Publications

Refine Results

(Filters Applied) Clear All

AAM-Gym: Artificial intelligence testbed for advanced air mobility

June 9, 2022
  |
Journal Article
Author:
Marc W. Brittain
…
Published in:
arXiv, 9 June 2022.
Topic:
artificial intelligence
R&D area:
R&D group:

Summary

We introduce AAM-Gym, a research and development testbed for Advanced Air Mobility (AAM). AAM has the potential to revolutionize travel by reducing ground traffic and emissions by leveraging new types of aircraft such as electric vertical take-off and landing (eVTOL) aircraft and new advanced artificial intelligence (AI) algorithms. Validation of AI algorithms require representative AAM scenarios, as well as a fast time simulation testbed to evaluate their performance. Until now, there has been no such testbed available for AAM to enable a common research platform for individuals in government, industry, or academia. MIT Lincoln Laboratory has developed AAM-Gym to address this gap by providing an ecosystem to develop, train, and validate new and established AI algorithms across a wide variety of AAM use-cases. In this paper, we use AAM-Gym to study the performance of two reinforcement learning algorithms on an AAM use-case, separation assurance in AAM corridors. The performance of the two algorithms is demonstrated based on a series of metrics provided by AAM-Gym, showing the testbed’s utility to AAM research.
READ LESS

Summary

We introduce AAM-Gym, a research and development testbed for Advanced Air Mobility (AAM). AAM has the potential to revolutionize travel by reducing ground traffic and emissions by leveraging new types of aircraft such as electric vertical take-off and landing (eVTOL) aircraft and new advanced artificial intelligence (AI) algorithms. Validation of...

READ MORE
AAM-Gym: Artificial intelligence testbed for advanced air mobility

Nearfield anechoic chamber and farfield on-site antenna calibration pattern comparison of an S-band planar phased array radar

April 27, 2022
  |
Conference Paper
Author:
Christine F. Parry
…
Published in:
IEEE Annual Conf. on Wireless and Microwave Technology, WAMICON, 27-28 April 2022.
Topic:
antennas
R&D area:
R&D group:

Summary

The Advanced Technology Demonstrator (ATD) is an active, S-band, dual-polarization phased array radar developed for weather sensing. The ATD is an active electronically scanned array (AESA) with a 4-m aperture comprised of 4,864 individual transmit/receive (T/R) modules. The antenna was calibrated at the element, subarray, and array levels. Calibration, validation, and verification testing was completed in two main stages, first in an anechoic chamber and second after it was installed on site in its permanent location. This paper describes the procedure used to collect antenna patterns at each stage and compares three key performance metrics: beamwidth, mean-squared sidelobe level (MSSL), and integrated sidelobe level (ISL).
READ LESS

Summary

The Advanced Technology Demonstrator (ATD) is an active, S-band, dual-polarization phased array radar developed for weather sensing. The ATD is an active electronically scanned array (AESA) with a 4-m aperture comprised of 4,864 individual transmit/receive (T/R) modules. The antenna was calibrated at the element, subarray, and array levels. Calibration, validation...

READ MORE
Nearfield anechoic chamber and farfield on-site antenna calibration pattern comparison of an S-band planar phased array radar

Correlated Bayesian model of aircraft encounters in the terminal area given a straight takeoff or landing

March 12, 2022
  |
Journal Article
Author:
Andrew J. Weinert
…
Published in:
Aerospace, Vol. 9, No.2, 12 March 2022.
Topic:
collision avoidance
R&D area:
R&D group:

Summary

The integration of new airspace entrants into terminal operations requires design and evaluation of Detect and Avoid systems that prevent loss of well clear from and collision with other aircraft. Prior to standardization or deployment, an analysis of the safety performance of those systems is required. This type of analysis has typically been conducted by Monte Carlo simulation with synthetic, statistically representative encounters between aircraft drawn from an appropriate encounter model. While existing encounter models include terminal airspace classes, none explicitly represents the structure expected while engaged in terminal operations, e.g., aircraft in a traffic pattern. The work described herein is an initial model of such operations where an aircraft landing or taking off via a straight trajectory encounters another aircraft landing or taking off, or transiting by any means. The model shares the Bayesian network foundation of other Massachusetts Institute of Technology Lincoln Laboratory encounter models but tailors those networks to address structured terminal operations, i.e., correlations between trajectories and the airfield and each other. This initial model release is intended to elicit feedback from the standards-writing community.
READ LESS

Summary

The integration of new airspace entrants into terminal operations requires design and evaluation of Detect and Avoid systems that prevent loss of well clear from and collision with other aircraft. Prior to standardization or deployment, an analysis of the safety performance of those systems is required. This type of analysis...

READ MORE
Correlated Bayesian model of aircraft encounters in the terminal area given a straight takeoff or landing

Radar coverage analysis for the Terminal Precipitation on the Glass Program

March 4, 2022
  |
Project Report
Author:
John Y. Cho
…
Published in:
MIT Lincoln Laboratory Report ATC-450
Topic:
radar
R&D area:
R&D group:

Summary

The Terminal Precipitation on the Glass (TPoG) program proposes to improve the STARS precipitation depiction by adding an alternative precipitation product based on a national weather-radar-based mosaic, i.e., the NextGen Weather System (aka NextGen Weather Processor [NWP] and Common Support Services Weather [CSS-Wx]). This report describes spatial and temporal domain analyses conducted over the 146 terminal radar approach control (TRACON) airspaces that are within scope of TPoG to identify and quantify future TPoG benefits, as well as potential operational issues.
READ LESS

Summary

The Terminal Precipitation on the Glass (TPoG) program proposes to improve the STARS precipitation depiction by adding an alternative precipitation product based on a national weather-radar-based mosaic, i.e., the NextGen Weather System (aka NextGen Weather Processor [NWP] and Common Support Services Weather [CSS-Wx]). This report describes spatial and temporal domain...

READ MORE
Radar coverage analysis for the Terminal Precipitation on the Glass Program

Adapting deep learning models to new meteorological contexts using transfer learning

December 15, 2021
  |
Conference Paper
Author:
Pooya R. Khorrami
…
Published in:
2021 IEEE International Conference on Big Data (Big Data), 2021, pp. 4169-4177, doi: 10.1109/BigData52589.2021.9671451.
Topic:
machine learning
R&D area:
R&D group:

Summary

Meteorological applications such as precipitation nowcasting, synthetic radar generation, statistical downscaling and others have benefited from deep learning (DL) approaches, however several challenges remain for widespread adaptation of these complex models in operational systems. One of these challenges is adequate generalizability; deep learning models trained from datasets collected in specific contexts should not be expected to perform as well when applied to different contexts required by large operational systems. One obvious mitigation for this is to collect massive amounts of training data that cover all expected meteorological contexts, however this is not only costly and difficult to manage, but is also not possible in many parts of the globe where certain sensing platforms are sparse. In this paper, we describe an application of transfer learning to perform domain transfer for deep learning models. We demonstrate a transfer learning algorithm called weight superposition to adapt a Convolutional Neural Network trained in a source context to a new target context. Weight superposition is a method for storing multiple models within a single set of parameters thus greatly simplifying model maintenance and training. This approach also addresses the issue of catastrophic forgetting where a model, once adapted to a new context, performs poorly in the original context. We apply weight superposition to the problem of synthetic weather radar generation and show that in scenarios where the target context has less data, a model adapted with weight superposition is better at maintaining performance when compared to simpler methods. Conversely, the simple adapted model performs better on the source context when the source and target contexts have comparable amounts of data.
READ LESS

Summary

Meteorological applications such as precipitation nowcasting, synthetic radar generation, statistical downscaling and others have benefited from deep learning (DL) approaches, however several challenges remain for widespread adaptation of these complex models in operational systems. One of these challenges is adequate generalizability; deep learning models trained from datasets collected in specific...

READ MORE
Adapting deep learning models to new meteorological contexts using transfer learning

CoSPA data product description

November 1, 2021
  |
Project Report
Author:
Diana L. Klingle-Wilson
…
Published in:
MIT Lincoln Laboratory Report ATC-449
Topic:
aviation weather
R&D area:
R&D group:

Summary

This document contains a description of Consolidated Storm Prediction for Aviation (CoSPA) data products that are packaged and distributed for external users. As described in Rappa and Troxel, 2013 [1] for Corridor Integrated Weather System (CIWS) data products, CoSPA products are categorized as gridded and non-gridded. Gridded products are typically expressed as rectangular arrays whose elements contain a data value coinciding with uniformly-spaced observations or computed results on a 2-D surface. Gridded data arrays map to the earth's surface through a map projection, for example, Lambert Conformal or Lambert Azimuthal Equal-Area. CoSPA generates only gridded products; there are no non-gridded data for CoSPA.
READ LESS

Summary

This document contains a description of Consolidated Storm Prediction for Aviation (CoSPA) data products that are packaged and distributed for external users. As described in Rappa and Troxel, 2013 [1] for Corridor Integrated Weather System (CIWS) data products, CoSPA products are categorized as gridded and non-gridded. Gridded products are typically...

READ MORE
CoSPA data product description

Effect of a wet spherical radome on the reflected power for an S-band planar phased array radar antenna

October 24, 2021
  |
Conference Paper
Author:
Christine F. Parry
…
Published in:
2021 Antenna Measurement Techniques Association Symp., AMTA, 24-29 October 2021.
Topic:
antennas
R&D area:
R&D group:

Summary

An active S-band dual-polarized multifunction phased array radar (MPAR), the Advanced Technology Demonstrator (ATD), has recently been developed for weather sensing and aircraft surveillance. The ATD is an active electronically scanned array (AESA) with 4864 transmit/receive (T/R) modules and was installed in a spherical radome. Simulations and a novel phased array measurement technique have been explored to assess the impact of high reflectivity from a wet radome during rain that can potentially induce voltages exceeding the transmit amplifier breakdown voltage. The measurement technique uses array elements radiating one at a time to illuminate the radome, and uses superposition to quantify the received signal power in a reference antenna on the face of the array. It is shown that when the radome surface is wet and highly reflective, certain electronic steering angles sum to a large reflected signal focused on the array face. This measurement technique can be used prior to high-power phased array radar operation to monitor the magnitude of reflections and help avoid element transmit amplifier failures.
READ LESS

Summary

An active S-band dual-polarized multifunction phased array radar (MPAR), the Advanced Technology Demonstrator (ATD), has recently been developed for weather sensing and aircraft surveillance. The ATD is an active electronically scanned array (AESA) with 4864 transmit/receive (T/R) modules and was installed in a spherical radome. Simulations and a novel phased...

READ MORE
Effect of a wet spherical radome on the reflected power for an S-band planar phased array radar antenna

Benchmarking the processing of aircraft tracks with triples mode and self-scheduling

September 20, 2021
  |
Conference Paper
Author:
Andrew J. Weinert
…
Published in:
2021 IEEE High Performance Extreme Computing Conf., HPEC, 20-24 September 2021.
Topic:
open systems
R&D area:
R&D group:

Summary

As unmanned aircraft systems (UASs) continue to integrate into the U.S. National Airspace System (NAS), there is a need to quantify the risk of airborne collisions between unmanned and manned aircraft to support regulation and standards development. Developing and certifying collision avoidance systems often rely on the extensive use of Monte Carlo collision risk analysis simulations using probabilistic models of aircraft flight. To train these models, high performance computing resources are required. We've prototyped a high performance computing workflow designed and deployed on the Lincoln Laboratory Supercomputing Center to process billions of observations of aircraft. However, the prototype has various computational and storage bottlenecks that limited rapid or more comprehensive analyses and models. In response, we've developed a novel workflow to take advantage of various job launch and task distribution technologies to improve performance. The workflow was benchmarked using two datasets of observations of aircraft, including a new dataset focused on the environment around aerodromes. Optimizing how the workflow was parallelized drastically reduced the execution time from weeks to days.
READ LESS

Summary

As unmanned aircraft systems (UASs) continue to integrate into the U.S. National Airspace System (NAS), there is a need to quantify the risk of airborne collisions between unmanned and manned aircraft to support regulation and standards development. Developing and certifying collision avoidance systems often rely on the extensive use of...

READ MORE
Benchmarking the processing of aircraft tracks with triples mode and self-scheduling

Benefits of realist ontologies to systems engineering

September 11, 2021
  |
Conference Paper
Author:
Marc W. Brittain
…
Published in:
Joint Ontology Workshops 2021 Episode VII: The Bolzano Summer of Knowledge, JOWO 2021, 11-18 September 2021.
Topic:
systems engineering
R&D area:
R&D group:

Summary

Applied ontologies have been used more and more frequently to enhance systems engineering. In this paper, we argue that adopting principles of ontological realism can increase the benefits that ontologies have already been shown to provide to the systems engineering process. Moreover, adopting Basic Formal Ontology (BFO), an ISO standard for top-level ontologies from which more domain specific ontologies are constructed, can lead to benefits in four distinct areas of systems engineering: (1) interoperability, (2) standardization, (3) testing, and (4) data exploitation. Reaping these benefits in a model-based systems engineering (MBSE) context requires utilizing an ontology's vocabulary when modeling systems and entities within those systems. If the chosen ontology abides by the principles of ontological realism, a semantic standard capable of uniting distinct domains, using BFO as a hub, can be leveraged to promote greater interoperability among systems. As interoperability and standardization increase, so does the ability to collect data during the testing and implementation of systems. These data can then be reasoned over by computational reasoners using the logical axioms within the ontology. This, in turn, generates new data that would have been impossible or too inefficient to generate without the aid of computational reasoners.
READ LESS

Summary

Applied ontologies have been used more and more frequently to enhance systems engineering. In this paper, we argue that adopting principles of ontological realism can increase the benefits that ontologies have already been shown to provide to the systems engineering process. Moreover, adopting Basic Formal Ontology (BFO), an ISO standard...

READ MORE
Benefits of realist ontologies to systems engineering

Demand and capacity modeling for advanced air mobility

August 2, 2021
  |
Conference Paper
Author:
Luis E. Alvarez
…
Published in:
AIAA Aviation 2021 Conf., 2-6 August 2021.
Topic:
air traffic control
R&D area:
R&D group:

Summary

Advanced Air Mobility encompasses emerging aviation technologies that transport people and cargo between local, regional, or urban locations that are currently underserved by aviation and other transportation modalities. The disruptive nature of these technologies has pushed industry, academia, and governments to devote significant investments to understand their impact on airspace risk, operational procedures, and passengers. A flexible framework was designed to assess the operational viability of these technologies and the sensitivity to a variety of assumptions. This framework is used to simulate air taxi traffic within New York City by replacing a portion of the city's taxi requests with trips taken with electric vertical takeoff and landing vehicles and evaluate the sensitivity of passenger trip time to a variety of system wide assumptions. In particular, the paper focuses on the impact of the passenger capacity, landing site vehicle capacity, and fleet size. The operation density is then compared with the current air traffic to assess operation constraints that will challenge the network UAM operations.
READ LESS

Summary

Advanced Air Mobility encompasses emerging aviation technologies that transport people and cargo between local, regional, or urban locations that are currently underserved by aviation and other transportation modalities. The disruptive nature of these technologies has pushed industry, academia, and governments to devote significant investments to understand their impact on airspace...

READ MORE
Demand and capacity modeling for advanced air mobility
11-20 of 931