SEARCH · Engineering Papers

Results for “Iterative 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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records

All sources NASA NTRS DOE OSTI

NASA NTRS1990

Learning control system design based on 2-D theory - An application to parallel link manipulator

An approach to iterative learning control system design based on two-dimensional system theory is presented. A two-dimensional model for the iterative learning control system which reveals the connections between learning control systems and two-dimensional system theory is established. A learning control algorithm is proposed, and the convergence of learning using this algorithm is guaranteed by two-dimensional stability. The learning algorithm is applied successfully to the trajectory tracking control problem for a parallel link robot manipulator. The excellent performance of this learning algorithm is demonstrated by the computer simulation results.

Geng, Z.↗

NASA NTRS1990

Intelligent control and adaptive systems; Proceedings of the Meeting, Philadelphia, PA, Nov. 7, 8, 1989

Various papers on intelligent control and adaptive systems are presented. Individual topics addressed include: control architecture for a Mars walking vehicle, representation for error detection and recovery in robot task plans, real-time operating system for robots, execution monitoring of a mobile robot system, statistical mechanics models for motion and force planning, global kinematics for manipulator planning and control, exploration of unknown mechanical assemblies through manipulation, low-level representations for robot vision, harmonic functions for robot path construction, simulation of dual behavior of an autonomous system. Also discussed are: control framework for hand-arm coordination, neural network approach to multivehicle navigation, electronic neural networks for global optimization, neural network for L1 norm linear regression, planning for assembly with robot hands, neural networks in dynamical systems, control design with iterative learning, improved fuzzy process control of spacecraft autonomous rendezvous using a genetic algorithm.

Rodriguez, Guillermo↗

NASA NTRS2015

Reinforcement Learning with Autonomous Small Unmanned Aerial Vehicles in Cluttered Environments

We present ongoing work in the Autonomy Incubator at NASA Langley Research Center (LaRC) exploring the efficacy of a data set aggregation approach to reinforcement learning for small unmanned aerial vehicle (sUAV) flight in dense and cluttered environments with reactive obstacle avoidance. The goal is to learn an autonomous flight model using training experiences from a human piloting a sUAV around static obstacles. The training approach uses video data from a forward-facing camera that records the human pilot's flight. Various computer vision based features are extracted from the video relating to edge and gradient information. The recorded human-controlled inputs are used to train an autonomous control model that correlates the extracted feature vector to a yaw command. As part of the reinforcement learning approach, the autonomous control model is iteratively updated with feedback from a human agent who corrects undesired model output. This data driven approach to autonomous obstacle avoidance is explored for simulated forest environments furthering autonomous flight under the tree canopy research. This enables flight in previously inaccessible environments which are of interest to NASA researchers in Earth and Atmospheric sciences.

Tran, Loc↗

NASA NTRS2022

L1 Adaptive Control with Switched Reference Models: Application to Learn-to-Fly

Learn-to-Fly (L2F) is a new framework that aims to replace the traditional iterative development paradigm for aerial vehicles with a combination of real-time aerodynamic modeling, guidance, and learning control. To ensure safe learning of the vehicle dynamics on the fly, this paper presents an L1 adaptive control (L1AC) based scheme, which actively estimates and compensates for the discrepancy between the intermediately learned dynamics and the actual dynamics. First, to incorporate the periodic update of the learned model within the L2F framework, this paper extends the L1AC architecture to handle a switched reference system subject to unknown time-varying parameters and disturbances. The paper also includes analysis of both transient and steady-state performance of the L1AC architecture in the presence of non-zero initialization error for the state predictor. Second, the paper presents how the proposed L1AC scheme is integrated into the L2F framework, including its interaction with the baseline controller and the real-time modeling module. Finally, flight tests on an unmanned aerial vehicle (UAV) validate the efficacy of the proposed control and learning scheme.

Steven Snyder↗

NASA NTRS1990

Neuromorphic learning of continuous-valued mappings from noise-corrupted data. Application to real-time adaptive control

The ability of feed-forward neural network architectures to learn continuous valued mappings in the presence of noise was demonstrated in relation to parameter identification and real-time adaptive control applications. An error function was introduced to help optimize parameter values such as number of training iterations, observation time, sampling rate, and scaling of the control signal. The learning performance depended essentially on the degree of embodiment of the control law in the training data set and on the degree of uniformity of the probability distribution function of the data that are presented to the net during sequence. When a control law was corrupted by noise, the fluctuations of the training data biased the probability distribution function of the training data sequence. Only if the noise contamination is minimized and the degree of embodiment of the control law is maximized, can a neural net develop a good representation of the mapping and be used as a neurocontroller. A multilayer net was trained with back-error-propagation to control a cart-pole system for linear and nonlinear control laws in the presence of data processing noise and measurement noise. The neurocontroller exhibited noise-filtering properties and was found to operate more smoothly than the teacher in the presence of measurement noise.

Troudet, Terry↗

NASA NTRS2011

Ensuring Success of Adaptive Control Research Through Project Lifecycle Risk Mitigation

Lessons Learne: 1. Design-out unnecessary risk to prevent excessive mitigation management during flight. 2. Consider iterative checkouts to confirm or improve human factor characteristics. 3. Consider the total flight test profile to uncover unanticipated human-algorithm interactions. 4. Consider test card cadence as a metric to assess test readiness. 5. Full-scale flight test is critical to development, maturation, and acceptance of adaptive control laws for operational use.

Pavlock, Kate M.↗

NASA NTRS2018

NASA's Learn-to-Fly Project Overview

Learn-to-Fly (L2F) is an advanced technology development effort aimed at assessing the feasibility of real-time, self-learning flight vehicles. Specifically, research has been conducted on merging real-time aerodynamic modeling, learning adaptive control, and other disciplines with the goal of using this “learn to fly” methodology to replace the current iterative vehicle development paradigm, substantially reducing the typical ground and flight testing requirements for air vehicle design. Recent activities included an aggressive flight test program with unique fully autonomous fight test vehicles to rapidly advance L2F technology. This paper presents an overview of the project and key components.

Heim, Eugene H. D.↗

NASA NTRS2014

Development of a Route Crossing Tool for Shared Airspace Environments

In current-day Terminal Radar Approach Control (TRACON) operations, departure and arrival controllers maintain separate and dedicated airspace for their respective traffic flows. Although this practice has obvious safety features, it also leads to inefficiencies; for example, departure aircraft may be routinely capped beneath arrival airspace. With the right decision-support and coordination tools, departures could continue to climb through arrival airspace when sufficient gaps exist. Previous studies of ‘shared airspace’ have examined pre-arranged coordination procedures, as well as tools that gave feedback to the controllers on where gaps between arrivals were located and whether the departure aircraft could be scheduled to fly through those gaps [1, 2, 3, 4]. Since then, the Route Crossing Tool (RCT) has been developed to allow controllers to assess multiple pre-defined route options at points where the arrivals and departures cross, thereby increasing the possibility of climbing a departure through an arrival gap.The RCT aids in ensuring lateral separation between departure and arrival aircraft that pass through the same altitude. Since the RCT can be applied tactically, it can enable aircraft to fly through arrival flows even if these aircraft depart outside scheduled times. The RCT makes use of a set of predefined parallel departure routes crossing the arrival flow at equidistant intersecting points on the arrival route. The RCT uses the Estimated Time of Arrival (ETA) of the departure aircraft at each intersecting point to calculate the lateral separation with the neighboring arrivals when it crosses that point; this information is graphically displayed to the controller. Additionally, the RCT incorporates forecast winds in its ETA predictions.Multiple prototypes of the RCT have been iteratively developed with feedback from Subject Matter Experts (SMEs). This paper presents the final design, the design process, and lessons learned. Initial results from a simulation suggest that the tool was successful in helping controllers to safely climb more aircraft. Controller feedback on the tool was also positive.

shared airspace↗

NASA NTRS1995

Locomotion training of legged robots using hybrid machine learning techniques

In this study artificial neural networks and fuzzy logic are used to control the jumping behavior of a three-link uniped robot. The biped locomotion control problem is an increment of the uniped locomotion control. Study of legged locomotion dynamics indicates that a hierarchical controller is required to control the behavior of a legged robot. A structured control strategy is suggested which includes navigator, motion planner, biped coordinator and uniped controllers. A three-link uniped robot simulation is developed to be used as the plant. Neurocontrollers were trained both online and offline. In the case of on-line training, a reinforcement learning technique was used to train the neurocontroller to make the robot jump to a specified height. After several hundred iterations of training, the plant output achieved an accuracy of 7.4%. However, when jump distance and body angular momentum were also included in the control objectives, training time became impractically long. In the case of off-line training, a three-layered backpropagation (BP) network was first used with three inputs, three outputs and 15 to 40 hidden nodes. Pre-generated data were presented to the network with a learning rate as low as 0.003 in order to reach convergence. The low learning rate required for convergence resulted in a very slow training process which took weeks to learn 460 examples. After training, performance of the neurocontroller was rather poor. Consequently, the BP network was replaced by a Cerebeller Model Articulation Controller (CMAC) network. Subsequent experiments described in this document show that the CMAC network is more suitable to the solution of uniped locomotion control problems in terms of both learning efficiency and performance. A new approach is introduced in this report, viz., a self-organizing multiagent cerebeller model for fuzzy-neural control of uniped locomotion is suggested to improve training efficiency. This is currently being evaluated for a possible patent by NASA, Johnson Space Center. An alternative modular approach is also developed which uses separate controllers for each stage of the running stride. A self-organizing fuzzy-neural controller controls the height, distance and angular momentum of the stride. A CMAC-based controller controls the movement of the leg from the time the foot leaves the ground to the time of landing. Because the leg joints are controlled at each time step during flight, movement is smooth and obstacles can be avoided. Initial results indicate that this approach can yield fast, accurate results.

Simon, William E.↗

NASA NTRS2007

Automated Knowledge Discovery From Simulators

A computational method, SimLearn, has been devised to facilitate efficient knowledge discovery from simulators. Simulators are complex computer programs used in science and engineering to model diverse phenomena such as fluid flow, gravitational interactions, coupled mechanical systems, and nuclear, chemical, and biological processes. SimLearn uses active-learning techniques to efficiently address the "landscape characterization problem." In particular, SimLearn tries to determine which regions in "input space" lead to a given output from the simulator, where "input space" refers to an abstraction of all the variables going into the simulator, e.g., initial conditions, parameters, and interaction equations. Landscape characterization can be viewed as an attempt to invert the forward mapping of the simulator and recover the inputs that produce a particular output. Given that a single simulation run can take days or weeks to complete even on a large computing cluster, SimLearn attempts to reduce costs by reducing the number of simulations needed to effect discoveries. Unlike conventional data-mining methods that are applied to static predefined datasets, SimLearn involves an iterative process in which a most informative dataset is constructed dynamically by using the simulator as an oracle. On each iteration, the algorithm models the knowledge it has gained through previous simulation trials and then chooses which simulation trials to run next. Running these trials through the simulator produces new data in the form of input-output pairs. The overall process is embodied in an algorithm that combines support vector machines (SVMs) with active learning. SVMs use learning from examples (the examples are the input-output pairs generated by running the simulator) and a principle called maximum margin to derive predictors that generalize well to new inputs. In SimLearn, the SVM plays the role of modeling the knowledge that has been gained through previous simulation trials. Active learning is used to determine which new input points would be most informative if their output were known. The selected input points are run through the simulator to generate new information that can be used to refine the SVM. The process is then repeated. SimLearn carefully balances exploration (semi-randomly searching around the input space) versus exploitation (using the current state of knowledge to conduct a tightly focused search). During each iteration, SimLearn uses not one, but an ensemble of SVMs. Each SVM in the ensemble is characterized by different hyper-parameters that control various aspects of the learned predictor - for example, whether the predictor is constrained to be very smooth (nearby points in input space lead to similar output predictions) or whether the predictor is allowed to be "bumpy." The various SVMs will have different preferences about which input points they would like to run through the simulator next. SimLearn includes a formal mechanism for balancing the ensemble SVM preferences so that a single choice can be made for the next set of trials.

Burl, Michael↗

NASA NTRS2016

A Tale of Two Chambers: Iterative Approaches and Lessons Learned from Life Support Systems Testing in Altitude Chambers

The drive for the journey to Mars is in a higher gear than ever before. We are developing new spacecraft and life support systems to take humans to the Red Planet. The journey that development hardware takes before its final incarnation in a fully integrated spacecraft can take years, as is the case for the Orion environmental control and life support system (ECLSS). Through the Pressure Integrated Suit Test (PIST) series, NASA personnel at Johnson Space Center have been characterizing the behavior of a closed loop ECLSS in the event of cabin depressurization. This kind of testing - one of the most hazardous activities performed at JSC - requires an iterative approach, increasing in complexity and hazards). The PIST series, conducted in the Crew and Thermal Systems Division (CTSD) 11-ft Chamber, started with unmanned test precursors before moving to a human-in-the-loop phase, and continues to evolve with the eventual goal of a qualification test for the final system that will be installed on Orion. Meanwhile, the Human Exploration Spacecraft Testbed for Integration and Advancement (HESTIA) program is an effort to research and develop technologies that will work in concert to support habitation on Mars. September 2015 marked the first unmanned HESTIA test, with the goal of characterizing how ECLSS technologies work together in a closed environment. HESTIA will culminate in crewed testing, but it can benefit from the lessons learned from another test that is farther ahead in its development and life cycle. Discussing PIST and HESTIA, this paper illustrates how we approach testing, the kind of information that facility teams need to ensure efficient collaborations and successful testing, and how we can apply what we learn to execute future tests.

Callini, Gianluca↗

NASA NTRSDate not supplied

Monte Carlo Tree Search for Integrated Planning, Learning, and Execution in Nondeterministic Python

We present a novel use of Monte Carlo Tree Search (MCTS),adapted to explore a search space produced by the choice points embedded in Python code. The choice points are non-deterministic assignment statements and subroutine calls. We present MCTS extensions required for doing tree search in this context which includes control constructs like hierarchical decomposition (subroutine calls), iterative while loops and conditional statements. We demonstrate how the system works in a simulated rideshare scenario in an urban setting, and present preliminary experiments as a proof of concept.

Automatic planning↗

NASA NTRS2016

Optical Breath Gas Extravehicular Activity Sensor for the Advanced Portable Life Support System

The function of the infrared gas transducer used during extravehicular activity (EVA) in the current space suit is to measure and report the concentration of carbon dioxide (CO2) in the ventilation loop. The next generation portable life support system (PLSS) requires highly accurate CO2 sensing technology with performance beyond that presently in use on the International Space Station extravehicular mobility unit (EMU). Further, that accuracy needs to be provided over the full operating pressure range of the suit (3 to 25 psia). Accommodation within space suits demands that optical sensors meet stringent size, weight, and power requirements. A laser diode (LD) sensor based on infrared absorption spectroscopy is being developed for this purpose by Vista Photonics, Inc. Version 1.0 prototype devices were delivered to NASA Johnson Space Center (JSC) in September 2011. The prototypes were upgraded with more sophisticated communications and faster response times to version 2.0 and delivered to JSC in July 2012. The sensors incorporate a laser diode based CO2 channel that also includes an incidental water vapor (humidity) measurement. The prototypes are controlled digitally with an field-programmable gate array microcontroller architecture. Based on the results of the iterative instrument development, further prototype development and testing of instruments were performed leveraging the lessons learned where feasible. The present development extends and upgrades the earlier hardware for the advanced PLSS 2.5 prototypes for testing at JSC. The prototypes provide significantly enhanced accuracy for water vapor measurement and eliminate wavelength drift affecting the earlier versions. Various improvements to the electronics and gas sampling are currently being advanced including the companion development of engineering development units that will ultimately be capable of radiation tolerance. The combination of low power electronics with the performance of a long wavelength laser spectrometer enables multi-gas sensors with significantly increased performance over that presently offered in the EMU.

Wood, William R.↗

NASA NTRS2008

Developing Humanoid Robots for Real-World Environments

Humanoids are steadily improving in appearance and functionality demonstrated in controlled environments. To address the challenges of operation in the real-world, researchers have proposed the use of brain-inspired architectures for robot control, and the use of robot learning techniques that enable the robot to acquire and tune skills and behaviours. In the first part of the paper we introduce new concepts and results in these two areas. First, we present a cerebellum-inspired model that demonstrated efficiency in the sensory-motor control of anthropomorphic arms, and in gait control of dynamic walkers. Then, we present a set of new ideas related to robot learning, emphasizing the importance of developing teaching techniques that support learning. In the second part of the paper we propose the use in robotics of the iterative and incremental development methodologies, in the context of practical task-oriented applications. These methodologies promise to rapidly reach system-level integration, and to early identify system-level weaknesses to focus on. We apply this methodology in a task targeting the automated assembly of a modular structure using HOAP-2. We confirm this approach led to rapid development of a end-to-end capability, and offered guidance on which technologies to focus on for gradual improvement of a complete functional system. It is believed that providing Grand Challenge type milestones in practical task-oriented applications accelerates development. As a meaningful target in short-mid term we propose the 'IKEA Challenge', aimed at the demonstration of autonomous assembly of various pieces of furniture, from the box, following included written/drawn instructions.

Stoica, Adrian↗

NASA NTRS1987

Performance improvement of robots using a learning control scheme

Many applications of robots require that the same task be repeated a number of times. In such applications, the errors associated with one cycle are also repeated every cycle of the operation. An off-line learning control scheme is used here to modify the command function which would result in smaller errors in the next operation. The learning scheme is based on a knowledge of the errors and error rates associated with each cycle. Necessary conditions for the iterative scheme to converge to zero errors are derived analytically considering a second order servosystem model. Computer simulations show that the errors are reduced at a faster rate if the error rate is included in the iteration scheme. The results also indicate that the scheme may increase the magnitude of errors if the rate information is not included in the iteration scheme. Modification of the command input using a phase and gain adjustment is also proposed to reduce the errors with one attempt. The scheme is then applied to a computer model of a robot system similar to PUMA 560. Improved performance of the robot is shown by considering various cases of trajectory tracing. The scheme can be successfully used to improve the performance of actual robots within the limitations of the repeatability and noise characteristics of the robot.

Krishna, Ramuhalli↗

NASA NTRS2023

SERFE PLSS Component Lessons Learned from ISS

NASA has been developing a new spacesuit, called the Exploration Extravehicular Mobility Unit (xEMU) for over a decade. This spacesuit is under development to support missions to the International Space Station (ISS) and also to the Moon. Improvements in the life and robustness of the Portable Life Support System (PLSS) has been a major objective of these efforts. The Suit Water Membrane Evaporator (SWME) was chosen as the technology to provide cooling to the xEMU and has undergone several iterations of development over this period. An ISS flight experiment centered around the SWME and other thermal control loop (TCL) technologies was developed and tested in an ISS EXpedite PRocessing of Experiments to the Space Station (EXPRESS) rack from November of 2020 to August of 2022. In addition to the SWME, the SWME EXPRESS Rack Flight Experiment (SERFE) contains several technologies from the xEMU project and demonstrated their performance in micro-gravity and over an extended duration. These included two dissimilar water pumps, custom check valves, custom bypass relieve valves, a custom thermal control valve, development pressure and temperature sensors, and the thermal loop controller. This paper presents PLSS component lessons learned after return of the SERFE flight unit in August of 2022. The SERFE team took the flight unit apart and handed hardware components over to hardware owners to see how parts of the TCL managed after almost 2 years on the ISS and 25 simulated EVAs (Exploration Extravehicular Activity) on orbit. The team performed inspection, testing, and analysis and provided lessons learned on PLSS components for NASA’s prototype spacesuit. This analysis included how well SWME maintained its heat rejection capability, as well as looked at the robustness of the other TCL hardware.

SERFE↗

NASA NTRS2023

SERFE PLSS Component Lessons Learned from ISS

SERFE↗

NASA NTRS2009

Low Impact Docking System (LIDS)

Since 1996, NASA has been developing a docking system that will simplify operations and reduce risks associated with mating spacecraft. This effort has focused on developing and testing an original, reconfigurable, active, closed-loop, force-feedback controlled docking system using modern technologies. The primary objective of this effort has been to design a docking interface that is tunable to the unique performance requirements for all types of mating operations (i.e. docking and berthing, autonomous and piloted rendezvous, and in-space assembly of vehicles, modules and structures). The docking system must also support the transfer of crew, cargo, power, fluid, and data. As a result of the past 10 years of docking system advancement, the Low Impact Docking System or LIDS was developed. The current LIDS design incorporates the lessons learned and development experiences from both previous and existing docking systems. LIDS feasibility was established through multiple iterations of prototype hardware development and testing. Benefits of LIDS include safe, low impact mating operations, more effective and flexible mission implementation with an anytime/anywhere mating capability, system level redundancy, and a more affordable and sustainable mission architecture with reduced mission and life cycle costs. In 1996 the LIDS project, then known as the Advanced Docking Berthing System (ADBS) project, launched a four year developmental period. At the end of the four years, the team had built a prototype of the soft-capture hardware and verified the control system that will be used to control the soft-capture system. In 2001, the LIDS team was tasked to work with the X- 38 Crew Return Vehicle (CRV) project and build its first Engineering Development Unit (EDU).

LaBauve, Tobie E.↗