Available Technologies by Category
New Light Detection and Ranging (LIDAR) Technique’s Unprecedented Time and Space Resolution Improves Understanding of Atmospheric Optical Covariances for Forecasting
  • Optimizing free-space optical communications tools with enhanced optical turbulence strength measurements as a function of time and range enables path for development of first of their kind tracebility standards.
  • Quantitative measurements of optical turbulence with unprecedented spatial and temporal coverage offer improved performance for long-range FSO applications.
  • Singular measurement of optical turbulence results from combination LIDAR measurements of wind, temperature, and water vapor, which enables better weather forecasting and models to be built.
9016
Predictive Maintenance System for Large-Scale Operations Offers Potential for Significant Cost Savings
  • Consistent workflow improvements: Offers repeatable and consistent enterprise-level improvements to the maintenance workflow.  
  • Proactive readiness: Improves maintenance scheduling, allowing for improved logistics, scheduling, virtual kitting, and part/component availability. 
  • Customizable: Customers can build and tailor their PMx solutions according to their needs, providing increased data control and an alternative to costly and limited solutions.
8793
High-Precision, Hands-Free Remote Control of Complex Robotic Systems Via Eye Movements
  • This two-camera eye-tracking system (TCES) integrates a commercial eye tracker with machine-learning technology for continuous real-time classification of gaze and eye directions for robotic arm control. 
  • The system provides highly accurate classification for four directions of eye movement and has achieved 99.99% accuracy in studies.
  • Using simple eye movement, the TCES offers low-cost, high-precision control of external devices/hardware for people with disabilities, surgery robots, warehouse systems, construction tools, and more. 
9184
Overvoltage Surge Protection System for Distributed Energy Resources
  • iMOV is a dynamic system capable of achieving voltage surge clamping within 20% of the system’s nominal voltage. This effectively provides protection for highly sensitive semiconductors present in DER-associated power converters. 
  • This system is built upon a metal oxide varistors (MOV) foundation, whose material composition inherently allows rapid device connection of 500 picoseconds for quicker response times. 
  • iMOV uses integrated microprocessors and sensors in a cloud-based architecture that provides protection against cyberattacks, reduces system cost, and allows system and power grid monitoring.
9190
AI-Designed High Energy–Density High-Temperature Polymers
  • The present materials are capable of withstanding enormous electric fields at very high temperatures.
  • The materials produced are extremely lightweight.
  • Vehicles making use of these materials will be lightweight, and lighter vehicles consume less energy.
9101
Intelligent Eye-Tracking System Offers Next-Gen Technology for Virtual and Augmented Reality (VR/AR) Applications
  • This system uses an AI accelerator chip with 4X higher throughput to achieve over 300 FPS, greatly improving processing speed without loss of accuracy.
  • EyeCoD achieves faster communication time by using a lens-less camera that reduces distance between the camera and the accelerator chip.
  • Using a “predict-then-focus” model, this system creates highly accurate images as well as improves visual privacy.
9202
Advanced Error Measurement System for Additive Manufacturing Machines
  • Advanced technology for precise error measurement in AM machine optomechanical systems
  • Innovative laser-based method to identify and correct focal errors in PBF-LB AM machines
  • Comprehensive approach enhances machine performance and output quality
9241
Algorithm for Optical Microscopy Image Denoising and Restoration
  • Miro performs consistent noise correction independent of the image sampling rate (working even with sparse images).
  • MIRO is compatible with all major imaging systems and camera types.
  • Unlike existing approaches, MIRO uses pattern, uniform, and non-uniform noise statistics to correct microscopy-relevant noise sources.
9103
Distributed Position, Navigation, and Timing (PNT) Chain Significantly Improves Drone Navigation When GPS Fails
  • The robust Distributed PNT Chain enables a swarm of drones or other autonomous platforms to effectively navigate when they are denied GPS access. 
  • The system shares and processes all available sensor data to significantly improve the robustness and reliability of drone teams.
  • The highly modular system is interoperable with preexisting GPS INSs and supports variable and evolving platform geometries.
9046
Generative Machine-Learning Model for Preference-Based Attribute Editing and Photorealistic Image Generation
  • User-controlled image attribute editing and generation through paired queries
  • Effective extraction of difficult-to-articulate preferences for personalized content
  • Applications in social media, e-commerce recommendations, and entertainment industries
9200
Synthetically Generated, Realistic, and Controllable Human Bio-Signals from Participant-Free Data Collection
  • Synthetic data generation system replicates human body signals and uses a deep generative model to create synthetic SCG beats without human participants. 
  • Transformer-based generative model synthesizes SCG beats that are physiologically diverse and realistic. 
  • Clinically relevant feature inputs act as controls for aortic opening (AO) and aortic closing (AC) features of the generated SCG beat.
9081
Quantum Tunneling Radio Positioning System Achieves Higher Levels of Accuracy and Longer Range for Next-Generation Wireless Networks
  • This radiolocation system uses quantum tunneling tags (QTT) capable of operating in non-line-of-sight conditions to achieve longer range communications in outdoor and indoor applications. 
  • The use of QTTs, paired with a frequency hopping reader, results in positioning accuracy not achievable with standard methods.
  • QTTs are inexpensive and operate under low power requirements to offer an affordable orientation system with long battery life.
8535
Patient-Centered Biofeedback Headset Can Isolate, Monitor, and Analyze Vocal Output in Real Time for Optimal Voice Modulation in Patients with Parkinson’s Disease
  • Innovative headset offers real-time haptic feedback for vocal improvement and increased patient autonomy.
  • Device stores easily accessible data for therapist review and fine-tuning of preset therapeutic thresholds to continually improve vocal output.
  • Lightweight, low-profile, battery-powered headset are favorable for all-day wear and use omnidirectional microphones for optimal comfort.
9134
AI Systems for Personalized Wearable Robotic Systems
  • The system generalizes to different users, varying terrain conditions and walking speeds.
  • The system is designed to transfer between different wearable robotics devices.
  • The system optimally estimates the physiological state of the user to provide the best assistance that the wearable robot can give the user allowing for optimal control across tasks.
8985
Multi-Modal Deep Learning Training Model
  • Resource Efficient
  • Improved Modeling Method
9098
Machine Learning–Based Transportation Asset Inventory
  • The invention performs more intelligent segmentation using advanced computation methods with Artificial Intelligence.
  • Makes use of cost-efficient 2-dimensional images of roadways, making it easier to implement on a larger scale.
  • Can detect transportation assets and inventory them simultaneously.
9109
Multi-Modal, Trustworthy, and Unsupervised Active Learning
  • The algorithm samples uniquely important unlabeled sample annotations. This results in reduced time, cost, and effort to achieve performance that is comparable to larger amounts of data labeled by subject experts.
  • Unlike existing methods, this overcomes the incorrect assumption that all information for a medical diagnosis is present only in the imagery and capitalizes on additional information present in other formats like annotations.
  • The algorithms produced are multi-modal and trustworthy, ensuring no loss in performance.
9099
Custom-Fit Reusable Respiratory Protective Device (RPD) with Continuous Fit Monitoring Improves Comfort and Protection
  • Vastly improves comfort and protection while bringing peace of mind to wearers through a custom fit and continuous monitoring
  • Reduces pressure injuries caused by extended RPD use through both a customized fit and alerts to the wearer when the RPD should be adjusted or removed
  • Minimizes exposures to workplace hazards by immediately detecting leakage during RPD use and alerting the wearer to adjust the device
8876, 9089, 9090, 9091
Deployable Critical Active Learning (DECAL) System Offers Better Characterization for Improved Diagnostics and Imaging
  • The deployable critical active learning (DECAL) system’s bi-modal interface enables better characterization with large training sets that generate more accurate output for higher precision.
  • The algorithm used during the initialization period creates a framework that can be expanded and generalized to any data method and application.
  •  The DECAL algorithm samples uniquely important, unlabeled data to aid existing active learning systems in generalizing more quickly, providing faster diagnosis statistics.
9099
Streamlined Combination Analysis by FORECAST Accurately Predicts and Identifies Pending Malware Attacks
  • Automating the combined techniques of memory forensics and symbolic analysis accelerates how fast an enterprise or government becomes aware of the true extent of malware’s capabilities.
  • When countering cyberattacks, FORECAST provides improved accuracy (94%, overall) with its automated analysis, which is crucial to helping cybersecurity efforts to efficiently focus on high-impact solutions.
  • FORECAST has the flexibility to be a valuable incidence response tool, even when malware is fileless since it uses the software’s memory image to accurately predict the program’s capabilities.
8581