Search NASA⌕ Search

SEARCH · Search NASA

Results for “sequential decision making”

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 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS1980

Sequential decision making and stochastic networks

To solve the problems inherent in working with sequential decision processes, it is proposed to (1) utilize concepts of dominance through bounding in the decision processes (DP) formalism to reduce the amount of computing required. This advocates the marrying of DP recursion and Branch-and-Bound methodology; and (2) relax the requirement of strict optimality in the search over the state space, and be content with a tolerable error.

Elmaghraby, S.↗
NASA NTRS1994

Human-Computer Interaction with Medical Decisions Support Systems

Decision Support Systems (DSSs) have been available to medical diagnosticians for some time, yet their acceptance and use have not increased with advances in technology and availability of DSS tools. Medical DSSs will be necessary on future long duration space missions, because access to medical resources and personnel will be limited. Human-Computer Interaction (HCI) experts at NASA's Human Factors and Ergonomics Laboratory (HFEL) have been working toward understanding how humans use DSSs, with the goal of being able to identify and solve the problems associated with these systems. Work to date consists of identification of HCI research areas, development of a decision making model, and completion of two experiments dealing with 'anchoring'. Anchoring is a phenomenon in which the decision maker latches on to a starting point and does not make sufficient adjustments when new data are presented. HFEL personnel have replicated a well-known anchoring experiment and have investigated the effects of user level of knowledge. Future work includes further experimentation on level of knowledge, confidence in the source of information and sequential decision making.

Adolf, Jurine A.↗
NASA NTRS1997

Collaborative, Sequential and Isolated Decisions in Design

The Massachusetts Institute of Technology (MIT) Commission on Industrial Productivity, in their report Made in America, found that six recurring weaknesses were hampering American manufacturing industries. The two weaknesses most relevant to product development were 1) technological weakness in development and production, and 2) failures in cooperation. The remedies to these weaknesses are considered the essential twin pillars of CE: 1) improved development process, and 2) closer cooperation. In the MIT report, it is recognized that total cooperation among teams in a CE environment is rare in American industry, while the majority of the design research in mathematically modeling CE has assumed total cooperation. In this paper, we present mathematical constructs, based on game theoretic principles, to model degrees of collaboration characterized by approximate cooperation, sequential decision making and isolation. The design of a pressure vessel and a passenger aircraft are included as illustrative examples.

Lewis, Kemper↗
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 NTRS2012

A Risk-Constrained Multi-Stage Decision Making Approach to the Architectural Analysis of Mars Missions

This paper presents a novel risk-constrained multi-stage decision making approach to the architectural analysis of planetary rover missions. In particular, focusing on a 2018 Mars rover concept, which was considered as part of a potential Mars Sample Return campaign, we model the entry, descent, and landing (EDL) phase and the rover traverse phase as four sequential decision-making stages. The problem is to find a sequence of divert and driving maneuvers so that the rover drive is minimized and the probability of a mission failure (e.g., due to a failed landing) is below a user specified bound. By solving this problem for several different values of the model parameters (e.g., divert authority), this approach enables rigorous, accurate and systematic trade-offs for the EDL system vs. the mobility system, and, more in general, cross-domain trade-offs for the different phases of a space mission. The overall optimization problem can be seen as a chance-constrained dynamic programming problem, with the additional complexity that 1) in some stages the disturbances do not have any probabilistic characterization, and 2) the state space is extremely large (i.e, hundreds of millions of states for trade-offs with high-resolution Martian maps). To this purpose, we solve the problem by performing an unconventional combination of average and minimax cost analysis and by leveraging high efficient computation tools from the image processing community. Preliminary trade-off results are presented.

entry, descent, and landing (EDL)↗
NASA NTRSDate not supplied

Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.

machine learningautonomous systems; flight simulat↗
NASA NTRSDate not supplied

Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.

machine learning↗
NASA NTRS2013

Risk-Constrained Dynamic Programming for Optimal Mars Entry, Descent, and Landing

A chance-constrained dynamic programming algorithm was developed that is capable of making optimal sequential decisions within a user-specified risk bound. This work handles stochastic uncertainties over multiple stages in the CEMAT (Combined EDL-Mobility Analyses Tool) framework. It was demonstrated by a simulation of Mars entry, descent, and landing (EDL) using real landscape data obtained from the Mars Reconnaissance Orbiter. Although standard dynamic programming (DP) provides a general framework for optimal sequential decisionmaking under uncertainty, it typically achieves risk aversion by imposing an arbitrary penalty on failure states. Such a penalty-based approach cannot explicitly bound the probability of mission failure. A key idea behind the new approach is called risk allocation, which decomposes a joint chance constraint into a set of individual chance constraints and distributes risk over them. The joint chance constraint was reformulated into a constraint on an expectation over a sum of an indicator function, which can be incorporated into the cost function by dualizing the optimization problem. As a result, the chance-constraint optimization problem can be turned into an unconstrained optimization over a Lagrangian, which can be solved efficiently using a standard DP approach.

Ono, Masahiro↗
NASA NTRSDate not supplied

Adaptive Stress Testing of Trajectory Predictions in Flight Management Systems

To find failure events and their likelihoods in flight-critical systems, we investigate the use of an advanced black-box stress testing approach called adaptive stress testing. We analyze a trajectory predictor from a developmental commercial flight management system which takes as input a collection of lateral waypoints and en-route environmental conditions. Our aim is to search for failure events relating to inconsistencies in the predicted lateral trajectories. The intention of this work is to find likely failures and report them back to the developers so they can address and potentially resolve shortcomings of the system before deployment. To improve search performance, this work extends the adaptive stress testing formulation to be applied more generally to sequential decision-making problems with episodic reward by collecting the state transitions during the search and evaluating at the end of the simulated rollout. We use a modified Monte Carlo tree search algorithm with progressive widening as our adversarial reinforcement learner. The performance is compared to direct Monte Carlo simulations and to the cross-entropy method as an alternative importance sampling baseline. The goal is to find potential problems otherwise not found by traditional requirements-based testing. Results indicate that our adaptive stress testing approach finds more failures and finds failures with higher likelihood relative to the baseline approaches.

adaptive stress testing↗
NASA NTRS1981

Sequential decision rules for failure detection

The formulation of the decision making of a failure detection process as a Bayes sequential decision problem (BSDP) provides a simple conceptualization of the decision rule design problem. As the optimal Bayes rule is not computable, a methodology that is based on the Baysian approach and aimed at a reduced computational requirement is developed for designing suboptimal rules. A numerical algorithm is constructed to facilitate the design and performance evaluation of these suboptimal rules. The result of applying this design methodology to an example shows that this approach is a useful one.

Chow, E. Y.↗
NASA NTRS1978

Discrete-time pilot model

Pilot behavior is considered as a discrete-time process where the decision making has a sequential nature. This model differs from both the quasilinear model which follows from classical control theory and from the optimal control model which considers the human operator as a Kalman estimator-predictor. An additional factor considered is that the pilot's objective may not be adequately formulated as a quadratic cost functional to be minimized, but rather as a more fuzzy measure of the closeness with which the aircraft follows a reference trajectory. All model parameters, in the digital program simulating the pilot's behavior, were successfully compared in terms of standard-deviation and performance with those of professional pilots in IFR configuration. The first practical application of the model was in the study of its performance degradation when the aircraft model static margin decreases.

Cavalli, D.↗
NASA NTRS1984

Bayesian design of decision rules for failure detection

The formulation of the decision making process of a failure detection algorithm as a Bayes sequential decision problem provides a simple conceptualization of the decision rule design problem. As the optimal Bayes rule is not computable, a methodology that is based on the Bayesian approach and aimed at a reduced computational requirement is developed for designing suboptimal rules. A numerical algorithm is constructed to facilitate the design and performance evaluation of these suboptimal rules. The result of applying this design methodology to an example shows that this approach is potentially a useful one.

Chow, E. Y.↗
NASA NTRS1974

Sequential decision analysis for nonstationary stochastic processes

A formulation of the problem of making decisions concerning the state of nonstationary stochastic processes is given. An optimal decision rule, for the case in which the stochastic process is independent of the decisions made, is derived. It is shown that this rule is a generalization of the Bayesian likelihood ratio test; and an analog to Wald's sequential likelihood ratio test is given, in which the optimal thresholds may vary with time.

Schaefer, B.↗
NASA NTRS1989

Algorithmic considerations of integrated design for CSI on a hypercube architecture

An approach is presented to the integrated design problem for actively controlled large, flexible mechanical systems for which Control Structure Interaction (CSI) problems are of concern. The two coupled design problems were identified as the optimal Structural Design problem the optimal Controller Design problem. These two problems can be addressed within a decision making loop that would consider each separately, and then sequentially analyze the effects of one on the other. Embedded in such a loop would be the simulation and coordination tasks as part of the decision tools required in a total (software) package. All of the above are compute-intensive tasks. In any such task, possible decompositions and gains due to the inherent parallelism have to be exploited. The problems under consideration, as applied to large flexible mechanical structures, are particularly suited to be mapped onto multicomputer systems in a hypercube topology.

Oezguener, UE.↗
NASA NTRS1980

A generalized formulation of minimum shift keying modulation

The modulator structure consisting of a single-input two-output sequential transducer whose output sequences control the modulated signal in the manner s(t) = x(i)p(t) + y(i)q(t) is considered. Here, iT is less than or equal to t, which is less than iT + T, where T is the modulation bit duration and where x(i) and y(i) take values in /+1, -1, 0/. The behavior of a sequential transducer is characterized by means of a 'trellis'. It is shown that, provided only that the 'carriers' p(t) and q(t) have the same energy in every bit interval, the optimum demodulator for the additive white Gaussian noise channel need process the received signal over only two bit intervals in making each data bit decision. It is demonstrated that particular choices of the sequential transducer yield differential minimum shift keying and differential staggered quadriphase shift keying. Possible generalizations of this approach are discussed.

Massey, J. L.↗
NASA NTRSDate not supplied

The Emphasis of Design Patterns in Expressing Expert Knowledge From A Technical Solution – A Framework for Continued Research

Digital Engineering is a transformative strategy that leverages an integrated model-based approach to improve communication, decision making, design understanding, and acquisition efficiency of system development. As modern systems are derived from pre-existing systems, harvesting expert knowledge from proven systems in a useful, model-based way will reduce the experiential learning and cognition required for new system development, contributing to a Digital Engineering transformation. Motivated by performance gains observed during a multi-year, sequential development activity, this survey reviews knowledge, architecture, and pattern literature to establish a framework for research of architectural methods for expert knowledge identification and description using Model Based System Engineering. The multi-year sequential development activity is offered as the experimental system of interest for this research. This work aims to enable a digital engineering strategy that improves concept phase decision making, accelerates knowledge acquisition from lessons learned repositories, and eases the burden of generational knowledge loss.

Lithium Ion↗