I-Corps: Translation potential of infrastructure-enabled safe autonomy

Texas A&M Engineering Experiment Station, College Station TX

Investigators

Abstract

The broader impact of this I-Corps project is the development of a technology system for smart infrastructure enabled autonomy. The promise of autonomous vehicles (AVs) has not come true despite the tremendous economic and societal benefits of AVs, potentially avoiding 40,000+ fatalities annually. The complexity, unreliability, and cost of additional on-board sensors required for autonomous driving have been major roadblocks preventing significant market deployment and adoption. As a result, the only viable market for AVs has been ride sharing and hauling services. The poor performance of robo-taxis has increased safety concerns over these technologies. For instance, such AVs have blocked road and emergency vehicles. They have also been involved in hundreds of crashes, including fatal ones. A significant portion of the underlying technological challenges can be resolved by leveraging smart infrastructure, leveraging recent dramatic growth in connectivity – 4G-LTE/5G and edge computers. This project will help overcome the challenges associated with complex driving scenarios, such as interaction with emergency vehicles, detecting vulnerable road users, merging onto highways, picking up and dropping off customers, etc. This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of the technology. This solution is based on the development of an integrated hardware/software platform that leverages sensors on infrastructure to infer traffic conditions and create a common situational awareness for all entities on the road. The platform sends situational awareness information wirelessly to vehicles and other consumers for real-time use, in-turn enabling multiple benefits, such as lower cost and faster deployment of autonomous vehicles, improved vulnerable road user safety, traffic optimization, and road maintenance. For these applications to be effective, situational awareness needs to be generated in real-time and be reliable across a range of sensing and communication faults and environmental conditions (adverse conditions). The core algorithms and software implementations developed during research based on resilient data fusion, enable automatic detection, mitigation, and graceful recovery from adverse conditions. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.