This project studied the feasibility of constructing an autonomous vehicle controller based on probabilistic inference and utility maximization. Several theoretical and algorithmic advances were required in order to create an inference system capable of handling vehicle monitoring in a real-time...

In this report, a combined longitudinal and lateral eighteen-state vehicle chassis, engine, and drive train model is developed and validated against existing longitudinal-only and lateral-only vehicle models. The full-size model is simplified to a three-state model to facilitate controller...

This document is a users manual for DYN-OPT, a linear program that optimally and dynamically assigns traffic to lanes on an automated highway. The program maximizes the total flow across the highway over a pre-specified length of time. DYN-OPT solves a path-based formulation in which the highway...

This report describes a combined steering and brake actuator system for use in automatic vehicle control research The system allows a standard passenger car to switch from normal manual operation to automatic operation and back in a seamless manner using largely standard parts. The system uses a...

This report presents two performance enhancement lateral control designs for single unit heavy vehicles. It is shown that robust performance can be achieved using the techniques on a feedback linearized system.

The purpose of MOU-233 is to evaluate and test a low cost, short range radar sensor developed by Amerigon corporation through a subcontract with the University of Southern California. The radar is designed to be used as a ranging sensor for automatic vehicle following applications. It is...

This study reports on a preliminary design of a health monitoring system for automated vehicles. A new detailed nonlinear vehicle simulation which extends the current simulation is documented and will be used as a future testbed for evaluating the performance of the health monitoring system. A...

This nal report describes the application of computer vision techniques to the lateral and longitudinal control of an autonomous highway vehicle. In the part of the project we focused on an analysis of the vehicle's lateral dynamics and the design of an appropriate controller for lateral control...

A fuzzy rule-based controller is applied to lateral guidance of a vehicle for an automated highway system. The fuzzy rules, based on human drivers' experiences, are developed to track the center of a lane in the presence of external disturbances and over a range of vehicle operating conditions.