Search Results

The research reported in this paper focuses on the automated steering aspects of intelligent highway vehicles. Proposed is a machine vision system for capturing driver views of the on-coming highway environment. The objective is to investigate various designs of artificial neural networks for processing the resulting images and generating acceptable steering commands for the vehicle. The research effort has involved the construction of a computer graphical simulation system, called the Road Machine, which is used as the experimental environment for analyzing, through simulation, alternative neural network approaches for controlling autonomous highway vehicles. The Road Machine serves as both the training environment and the experimental testing environment for the autonomous highway vehicle. It is composed of five (5) major modules: Highway design, Driver view simulation, Image processing, Neural network design and training, and Autonomous driving simulation.

Lateral control of a simulated vehicle in a simulated highway driving environment is explored. Three modules are used: a driving simulator, a visual preprocessor, and a neural network. The driving simulator, called RoadWay, is a three-dimensional computer graphics environment which supports interactive highway design and driving capabilities. The visual preprocessor, RoadVision, receives images from RoadWay, which represent forward-looking views from the cockpit of the simulated vehicle, and encodes these images using a family of oriented two-dimensional Gabor filters. Two Adaptive Resonance Theory neural network architectures, ART2 and ARTMAP, constituting the RoadBrain module, are employed to learn mappings between the visual encodings and emergent image categories, and then to associate these image categories with appropriate steering decisions.