The passive sensing suite of the TerraMax autonomous vehicle

Abstract

Abstract-This paper presents the TerraMax autonomous vehicle, which competed in the DARPA Urban Challenge 2007. The sensing system is mainly based on passive sensors, in particular four vision subsystems are used to cover a 360• area around the vehicle, and to cope with the problems related to complex traffic scenes navigation. A trinocular system derived from the one used during the 2005 Grand Challenge performs obstacle and lane detection, twin stereo systems (one in the front and one in the back) monitor the area close to the truck, two lateral cameras detect oncoming vehicles at intersections, and a rear view system monitors the lanes next to the truck looking for overtaking vehicles. Data fusion between laserscanners and vision will be discussed, focusing on the benefits of this approach.

Accurate hardware-based stereo vision

“…It has been successfully used in applications such as robot navigation [18], space missions [17] or obstacle detection for autonomous vehicles in an urban environment [5,6,34]. Therefore, a stereo vision sensor is required to deliver a high frame rate, which can be achieved by the use of hardware-based implementations [36].…”

Design of automated driving system of a wheeled heavy duty off-road vehicle

“…There is little research on the wheeled heavy duty off-road autonomous vehicles. Team Oshkosh's vehicle, TerraMax, for example, is a typical wheeled heavy duty off-road autonomous vehicle kit system that advances an automatic control system to increase performance in autonomous missions [5,6,7,8]. In this paper, concentrated on a wheeled heavy duty off-road vehicle, we realize its modification by designing an automated driving system consisting of lateral control, longitudinal control and integrated control based on x-by-wire, so as to achieve automated driving in real scenarios.…”

Vehicle detection for autonomous parking using a Soft-Cascade AdaBoost classifier

“…On the research side, current state of the art in AGV driving [1] provides reliable all-around perception, at the cost of adopting a highly sophisticated suite of expensive sensors, such as sweeping laser range finders, RADAR systems, and color cameras.…”