An improved algorithm for learning systems
Algorithm for implementing learning controller based on subgoal concept applicable to linear stationary system
Lindorff, D. P.↗
SEARCH · Search NASA
Results for “learning control”
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.
System parameter adaptation via a learning procedure
The paper considers the problem of designing a learning control system (LCS) that is capable of meeting design requirements over many possible operating conditions of the plant by adjusting, in a prescribed manner, the feedforward and feedback gains of the plant. The approach utilizes the best features of two methods, gain scheduling and adaptive control. The LCS was implemented using two models, one representing the longitudinal dynamics and the other the lateral dynamics of the simulated plant. A block diagram illustrating the functional organization of an LCS is presented.
Mekel, R.↗
System identification in the repetition domain
Procedures for system identification using realization theory in conjunction with learning control ideas are developed. The Markov parameters of the system are identified by combining data from repeated experiments. Three approaches are discussed for identification of as many Markov parameters as sample points in the experiment. Making use of all the parameters, realization theory is then employed to determine the system order and to obtain a minimal order representation. The first two approaches are non-recursive, which in the case of noise-free data yields a one step solution. The third approach uses a recursive formulation rendered from adaptive control but modified for successive experiments. A simple example shows the numerical convergence of the identified parameters as a function of the number of experiments. The procedure presented herein is an extension of the existing Eigensystem Realization Algorithm (ERA), which has been successfully applied for system identification of large structures.
Juang, Jer-Nan↗
Search-based model identification of smart-structure damage
This paper describes the use of a combined model and parameter identification approach, based on modal analysis and artificial intelligence (AI) techniques, for identifying damage or flaws in a rotating truss structure incorporating embedded piezoceramic sensors. This smart structure example is representative of a class of structures commonly found in aerospace systems and next generation space structures. Artificial intelligence techniques of classification, heuristic search, and an object-oriented knowledge base are used in an AI-based model identification approach. A finite model space is classified into a search tree, over which a variant of best-first search is used to identify the model whose stored response most closely matches that of the input. Newly-encountered models can be incorporated into the model space. This adaptativeness demonstrates the potential for learning control. Following this output-error model identification, numerical parameter identification is used to further refine the identified model. Given the rotating truss example in this paper, noisy data corresponding to various damage configurations are input to both this approach and a conventional parameter identification method. The combination of the AI-based model identification with parameter identification is shown to lead to smaller parameter corrections than required by the use of parameter identification alone.
Glass, B. J.↗
A Rideshare Tensegrity Rover Concept to Explore Titan’s Lands and Oceans
The Tension Adjustable Network for Deploying Entry Membrane (TANDEM) concept is a phase II NASA Innovative Advanced Concepts (NIAC) project. One of the goals for this project was to extend the application of tensegrity-based rovers to a rideshare concept for a Titan mission. This report provides preliminary details of the TANDEM concept for Titan. System analyses of the entry vehicle were performed and compared to data from the Huygens mission to Titan. The entry aeroshell was based on Huygens and Stardust aeroshells. Modeling, simulation and design of the tensegrity deployment were performed using a nonlinear optimization form-finding algorithm. Lastly, a neuroevolution-based machine learning control strategy was applied, which produced efficient rolling locomotion gaits.
tensegrity↗
SoMoGym: A Toolkit for Developing and Evaluating Controllers and Reinforcement Learning Algorithms for Soft Robots
Soft robotsoffer a host of benefits over traditional rigid robots, including inherent compliance that lets them passively adapt to variable environments and operate safely around humans and fragile objects. However, that same compliance makes it hard to use model-based methods in planning tasks requiring high precision or complex actuation sequences. Reinforcement learning (RL) can potentially find effective control policies, but training RL using physical soft robots is often infeasible, and training using simulations has had a high barrier to adoption. To accelerate research in control and RL for soft robotic systems, we introduce SoMoGym ( So ft Mo tion Gym ), a software toolkit that facilitates training and evaluating controllers for continuum robots. SoMoGym provides a set of benchmark tasks in which soft robots interact with various objects and environments. It allows evaluation of performance on these tasks for controllers of interest, and enables the use of RL to generate new controllers. Custom environments and robots can likewise be added easily. We provide and evaluate baseline RL policies for each of the benchmark tasks. These results show that SoMoGym enables the use of RL for continuum robots, a class of robots not covered by existing benchmarks, giving them the capability to autonomously solve tasks that were previously unattainable.
Moritz A. Graule↗
Various Embodiments of the Non-Invasive Endoscopic Feedback for Learning of Voluntary Control of Physiological Functioning
The research performed was a small portion of the patent to be submitted by Dr. Alan T. Pope entitled 'A Method of Providing Veridical Non-Invasive Endoscopic Feedback for Learning of Voluntary Control of Physiological Functioning'. The focus of this study is to incorporate the emerging technology of virtual reality with the forms of biofeedback already in existance producing a life-like, real-time model of the body's functioning without using invasive procedures, yet still producing the equivalent of a picture from an invasive endoscopic procedure in the region of interest. The portion of the project designated to me was to research and report as many possible uses for such technology as possible.
Henriksen, Mina D.↗
Neural controller for adaptive movements with unforeseen payloads
A theory and computer simulation of a neural controller that learns to move and position a link carrying an unforeseen payload accurately are presented. The neural controller learns adaptive dynamic control from its own experience. It does not use information about link mass, link length, or direction of gravity, and it uses only indirect uncalibrated information about payload and actuator limits. Its average positioning accuracy across a large range of payloads after learning is 3 percent of the positioning range. This neural controller can be used as a basis for coordinating any number of sensory inputs with limbs of any number of joints. The feedforward nature of control allows parallel implementation in real time across multiple joints.
Kuperstein, Michael↗
Implementation Challenges for Multivariable Control: What You Did Not Learn in School
Multivariable control allows controller designs that can provide decoupled command tracking and robust performance in the presence of modeling uncertainties. Although the last two decades have seen extensive development of multivariable control theory and example applications to complex systems in software/hardware simulations, there are no production flying systems aircraft or spacecraft, that use multivariable control. This is because of the tremendous challenges associated with implementation of such multivariable control designs. Unfortunately, the curriculum in schools does not provide sufficient time to be able to provide an exposure to the students in such implementation challenges. The objective of this paper is to share the lessons learned by a practitioner of multivariable control in the process of applying some of the modern control theory to the Integrated Flight Propulsion Control (IFPC) design for an advanced Short Take-Off Vertical Landing (STOVL) aircraft simulation.
Garg, Sanjay↗
NASA Ares I Launch Vehicle Roll and Reaction Control Systems Lessons Learned
On April 15, 2010 President Barak Obama made the official announcement that the Constellation Program, which included the Ares I launch vehicle, would be canceled. NASA s Ares I launch vehicle was being designed to launch the Orion Crew Exploration Vehicle, returning humans to the moon, Mars, and beyond. It consisted of a First Stage (FS) five segment solid rocket booster and a liquid J-2X Upper Stage (US) engine. Roll control for the FS was planned to be handled by a dedicated Roll Control System (RoCS), located on the connecting interstage. Induced yaw or pitch moments experienced during FS ascent would have been handled by vectoring of the booster nozzle. After FS booster separation, the US Reaction Control System (ReCS) would have provided the US Element with three degrees of freedom control as needed. The lessons learned documented in this paper will be focused on the technical designs and producibility of both systems along with the partnership between NASA and Boeing, who was on contract to build the Ares I US Element, which included the FS RoCS and US ReCS. In regards to partnership, focus will be placed on integration along with technical work accomplished by Boeing with special emphasis on each task order. In summary, this paper attempts to capture key lessons learned that should be helpful in the development of future launch vehicle RCS designs.
Butt, Adam↗
Learning and tuning fuzzy logic controllers through reinforcements
A new method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system is presented. In particular, our Generalized Approximate Reasoning-based Intelligent Control (GARIC) architecture: (1) learns and tunes a fuzzy logic controller even when only weak reinforcements, such as a binary failure signal, is available; (2) introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; (3) introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and (4) learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward network, which can then adaptively improve performance by using gradient descent methods. We extend the AHC algorithm of Barto, Sutton, and Anderson to include the prior control knowledge of human operators. The GARIC architecture is applied to a cart-pole balancing system and has demonstrated significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.
Berenji, Hamid R.↗
X-29 flight control system: Lessons learned
Two X-29A aircraft were flown at the NASA Dryden Flight Research Center over a period of eight years. The airplanes' unique features are the forward-swept wing, variable incidence close-coupled canard and highly relaxed longitudinal static stability (up to 35-percent negative static margin at subsonic conditions). This paper describes the primary flight control system and significant modifications made to this system, flight test techniques used during envelope expansion, and results for the low- and high-angle-of-attack programs. Through out the paper, lessons learned will be discussed to illustrate the problems associated with the implementation of complex flight control systems.
Clarke, Robert↗
Staffing the ISS Control Centers: Lessons Learned from Long-Duration Human Space Flight
The International Space Station (ISS) has been in operation with a permanent human presence in space for over five years, and plans for continued operations stretch ten years into the future. Ground control and support operations are, likewise, a 15-year enterprise. This long-term, 24-hour per day, 7 day per week support has presented numerous challenges in the areas of ground crew training, initial and continued certification, and console staffing. The Mission Control Center in Houston, Texas and the Payload Operations Center in Huntsville, Alabama have both tackled these challenges, with similar, yet distinct, approaches. This paper describes the evolution of the staffing and training policies of both control centers in a chronological progression. The relative merits and shortcomings of the various policies employed are discussed and a summary of "lessons learned" is presented. Finally, recommendations are made as best practices for future long-term space missions.
Olsen, Carrie D.↗
Rule-based mechanisms of learning for intelligent adaptive flight control
How certain aspects of human learning can be used to characterize learning in intelligent adaptive control systems is investigated. Reflexive and declarative memory and learning are described. It is shown that model-based systems-theoretic adaptive control methods exhibit attributes of reflexive learning, whereas the problem-solving capabilities of knowledge-based systems of artificial intelligence are naturally suited for implementing declarative learning. Issues related to learning in knowledge-based control systems are addressed, with particular attention given to rule-based systems. A mechanism for real-time rule-based knowledge acquisition is suggested, and utilization of this mechanism within the context of failure diagnosis for fault-tolerant flight control is demonstrated.
Handelman, David A.↗
Design and Control of Large Collections of Learning Agents
The intelligent control of multiple autonomous agents is an important yet difficult task. Previous methods used to address this problem have proved to be either too brittle, too hard to use, or not scalable to large systems. The 'Collective Intelligence' project at NASA/Ames provides an elegant, machine-learning approach to address these problems. This approach mathematically defines some essential properties that a reward system should have to promote coordinated behavior among reinforcement learners. This work has focused on creating additional key properties and algorithms within the mathematics of the Collective Intelligence framework. One of the additions will allow agents to learn more quickly, in a more coordinated manner. The other will let agents learn with less knowledge of their environment. These additions will allow the framework to be applied more easily, to a much larger domain of multi-agent problems.
Agogino, Adrian↗
Machine learning in motion control
The existing methodologies for robot programming originate primarily from robotic applications to manufacturing, where uncertainties of the robots and their task environment may be minimized by repeated off-line modeling and identification. In space application of robots, however, a higher degree of automation is required for robot programming because of the desire of minimizing the human intervention. We discuss a new paradigm of robotic programming which is based on the concept of machine learning. The goal is to let robots practice tasks by themselves and the operational data are used to automatically improve their motion performance. The underlying mathematical problem is to solve the problem of dynamical inverse by iterative methods. One of the key questions is how to ensure the convergence of the iterative process. There have been a few small steps taken into this important approach to robot programming. We give a representative result on the convergence problem.
Su, Renjeng↗
Learning and tuning fuzzy logic controllers through reinforcements
This paper presents a new method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system. In particular, our generalized approximate reasoning-based intelligent control (GARIC) architecture (1) learns and tunes a fuzzy logic controller even when only weak reinforcement, such as a binary failure signal, is available; (2) introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; (3) introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and (4) learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward neural network, which can then adaptively improve performance by using gradient descent methods. We extend the AHC algorithm of Barto et al. (1983) to include the prior control knowledge of human operators. The GARIC architecture is applied to a cart-pole balancing system and demonstrates significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.
Berenji, Hamid R.↗
Designing Specification Languages for Process Control Systems: Lessons Learned and Steps to the Future
Previously, we defined a blackbox formal system modeling language called RSML (Requirements State Machine Language). The language was developed over several years while specifying the system requirements for a collision avoidance system for commercial passenger aircraft. During the language development, we received continual feedback and evaluation by FAA employees and industry representatives, which helped us to produce a specification language that is easily learned and used by application experts. Since the completion of the PSML project, we have continued our research on specification languages. This research is part of a larger effort to investigate the more general problem of providing tools to assist in developing embedded systems. Our latest experimental toolset is called SpecTRM (Specification Tools and Requirements Methodology), and the formal specification language is SpecTRM-RL (SpecTRM Requirements Language). This paper describes what we have learned from our use of RSML and how those lessons were applied to the design of SpecTRM-RL. We discuss our goals for SpecTRM-RL and the design features that support each of these goals.
Leveson, Nancy G.↗