Neya Systems (United States)

<title>ABSTRACT</title> <p>Off-road autonomy development is increasingly leveraging simulation for its ability to rapidly test and train new algorithms as well as simulate a wide variety of terrains and environmental conditions. Unstructured off-road environments require modeling complex environmental phenomena, such as LIDAR responses from vegetation. Neya has developed an approach to characterize the variability of measurements of vegetation and approximate the variability of vegetation measurements using that characterization. This method adds a small overhead to existing LIDAR models, works with many types of LIDAR sensor models, and simply requires objects to be tagged in the environment as vegetation for the sensor models to respond appropriately.</p> <p><bold>Citation:</bold> R. Mattes, J. Pace, “Fast LIDAR Vegetation Response Modeling in Simulation”, In <italic>Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium</italic> (GVSETS), NDIA, Novi, MI, Aug. 10-12, 2021.</p>

Robotic perception is currently at a cross-roads between modern methods, which operate in an efficient latent space, and classical methods, which are mathematically founded and provide interpretable, trustworthy results. In this paper, we introduce a Convolutional Bayesian Kernel Inference (Con-vBKI) layer which learns to perform explicit Bayesian inference within a depthwise separable convolution layer to maximize efficency while maintaining reliability simultaneously. We apply our layer to the task of real-time 3D semantic mapping, where we learn semantic-geometric probability distributions for Li-DAR sensor information and incorporate semantic predictions into a global map. We evaluate our network against stateof-the-art semantic mapping algorithms on the KITTI data set, demonstrating improved latency with comparable semantic label inference results. DISTRIBUTION A. Approved for public release; distribution unlimited. OPSECEC#6844.

Introduction: Currently, the only disease-modifying therapy for degenerative mitral stenosis (DMS) due to mitral annular calcification (MAC) is open surgical valve repair or replacement, but it is technically challenging, and patients with DMS are often at elevated risk of surgical complications. As such, there is an unmet need for less-invasive strategies to treat DMS. Given the ability of shock-wave grade therapeutic ultrasound to disrupt calcifications, we set out to determine whether therapeutic ultrasound may be a possible treatment strategy for DMS. Hypothesis: This study aimed to evaluate whether ex vivo histotripsy can produce internal disruption of calcified nodules in the mitral annulus, a precursor to improving valve function in DMS. Methods: All experiments were performed on a formalin-fixed human cadaveric heart with severe MAC (Figure 1 A). Histotripsy cavitation was directed at calcified nodules utilizing a sonic concepts HIFUPlex Focused 128 element,1.1MHz array therapy transducer (Figure 1 E). B-mode ultrasound imaging was used to guide therapy. Transducer settings were PRF: 60 Hz, Duty cycle: 8x10^-4, transmit frequency: 1.1 MHz, HIFU Voltage: 60 V, resulting in an estimated pressure output of 34.6 MPa_pk. Results: A total of three histotripsy experiments were performed on the primary dominant calcium nodule. Visual assessment of treatment X-ray microtomography (Micro-CT) revealed qualitative fracturing of the calcified nodule from baseline (Figure 1 B), after the first treatment (Figure 1 C), and after three treatments (Figure 1 D). Gross visual inspection and Micro-CT demonstrated no changes to the surrounding fibrous annulus. Conclusions: In a feasibility study involving a fixed cadaveric heart, histotripsy therapeutic ultrasound demonstrated the potential to internally disrupt a MAC nodule without injuring the mitral annulus. Further studies are needed to address the ability of histotripsy to improve valve function in DMS.

By employing selective reasoning for wheel placement on uneven terrain, planning systems generate safer trajectories that reduce overall mission risk by preventing high-centering and excessive wheel jolt, and therefore expand an autonomous vehicle’s mission portfolio by enabling them to navigate previously untraversable terrain. We show successful wheel placement reasoning in a diverse set of environments, including unimproved roads and expeditionary scenarios. We quantify the performance improvement by measuring ride safety measures (vertical acceleration and underbody clearance) and the number of vehicle collisions in a boulder corridor test environment.

Individual image quality metrics that focus on a particular form of image degradation have the virtue of being readily decipherable but also the drawback of not relating directly to the purpose for which the image is used. We describe here a method for learning the quality of iris images from the output of iris matching algorithms. We extract a large number of image quality features forming a high dimensional feature vector and label each training image with the match score for its corresponding genuine image in the enrolled database. We then train a Random Forest regressor to predict this match score, and in the course of training apply feature selection to dramatically reduce the feature vector dimensionality. A comparison of several alternative methods of feature selection is given. Our method demonstrates that the effects of image quality degradation on match scores can be predicted from image features. The predicted genuine match score serves as a quality metric, enabling filtering of poor quality images before enrollment or identification.

The Under Secretary of Defense (Acquisition, Technology and Logistics) directed the Services in 2009 to jointly develop and demonstrate a common architecture for command and control of Department of Defense (DoD) Unmanned Aircraft Systems (UAS) Groups 2 through 5. The UAS Control Segment (UCS) Architecture is an architecture framework for specifying and designing the softwareintensive capabilities of current and emerging UCS systems in the DoD inventory. The UCS Architecture is based on Service Oriented Architecture (SOA) principles that will be adopted by each of the Services as a common basis for acquiring, integrating, and extending the capabilities of the UAS Control Segment. The UAS Task Force established the UCS Working Group to develop and support the UCS Architecture. The Working Group currently has over three hundred members, and is open to qualified representatives from DoD-approved defense contractors, academia, and the Government. The UCS Architecture is currently at Release 2.2, with Release 3.0 planned for July 2013. This paper discusses the current and planned elements of the UCS Architecture, and related activities of the UCS Community of Interest.