Search NASA⌕ Search

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.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Deploying Traffic Smoothing Cruise Controllers Learned from Trajectory Data

Autonomous vehicle-based traffic smoothing con- trollers are often not transferred to real-world use due to challenges in calibrating many-agent traffic simulators. We show a pipeline to sidestep such calibration issues by collecting trajectory data and learning controllers directly from trajectory data that are then deployed zero-shot onto the highway. We construct a dataset of 772.3 kilometers of recorded drives on the I-24. We then construct a simple simulator using the recorded drives as the lead vehicle in front of a simulated platoon consisting of one autonomous vehicle and five human followers. Using policy-gradient methods with an asymmetric critic to learn the controller, we show that we are able to improve average MPG by 11% in simulation on congested trajectories. We deploy this controller to a mixed platoon of 4 autonomous Toyota RAV-4’s and 7 human drivers in a validation experiment and demonstrate that the expected time-gap of the controller is maintained in the real world test. Finally, we release the driving dataset [1], the simulator, and the trained controller at https://github.com/nathanlct/trajectory-training-icra.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2018

Geometric Analysis Based Double Closed-loop Iterative Learning Control of Output PDF Shaping of Fiber Length Distribution in Refining Process

In order to improve the pulp quality and to reduce the energy consumption, the fiber length distribution (FLD) is generally employed as one of the important technological indexes in the refining process. Considering that the traditional mean and variance of fiber length are unable to adequately characterize the non-Gaussian distribution properties, this paper proposes a novel geometric analysis based double closed-loop iterative learning control (ILC) method for probability density function (PDF) shaping of output FLD in the refining process. Primarily, a RBF neural network (NN) with Gaussian-type is utilized to approximate the square root PDF in the inner loop, where the RBF basis function parameters (center and width) are tuned between any two adjacent batches by using an ILC law, and the subspace identification method can be applied to establish the state-space model of weight vector. Then, for the sake of accelerating the convergence rate of the closed-loop sysyem, a geometric analysis based ILC method is adopted in the outer loop. Lastly, both simulation and experiments demonstrate the effectiveness and practicability of the proposed approach.

42 ENGINEERING↗
DOE OSTI2020

Iterative Learning Control for Video-rate Atomic Force Microscopy

We present a control scheme for video-rate atomic force microscopy with rosette pattern. The controller structure involves a feedback internal-model-based controller and a feedforward iterative learning controller. The iterative learning controller is designed to improve tracking performance of the feedback-controlled scanner by rejecting the repetitive disturbances arising from the system nonlinearities. We investigate the performance of two inversion techniques for constructing the learning filter. We conduct tracking experiments using a two-degree-of-freedom microelectromechanical system (MEMS) nanopositioner at frame rates ranging from 5 to 20 frames per second. Furthermore, the results reveal that the algorithm converges rapidly and the iterative learning controller significantly reduces both the transient and steady-state tracking errors. We acquire and report a series of high-resolution time-lapsed video-rate AFM images with the rosette pattern.

42 ENGINEERING↗
DOE OSTI2023

Challenges and opportunities of machine learning control in building operations

Machine learning control (MLC) is a highly flexible and adaptable method that enables the design, modeling, tuning, and maintenance of building controllers to be more accurate, automated, flexible, and adaptable. The research topic of MLC in building energy systems is developing rapidly, but to our knowledge, no review has been published that specifically and systematically focuses on MLC for building energy systems. Here this paper provides a systematic review of MLC in building energy systems. We review technical papers in two major categories of applications of machine learning in building control: (1) building system and component modeling for control, and (2) control process learning. We identify MLC topics that have been well-studied and those that need further research in the field of building operation control. We also identify the gaps between the present and future application of MLC and predict future trends and opportunities.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Deep reinforcement learning control of hydraulic fracturing

Hydraulic fracturing is a technique to extract oil and gas from shale formations, and obtaining a uniform proppant concentration along the fracture is key to its productivity. Recently, various model predictive control schemes have been proposed to achieve this objective. But such controllers require an accurate and computationally efficient model which is difficult to obtain given the complexity of the process and uncertainties in the rock formation properties. In this article, we design a model-free data-based reinforcement learning controller which learns an optimal control policy through interactions with the process. Deep reinforcement learning (DRL) controller is based on the Deep Deterministic Policy Gradient algorithm that combines Deep-Q-network with actor-critic framework. In addition, we utilize dimensionality reduction and transfer learning to quicken the learning process. We show that the controller learns an optimal policy to obtain uniform proppant concentration despite the complex nature of the process while satisfying various input constraints.

42 ENGINEERING↗
DOE OSTI2022

RLC4CLR (Reinforcement Learning Controller for Critical Load Restoration Problems)

RLC4CLR demonstrates using a reinforcement learning controller (RLC) to solve a critical load restoration (CLR) problem, which improves the grid resilience after a substation outage event. RLC4CLR consists of two parts. (1) RL environment: This environment encapsulates the CLR problem to be solved and provides interfacing functions to follow the standard OpenAI Gym format. A power system simulator, i.e., OpenDSS, is included to provide the power flow solution. Controller inputs and outputs (RL state and action) as well as the reward are defined in this environment as well. In summary, the RL environment is the problem formulation from which the RL agent can learn. (2) RL training script: The training script enables the RL agent to learn its control policy by interacting with the RL environment. For RL training, an open-sourced RL library, i.e., RLlib, is leveraged which is based on a distributed computing framework (Ray). The training script is designed to be able to be run on both local machine or the NREL HPC system. Other components of RLC4CLR include input data, e.g., grid model (standard IEEE test feeders), and other files used for results analysis.

Zhang, Xiangyu↗
DOE OSTI2024

A Transfer Learning Strategy for Improving the Data Efficiency of Deep Reinforcement Learning Control in Smart Buildings

Reinforcement learning (RL) is a powerful tool that has shown promising results in many domains such as robotics and game-playing. Because RL algorithms learn optimal control policies by continuously interacting with their environments, these algorithms require a lot of data to learn, which limits their application to a wide range of domains. For this reason, there is an immense need for improving the training and data efficiency of RL. Towards addressing this research gap, this paper proposes a transfer learning (TL) approach to improve the efficiency of the RL algorithms by reducing data need and, thus, reducing training time. To demonstrate the proposed approach, a knowledge transfer from a set of buildings to another building was conducted. The results show that the proposed TL approach is a promising method that can efficiently harness the information from similar RL tasks and reduce the data needs of RL algorithms.

Amasyali, Kadir↗
DOE OSTI2019

Iterative Learning Control for High-Speed Rosette Trajectory Tracking

We demonstrate high-speed tracking of a selfrepeating non-raster scan AFM pattern known as rosette. To generate this pattern, the lateral axes of the scanner trace a sum of two sinusoids with different frequencies but identical amplitudes. A feedback controller is combined with an iterative learning controller (ILC) to track this repetitive pattern. The feedback controller is designed based on the internal model principle and incorporates the fundamental reference frequencies. The ILC eliminates the repeating deterministic disturbances that appear in the tracking error. To verify the efficacy of the control approach, an experiment is conducted using a two degrees-of-freedom microelectromechanical system nanopositioner to track a rosette pattern sequentially at the rate= of five frames per second. The experimental results show that the root-mean-square value of tracking error has been reduced by more than 50% owing to the ILC

42 ENGINEERING↗
DOE OSTI2018

Tracking Error Learning Control for Precise Mobile Robot Path Tracking in Outdoor Environment

This article presents a Tracking-Error Learning Control (TELC) algorithm for precise mobile robot path tracking in off-road terrain. In traditional tracking error-based control approaches, feedback and feedforward controllers are designed based on the nominal model which cannot capture the uncertainties, disturbances and changing working conditions so that they cannot ensure precise path tracking performance in the outdoor environment. In TELC algorithm, the feedforward control actions are updated by using the tracking error dynamics and the plant-model mismatch problem is thus discarded. Therefore, the feedforward controller gradually eliminates the feedback controller from the control of the system once the mobile robot has been ontrack. In addition to the proof of the stability, it is proven that the cost functions do not have local minima so that the coefficients in TELC algorithm guarantee that the global minimum is reached. The experimental results show that the TELC algorithm results in better path tracking performance than the traditional tracking error-based control method. The mobile robot controlled by TELC algorithm can track a target path precisely with less than 10 cm error in off-road terrain.

42 ENGINEERING↗
DOE OSTI2021

Restoring Critical Loads In Resilient Distribution Systems using A Curriculum Learned Controller

In this paper, we propose a curriculum learned reinforcement learning (RL) controller to facilitate distribution system critical load restoration (CLR), leveraging RL's fast online response and its outstanding optimal sequential control capability. Like many grid control problems, CLR is complicated due to the large control action space and renewable uncertainty in a heavily constrained non-linear environment with strong intertemporal dependency. The nature of the problem oftentimes causes the RL policy to converge to a poor-performing local optimum if learned directly. To overcome this, we design a two-stage curriculum in which the RL agent will learn generation control and load restoration decision under different scenarios progressively. Via curriculum learning, the trained RL controller is expected to achieve a better control performance, with critical loads restored as rapidly and reliably as possible. Using the IEEE 13-bus test system, we illustrate the performance of the RL controller trained by the proposed curriculum-based method.

curriculum learning↗
DOE OSTI2023

Inverse reinforcement learning control for building energy management

Reinforcement learning (RL) based control is widely considered a promising approach in building automation and control as it has demonstrated the potential to deal with complex objectives in adjacent domains like robotics, autonomous vehicles, gaming applications, and advertisement recommendations. When applied to any environment, model-free RL learns to improve its control performance over time without requiring a control model, by receiving and then analyzing feedback from the building environment after each control action. Operational objectives are becoming increasingly complex through the simultaneous consideration of thermal comfort, carbon emissions, grid services, and indoor air quality. In this context, conventional rule-based control approaches are proving sub-optimal, mostly heuristic, and inadequate. The model-free and self learning nature of RL appears promising and attractive as it may address the scalability issues associated with advanced control approaches. However, it suffers from long training times and unstable control behavior during the early stages of its learning process, which makes it unsuitable to be applied directly to buildings. This paper addresses these issues using an inverse reinforcement learning approach (IRL), a technique utilized to learn the objective of a controller agent which is considered an expert in its respective domain. Here, we consider a rule-based control as the expert demonstrator. IRL is different from a direct imitation (i.e., direct mapping of states to actions) of control actions as it tries to find the underlying intent of an expert's policy, providing the controller with a better-generalized policy for unseen states or environments with slightly different dynamics. This approach propels the RL controller's policy to levels similar to or better than that of a rule-based policy before it starts learning by interacting with the building. This makes RL for building energy management applications more practical as it prevents the erratic and exploratory behavior in the initial training period, simultaneously speeding up the learning process when compared to applying an untrained RL agent directly to a building environment.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2019

Closed-Loop Error Learning Control for Uncertain Nonlinear Systems With Experimental Validation on a Mobile Robot

This article develops a closed-loop error learning control (CLELC) algorithm for feedback linearizable systems with experimental validation on a mobile robot. Traditional feedback and feedforward controllers are designed based on the nominal model by using the feedback linearization control (FLC) method. Then, an intelligent controller is designed based on the sliding mode learning algorithm that utilizes closed-loop error dynamics to learn the system behavior. The controllers are working in parallel, and the intelligent controller can gradually replace the feedback controller from the control of the system. In addition to the stability of the sliding mode learning algorithm, the closed-loop stability of an nth-order feedback linearizable system is proven. The simulation results demonstrate that the CLELC algorithm can improve control performance (e.g., smaller rise time, settling time, and overshoot) in the absence of uncertainties, and also provides robust control performance in the presence of uncertainties as compared to traditional FLC method. To test the efficiency and efficacy of the CLELC algorithm, the trajectory tracking problem of a tracked mobile robot is studied in real time. The experimental results demonstrate that the CLELC algorithm ensures highly accurate trajectory tracking performance than traditional FLC method.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Restoring Critical Loads in Resilient Distribution Systems Using a Curriculum Learned Controller: Preprint

In this paper, we propose a curriculum learned reinforcement learning (RL) controller to facilitate distribution system critical load restoration (CLR), leveraging RL's fast online response and its outstanding optimal sequential control capability. Like many grid control problems, CLR is complicated due to the large control action space and renewable uncertainty in a heavily constrained non-linear environment with strong intertemporal dependency. The nature of the problem oftentimes causes the RL policy to converge to a poor-performing local optimum if learned directly. To overcome this, we design a two-stage curriculum in which the RL agent will learn generation control and load restoration decision under different scenarios progressively. Via curriculum learning, the trained RL controller is expected to achieve a better control performance, with critical loads restored as rapidly and reliably as possible. Using the IEEE 13-bus test system, we illustrate the performance of the RL controller trained by the proposed curriculum-based method.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2021

On Distributed Model-Free Reinforcement Learning Control with Stability Guarantee

Distributed learning can enable scalable and effective decision making in numerous complex cyber-physical systems such as smart transportation, robotics swarm, power systems, etc. However, the stability of the system is usually not guaranteed in most existing learning paradigms; and this limitation can hinder the wide deployment of machine learning in decision making of safety-critical systems. This paper presents a stability guaranteed distributed reinforcement learning (SGDRL) framework for interconnected linear subsystems, without knowing the subsystem models. While the learning process requires data from a peer-to-peer (p2p) communication architecture, the control implementation of each subsystem is only based on its local state. The stability of the interconnected subsystems will be ensured by a diagonally dominant eigenvalue condition, which will then be used in a model-free RL algorithm to learn the feedback control gains. The RL algorithm structure follows an off-policy iterative framework, with interleaved policy evaluation and policy update steps. We numerically validate our theoretical results by performing simulations on four interconnected sub-systems.

Mukherjee, Sayak↗
DOE OSTI2019

Simultaneous iterative learning control of mode entrainment and error field

Here, it is shown that static error fields (EFs) can severely limit the maximum rotation frequency achievable in mode entrainment by applied rotating fields. It is also shown that the rotation non-uniformities caused by an EF can be used to diagnose and correct said EF in real time. Simulations using typical DIII-D data show that this can be achieved within a small number of mode rotation periods by an iterative learning control algorithm. Further to rapidly correcting the EF, this gives access to high entrainment frequencies that would not be accessible otherwise, and paves the way to rotational stabilization and improved mode control.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Machine learning control for disruption and tearing mode avoidance

In this work, real-time feedback control based on machine learning algorithms (MLA) was successfully developed and tested on DIII-D plasmas to avoid tearing modes and disruptions while maximizing the plasma performance, which is measured by normalized plasma beta. Control uses MLAs that were trained with ensemble learning methods using only the data available to the real-time Plasma Control System (PCS) from several thousand DIII-D discharges. A `tearability' metric that quantifies the likelihood of the onset of 2/1 tearing modes (TM) in a given time window, and a 'disruptivity' metric that quantifies the likelihood of the onset of plasma disruptions were first tested o -line then implemented on the PCS. A real-time control system based on these MLAs was successfully tested on DIII-D discharges, using feedback algorithms to maximize β Ν while avoiding tearing modes and to dynamically adjust ramp down to avoid high-current disruptions in ramp down.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

An innovative heterogeneous transfer learning framework to enhance the scalability of deep reinforcement learning controllers in buildings with integrated energy systems

Deep Reinforcement Learning (DRL)-based control shows enhanced performance in the management of integrated energy systems when compared with Rule-Based Controllers (RBCs), but it still lacks scalability and generalisation due to the necessity of using tailored models for the training process. Transfer Learning (TL) is a potential solution to address this limitation. However, existing TL applications in building control have been mostly tested among buildings with similar features, not addressing the need to scale up advanced control in real-world scenarios with diverse energy systems. This paper assesses the performance of an online heterogeneous TL strategy, comparing it with RBC and offline and online DRL controllers in a simulation setup using EnergyPlus and Python. The study tests the transfer in both transductive and inductive settings of a DRL policy designed to manage a chiller coupled with a Thermal Energy Storage (TES). The control policy is pre-trained on a source building and transferred to various target buildings characterised by an integrated energy system including photovoltaic and battery energy storage systems, different building envelope features, occupancy schedule and boundary conditions (e.g., weather and price signal). The TL approach incorporates model slicing, imitation learning and fine-tuning to handle diverse state spaces and reward functions between source and target buildings. Results show that the proposed methodology leads to a reduction of 10% in electricity cost and between 10% and 40% in the mean value of the daily average temperature violation rate compared to RBC and online DRL controllers. Moreover, online TL maximises self-sufficiency and self-consumption by 9% and 11% with respect to RBC. Conversely, online TL achieves worse performance compared to offline DRL in either transductive or inductive settings. However, offline Deep Reinforcement Learning (DRL) agents should be trained at least for 15 episodes to reach the same level of performance as the online TL. Therefore, the proposed online TL methodology is effective, completely model-free and it can be directly implemented in real buildings with satisfying performance.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗