Publications

Refine Results

(Filters Applied) Clear All

What could we do with a 20-meter tower on the Lunar South Pole? Applications of the Multifunctional Expandable Lunar Lite & Tall Tower (MELLTT)

Summary

Lunar polar regions and permanently shadowed regions (PSRs) are a key component of NASA's exploration objectives for the lunar surface, given their potential for a high abundance of volatiles like water. The Massachusetts Institute of Technology (MIT) Big Idea Challenge Team proposed the use of deployable towers to support robotic and remote exploration of these PSRs, alleviating limitations imposed by the rugged terrain. This deployable tower technology (called MELLTT) could enable an extended ecosystem on the lunar surface. This paper seeks to build on this initial concept by showcasing the advantages of self-deploying lightweight lunar towers through the development of various payload concepts. The payloads include 5-kg packages for an initial proof-of-concept deployment, as well as 50-kg payloads and payloads across multiple towers for future exploration architectures. The primary goal of a 5-kg tower payload is to return unique scientific data from a PSR while minimizing risk to a tower technology demonstration mission. Concepts include passive imagers to provide a step-change improvement in resolution, solar reflectors capable of illuminating PSRs, communications infrastructure for human and robotic exploration, a power beaming demonstration, and a PSR impactor. These payloads demonstrate the utility of towers on the lunar surface and how incremental improvements in the capability of towers can further NASA's exploration program.
READ LESS

Summary

Lunar polar regions and permanently shadowed regions (PSRs) are a key component of NASA's exploration objectives for the lunar surface, given their potential for a high abundance of volatiles like water. The Massachusetts Institute of Technology (MIT) Big Idea Challenge Team proposed the use of deployable towers to support robotic...

READ MORE

Fast training of deep neural networks robust to adversarial perturbations

Summary

Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their learned feature representations are often difficult to interpret, raising concerns about their true capability and trustworthiness. Recent work in adversarial training, a form of robust optimization in which the model is optimized against adversarial examples, demonstrates the ability to improve performance sensitivities to perturbations and yield feature representations that are more interpretable. Adversarial training, however, comes with an increased computational cost over that of standard (i.e., nonrobust) training, rendering it impractical for use in largescale problems. Recent work suggests that a fast approximation to adversarial training shows promise for reducing training time and maintaining robustness in the presence of perturbations bounded by the infinity norm. In this work, we demonstrate that this approach extends to the Euclidean norm and preserves the human-aligned feature representations that are common for robust models. Additionally, we show that using a distributed training scheme can further reduce the time to train robust deep networks. Fast adversarial training is a promising approach that will provide increased security and explainability in machine learning applications for which robust optimization was previously thought to be impractical.
READ LESS

Summary

Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their learned feature representations are often difficult to interpret, raising concerns about their true capability and trustworthiness. Recent...

READ MORE

Antennas and RF components designed with graded index composite materials

Summary

Antennas and RF components in general, can greatly benefit with the recent development of low-loss 3D print graded index materials. The additional degrees of freedom provided by graded index materials can result in the design of antennas and other RF components with superior performance than currently available designs based on conventional constant permittivity materials. Here we discuss our work designing flat lenses for antennas and RF matching networks as well as filters based on graded index composite materials.
READ LESS

Summary

Antennas and RF components in general, can greatly benefit with the recent development of low-loss 3D print graded index materials. The additional degrees of freedom provided by graded index materials can result in the design of antennas and other RF components with superior performance than currently available designs based on...

READ MORE

Adjoint analysis of guidance systems for time-series inputs using Fourier analysis

Author:
Published in:
J. Guid., Control, Dyn., Vol. 43, No. 7, July 2020.

Summary

The adjoint technique is a proven technique for analysis of linear time-varying systems and is widely used in the missile design community. It is a very efficient technique that can solve for both deterministic and stochastic disturbances and can develop a miss distance budget in a single computer solution of the differential equations without use of time-consuming Monte Carlo simulations. The adjoint technique is very valuable in both preliminary and more advanced missile design stages and is based upon the mathematical adjoint of the system dynamics matrix of the homing loop. Zarchan [1,2] describes extensive use of the technique for a variety of disturbances for homing missiles, and this author has developed its use for command guided missiles [3]. For adjoint analysis, the usual method of modeling maneuver disturbances to a missile guidance system starts by modeling the maneuver in the forward-time system as a delta function input into a transfer function with the same second-order statistics as the maneuver, and its output is input into the guidance system; then the system is converted into its adjoint system [1]. Bucco and Weiss [4] show that a set of nonstandard time-varying inputs cannot be treated in the normal fashion [2,5,6], and they present a new technique that enables these nonstandard inputs to be analyzed using adjoint analysis. This paper was inspired by and extends the results of the paper by Bucco and Weiss [4]. This paper shows that the use of the complex digital Fourier amplitude spectrums of both the maneuver and the adjoint impulse response at the maneuver point allows adjoint analysis to address another type of nonstandard input, namely, an arbitrary time-series inputs such as specific target maneuvers that are not representable by an impulse input into a transfer function; heretofore, these time-series inputs have not been treatable with adjoint analysis. Additionally, if there are several sets of arbitrary time series of target maneuvers, each with an associated probability of occurrence, the root-mean-square (rms) value of the set of probabilistic maneuvers can be calculated, another significant new capability introduced in this paper.
READ LESS

Summary

The adjoint technique is a proven technique for analysis of linear time-varying systems and is widely used in the missile design community. It is a very efficient technique that can solve for both deterministic and stochastic disturbances and can develop a miss distance budget in a single computer solution of...

READ MORE

A hands-on middle-school robotics software program at MIT

Summary

Robotics competitions at the high school level attract a large number of students across the world. However, there is little emphasis on leveraging robotics to get middle school students excited about pursuing STEM education. In this paper, we describe a new program that targets middle school students in a local, four-week setting at the Massachusetts Institute of Technology (MIT). It aims to excite students by teaching the very basics of computer vision and robotics. The students program mini car-like robots, equipped with state-of-the-art computers, to navigate autonomously in a mock race track. We describe the hardware and software infrastructure that enables the program, the details of our curriculum, and the results of a short assessment. In addition, we describe four short programs, as well as a session where we teach high school teachers how to teach similar courses at their schools to their own students. The self-assessment indicates that the students feel more confident in programming and robotics after leaving the program, which we hope will enable them to pursue STEM education and robotics initiatives at school.
READ LESS

Summary

Robotics competitions at the high school level attract a large number of students across the world. However, there is little emphasis on leveraging robotics to get middle school students excited about pursuing STEM education. In this paper, we describe a new program that targets middle school students in a local...

READ MORE

Safe predictors for enforcing input-output specifications [e-print]

Summary

We present an approach for designing correct-by-construction neural networks (and other machine learning models) that are guaranteed to be consistent with a collection of input-output specifications before, during, and after algorithm training. Our method involves designing a constrained predictor for each set of compatible constraints, and combining them safely via a convex combination of their predictions. We demonstrate our approach on synthetic datasets and an aircraft collision avoidance problem.
READ LESS

Summary

We present an approach for designing correct-by-construction neural networks (and other machine learning models) that are guaranteed to be consistent with a collection of input-output specifications before, during, and after algorithm training. Our method involves designing a constrained predictor for each set of compatible constraints, and combining them safely via...

READ MORE

AI enabling technologies: a survey

Summary

Artificial Intelligence (AI) has the opportunity to revolutionize the way the United States Department of Defense (DoD) and Intelligence Community (IC) address the challenges of evolving threats, data deluge, and rapid courses of action. Developing an end-to-end artificial intelligence system involves parallel development of different pieces that must work together in order to provide capabilities that can be used by decision makers, warfighters and analysts. These pieces include data collection, data conditioning, algorithms, computing, robust artificial intelligence, and human-machine teaming. While much of the popular press today surrounds advances in algorithms and computing, most modern AI systems leverage advances across numerous different fields. Further, while certain components may not be as visible to end-users as others, our experience has shown that each of these interrelated components play a major role in the success or failure of an AI system. This article is meant to highlight many of these technologies that are involved in an end-to-end AI system. The goal of this article is to provide readers with an overview of terminology, technical details and recent highlights from academia, industry and government. Where possible, we indicate relevant resources that can be used for further reading and understanding.
READ LESS

Summary

Artificial Intelligence (AI) has the opportunity to revolutionize the way the United States Department of Defense (DoD) and Intelligence Community (IC) address the challenges of evolving threats, data deluge, and rapid courses of action. Developing an end-to-end artificial intelligence system involves parallel development of different pieces that must work together...

READ MORE

CW radar operation in the focused near-field

Published in:
2019 Intl. Applied Computational Electromagnetics Society Symp., ACES, 14-19 April 2019.

Summary

In this paper we will show by computer simulation and by measurements that the horn antennas of a bi-static radar operating in the near-field have a distinct maximum at a non-zero range. By focusing the antennas on this hot spot a low-powered, continuous-wave Ku-band radar could detect flying mosquitoes at very short range.
READ LESS

Summary

In this paper we will show by computer simulation and by measurements that the horn antennas of a bi-static radar operating in the near-field have a distinct maximum at a non-zero range. By focusing the antennas on this hot spot a low-powered, continuous-wave Ku-band radar could detect flying mosquitoes at...

READ MORE

Simulation approach to sensor placement using Unity3D

Summary

3D game simulation engines have demonstrated utility in the areas of training, scientific analysis, and knowledge solicitation. This paper will make the case for the use of 3D game simulation engines in the field of sensor placement optimization. Our study used a series of parallel simulations in the Unity3D simulation framework to answer the questions: how many sensors of various modalities are required and where they should be placed to meet a desired threat detection threshold? The result is a framework that not only answers this sensor placement question, but can be easily expanded to differing optimization criteria as well as answer how a particular configuration responds to differing crowd flows or informed/non-informed adversaries. Additionally, we demonstrate the scalability of this framework by running parallel instances on a supercomputing grid and illustrate the processing speed gained.
READ LESS

Summary

3D game simulation engines have demonstrated utility in the areas of training, scientific analysis, and knowledge solicitation. This paper will make the case for the use of 3D game simulation engines in the field of sensor placement optimization. Our study used a series of parallel simulations in the Unity3D simulation...

READ MORE

Human-machine collaborative optimization via apprenticeship scheduling

Summary

Coordinating agents to complete a set of tasks with intercoupled temporal and resource constraints is computationally challenging, yet human domain experts can solve these difficult scheduling problems using paradigms learned through years of apprenticeship. A process for manually codifying this domain knowledge within a computational framework is necessary to scale beyond the "single-expert, single-trainee" apprenticeship model. However, human domain experts often have difficulty describing their decision-making processes. We propose a new approach for capturing this decision-making process through counterfactual reasoning in pairwise comparisons. Our approach is model-free and does not require iterating through the state space. We demonstrate that this approach accurately learns multifaceted heuristics on a synthetic and real world data sets. We also demonstrate that policies learned from human scheduling demonstration via apprenticeship learning can substantially improve the efficiency of schedule optimization. We employ this human-machine collaborative optimization technique on a variant of the weapon-to-target assignment problem. We demonstrate that this technique generates optimal solutions up to 9.5 times faster than a state-of-the-art optimization algorithm.
READ LESS

Summary

Coordinating agents to complete a set of tasks with intercoupled temporal and resource constraints is computationally challenging, yet human domain experts can solve these difficult scheduling problems using paradigms learned through years of apprenticeship. A process for manually codifying this domain knowledge within a computational framework is necessary to scale...

READ MORE