The objective of this research is to study, develop and implement a comprehensive set of techniques that will eventually enable automobiles to be driven autonomously. The approach taken is to (a) address cyber-physical challenges of reliable, safe and timely operations inside the automobile, (b) tackle a range of physical conditions and uncertainties in the external environment, (c) enable real-time communications to and from the automobile to other vehicles and the infrastructure, and (d) study verification and validation technologies to ensure correct implementations. Intellectual Merits: The project seeks to make basic research contributions in the domains of safety-critical real-time fault-tolerant distributed cyber-physical platforms, end-to-end resource management, cooperative vehicular networks, cyber-physical system modeling and analysis tools, dynamic object detection/recognition, hybrid systems verification, safe dynamic behaviors under constantly changing operating conditions, and real-time perception and planning algorithms. Multiple intermediate capabilities in the form of active safety features will also be enabled. Broader Impacts: Automotive accidents result in about 40,000 fatalities and 3 million injuries every year in the USA. The global annual cost of road injuries is $518 billion. Many accidents are due to humans being distracted. Autonomous vehicles controlled by ever-vigilant cyber-physical systems can lead to significant declines in accidents, deaths and injuries. Autonomous vehicles can also offload driving chores from humans, and make time spent in automobiles more productive. Vehicular networks can help find the best possible routes to a destination in real-time. Broader impacts in this area are amplified by the project's partnerships with companies in the transportation and agricultural technology industries, and in information technology. Broader impacts are also sought through demonstrations and outreach to attract students into science and technology, and in particular to cyber-physical systems research.
Ragunathan Rajkumar
Performance Period: 10/01/2010 - 09/30/2016
Institution: Carnegie-Mellon University
Sponsor: National Science Foundation
Award Number: 1035813