Search Results

The explosion of big data has created challenges for both cloud-based systems and Autonomous Vehicles (AVs) in data collection and management. The same challenges are now being realized in developing databases for integrated sensors, streaming, real-time and on-demand services in AVs. With just one AV expecting to generate over 30 Terabytes of data a day, modern NoSQL databases provide opportunities to horizontally scale AV data seamlessly. NoSQL provides solutions designed to accommodate a wide variety of data models such as, key-value, document, column and graph databases. Key-value stores are by nature scalable, fast processing, and distribute horizontally. These databases are tasked with handling several data types including IoT, radar, lidar, ultra-sonic sensors, GPS, odometry, and sensor data while providing streaming and real-time services. NoSQL can store and utilize structured, semi-structured, and unstructured data necessary for multimedia storage needs.

The development of Autonomous Vehicles (AV) has become a popular subject in academia and industry. Companies and cities are quickly realizing the opportunities that AVs can generate from Mobility as a Service to traffic safety. The challenges for the infrastructure to incorporate AVs as a viable transportation source are immense, from an outdated infrastructure to radical Smart-City designs. Historically, the transportation infrastructure has faced challenges from underfunding, economics, and much needed improvements. With the current infrastructure unable to support many of the services required by a fully connected network, a transformation will be necessary to meet growing mobility needs. The role of accelerating technology in data centers are key for production operations among industry leaders such as Amazon and Microsoft for real-time processing.

Artificial Intelligence (A.I.) and Big Data are increasing become more applicable in the development of technology from machine design and mobility to bio-printing and drug discovery. The ability to quantify large amounts of data these systems generate will be paramount to establishing a robust infrastructure for interdisciplinary autonomous applications. This paper purposes an integrated approach to the environment, pre/post data processing, integration, and system security for robust systems in intelligent transportation systems. The systems integration is based on a FPGA embedded system design and computing (EDGE) platform utilizing image processing CNN algorithms from High Energy Physics (HEP) experiments in data centers with associative memory to ROS- FPGA technology in vehicles for hyper-scale infrastructure scalability. The ability to process data in the future is equivalent to collision particle detection that the Large Hadron Collider (LHC) produces at CERN.