Machine learning based perception algorithms are increasingly being used for the development of autonomous navigation systems of self-driving vehicles. These vehicles are mainly designed to operate on structured roads or lanes and the ML algorithms are primarily used for functionalities such as object tracking, lane detection and semantic understanding. On the other hand, Autonomous/ Unmanned Ground Vehicles (UGV) being developed for military applications need to operate in unstructured, combat environment including diverse off-road terrain, inclement weather conditions, water hazards, GPS denied environment, smoke etc. Therefore, the perception algorithm requirements are different and have to be robust enough to account for several diverse terrain conditions and degradations in visual environment. In this paper, we present military-relevant requirements and challenges for scene perception that are not met by current state-of-the-art algorithms, and discuss potential strategies to address these capability gaps. We also present a survey of ML algorithms and datasets that could be employed to support maneuver of autonomous systems in complex terrains, focusing on techniques for (1) distributed scene perception using heterogeneous platforms, (2) computation in resource constrained environment (3) object detection in degraded visual imagery.
A significant remaining challenge in chemical detection is the ability to rapidly detect with high fidelity a full suite of CWAs and TICs in a single point-detection system. Gas chromatography (GC) is a proven laboratory technique that can achieve the stated detection goal, but not at the required speed and not in a wearable (or even portable) form factor. Efforts in miniaturizing GCs yielded small devices, but they remain slow as they retain the end-of-column detection paradigm which results in long elution times of CWAs and TICs. We describe a novel concept of in-column detection by probing the sorbent coating (stationary phase) of a micro-GC column through optical evanescent field interactions in the long-wave infrared (“chemical fingerprint”) spectral region (U.S. Patent US9599567B2). Detection closer to the injection port ensures a rapid response for slow-eluting analytes. Although this results in poor separation (i.e. poor ability to identify chemicals), this is more than compensated by having full IR absorbance spectra at each location. This orthogonal spectral signature (along with GC retention times) is used in a powerful algorithm to quickly identify components in a complex mixture under conditions of incomplete separation. We present results with an ATR-based system that uses a focused tunable quantum cascade laser beam directed by galvo mirrors at points along a molded micro-GC column whose bottom wall is the sorbent coated ATR prism. Efforts are under way to further miniaturize this device by employing novel long-wave-IR photonic waveguides for a truly portable integrated photonic chromatographic detector of CBRNE threats.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.