Engineering Commons^™

Risk-Aware Path Planning For Autonomous Vehicles, Shaghayegh Gaeini

Graduate Research Theses & Dissertations

Autonomous vehicles have been the subject of intense research leading to great improvements in safety, comfort, accessibility, efficiency, etc. Path planning which provides the autonomous vehicle with a smooth, collision-free, and safe path towards its destination, is a crucial part of autonomous vehicles (AVs). Various path planning techniques have been developed in the past decades that can successfully plan a smooth and safe path in various driving scenarios. Nevertheless, these algorithms perform poorly in critical situations where the vehicle needs to quickly make a decision. To address this issue, a couple of algorithms have been proposed to replace the AV’s …

Adaptive Object Detection For Autonomous Vehicles, Christopher Wolfe

Graduate Research Theses & Dissertations

Autonomous vehicles are gradually entering our daily lives. The goal of fully autonomous commercially available vehicles is becoming closer to reality each day as the contributions from researchers and various institutions are being added to the overall body of knowledge. Object detection is a critical component of an autonomous or semi-autonomous vehicle and draws extensively on results from many fields such as image processing and statistics. In this thesis, we consider ideas from the study of real-time computing and control systems to present a novel method of real-time adaptive object detection. We present a conceptual framework of the method as …

Real-Time Traffic Sign Detection And Classification Based On A Video Feed, Victor Ciuntu

Graduate Research Theses & Dissertations

Autonomous vehicle development is currently progressing at a very fast pace and traffic sign detection and classification has an important role in it. This thesis looks at the history of autonomous vehicles as well as different implementations for traffic sign detection and classification. Multiple possible approaches are analyzed with the final goal of doing this task in real-time using a portable system.

To accomplish this task, the final solution uses a convolutional neural network for detection and classification combined with a custom optical character recognition algorithm for speed limit signs. The optical character recognition algorithm is built from the ground …