Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Machine learning”

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 1,387 records · Page 77

Deciding When and How to Learn

Learning is an important aspect of intelligent behavior. Unfortunately, learning rarely comes for free.

machine learning powerful learning approaches comp↗

ICE-RASSOR: Intelligent Capabilities Enhanced

NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for In-Situ Resource Utilization (ISRU) processing. RAS-SOR’s design enables it to efficiently collect and deposit regolith, return collected material for processing, and myriad related ISRU activities. To reliably perform these operations on the lunar sur-face, RASSOR software and sensory systems need to be robust and maximize the information extracted from on-board sensing. Herein, we present preliminary findings from the Intelligent Capabilities Enhanced RASSOR project. We apply supervised learning using real data to estimate the soil mass collected without the need for mass flow rate monitors or other explicate sensing techniques. We also create a reduced-order simulation environment to develop autonomous trenching controllers via reinforcement learning and proto-type state estimation architectures. Our initial results suggest that excavated regolith mass can be inferred within 2.9% RMS error of full scale, and reinforcement learning for autonomous operations has learned viable trenching strategies and helped identify desirable sensing capabilities, arrangements, and considerations. Future work includes regolith mass estimation during dynamic operation, expanding our simulation to more complex environments, and transfer learning from simulation to hardware.

machine learning↗

Adaptive Learning for Reliability Analysis using Support Vector Machines

A novel algorithm is presented for adaptive learning of an unknown function that separates two regions of a domain.In the context of reliability analysis these two regions represent the failure domain, where a set of constraints or requirements are violated, and a safe domain where they are satisfied. The Limit State Function (LSF) separates these two regions. Evaluating the constraints for a given parameter point requires the evaluation of a computational model that may well be expensive. For this reason we wish to construct a meta-model that can estimate the LSFas accurately as possible, using only a limited amount of training data. This work presents an adaptive strategy employing a Support Vector Machine (SVM) as a meta-model to provide a semi-algebraic approximation of the LSF.We describe an optimization process that is used to select informative parameter points to add to training data at each iteration to improve the accuracy of this approximation. A formulation is introduced for bounding the predictions of the meta-model; in this way we seek to incorporate this aspect of Gaussian Process Models (GPMs) within anSVM meta-model. Finally, we apply our algorithm to two benchmark test cases, demonstrating performance that is comparable with, if not superior, to a standard technique for reliability analysis that employs GPMs

Adaptive learning↗

Environment Adversarial Reinforcement Learning

This paper presents a training method for increasing performance of reinforcement learning agents. The method is named Environment Adversarial Reinforcement Learning. The method requires the reinforcement learning environment to be parameterizeable. Over the course of training, environment parameters are updated in a direction of increasing difficulty for the agent. The direction for these updates is found using a performance prediction network trained on data from tests of the agent under varying environment parameters. The method was tested on a CartPole environment. A 28-58\% improvement in mean return was found when comparing performance to a baseline reinforcement learning algorithm on both easy and hard versions of the task.

machine learning↗

Informing NLP Learning Tasks by Tracking User Features: An ASRS Use Case using Kaona

There has been growing interest in utilizing natural language processing (NLP) algorithms in Aviation Safety. This interest has extended to leveraging the decades of records publicly available on the Aviation Safety Reporting System (ASRS). While related literature has given more emphasis in lessons learned from the narratives, our prior work has focused on using NLP to support narrative search in the ASRS. Specifically, we evaluated if the use of alternative search mechanisms to keyword search, such as the retrieval of related narratives even without matching keywords could improve narrative discovery. A difficulty in experimenting alternative search mechanisms in any information retrieval task is the lack of ground truth. To address this limitation, we propose Kaona, a lightweight interface which enables the prototyping of alternative search retrieval tasks, by tracking user experience both explicitly (user-specified feedback), or implicitly (user navigation through interface affordances). Differently from distracting requests for feedback during user navigation, Kaona collects explicit feedback from users by mapping them to affordances which support the user workflow, while obtaining ground truth information for learning tasks.

human-computer-interaction↗

Using Ensemble Decisions and Active Selection to Improve Low-Cost Labeling for Multi-View Data

This paper seeks to improve low-cost labeling in terms of training set reliability (the fraction of correctly labeled training items) and test set performance for multi-view learning methods. Co-training is a popular multiview learning method that combines high-confidence example selection with low-cost (self) labeling. However, co-training with certain base learning algorithms significantly reduces training set reliability, causing an associated drop in prediction accuracy. We propose the use of ensemble labeling to improve reliability in such cases. We also discuss and show promising results on combining low-cost ensemble labeling with active (low-confidence) example selection. We unify these example selection and labeling strategies under collaborative learning, a family of techniques for multi-view learning that we are developing for distributed, sensor-network environments.

machine learning↗

Reinforcement Learning Approach to Flight Control Allocation with Distributed Electric Propulsion

The flight control system of the SUSAN Electrofan concept aircraft achieves attitude control using both conventional flight control surfaces and differential thrust through distributed electric propulsion (DEP) from sixteen wing-mounted electric engines. The introduction of eight pairs of wing fans for attitude control creates a highly actuated system. Such a system requires more sophisticated control to operate, especially in the presence of wingfan failures where the loss of a single wingfan can result in a thrust imbalance. This paper investigates the use of deep reinforcement learning (RL) using proximal policy optimization (PPO) to achieve attitude control through a combination of DEP and control surface deflections. First, the paper examines the aircraft undergoing a coordinated turn. Then, it examines the aircraft experiencing a wingfan failure during cruise conditions. It is shown that deep reinforcement learning can be a potential avenue for nonlinear flight control design.

Distributed Electric Propulsion↗

Onboard Hyperspectral Image Classification via Transfer Learning for Communication-Limited Spacecraft

Employing deep-learning and artificial-intelligence (AI) techniques onboard spacecraft can dramatically improve priority data selection to ensure more effective use of the available downlink. However, deployment of effective deep-learning models requires significant training on the ground, which may not be feasible, due to limited data available in an unexplored environment. Therefore, this research explores building robust classification models for onboard data processing where training data is highly limited using transfer-learning techniques. In this paper, we focus on the use case of hyperspectral imaging for remote sensing, a domain where the high dimensionality of the data from the sensor can rapidly saturate the downlink bandwidth. With this bottleneck, there is an impending need to autonomously and robustly classify data onboard to optimize downlink of high-impact measurements, thus maximizing the scientific utility per bit transmitted to the ground. This paper examines the use of deep neural networks onboard for hyperspectral image classification in a communication-limited scenario to analyze how the models perform with limited training data. The use of transfer learning can ameliorate the issue of poor generalization by transferring features learned from training on a large source dataset for one classification task to the target classification task with limited training data. For two deep-learning models from literature, we compare the accuracy of the models trained using transfer learning to models trained from scratch using a random weight initialization with varying amounts of training data. We demonstrate the feasibility and performance of running inference of the deep-learning models on representative flight-like hardware.

Advanced Avionics, Machine Learning, Data Processi↗

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

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

machine learning↗

Efficient Heuristic Hypothesis Ranking

This paper considers the problem of learning the ranking of a set of stochastic alternatives based upon incomplete information (i.e., a limited number of samples).

machine↗

Communication Network Awareness Machine System Phase I Development: The Intelligent Party-Line Schema

As NextGen continues toward the full implementation of a Net-Centric Architecture (N-CA)it will inherently provide a continuous increase to the Three-Vs components (Volume, Velocity, and Variety) of big data . This will create an insurmountable environment for direct-action aviation personnel (DAAP)as the DAAP’s natural abilities to manage and process data into actionable information will be overmatched by the Three-Vs. Therefore, conducting operations within a N-CA requires that new tools and applications be researched and developed to aid the DAAP’s ability to understand and manage data, mitigate non-normals, create contingency plans and actions. This paper will describe a research area at NASA Langley Research Center known as the Intelligent Party-Line (IPL).

Intelligent Party-Line↗

Robust Semantic Mapping and Localization on a Free-Flying Robot in Microgravity

We propose a system that uses semantic object detections to localize a microgravity free-flyer. Many applications require absolute localization in a known reference frame, such as the execution of waypoint trajectories defined by human operators. Classical geometric methods build a map of point features, which may not be able to be associated after lighting or environmental changes. By contrast, semantics remain invariant to changes up to the robustness of the detection algorithm and motion of the semantic objects. In this work, we describe our approaches for both offline semantic map generation as well as online localization against a semantic map, intended to run in real-time on the robot. We additionally demonstrate how our semantic localizer outperforms image-feature matching in some cases, and show the robustness of the algorithm to environmental changes. Crucially, we show in our experiments that when semantics are used to supplement point features, localization is always improved. To our knowledge, these experiments demonstrate the first use of learned semantics for localization on a free-flying robot in microgravity.

Localization↗

ICE-RASSOR: Intelligent Capabilities Enhanced Regolith Advanced Surface Systems Operations Robot

NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for In-Situ Resource Utilization (ISRU)processing. RASSOR’s design enables it to efficiently collect and deposit regolith, return collected material for processing, and myriad related ISRU activities. To reliably perform these operations on the lunar surface, RASSOR software and sensory systems need to be robust and maximize the information extracted from a reduced sensor payload. Herein, we present preliminary findings from the Intelligent Capabilities Enhanced RASSOR project. We apply supervised learning using real data to estimate the soil mass collected without the need for mass flow rate monitors or other explicate sensing techniques. We also create a reduced-order simulation environment to develop autonomous trenching controllers via reinforcement learning and prototype state estimation architectures. Our initial results suggest that excavated regolith mass can be inferred within 2.9% RMS error of full scale, and reinforcement learning for autonomous operations has learned viable trenching strategies and helped identify desirable sensing capabilities, arrangements, and considerations. Future work includes regolith mass estimation during dynamic operation, expanding our simulation to more complex environments, and transfer learning from simulation to hardware.

machine learning↗