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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Towards the Development of a Multi-Agent Cognitive Networking System for the Lunar Environment

This paper details the development of a multi-agent cognitive system intended to optimize networking performance in the lunar environment. NASA’s current concept of the future of lunar communication, LunaNet, outlines a complex network of networks. Challenges such as scalability, interoperability and reliability must first be addressed to successfully fulfill this vision. Machine intelligence can greatly reduce the reliance on human operators and enable efficient operations for tasks such as scheduling and network management. The application of machine learning, artificial intelligence, and other automated decision-making techniques can be used to allow network nodes to intelligently sense and adapt to changes in the environment such as link disruptions, new nodes joining the network, and support for a diverse range of protocols. Cognitive networking seeks to evolve these technologies into an autonomous system with improved science data return, reliability, and scalability. In this paper, we study three main areas a means to further develop cognitive networking capabilities: networking and flight software development, analysis of wireless data for modeling and simulation, and development of algorithms for a multi-agent system.

Rachel Dudukovich↗
NASA NTRS2004

Efficient Evaluation Functions for Multi-Rover Systems

Evolutionary computation can be a powerful tool in cresting a control policy for a single agent receiving local continuous input. This paper extends single-agent evolutionary computation to multi-agent systems, where a collection of agents strives to maximize a global fitness evaluation function that rates the performance of the entire system. This problem is solved in a distributed manner, where each agent evolves its own population of neural networks that are used as the control policies for the agent. Each agent evolves its population using its own agent-specific fitness evaluation function. We propose to create these agent-specific evaluation functions using the theory of collectives to avoid the coordination problem where each agent evolves a population that maximizes its own fitness function, yet the system has a whole achieves low values of the global fitness function. Instead we will ensure that each fitness evaluation function is both "aligned" with the global evaluation function and is "learnable," i.e., the agents can readily see how their behavior affects their evaluation function. We then show how these agent-specific evaluation functions outperform global evaluation methods by up to 600% in a domain where a set of rovers attempt to maximize the amount of information observed while navigating through a simulated environment.

Agogino, Adrian↗
NASA NTRS2000

Optimal Reward Functions in Distributed Reinforcement Learning

We consider the design of multi-agent systems so as to optimize an overall world utility function when (1) those systems lack centralized communication and control, and (2) each agents runs a distinct Reinforcement Learning (RL) algorithm. A crucial issue in such design problems is to initialize/update each agent's private utility function, so as to induce best possible world utility. Traditional 'team game' solutions to this problem sidestep this issue and simply assign to each agent the world utility as its private utility function. In previous work we used the 'Collective Intelligence' framework to derive a better choice of private utility functions, one that results in world utility performance up to orders of magnitude superior to that ensuing from use of the team game utility. In this paper we extend these results. We derive the general class of private utility functions that both are easy for the individual agents to learn and that, if learned well, result in high world utility. We demonstrate experimentally that using these new utility functions can result in significantly improved performance over that of our previously proposed utility, over and above that previous utility's superiority to the conventional team game utility.

Wolpert, David H.↗
NASA NTRS2005

Towards the Verification of Human-Robot Teams

Human-Agent collaboration is increasingly important. Not only do high-profile activities such as NASA missions to Mars intend to employ such teams, but our everyday activities involving interaction with computational devices falls into this category. In many of these scenarios, we are expected to trust that the agents will do what we expect and that the agents and humans will work together as expected. But how can we be sure? In this paper, we bring together previous work on the verification of multi-agent systems with work on the modelling of human-agent teamwork. Specifically, we target human-robot teamwork. This paper provides an outline of the way we are using formal verification techniques in order to analyse such collaborative activities. A particular application is the analysis of human-robot teams intended for use in future space exploration.

Fisher, Michael↗
NASA NTRS2000

Adaptivity in Agent-Based Routing for Data Networks

Adaptivity, both of the individual agents and of the interaction structure among the agents, seems indispensable for scaling up multi-agent systems (MAS s) in noisy environments. One important consideration in designing adaptive agents is choosing their action spaces to be as amenable as possible to machine learning techniques, especially to reinforcement learning (RL) techniques. One important way to have the interaction structure connecting agents itself be adaptive is to have the intentions and/or actions of the agents be in the input spaces of the other agents, much as in Stackelberg games. We consider both kinds of adaptivity in the design of a MAS to control network packet routing. We demonstrate on the OPNET event-driven network simulator the perhaps surprising fact that simply changing the action space of the agents to be better suited to RL can result in very large improvements in their potential performance: at their best settings, our learning-amenable router agents achieve throughputs up to three and one half times better than that of the standard Bellman-Ford routing algorithm, even when the Bellman-Ford protocol traffic is maintained. We then demonstrate that much of that potential improvement can be realized by having the agents learn their settings when the agent interaction structure is itself adaptive.

Wolpert, David H.↗
NASA NTRS2003

Self-Supervised Dynamical Systems

Some progress has been made in a continuing effort to develop mathematical models of the behaviors of multi-agent systems known in biology, economics, and sociology (e.g., systems ranging from single or a few biomolecules to many interacting higher organisms). Living systems can be characterized by nonlinear evolution of probability distributions over different possible choices of the next steps in their motions. One of the main challenges in mathematical modeling of living systems is to distinguish between random walks of purely physical origin (for instance, Brownian motions) and those of biological origin. Following a line of reasoning from prior research, it has been assumed, in the present development, that a biological random walk can be represented by a nonlinear mathematical model that represents coupled mental and motor dynamics incorporating the psychological concept of reflection or self-image. The nonlinear dynamics impart the lifelike ability to behave in ways and to exhibit patterns that depart from thermodynamic equilibrium. Reflection or self-image has traditionally been recognized as a basic element of intelligence. The nonlinear mathematical models of the present development are denoted self-supervised dynamical systems. They include (1) equations of classical dynamics, including random components caused by uncertainties in initial conditions and by Langevin forces, coupled with (2) the corresponding Liouville or Fokker-Planck equations that describe the evolutions of probability densities that represent the uncertainties. The coupling is effected by fictitious information-based forces, denoted supervising forces, composed of probability densities and functionals thereof. The equations of classical mechanics represent motor dynamics that is, dynamics in the traditional sense, signifying Newton s equations of motion. The evolution of the probability densities represents mental dynamics or self-image. Then the interaction between the physical and metal aspects of a monad is implemented by feedback from mental to motor dynamics, as represented by the aforementioned fictitious forces. This feedback is what makes the evolution of probability densities nonlinear. The deviation from linear evolution can be characterized, in a sense, as an expression of free will. It has been demonstrated that probability densities can approach prescribed attractors while exhibiting such patterns as shock waves, solitons, and chaos in probability space. The concept of self-supervised dynamical systems has been considered for application to diverse phenomena, including information-based neural networks, cooperation, competition, deception, games, and control of chaos. In addition, a formal similarity between the mathematical structures of self-supervised dynamical systems and of quantum-mechanical systems has been investigated.

Zak, Michail↗
NASA NTRS2005

Trusted Autonomy for Space Flight Systems

NASA has long supported research on intelligent control technologies that could allow space systems to operate autonomously or with reduced human supervision. Proposed uses range from automated control of entire space vehicles to mobile robots that assist or substitute for astronauts to vehicle systems such as life support that interact with other systems in complex ways and require constant vigilance. The potential for pervasive use of such technology to extend the kinds of missions that are possible in practice is well understood, as is its potential to radically improve the robustness, safety and productivity of diverse mission systems. Despite its acknowledged potential, intelligent control capabilities are rarely used in space flight systems. Perhaps the most famous example of intelligent control on a spacecraft is the Remote Agent system flown on the Deep Space One mission (1998 - 2001). However, even in this case, the role of the intelligent control element, originally intended to have full control of the spacecraft for the duration of the mission, was reduced to having partial control for a two-week non-critical period. Even this level of mission acceptance was exceptional. In most cases, mission managers consider intelligent control systems an unacceptable source of risk and elect not to fly them. Overall, the technology is not trusted. From the standpoint of those who need to decide whether to incorporate this technology, lack of trust is easy to understand. Intelligent high-level control means allowing software io make decisions that are too complex for conventional software. The decision-making behavior of these systems is often hard to understand and inspect, and thus hard to evaluate. Moreover, such software is typically designed and implemented either as a research product or custom-built for a particular mission. In the former case, software quality is unlikely to be adequate for flight qualification and the functionality provided by the system is likely driven largely by the need to publish innovative work. In the latter case, the mission represents the first use of the system, a risky proposition even for relatively simple software.

Freed, Michael↗
NASA NTRS2019

Vehicle to Vehicle (V2V) Communication for Collision Avoidance for Multi-Copters Flying in UTM -TCL4

NASA’s UAS Traffic management (UTM) research initiative is aimed at identifying requirements for safe autonomous operations of UAS operating in dense urban environments. For complete autonomous operations vehicle to vehicle (V2V) communications has been identified as an essential tool. In this paper we simulate a complete urban operations in an high fidelity simulation environment. We design a V2V communication protocol and all the vehicles participating communicate over this system. We show how V2V communication can be used for finding feasible, collision-free paths for multi agent systems. Different collision avoidance schemes are explored and an end to end simulation study shows the use of V2V communication for UTM TCL4 deployment.

Chakrabarty, Anjan↗
NASA NTRS2011

Systems, methods and apparatus for developing and maintaining evolving systems with software product lines

Systems, methods and apparatus are provided through which an evolutionary system is managed and viewed as a software product line. In some embodiments, the core architecture is a relatively unchanging part of the system, and each version of the system is viewed as a product from the product line. Each software product is generated from the core architecture with some agent-based additions. The result may be a multi-agent system software product line.

Hinchey, Michael G.↗
NASA NTRS2010

Development and Evaluation of Sensor Concepts for Ageless Aerospace Vehicles: Report 6 - Development and Demonstration of a Self-Organizing Diagnostic System for Structural Health Monitoring

This report describes a significant advance in the capability of the CSIRO/NASA structural health monitoring Concept Demonstrator (CD). The main thrust of the work has been the development of a mobile robotic agent, and the hardware and software modifications and developments required to enable the demonstrator to operate as a single, self-organizing, multi-agent system. This single-robot system is seen as the forerunner of a system in which larger numbers of small robots perform inspection and repair tasks cooperatively, by self-organization. While the goal of demonstrating self-organized damage diagnosis was not fully achieved in the time available, much of the work required for the final element that enables the robot to point the video camera and transmit an image has been completed. A demonstration video of the CD and robotic systems operating will be made and forwarded to NASA.

Batten, Adam↗
NASA NTRSDate not supplied

Autonomous Spacecraft Inspection with Free-Flying Drones

This paper describes a proof-of-concept mission demonstrating a multi-agent system performing visual inspection of damage sustained by a spacecraft. Free-flying satellites, simulated by unmanned aerial vehicles (UAVs), autonomously fly around a mock space module maximizing the search space for damage detection. The free-flyers are responsible for independently coordinating their flights to avoid collision with the space module and each other, while executing mission tasks. Damage analysis on the surface of the mock space module is performed in real-time using video from each free-flyer. Three-dimensional modeling is deployed offline to supplement and improve damage detection. This approach demonstrates the feasibility of deploying real space systems for damage detection, where 2D analysis can quickly determine region of interest and 3D visualization can produce a human-navigable virtual environment with depth perspective for further investigation.

unmanned aerial vehicle (UAV)↗
NASA NTRS2005

Distributed Optimization

We demonstrate a new framework for analyzing and controlling distributed systems, by solving constrained optimization problems with an algorithm based on that framework. The framework is ar. information-theoretic extension of conventional full-rationality game theory to allow bounded rational agents. The associated optimization algorithm is a game in which agents control the variables of the optimization problem. They do this by jointly minimizing a Lagrangian of (the probability distribution of) their joint state. The updating of the Lagrange parameters in that Lagrangian is a form of automated annealing, one that focuses the multi-agent system on the optimal pure strategy. We present computer experiments for the k-sat constraint satisfaction problem and for unconstrained minimization of NK functions.

Macready, William↗
NASA NTRS2010

Modeling Common-Sense Decisions in Artificial Intelligence

A methodology has been conceived for efficient synthesis of dynamical models that simulate common-sense decision- making processes. This methodology is intended to contribute to the design of artificial-intelligence systems that could imitate human common-sense decision making or assist humans in making correct decisions in unanticipated circumstances. This methodology is a product of continuing research on mathematical models of the behaviors of single- and multi-agent systems known in biology, economics, and sociology, ranging from a single-cell organism at one extreme to the whole of human society at the other extreme. Earlier results of this research were reported in several prior NASA Tech Briefs articles, the three most recent and relevant being Characteristics of Dynamics of Intelligent Systems (NPO -21037), NASA Tech Briefs, Vol. 26, No. 12 (December 2002), page 48; Self-Supervised Dynamical Systems (NPO-30634), NASA Tech Briefs, Vol. 27, No. 3 (March 2003), page 72; and Complexity for Survival of Living Systems (NPO- 43302), NASA Tech Briefs, Vol. 33, No. 7 (July 2009), page 62. The methodology involves the concepts reported previously, albeit viewed from a different perspective. One of the main underlying ideas is to extend the application of physical first principles to the behaviors of living systems. Models of motor dynamics are used to simulate the observable behaviors of systems or objects of interest, and models of mental dynamics are used to represent the evolution of the corresponding knowledge bases. For a given system, the knowledge base is modeled in the form of probability distributions and the mental dynamics is represented by models of the evolution of the probability densities or, equivalently, models of flows of information. Autonomy is imparted to the decisionmaking process by feedback from mental to motor dynamics. This feedback replaces unavailable external information by information stored in the internal knowledge base. Representation of the dynamical models in a parameterized form reduces the task of common-sense-based decision making to a solution of the following hetero-associated-memory problem: store a set of m predetermined stochastic processes given by their probability distributions in such a way that when presented with an unexpected change in the form of an input out of the set of M inputs, the coupled motormental dynamics converges to the corresponding one of the m pre-assigned stochastic process, and a sample of this process represents the decision.

Zak, Michail↗
NASA NTRS2003

Transition-Independent Decentralized Markov Decision Processes

There has been substantial progress with formal models for sequential decision making by individual agents using the Markov decision process (MDP). However, similar treatment of multi-agent systems is lacking. A recent complexity result, showing that solving decentralized MDPs is NEXP-hard, provides a partial explanation. To overcome this complexity barrier, we identify a general class of transition-independent decentralized MDPs that is widely applicable. The class consists of independent collaborating agents that are tied up by a global reward function that depends on both of their histories. We present a novel algorithm for solving this class of problems and examine its properties. The result is the first effective technique to solve optimally a class of decentralized MDPs. This lays the foundation for further work in this area on both exact and approximate solutions.

Becker, Raphen↗
NASA NTRSDate not supplied

Impact of Traffic-Following on Order of Autonomous Airspace Operations

In this paper, we investigate the dynamic emergence of traffic order in a distributed multi-agent system, aiming to minimize inefficiencies that stem from unnecessary structural impositions. We introduce a methodology for developing a dynamically updating traffic pattern map of the airspace by leveraging information about the consistency and frequency of flow directions used by current as well as preceding traffic. Informed by this map, an agent can discern the degree to which it is advantageous to follow traffic by trading off utilities such as time and order. We show that for the traffic levels studied, for low degrees of traffic-following behavior, there is minimal penalty in terms of aircraft travel times while improving the overall orderliness of the airspace. On the other hand, heightened traffic-following behavior may result in increased aircraft travel times, while marginally reducing the overall entropy of the airspace. Ultimately, the methods and metrics presented in this paper can be used to optimally and dynamically adjust an agent’s traffic-following behavior based on these trade-offs.

Airspace Operations↗
NASA NTRSDate not supplied

Impact of Traffic-Following on Order of Autonomous Airspace Operations

We investigate the dynamic emergence of traffic order in a distributed multi-agent system, aiming to minimize inefficiencies that stem from unnecessary structural impositions. We introduce a methodology for developing a dynamically updating traffic pattern map of the airspace by leveraging information about the consistency and frequency of flow directions used by current as well as preceding traffic. Informed by this map, an agent can discern the degree to which it is advantageous to follow traffic by trading off utilities such as time and order. We show that for the traffic levels studied, for low degrees of traffic-following behavior, there is minimal penalty in terms of aircraft travel times while improving the overall orderliness of the airspace. On the other hand, heightened traffic-following behavior may result in increased aircraft travel times, while marginally reducing the overall entropy of the airspace. Ultimately, the methods and metrics presented in this paper can be used to optimally and dynamically adjust an agent’s traffic-following behavior based on these trade-offs.

Airspace Operations↗
NASA NTRSDate not supplied

Zero-Trust Architecture for Autonomous Edge Computing

We are at the apex of an aviation revolution where autonomy will play a central role in enabling complex, multi-agent systems to communicate, interact, and collaborate on a myriad of applications spanning autonomous swarms to wild-fire management. Autonomy is not an absolute but rather a spectrum ranging from a system requiring significant human intervention to one requiring little to none [1]. For example, the extreme, in the case of an autonomous aircraft, is one that operates independently in the airspace interacting with all other elements (air traffic controllers, other pilots) as if it were a human pilot. Critical to this vision is an architecture that enables autonomous agents to interact with minimal latency. Edge computing is an emerging architecture where compute and storage is pushed to the ‘edge’ of the network in order to minimize the round-trip time from agent to resource thereby mitigating the latency associated with cloud-only based approaches. Additionally, services can generate massive amounts of data (e.g., video feeds), which may require analysis in near real-time. Moving this data to the cloud for further processing may not be feasible due to latency, bandwidth, and cost. Privacy, security, and reliability can also be improved by edge computing architectures. However, this geo-distributed and dynamic* architecture complicates the establishment of unambiguous network security boundaries and can lead to vulnerabilities including man in the middle attacks, replay attacks, physical security breaches of edge nodes, signal interception, etc. This motivates the need for zero-trust architectures [2–4] which de-emphasize the notion of static network perimeters and, as the name implies, do not instill any innate trust in any particular agent. It is required that all agents must be authorized and approved in every transaction. In this paper, we present a zero-trust architecture suitable for edge-computing applications that demand significant low-latency, security, privacy, and reliability.

zero trust↗
NASA NTRSDate not supplied

Inertial Transfer: Concept and Multi-Agent Approach

Research and development of cost saving technologies is vital to the success of NASA’s strategic goal to extend human presence deeper into space and to the moon for sustainable long-term exploration and utilization. Reduction of mass has long been a method of reducing space mission costs. In this submission, Inertial Transfer, a new approach to mass transfer in space, is presented. A Multi-Agent System solution to the problem space is discussed. A scaled base-line simulator is constructed and demonstrated which will enable the development of AI capabilities necessary to perform Inertial Transfer. Finally, future work and key challenges are discussed.

Multi-Agent↗