Robert C. Leishman

Kyung Kim, Robert C. Leishman, Scott L. Nykl

Monocular visual navigation methods have seen significant advances in the last decade, recently producing several real-time solutions for autonomously navigating small unmanned aircraft systems without relying on GPS. This is critical for military operations which may involve environments where GPS signals are degraded or denied. However, testing and comparing visual navigation algorithms remains a challenge since visual data is expensive to gather. Conducting flight tests in a virtual environment is an attractive solution prior to committing to outdoor testing. This work presents a virtual testbed for conducting simulated flight tests over real-world terrain and analyzing the real-time performance of visual navigation algorithms at 31 Hz. This tool was created to ultimately find a visual odometry algorithm appropriate for further GPS-denied navigation research on fixed-wing aircraft, even though all of the algorithms were designed for other modalities. This testbed was used to evaluate three current state-of-the-art, open-source monocular visual odometry algorithms on a fixed-wing platform: Direct Sparse Odometry, Semi-Direct Visual Odometry, and ORB-SLAM2 (with loop closures disabled).

Randall Christensen, Greg Droge, Robert Leishman

Path planning in an uncertain environment is a key enabler of true vehicle autonomy. Over the past two decades, numerous approaches have been developed to account for errors in the vehicle path while navigating complex and often uncertain environments. An important capability of such planning is the prediction of vehicle dispersion covariances about a candidate path. This work develops a new closed-loop linear covariance (CL-LinCov) framework applicable to a wide range of autonomous system architectures. Important features of the developed framework include the (1) separation of high-level guidance from low-level control, (2) support for output-feedback controllers with internal states, dynamics, and output, and (3) multi-use continuous sensors for navigation state propagation, guidance, and feedback control. The closed-loop nature of the framework preserves the important coupling between the system dynamics, exogenous disturbances, and the guidance, navigation, and control algorithms. The developed framework is applied to a simplified model of an unmanned aerial vehicle and validated by comparison via Monte Carlo analysis. The utility of the CL-LinCov information is illustrated by its application to path planning in a static, uncertain obstacle field via a modified version of the Rapidly Exploring Random Tree algorithm.

Ryan M. Watson, Jason N. Gross, Clark N. Taylor et al.

Recent advances in the fields of robotics and automation have spurred significant interest in robust state estimation. To enable robust state estimation, several methodologies have been proposed. One such technique, which has shown promising performance, is the concept of iteratively estimating a Gaussian Mixture Model (GMM), based upon the state estimation residuals, to characterize the measurement uncertainty model. Through this iterative process, the measurement uncertainty model is more accurately characterized, which enables robust state estimation through the appropriate de-weighting of erroneous observations. This approach, however, has traditionally required a batch estimation framework to enable the estimation of the measurement uncertainty model, which is not advantageous to robotic applications. In this paper, we propose an efficient, incremental extension to the measurement uncertainty model estimation paradigm. The incremental covariance estimation (ICE) approach, as detailed within this paper, is evaluated on several collected data sets, where it is shown to provide a significant increase in localization accuracy when compared to other state-of-the-art robust, incremental estimation algorithms.

Mark B. Skouson, Brett J. Borghetti, Robert C. Leishman

This paper describes a neural network layer, named Ursa, that uses a constellation of points to learn classification information from point cloud data. Unlike other machine learning classification problems where the task is to classify an individual high-dimensional observation, in a point-cloud classification problem the goal is to classify a set of d-dimensional observations. Because a point cloud is a set, there is no ordering to the collection of points in a point-cloud classification problem. Thus, the challenge of classifying point clouds inputs is in building a classifier which is agnostic to the ordering of the observations, yet preserves the d-dimensional information of each point in the set. This research presents Ursa, a new layer type for an artificial neural network which achieves these two properties. Similar to new methods for this task, this architecture works directly on d-dimensional points rather than first converting the points to a d-dimensional volume. The Ursa layer is followed by a series of dense layers to classify 2D and 3D objects from point clouds. Experiments on ModelNet40 and MNIST data show classification results comparable with current methods, while reducing the training parameters by over 50 percent.