<title>Road detection and tracking for autonomous mobile robots</title>

Abstract

As part of the Army's Demo III project, a sensor-based system has been developed to identify roads and to enable a mobile robot to drive along them. A ladar sensor, which produces range images, and a color camera are used in conjunction to locate the road surface and its boundaries. Sensing is used to constantly update an internal world model of the road surface. The world model is used to predict the future position of the road and to focus the attention of the sensors on the relevant regions in their respective images. The world model also determines the most suitable algorithm for locating and tracking road features in the images based on the current task and sensing information. The planner uses information from the world model to determine the best path for the vehicle along the road. Several different algorithms have been developed and tested on a diverse set of road sequences. The road types include some paved roads with lanes, but most of the sequences are of unpaved roads, including dirt and gravel roads. The algorithms compute various features of the road images including smoothness in the world model map and in the range domain, and color features and texture in the color domain. Performance in road detection and tracking are described and examples are shown of the system in action.

Learning long‐range vision for autonomous off‐road driving

“…This is especially useful for roadfollowing vehicles (Dahlkamp et al, 2006;Leib et al, 2005;Hong et al, 2002); the ground immediately in front of the vehicle is assumed to be traversable, and the rest of the image is then filtered to find similarly colored or textured pixels. Although this approach helped to win the 2005 DARPA Grand Challenge , its utility was limited by the inherent fragility of color-based methods, and the online visual classifier was only used to slightly modulate the speed of the autonomous car, rather than used for planning of any sort.…”

A Fast and Robust Approach to Lane Marking Detection and Lane Tracking

“…A challenging task is to create a lane model based on the features found in the image. Simple approaches try to fit a single line to the data [5], more complex approaches model the street as B-Snakes [10] or concentric circular arcs [6]. Surprisingly, only very few attempts have been made to work on color images [3] which is indispensable when colored lane marks should be detected.…”

“…Surprisingly, only very few attempts have been made to work on color images [3] which is indispensable when colored lane marks should be detected. In order to cope with limitations of monocular systems, the use of additional geometric information has been proposed [5]. Graphics hardware can be used to accelerate image processing and detection [9].…”

Deep belief net learning in a long-range vision system for autonomous off-road driving

“…This is especially useful for road-following vehicles [2], [12], [8]; the ground immediately in front of the vehicle is assumed to be traversable, and the rest of the image is then filtered to find similarly colored or textured pixels. Although this approach helped to win the 2005 DARPA Grand Challenge, its utility is limited by the inherent fragility of color-based methods.…”