August 24, 2018 - Novateur has been awarded multiple DoD contracts to continue developing its technologies on biologically inspired intelligent systems.
October 15, 2017 - Novateur has been awarded a USDA SBIR grant to develop machine learning technologies for animal welfare
March 20, 2017 - Novateur has been awarded a Defense Advanced Research Projects Agency (DARPA) contract to develop biologically inspired swarm-based control and management technologies for large-scale multi-agent systems. Novateur is working with Social Insect Lab at the University of Arizona to develop swarm computational models based on experiments and modeling of collective behavior in ant colonies. The learned models from biological swarm systems will enable development of decentralized multi-agent algorithms for large-scale complex systems operating in challenging and dynamic environments with performance guarantees on emergent behavior.
June 16, 2016 - Novateur has been awarded a Air Force Office of Scientific Research SBIR Phase I contract to develop real-time computer vision technologies for mobile sensors. Novateur will be working with GRASP Laboratory at University of Pennsylvania to develop advanced mathematical models and subspace estimation algorithms that are several order of magnitude faster than the state-of-the-art methods. The resulting technologies will not require hardware optimizations or special computational architectures and therefore will enable real-time performance on a variety of mobile processors and small UAV platforms
May 16, 2016 - Novateur has been awarded a Department of Transportation, Federal Transit Administration SBIR Phase I contract to develop a robust and cost-effective pedestrian/cyclist detection and collision warning system for transit buses. Pedestrians represent a considerable portion of traffic-related (cars, trucks and transit) injuries and deaths on our nation’s highways. In 2008, 4,378 pedestrians were killed and 69,000 were injured in traffic crashes in the United States; this represents 12% and 3%, respectively, of all the traffic fatalities and injuries. The majority of these fatalities occurred in urban areas (72%) where pedestrians, cyclists, and vehicular traffic, including transit buses, tend to co-mingle. Although, the pedestrian injuries and fatalities are few in number relative to other collision types, bus collisions involving pedestrians and cyclists usually carry very high cost (injury claims), attract negative media attention, and have the potential to create a negative public perception of transit safety. While there are some sensor systems and collision warning technologies currently available, there are significant concerns about the reliability and questions about their performance under different scenarios. Under this project, Novateur will be leveraging its experience with sensor exploitation and autonomous robotic systems to develop economically-viable, accurate, and durable pedestrian detection and collision warning system to significantly improve the safety of pedestrians and bicyclists in a transit environment.
April 11, 2016 - Novateur has been awarded an SBIR Phase II contract by the Office of Naval Research to transition its biologically inspired visual attention and deep learning technologies for automated unmanned ground vehicle (UGV) systems. Working with University of California San Diego (UCSD), Novateur successfully demonstrated the effectiveness of visual attention and deep learning technologies to significantly improve both the efficiency and accuracy of key visual scene understanding tasks, such as target detection and tracking. Novateur will be developing the prototype product for integration with the SPAWAR and NAVSEA's robotic platforms
May 19, 2015 - Novateur has been awarded an Air Force Research Laboratory contract to develop novel technologies that enable target hand-off in a swarm of UAV platforms operating in GPS-denied and bandwidth constrained environment. Novateur will be working with GRASP Laboratory at University of Pennsylvania to develop a distributed sensor pose estimation framework that allows UAV platforms to continually update their relative pose estimates based on a variety of intra-platform and inter-platform measurements.
December 15, 2014 - Novateur has successfully integrated its attention-based object detection technologies to Constellation Diagnostics product for automatic detection of melanoma growth from consumer imagery. Early detection of skin cancer dramatically increases patient survival rates (the survival rate increases to 94% from 49% with early detection). Using Novateur's technologies, Constellation's imaging system empowers patients to conduct quick, cost-effective, full body scans every month in the privacy of their homes, health clubs, doctors’ offices, and other commercial settings.
December 1, 2014 - Novateur has been awarded an Office of Naval Research contract to develop novel biologically inspired visual attention technologies for automated unmanned ground vehicle (UGV) systems. Novateur will be working with University of California San Diego (UCSD) to develop attention models that integrate both bottom-up (unsupervised) and top-down (context and task-driven) saliency to guide visual understanding. The attention models will enable onboard UGV perception systems to perform context-based and task-driven identification and tracking of objects of interest in real-time.
December 1, 2014 - Novateur has been awarded an Office of Naval Research contract to enable intelligent autonomous UxVs, i.e., the UxV systems that improve their performance over time. Novateur is working with The Ohio State University to develop biologically inspired computational memory and learning models that are capable of managing and organizing large amounts of sensory data in real-time and exploiting that data to enable long-term inference and prediction. Novateur's solution provides a framework for modeling and solving a large variety of autonomous learning and prediction problems that arise in UAV and UGV missions. The resulting autonomous systems will be able to i) handle long duration data streams; ii) identify informative features in data streams; iii) learn from unlabeled sensor observations; iv) adapt to new scenarios; perform prediction and inference using the observations and learned models; and vi) store learned experiences and their semantic associations in short-term and long-term memories
November 10, 2014 - Novateur has entered into a technology partnership agreement with ClearGrid Innovations, a New York-based startup company providing data analytics for energy sector. Novateur and ClearGrid are developing innovative image analysis technologies that will enable utility companies and other stake-holders to i) prevent and respond to distribution-related power outages more effectively, ii) improve the accuracy of GIS, iii) keep better track of equipment locations and status, and iv) improve infrastructure management.