GOALI: Next Generation Active Safety Control Systems for Crash-Avoidance of Passenger Vehicles Using Expert Driver Knowledge

Georgia Tech Research Corporation, Atlanta GA

Investigators

Abstract

Driven by federal directives and the public mandate to increase safety, economy and comfort, current passenger cars incorporate a variety of technological advances such as active suspension systems, ABS, differential traction control and electronic stability programs (ESP) to meet these goals. Future vehicles will incorporate even more sophisticated technologies such as four-wheel independent steering, drive-by-wire, brake-by-wire, autonomous navigation and platooning, etc. This research directly supports the development of such active safety systems and facilitate their transfer to production vehicles through a comprehensive collaboration plan with Ford Motor Company as part of the NSF-GOALI Program. Intellectual Merit: This project involves the development of a control architecture for the next generation of drive management systems (DMS) for passenger vehicles. Supported by advances in MEMS sensor technology and the development of dedicated embedded hardware and software, DMS will soon become a reality for the next generation of passenger vehicles. Several automotive companies, notably Ford (in collaboration with Volvo of Sweden), have started an ambitious project to develop an "accident-free" car by 2020. This goal cannot be achieved without sophisticated "drive-by-wire" (DBW) control systems which as part of the overall DMS architecture will prevent the driver from taking an incorrect action that would violate the safe limits of the vehicle, and also help the driver recover from such unsafe regimes. To achieve this goal, the approach borrows well-studied and validated techniques, practices and experiences from the aerospace industry, where "fly-by-wire" (FBW) and flight management systems (FMS) have increased the safety, reliability, performance, and fuel efficiency of civil and military aircraft during the last two decades. The four cornerstones of the methodology are: (i) Collaboration with expert race drivers who will provide valuable input on advanced driving techniques to recover from abnormal and dangerous driving conditions; (ii) Development of mathematical models of these driving techniques; (iii) On-line implementation of these maneuvers using finite state automata; (iv) Numerical and experimental validation of the controllers on passenger vehicles at Ford's test facilities. With the support from this GOALI proposal, one student or post-doc from the PI's research group will spend at least six months each year at Ford for the duration of the project and work with the Ford engineers to help transition the technology to production vehicles. Broader Impacts: The results of this work will have an immediate impact on the improvement of safety standards of passenger vehicles. Technology transfer will be facilitated through the Technology Licensing Office of Georgia Tech. The educational impact of this project can be classified according to the targeted audience as precollege, undergraduate, graduate students and professionals. Due to the diversity of this audience, the PIs plan to use separate avenues to reach each group through direct support from the NSF under this award as well as a URP award from Ford. This program facilitates the involvement of minority students. Dissemination of the results of this work to professionals and the layperson will be achieved via the web and press releases from Ford.