstations with eventual deployment on on-board processors. ART-Ada technology enables this migration while Lisp-based technologies make it difficult if not impossible. In addition to reactive and cognitive agents, a meta-level agent would be needed to coordinate multiple agents and to provide meta-level control.

Lee, S. Daniel↗
NASA NTRS2018

Considerations in Assuring Safety of Increasingly Autonomous Systems

Recent technological advances have accelerated the development and application of increasingly autonomous (IA) systems in civil and military aviation. IA systems can provide automation of complex mission tasks-ranging across reduced crew operations, air-traffic management, and unmanned, autonomous aircraft-with most applications calling for collaboration and teaming among humans and IA agents. IA systems are expected to provide benefits in terms of safety, reliability, efficiency, affordability, and previously unattainable mission capability. There is also a potential for improving safety by removal of human errors. There are, however, several challenges in the safety assurance of these systems due to the highly adaptive and non-deterministic behavior of these systems, and vulnerabilities due to potential divergence of airplane state awareness between the IA system and humans. These systems must deal with external sensors and actuators, and they must respond in time commensurate with the activities of the system in its environment. One of the main challenges is that safety assurance, currently relying upon authority transfer from an autonomous function to a human to mitigate safety concerns, will need to address their mitigation by automation in a collaborative dynamic context. These challenges have a fundamental, multidimensional impact on the safety assurance methods, system architecture, and V&V capabilities to be employed. The goal of this report is to identify relevant issues to be addressed in these areas, the potential gaps in the current safety assurance techniques, and critical questions that would need to be answered to assure safety of IA systems. We focus on a scenario of reduced crew operation when an IA system is employed which reduces, changes or eliminates a human's role in transition from two-pilot operations.

Alves, Erin E.↗
NASA NTRS2004

Autonomous and Autonomic Systems: A Paradigm for Future Space Exploration Missions

NASA increasingly will rely on autonomous systems concepts, not only in the mission control centers on the ground, but also on spacecraft and on rovers and other assets on extraterrestrial bodies. Automomy enables not only reduced operations costs, But also adaptable goal-driven functionality of mission systems. Space missions lacking autonomy will be unable to achieve the full range of advanced mission objectives, given that human control under dynamic environmental conditions will not be feasible due, in part, to the unavoidably high signal propagation latency and constrained data rates of mission communications links. While autonomy cost-effectively supports accomplishment of mission goals, autonomicity supports survivability of remote mission assets, especially when human tending is not feasible. Autonomic system properties (which ensure self-configuring, self-optimizing self-healing, and self-protecting behavior) conceptually may enable space missions of a higher order into any previously flown. Analysis of two NASA agent-based systems previously prototyped, and of a proposed future mission involving numerous cooperating spacecraft, illustrates how autonomous and autonomic system concepts may be brought to bear on future space missions.

Truszkowski, Walter F.↗
NASA NTRS2020

Assemblers: A Modular, Reconfigurable Manipulator for Autonomous in-Space Assembly

This paper presents a modular, reconfigurable robotic manipulator for autonomous in-space assembly. On-orbit and planetary surface assembly is a challenging domain that encompasses various technological thrusts to support human exploration, science, and technology demonstration missions. The system architecture presented here addresses the need for robotic assembly of structures in locations that prohibit constant human oversight and/or teleoperation. This system is capable of scheduling, reconfiguring itself, and executing structural assembly tasks with the ability to assess construction and correct errors during the assembly as needed. An example concept of operations is presented. Details of the mechanical and electrical design of the robotic modules as well as the dynamic modeling approach, control algorithms, and sensing and perception systems are also provided.

robotics↗