Search NASA⌕ Search

SEARCH · Search NASA

Results for “Stochastic Algorithms”

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 289 records · Page 16

Molecular phylogenetic trees - On the validity of the Goodman-Moore augmentation algorithm

A response is made to the reply of Nei and Tateno (1979) to the letter of Holmquist (1978) supporting the validity of the augmentation algorithm of Moore (1977) in reconstructions of nucleotide substitutions by means of the maximum parsimony principle. It is argued that the overestimation of the augmented numbers of nucleotide substitutions (augmented distances) found by Tateno and Nei (1978) is due to an unrepresentative data sample and that it is only necessary that evolution be stochastically uniform in different regions of the phylogenetic network for the augmentation method to be useful. The importance of the average value of the true distance over all links is explained, and the relative variances of the true and augmented distances are calculated to be almost identical. The effects of topological changes in the phylogenetic tree on the augmented distance and the question of the correctness of ancestral sequences inferred by the method of parsimony are also clarified.

Holmquist, R.↗

Adaptive piezoelectric sensoriactuator

An adaptive algorithm implemented in digital or analog form is used in conjunction with a voltage controlled amplifier to compensate for the feedthrough capacitance of piezoelectric sensoriactuator. The mechanical response of the piezoelectric sensoriactuator is resolved from the electrical response by adaptively altering the gain imposed on the electrical circuit used for compensation. For wideband, stochastic input disturbances, the feedthrough capacitance of the sensoriactuator can be identified on-line, providing a means of implementing direct-rate-feedback control in analog hardware. The device is capable of on-line system health monitoring since a quasi-stable dynamic capacitance is indicative of sustained health of the piezoelectric element.

Clark, Jr., Robert L.↗

Design of optimal partial state feedback controllers for linear systems in stochastic environments

The problem of obtaining an optimal control law, which is constrained to be a feedback of the available measurements, is considered for both continuous and discrete time linear systems subjected to additive white process noise and measurement noise. Necessary conditions are obtained for minimizing a quadratic performance function for both finite and infinite duration cases. The feedback gain matrices are constrained to be constant for the infinite duration cases. For all the cases considered, algorithms are derived for generating sequences of feedback gain matrices which successively improve the performance function. Computational aspects are discussed via application to two continuous time processes, including a helicopter/slung load system subjected to measurement noise and random wind gust input.

Joshi, S. M.↗

Distance estimation and collision prediction for on-line robotic motion planning

An efficient method for computing the minimum distance and predicting collisions between moving objects is presented. This problem is incorporated into the framework of an in-line motion-planning algorithm to satisfy collision avoidance between a robot and moving objects modeled as convex polyhedra. In the beginning, the deterministic problem where the information about the objects is assumed to be certain is examined. L(1) or L(infinity) norms are used to represent distance and the problem becomes a linear programming problem. The stochastic problem is formulated where the uncertainty is induced by sensing and the unknown dynamics of the moving obstacles. Two problems are considered: First, filtering of the distance between the robot and the moving object at the present time. Second, prediction of the minimum distance in the future in order to predict the collision time.

Kyriakopoulos, K. J.↗

Feedback control for unsteady flow and its application to the stochastic Burgers equation

The study applies mathematical methods of control theory to the problem of control of fluid flow with the long-range objective of developing effective methods for the control of turbulent flows. Model problems are employed through the formalism and language of control theory to present the procedure of how to cast the problem of controlling turbulence into a problem in optimal control theory. Methods of calculus of variations through the adjoint state and gradient algorithms are used to present a suboptimal control and feedback procedure for stationary and time-dependent problems. Two types of controls are investigated: distributed and boundary controls. Several cases of both controls are numerically simulated to investigate the performances of the control algorithm. Most cases considered show significant reductions of the costs to be minimized. The dependence of the control algorithm on the time-descretization method is discussed.

Choi, Haecheon↗

Radiative transfer calculated from a Markov chain formalism

The theory of Markov chains is used to formulate the radiative transport problem in a general way by modeling the successive interactions of a photon as a stochastic process. Under the minimal requirement that the stochastic process is a Markov chain, the determination of the diffuse reflection or transmission from a scattering atmosphere is equivalent to the solution of a system of linear equations. This treatment is mathematically equivalent to, and thus has many of the advantages of, Monte Carlo methods, but can be considerably more rapid than Monte Carlo algorithms for numerical calculations in particular applications. We have verified the speed and accuracy of this formalism for the standard problem of finding the intensity of scattered light from a homogeneous plane-parallel atmosphere with an arbitrary phase function for scattering. Accurate results over a wide range of parameters were obtained with computation times comparable to those of a standard 'doubling' routine. The generality of this formalism thus allows fast, direct solutions to problems that were previously soluble only by Monte Carlo methods. Some comparisons are made with respect to integral equation methods.

Esposito, L. W.↗

Distributed state-space generation of discrete-state stochastic models

High-level formalisms such as stochastic Petri nets can be used to model complex systems. Analysis of logical and numerical properties of these models of ten requires the generation and storage of the entire underlying state space. This imposes practical limitations on the types of systems which can be modeled. Because of the vast amount of memory consumed, we investigate distributed algorithms for the generation of state space graphs. The distributed construction allows us to take advantage of the combined memory readily available on a network of workstations. The key technical problem is to find effective methods for on-the-fly partitioning, so that the state space is evenly distributed among processors. In this paper we report on the implementation of a distributed state-space generator that may be linked to a number of existing system modeling tools. We discuss partitioning strategies in the context of Petri net models, and report on performance observed on a network of workstations, as well as on a distributed memory multi-computer.

Ciardo, Gianfranco↗

Q-Markov covariance equivalent realization and its application to flexible structure identification

The Q-Markov covariance equivalent realization algorithm is applied to NASA's Minimast structure to identify state-space models for the purpose of designing closed-loop controllers, and laboratory test results are shown for the identification and for the closed-loop performance. The paper also presents for the first time a deterministic formulation of covariance parameters from a pulse response, a stochastic formulation of Markov parameters from a white-noise response, and a simple Q-Markov covariance equivalent realization formulation. This requires only pulse laboratory tests or only white-noise laboratory tests to generate Q-Markov covariance equivalent realizations.

Liu, Ketao↗

The Integrated Medical Model - Optimizing In-flight Space Medical Systems to Reduce Crew Health Risk and Mission Impacts

The Integrated Medical Model (IMM) is a decision support tool used by medical system planners and designers as they prepare for exploration planning activities of the Constellation program (CxP). IMM provides an evidence-based approach to help optimize the allocation of in-flight medical resources for a specified level of risk within spacecraft operational constraints. Eighty medical conditions and associated resources are represented in IMM. Nine conditions are due to Space Adaptation Syndrome. The IMM helps answer fundamental medical mission planning questions such as What medical conditions can be expected? What type and quantity of medical resources are most likely to be used?", and "What is the probability of crew death or evacuation due to medical events?" For a specified mission and crew profile, the IMM effectively characterizes the sequence of events that could potentially occur should a medical condition happen. The mathematical relationships among mission and crew attributes, medical conditions and incidence data, in-flight medical resources, potential clinical and crew health end states are established to generate end state probabilities. A Monte Carlo computational method is used to determine the probable outcomes and requires up to 25,000 mission trials to reach convergence. For each mission trial, the pharmaceuticals and supplies required to diagnose and treat prevalent medical conditions are tracked and decremented. The uncertainty of patient response to treatment is bounded via a best-case, worst-case, untreated case algorithm. A Crew Health Index (CHI) metric, developed to account for functional impairment due to a medical condition, provides a quantified measure of risk and enables risk comparisons across mission scenarios. The use of historical in-flight medical data, terrestrial surrogate data as appropriate, and space medicine subject matter expertise has enabled the development of a probabilistic, stochastic decision support tool capable of optimizing in-flight medical systems based on crew and mission parameters. This presentation will illustrate how to apply quantitative risk assessment methods to optimize the mass and volume of space-based medical systems for a space flight mission given the level of crew health and mission risk.

Kerstman, Eric↗

Planning with Continuous Resources in Stochastic Domains

We consider the problem of optimal planning in stochastic domains with metric resource constraints. Our goal is to generate a policy whose expected sum of rewards is maximized for a given initial state. We consider a general formulation motivated by our application domain--planetary exploration--in which the choice of an action at each step may depend on the current resource levels. We adapt the forward search algorithm AO* to handle our continuous state space efficiently.

Mausam, Mausau↗

Distance estimation and collision prediction for on-line robotic motion planning

An efficient method for computing the minimum distance and predicting collisions between moving objects is presented. This problem has been incorporated in the framework of an in-line motion planning algorithm to satisfy collision avoidance between a robot and moving objects modeled as convex polyhedra. In the beginning the deterministic problem, where the information about the objects is assumed to be certain is examined. If instead of the Euclidean norm, L(sub 1) or L(sub infinity) norms are used to represent distance, the problem becomes a linear programming problem. The stochastic problem is formulated, where the uncertainty is induced by sensing and the unknown dynamics of the moving obstacles. Two problems are considered: (1) filtering of the minimum distance between the robot and the moving object, at the present time; and (2) prediction of the minimum distance in the future, in order to predict possible collisions with the moving obstacles and estimate the collision time.

Kyriakopoulos, K. J.↗

Simulation of Rotor Blade Element Turbulence

A turbulence model has been developed for blade-element helicopter simulation. This model, called Simulation of Rotor Blade Element Turbulence (SORBET), uses an innovative temporal and geometrical distribution algorithm that preserves the statistical characteristics of the turbulence spectra over the rotor disc, while providing velocity components in real time to each of five blade-element stations along each of four blades. An initial investigation of SORBET has been performed using a piloted, motion-based simulation of the Sikorsky UH60A Black Hawk. Although only the vertical component of stochastic turbulence was used in this investigation, vertical turbulence components induce vehicle responses in all translational and rotational degrees of freedom of the helicopter. The single-degree-of-freedom configuration of SORBET was compared to a conventional full 6-degrees-of-freedom baseline configuration, where translational velocity inputs are superimposed at the vehicle center of gravity, and rotational velocity inputs are created from filters that approximate the immersion rate into the turbulent field. For high-speed flight the vehicle responses were satisfactory for both models. Test pilots could not distinguish differences between the baseline configuration and SORBET. In low-speed flight the baseline configuration received criticism for its high frequency content, whereas the SORBET model elicited favorable pilot opinion. For this helicopter, which has fully articulated blades, results from SORBET show that vehicle responses to turbulent blade-station disturbances are severely attenuated. This is corroborated by in-flight observation of the rotor tip path plane as compared to vehicle responses.

McFarland, R. E.↗

Using neural networks and Dyna algorithm for integrated planning, reacting and learning in systems

The traditional AI answer to the decision making problem for a robot is planning. However, planning is usually CPU-time consuming, depending on the availability and accuracy of a world model. The Dyna system generally described in earlier work, uses trial and error to learn a world model which is simultaneously used to plan reactions resulting in optimal action sequences. It is an attempt to integrate planning, reactive, and learning systems. The architecture of Dyna is presented. The different blocks are described. There are three main components of the system. The first is the world model used by the robot for internal world representation. The input of the world model is the current state and the action taken in the current state. The output is the corresponding reward and resulting state. The second module in the system is the policy. The policy observes the current state and outputs the action to be executed by the robot. At the beginning of program execution, the policy is stochastic and through learning progressively becomes deterministic. The policy decides upon an action according to the output of an evaluation function, which is the third module of the system. The evaluation function takes the following as input: the current state of the system, the action taken in that state, the resulting state, and a reward generated by the world which is proportional to the current distance from the goal state. Originally, the work proposed was as follows: (1) to implement a simple 2-D world where a 'robot' is navigating around obstacles, to learn the path to a goal, by using lookup tables; (2) to substitute the world model and Q estimate function Q by neural networks; and (3) to apply the algorithm to a more complex world where the use of a neural network would be fully justified. In this paper, the system design and achieved results will be described. First we implement the world model with a neural network and leave Q implemented as a look up table. Next, we use a lookup table for the world model and implement the Q function with a neural net. Time limitations prevented the combination of these two approaches. The final section discusses the results and gives clues for future work.

Lima, Pedro↗

Chemical application of diffusion quantum Monte Carlo

The diffusion quantum Monte Carlo (QMC) method gives a stochastic solution to the Schroedinger equation. This approach is receiving increasing attention in chemical applications as a result of its high accuracy. However, reducing statistical uncertainty remains a priority because chemical effects are often obtained as small differences of large numbers. As an example, the single-triplet splitting of the energy of the methylene molecule CH sub 2 is given. The QMC algorithm was implemented on the CYBER 205, first as a direct transcription of the algorithm running on the VAX 11/780, and second by explicitly writing vector code for all loops longer than a crossover length C. The speed of the codes relative to one another as a function of C, and relative to the VAX, are discussed. The computational time dependence obtained versus the number of basis functions is discussed and this is compared with that obtained from traditional quantum chemistry codes and that obtained from traditional computer architectures.

Reynolds, P. J.↗

The stochastic evolution of asteroidal regoliths and the origin of brecciated and gas-rich meteorites

A model is constructed which views regolith evolution on asteroids as a stochastic process. Average values are shown to be poor descriptors of regolith depth. The utility of the average depth is not significantly increased by avoiding large craters or thick ejecta deposits, a procedure adopted in previous regolith studies. The statistical uncertainty associated with regolith depth severely limits the power of regolith models in predicting parent-body size for brecciated meteorites. A Monte Carlo algorithm was used to simulate the random walks and corresponding charged-particle irradiation histories of grains in regoliths. On rocky asteroids, only about 20 percent of the grains was exposed to solar cosmic ray ions. Results based on present-day conditions in the asteroid belt agree well with irradiation features observed in gas-rich meteorites. An origin during epochs of early solar system evolution is not required.

Housen, K. R.↗

Identification of observer/Kalman filter Markov parameters: Theory and experiments

An algorithm to compute Markov parameters of an observer or Kalman filter from experimental input and output data is discussed. The Markov parameters can then be used for identification of a state space representation, with associated Kalman gain or observer gain, for the purpose of controller design. The algorithm is a non-recursive matrix version of two recursive algorithms developed in previous works for different purposes. The relationship between these other algorithms is developed. The new matrix formulation here gives insight into the existence and uniqueness of solutions of certain equations and gives bounds on the proper choice of observer order. It is shown that if one uses data containing noise, and seeks the fastest possible deterministic observer, the deadbeat observer, one instead obtains the Kalman filter, which is the fastest possible observer in the stochastic environment. Results are demonstrated in numerical studies and in experiments on an ten-bay truss structure.

Juang, Jer-Nan↗

Identification of observer/Kalman filter Markov parameters - Theory and experiments

An algorithm to compute Markov parameters of an observer or Kalman filter from experimental input and output data is discussed. The Markov parameters can then be used for identification of a state space representation, with associated Kalman gain or observer gain, for the purpose of controller design. The algorithm is a non-recursive matrix version of two recursive algorithms developed in previous works for different purposes. The relationship between these other algorithms is developed. The new matrix formulation here gives insight into the existence and uniqueness of solutions of certain equations and gives bounds on the proper choice of observer order. It is shown that if one uses data containing noise, and seeks the fastest possible deterministic observer, the deadbeat observer, one instead obtains the Kalman filter, which is the fastest possible observer in the stochastic environment. Results are demonstrated in numerical studies and in experiments on a ten-bay truss structure.

Juang, Jer-Nan↗

A variable-gain output feedback control design methodology

A digital control system design technique is developed in which the control system gain matrix varies with the plant operating point parameters. The design technique is obtained by formulating the problem as an optimal stochastic output feedback control law with variable gains. This approach provides a control theory framework within which the operating range of a control law can be significantly extended. Furthermore, the approach avoids the major shortcomings of the conventional gain-scheduling techniques. The optimal variable gain output feedback control problem is solved by embedding the Multi-Configuration Control (MCC) problem, previously solved at ICS. An algorithm to compute the optimal variable gain output feedback control gain matrices is developed. The algorithm is a modified version of the MCC algorithm improved so as to handle the large dimensionality which arises particularly in variable-gain control problems. The design methodology developed is applied to a reconfigurable aircraft control problem. A variable-gain output feedback control problem was formulated to design a flight control law for an AFTI F-16 aircraft which can automatically reconfigure its control strategy to accommodate failures in the horizontal tail control surface. Simulations of the closed-loop reconfigurable system show that the approach produces a control design which can accommodate such failures with relative ease. The technique can be applied to many other problems including sensor failure accommodation, mode switching control laws and super agility.

Halyo, Nesim↗