Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning 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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS2020

Machine Learning Algorithm Performance on the Lucata Computer

A new parallel computing paradigm (processor in memory, or PIM) has recently become available, one that uses many lightweight threads, and where each thread migrates automatically to the memory used by that thread. Our effort focuses on understanding how suitable this architecture is for our application, and whether the hardware can sustain speedups as high as the system size permits. In particular we explore the kind of code optimizations needed, and how well optimized code scales. This paper describes some of the those optimizations, and the payoff in terms of scaling.

Kogge, Peter↗
NASA NTRSDate not supplied

Towards Autonomous Lunar Resource Excavation via Reinforcement Learning

To continue on a sustainable and flexible path, NASA needs to address the challenge of collecting and moving large amounts of regolith at the destination. 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 created reduced-order simulation environments to develop autonomous trenching controllers via reinforcement learning and prototype state estimation architectures. The goal of reinforcement learning is for an agent to learn a policy (task strategy) through interactions with an environment. When the agent performs an action, a change occurs in environment state and a numerical reward is received which informs the agent whether the action performed was good or not. Since reinforcement learning algorithms learn through trial-and-error, a simulation is a desirable first environment for development and learning. We developed two simulations, the first is a 2D excavation simulation developed to facilitate parameter selection, and a 3D simulation developed using a game physics engine, to simulate simplified soil interactions and increase the fidelity of the dynamic models of the robotic agents. The development of this 3D simulation has enabled the training of additional sensing capabilities and research both at the granular mechanics and operations levels. We experimented with various virtual sensor payloads to identify a combination that enabled efficient excavation operation and learning. Our reward function is based on how much material is excavated per step. A penalty is also received for leaving the dig site and to smooth the acceleration of the drum arms. We implemented pseudo time-of-flight sensors to report distance from each drum to ground and the height above ground which was found to be more efficient than existing solutions. Our findings suggest that reinforcement learning for autonomous operations has learned viable trenching strategies within 3000 training episodes in our simplified 2D environment and helped identify desirable sensing capabilities, arrangements, and considerations such as the positioning of time-of-flight sensors. Future work includes expanding our simulation to more complex environments and scenarios, and transfer learning from simulation to RASSOR 2.0 hardware for deployment in the Regolith Test Bin at NASA's Kennedy Space Center.

rassor↗
NASA NTRSDate not supplied

Machine Learning for the Validation of Expert-Elicited Causal Risk Diagrams

Exposure to spaceflight poses risk to human health in complex ways. To help manage this risk, the Human Systems Risk Board (HSRB) at the National Aeronautics and Space Administration (NASA) maintains a set of causal diagrams that attempt to explain how spaceflight hazards generate health risks and lead to adverse outcomes both in-mission, immediately post-mission, and over the long term. These causal risk diagrams are formulated as directed acyclic graphs (DAGs) and can function as knowledge graphs of connected risks and outcomes. These DAGs have proven useful for communication, and, through network analysis, have allowed for the identification of structurally important factors in the risk network. However, the utility these DAGs provide is directly proportional to their verisimilitude, making assessment of this trait using empirical data – whether from actual human spaceflight or various spaceflight analogue exposures and model organisms – a high priority. In this research we explore the use of machine learning algorithms to learn DAG structure from empirical data as a means of evaluating human-elicited DAG structures. To do so, we test several different graph structure-learning algorithms on data concerning changes in the bones of rats and mice after exposure to either spaceflight or a spaceflight analogue. We explore potential methods for indexing the similarity between each algorithm’s output DAG with all the others and with that of the expert-elicited DAG. We discuss next steps in this ongoing line of research and open science initiatives underway to complete them.

directed acyclic graphs↗
NASA NTRS1990

A coordination theory for intelligent machines

A formal model for the coordination level of intelligent machines is established. The framework of the coordination level investigated consists of one dispatcher and a number of coordinators. The model called coordination structure has been used to describe analytically the information structure and information flow for the coordination activities in the coordination level. Specifically, the coordination structure offers a formalism to (1) describe the task translation of the dispatcher and coordinators; (2) represent the individual process within the dispatcher and coordinators; (3) specify the cooperation and connection among the dispatcher and coordinators; (4) perform the process analysis and evaluation; and (5) provide a control and communication mechanism for the real-time monitor or simulation of the coordination process. A simple procedure for the task scheduling in the coordination structure is presented. The task translation is achieved by a stochastic learning algorithm. The learning process is measured with entropy and its convergence is guaranteed. Finally, a case study of the coordination structure with three coordinators and one dispatcher for a simple intelligent manipulator system illustrates the proposed model and the simulation of the task processes performed on the model verifies the soundness of the theory.

Wang, Fei-Yue↗
NASA NTRS2019

Using Machine-Learning to Dynamically Generate Operationally Acceptable Strategic Reroute Options

The newly developed Trajectory Option Set (TOS), a preference-weighted set of alternative routes submitted by flight operators, is a capability in the U.S. traffic flow management system that enables automated trajectory negotiation between flight operators and Air Navigation Service Providers. The objective of this paper is to describe and demonstrate an approach for automatically generating pre-departure and airborne TOSs that have a high probability of operational acceptance. The approach uses hierarchical clustering of historical route data to identify route candidates. The probability of operational acceptance is then estimated using predictors trained on historical flight plan amendment data using supervised machine learning algorithms, allowing the routes with highest probability of operational acceptance to be selected for the TOS. Features used describe historical route usage, difference in flight time and downstream demand to capacity imbalance. A random forest was found to be the best performing algorithm for learning operational acceptability, with a model accuracy of 0.96. The approach is demonstrated for an historical pre-departure flight from Dallas/Fort Worth International Airport to Newark Liberty International Airport.

Evans, Antony↗
NASA NTRS2019

Using Machine-Learning to Dynamically Generate Operationally Acceptable Strategic Reroute Options

The newly developed Trajectory Option Set (TOS), a preference-weighted set of alternative routes submitted by flight operators, is a capability in the U.S. traffic flow management system that enables automated trajectory negotiation between flight operators and Air Navigation Service Providers. The objective of this paper is to describe and demonstrate an approach for automatically generating pre-departure and airborne TOSs that have a high probability of operational acceptance. The approach uses hierarchical clustering of historical route data to identify route candidates. The probability of operational acceptance is then estimated using predictors trained on historical flight plan amendment data using supervised machine learning algorithms, allowing the routes with highest probability of operational acceptance to be selected for the TOS. Features used describe historical route usage, difference in flight time and downstream demand to capacity imbalance. A random forest was found to be the best performing algorithm for learning operational acceptability, with a model accuracy of 0.96. The approach is demonstrated for an historical pre-departure flight from Dallas/Fort Worth International Airport to Newark Liberty International Airport.

Evans, Antony↗