22 Nov 2021

Imagery Classification for Autonomous Ground Vehicle Mobility in Cold Weather Environments

Abstract: Autonomous ground vehicle (AGV) research for military applications is important for developing ways to remove soldiers from harm’s way. Current AGV research tends toward operations in warm climates and this leaves the vehicle at risk of failing in cold climates. To ensure AGVs can fulfill a military vehicle’s role of being able to operate on- or off-road in all conditions, consideration needs to be given to terrain of all types to inform the on-board machine learning algorithms. This research aims to correlate real-time vehicle performance data with snow and ice surfaces derived from multispectral imagery with the goal of aiding in the development of a truly all-terrain AGV. Using the image data that correlated most closely to vehicle performance the images were classified into terrain units of most interest to mobility. The best image classification results were obtained when using Short Wave InfraRed (SWIR) band values and a supervised classification scheme, resulting in over 95% accuracy.

18 Nov 2021

ROS Integrated Object Detection for SLAM in Unknown, Low-Visibility Environments

Abstract: Integrating thermal (or infrared) imagery on a robotics platform allows Unmanned Ground Vehicles (UGV) to function in low-visibility environments, such as pure darkness or low-density smoke. To maximize the effectiveness of this approach we discuss the modifications required to integrate our low-visibility object detection model on a Robot Operating System (ROS). Furthermore, we introduce a method for reporting detected objects while performing Simultaneous Localization and Mapping (SLAM) by generating bounding boxes and their respective transforms in visually challenging environments.

24 Sep 2021

Autonomous Transport Innovation: A Review of Enabling Technologies

Purpose: This document is the first of the technical note series under the Autonomous Transport Innovation (ATI) research program. The series intends to be an introduction on autonomous vehicles (AVs), their testing, and associated infrastructure. A review of technologies that enable vehicle autonomy is necessary to provide the basis for understanding vehicle performance in testing scenarios and in actual use.

20 Sep 2021

Integration of Autonomous Electric Transport Vehicles into a Tactical Microgrid: Final Report

Abstract: The objective of the Autonomous Transport Innovation (ATI) technical research program is to investigate current gaps and challenges and develop solutions to integrate emerging electric transport vehicles, vehicle autonomy, vehicle-to-grid (V2G) charging and microgrid technologies with military legacy equipment. The ATI research area objectives are to: identify unique military requirements for autonomous transportation technologies; identify currently available technologies that can be adopted for military applications and validate the suitability of these technologies to close need gaps; identify research and operational tests for autonomous transport vehicles; investigate requirements for testing and demonstrating of bidirectional-vehicle charging within a tactical environment; develop requirements for a sensored, living laboratory that will be used to assess the performance of autonomous innovations; and integrate open standards to promote interoperability and broad-platform compatibility. This final report summarizes the team’s research, which resulted in an approach to develop a sensored, living laboratory with operational testing capability to assess the safety, utility, interoperability, and resiliency of autonomous electric transport and V2G technologies in a tactical microgrid. The living laboratory will support research and assessment of emerging technologies and determine the prospect for implementation in defense transport operations and contingency base energy resilience.

1 Sep 2020

PUBLICATION NOTICE: Sensor and Environment Physics in the Virtual Autonomous Navigation Environment (VANE)

Abstract: This report documents the physics models that are implemented in the Virtual Autonomous Navigation Environment (VANE), a sensor simulator that uses physics-based ray tracing to simulate common robotic sensors such as cameras, LiDAR, GPS, and automotive RADAR. The report will provide information about the underlying assumptions and implementation details regarding the physics models used in VANE simulations. These include surface reflectance and texture models, atmospheric models, weather effects, and sensor properties. The purpose of this report is to provide information for VANE users, developers, and analysts who would like to use the VANE for sensor simulations.

2 Jun 2020

PUBLICATION NOTICE: An Assessment of an Inexpensive COTS 360-degree Camera for Mapping and Localization in a GPS-denied Area

Purpose: The efficacy of using a low Size, Weight, Power, and Cost (SWAP-C) Commercial off the Shelf (COTS) 360-degree camera was evaluated for localization and positioning in a GPS-denied environment. Specifically, OpenVSLAM was utilized to generate point clouds with negligible drift using a RICOH THETA S 360-degree field of view camera without the aid of an Inertial Measurement Unit (IMU). OpenVSLAM is also demonstrated to show that it can localize and position with a pre-generated map.