Publications

Refine Results

(Filters Applied) Clear All

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

A cloud-based brain connectivity analysis tool

Summary

With advances in high throughput brain imaging at the cellular and sub-cellular level, there is growing demand for platforms that can support high performance, large-scale brain data processing and analysis. In this paper, we present a novel pipeline that combines Accumulo, D4M, geohashing, and parallel programming to manage large-scale neuron connectivity graphs in a cloud environment. Our brain connectivity graph is represented using vertices (fiber start/end nodes), edges (fiber tracks), and the 3D coordinates of the fiber tracks. For optimal performance, we take the hybrid approach of storing vertices and edges in Accumulo and saving the fiber track 3D coordinates in flat files. Accumulo database operations offer low latency on sparse queries while flat files offer high throughput for storing, querying, and analyzing bulk data. We evaluated our pipeline by using 250 gigabytes of mouse neuron connectivity data. Benchmarking experiments on retrieving vertices and edges from Accumulo demonstrate that we can achieve 1-2 orders of magnitude speedup in retrieval time when compared to the same operation from traditional flat files. The implementation of graph analytics such as Breadth First Search using Accumulo and D4M offers consistent good performance regardless of data size and density, thus is scalable to very large dataset. Indexing of neuron subvolumes is simple and logical with geohashing-based binary tree encoding. This hybrid data management backend is used to drive an interactive web-based 3D graphical user interface, where users can examine the 3D connectivity map in a Google Map-like viewer. Our pipeline is scalable and extensible to other data modalities.
READ LESS

Summary

With advances in high throughput brain imaging at the cellular and sub-cellular level, there is growing demand for platforms that can support high performance, large-scale brain data processing and analysis. In this paper, we present a novel pipeline that combines Accumulo, D4M, geohashing, and parallel programming to manage large-scale neuron...

READ MORE

Learning to tutor from expert demonstrators via apprenticeship scheduling

Published in:
AAAI-17 Workshop on Human-Machine Collaborative Learning, 4 February 2017.

Summary

We have conducted a study investigating the use of automated tutors for educating players in the context of serious gaming (i.e., game designed as a professional training tool). Historically, researchers and practitioners have developed automated tutors through a process of manually codifying domain knowledge and translating that into a human-interpretable format. This process is laborious and leaves much to be desired. Instead, we seek to apply novel machine learning techniques to, first, learn a model from domain experts' demonstrations how to solve such problems, and, second, use this model to teach novices how to think like experts. In this work, we present a study comparing the performance of an automated and a traditional, manually-constructed tutor. To our knowledge, this is the first investigation using learning from demonstration techniques to learn from experts and use that knowledge to teach novices.
READ LESS

Summary

We have conducted a study investigating the use of automated tutors for educating players in the context of serious gaming (i.e., game designed as a professional training tool). Historically, researchers and practitioners have developed automated tutors through a process of manually codifying domain knowledge and translating that into a human-interpretable...

READ MORE

Apprenticeship scheduling: learning to schedule from human experts

Published in:
Proc. of the Int. Joint Conf. Artificial Intelligence (IJCAI), 9-15 July 2016.

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, causing the codification of this knowledge to become laborious. We propose a new approach for capturing domain-expert heuristics through a pairwise ranking formulation. Our approach is model-free and does not require enumerating or iterating through a large state-space. We empirically demonstrate that this approach accurately learns multifaceted heuristics on both a synthetic data set incorporating job-shop scheduling and vehicle routing problems and a real-world data set consisting of demonstrations of experts solving a weapon-to-target assignment problem.
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

Comparisons between the extended Kalman filter and the state-dependent Riccati estimator

Summary

The state-dependent Riccati equation-based estimator is becoming a popular estimation tool for nonlinear systems since it does not use system linearization. In this paper, the state-dependent Riccati equation-based estimator is compared with the widely used extended Kalman filter for three simple examples that appear in the open literature. It is demonstrated that, by simulation, the state-dependent Riccati equation-based estimator at best has comparable results to the extended Kalman filter but is often worse than the extended Kalman filter. In some cases, the state-dependent Riccati equation-based estimator does not converge, even though the system considered satisfies all the mathematical constraints on controllability and observability. Sufficient detail is presented in the paper so that the interested reader cannot only duplicate the results but perhaps make suggestions on how to get the state-dependent Riccati equation-based estimator to perform better.
READ LESS

Summary

The state-dependent Riccati equation-based estimator is becoming a popular estimation tool for nonlinear systems since it does not use system linearization. In this paper, the state-dependent Riccati equation-based estimator is compared with the widely used extended Kalman filter for three simple examples that appear in the open literature. It is...

READ MORE

Geospatial analysis based on GIS integrated with LADAR

Summary

In this work, we describe multi-layered analyses of a high-resolution broad-area LADAR data set in support of expeditionary activities. High-level features are extracted from the LADAR data, such as the presence and location of buildings and cars, and then these features are used to populate a GIS (geographic information system) tool. We also apply line-of-sight (LOS) analysis to develop a path-planning module. Finally, visualization is addressed and enhanced with a gesture-based control system that allows the user to navigate through the enhanced data set in a virtual immersive experience. This work has operational applications including military, security, disaster relief, and task-based robotic path planning.
READ LESS

Summary

In this work, we describe multi-layered analyses of a high-resolution broad-area LADAR data set in support of expeditionary activities. High-level features are extracted from the LADAR data, such as the presence and location of buildings and cars, and then these features are used to populate a GIS (geographic information system)...

READ MORE

Distributed multi-modal sensor system for searching a foliage-covered region

Summary

We designed and constructed a system that includes aircraft, ground vehicles, and throwable sensors to search a semiforested region that was partially covered by foliage. The system contained 4 radio-controlled (RC) trucks, 2 aircraft, and 30 SensorMotes (throwable sensors). We also investigated communications links, search strategies, and system architecture. Our system is designed to be low-cost, contain a variety of sensors, and distributed so that the system is robust even if individual components are lost.
READ LESS

Summary

We designed and constructed a system that includes aircraft, ground vehicles, and throwable sensors to search a semiforested region that was partially covered by foliage. The system contained 4 radio-controlled (RC) trucks, 2 aircraft, and 30 SensorMotes (throwable sensors). We also investigated communications links, search strategies, and system architecture. Our...

READ MORE

Bioinspired resource management for multiple-sensor target tracking systems

Summary

We present an algorithm, inspired by self-organization and stigmergy observed in biological swarms, for managing multiple sensors tracking large numbers of targets. We devise a decentralized architecture wherein autonomous sensors manage their own data collection resources and task themselves. Sensors cannot communicate with each other directly; however, a global track file, which is continuously broadcast, allows the sensors to infer their contributions to the global estimation of target states. Sensors can transmit their data (either as raw measurements or some compressed format) only to a central processor where their data are combined to update the global track file. We outline information-theoretic rules for the general multiple-sensor Bayesian target tracking problem. We provide specific formulas for problems dominated by additive white Gaussiannoise. Using Cramer-Rao lower bounds as surrogates for error covariances, we illustrate, using numerical scenarious involving ballistic targets, that the bioinspired algorithm is highly scalable and peforms very well for large numbers of targets.
READ LESS

Summary

We present an algorithm, inspired by self-organization and stigmergy observed in biological swarms, for managing multiple sensors tracking large numbers of targets. We devise a decentralized architecture wherein autonomous sensors manage their own data collection resources and task themselves. Sensors cannot communicate with each other directly; however, a global track...

READ MORE

A component model approach for the RCS validation of an electrically large open-ended cylindrical cavity

Published in:
IEEE Antennas and Propagation Society Int. Symp., 2007 Digest, 9-15 June 2007, pp. 2275-2278.

Summary

A novel RCS component prediction model approach to producing both fast and accurate scattering from an electrically large open-ended cylindrical cavity (circular cross section) is presented. The component model is a hybrid approach which easily permits individual scattering mechanisms to be coherently combined to produce a high fidelity signature. For this problem, the component model included scattering produced from the interior of the cavity calculated via the waveguide modal approach combined with the scattering produced from the cavity's finite thick rim opening (i.e., annulus) computed via the Method of Moments (MoM) and finally combined with the cavity's external base ring edge diffraction computed via PTD. Narrowband and wideband signature analysis for the circular cylindrical cavity configuration are presented to validate the component prediction model with static range measurements, and another prediction result computed using MoM for X- band frequencies and linear polarization. Excellent agreement is achieved among the data sets: measurement and prediction (component and MoM model).
READ LESS

Summary

A novel RCS component prediction model approach to producing both fast and accurate scattering from an electrically large open-ended cylindrical cavity (circular cross section) is presented. The component model is a hybrid approach which easily permits individual scattering mechanisms to be coherently combined to produce a high fidelity signature. For...

READ MORE

Advances in radar signal processing

Published in:
Electro/76, 11-14 May 1976.

Summary

The recent availability of new solid-state digital components has made possible the development of radar signal processing techniques only dreamed of in the past. The philosophy and design of these techniques is described in terms of a new signal processor for Airport Surveillance Radars called the Moving Target Detector (MTD). Test results showing greatly improved automatic aircraft acquisition and tracking are discussed.
READ LESS

Summary

The recent availability of new solid-state digital components has made possible the development of radar signal processing techniques only dreamed of in the past. The philosophy and design of these techniques is described in terms of a new signal processor for Airport Surveillance Radars called the Moving Target Detector (MTD)...

READ MORE