VITS-a vision system for autonomous land vehicle navigation

Turk, Matthew; Morgenthaler, David G.; Gremban, K. D.; Marra, M.

doi:10.1109/34.3899

Cited by 327 publications

(102 citation statements)

References 20 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…The use of color to compensate for these differences in illumination conditions has been explored in many outdoor navigation systems. Some of the earliest systems to use color to distinguish shadows from obstacles are by Thorpe et al [143] and Turk et al [151]. Another more recent example of this is in [91], where the authors have addressed the problem of vision-guided obstacle avoidance using three redundant vision modules, one for intensity (BW), one for RGB, and one for HSV.…”

Section: Illumination and Outdoor Navigationmentioning

confidence: 99%

“…Another pioneering development in road-following was VITS (Vision Task Sequencer) by Turk et al [151]. VITS was a system developed for Alvin, the eight-wheeled Autonomous Land Vehicle at Martin Marietta Denver Aerospace.…”

Section: Outdoor Navigation In Structured Environmentsmentioning

confidence: 99%

“…In a manner similar to [151], Mori uses what is referred to as the color impression factor-Red minus Blue-to compensate for hue shifts due to variations in sunlight conditions, weather, season, view position, etc. However, instead of storing models of "sunny road" and "shaded road," as in Navlab and VITS [143], [151] (which are useful only when the robot is in completely sunny or completely shady regions), the system presented by Mori uses three windows positioned in the image to correspond to three regions ahead of the robot: far (4 meters), middle (3 meters), and near (2 meters). The windows are analyzed and the computed color impression factor is used to facilitate transitions from/to sunny to/from shaded regions.…”

Section: Illumination and Outdoor Navigationmentioning

confidence: 99%

See 2 more Smart Citations

Vision for mobile robot navigation: a survey

DeSouza

Kak

2002

IEEE Trans. Pattern Anal. Machine Intell.

1,181

504

View full text Add to dashboard Cite

Abstract-This paper surveys the developments of the last 20 years in the area of vision for mobile robot navigation. Two major components of the paper deal with indoor navigation and outdoor navigation. For each component, we have further subdivided our treatment of the subject on the basis of structured and unstructured environments. For indoor robots in structured environments, we have dealt separately with the cases of geometrical and topological models of space. For unstructured environments, we have discussed the cases of navigation using optical flows, using methods from the appearance-based paradigm, and by recognition of specific objects in the environment.

show abstract

Section: Illumination and Outdoor Navigationmentioning

confidence: 99%

Section: Outdoor Navigation In Structured Environmentsmentioning

confidence: 99%

Section: Illumination and Outdoor Navigationmentioning

confidence: 99%

See 1 more Smart Citation

Vision for mobile robot navigation: a survey

DeSouza

Kak

2002

IEEE Trans. Pattern Anal. Machine Intell.

1,181

504

View full text Add to dashboard Cite

show abstract

“…Roads can be represented in a number of ways. A list of vehicle-centered 3D points denoting left and right edges were used to represent the road in [5]. A sequence of vanishing points can be used to represent the 3D shape of a curved road as in [6] [7].…”

Section: Literature Reviewmentioning

confidence: 99%

A 3-D Traffic Animation System with Storm Surge Response

Li¹,

Chatterjee²,

Chen³

et al. 2009

2009 11th IEEE International Symposium on Multimedia

View full text Add to dashboard Cite

Abstract-This paper presents a 3D traffic animation system that provides features of vehicle interaction and storm surge response to emulate realistic scenarios in a hurricane affected area. The proposed system constructs road objects based on a series of line segments. Vehicles on the roads are animated by keeping them coherent with the direction of the road segment and adjusting their speeds with respect to one another. The vehicle speed is controlled based upon a collision-circumventing policy and they automatically respond to flood water caused by a storm surge. The system can automatically plant lamp posts along the roads, which also respond to surge flooding. An implementation conducted with the 3D scenes on a couple of south Florida's surge-susceptible areas demonstrates the system's excellence in animating real traffic scenes and impacts of storm surge on coastal regions.

show abstract

“…In contrast, and despite significant progress over the last decades, artificial systems struggle to approach human performance in any of these tasks, let alone all of them. Early approaches in autonomous driving can be traced back to the 70's (e.g., VITS [12], ALVINN [7], see [5] for a review) up to stateof-the-art systems such as the Stanley robot [11], the Google car 1 or Oxford's RoboCar UK 2 -for example the UK is planning to test them in selected cities as early as 2015. Yet today, all working systems must rely on extensive arrays of sensors (LIDAR, GPS, aerial images, road maps) to palliate the insufficiencies of machine vision.…”

Section: Introductionmentioning

confidence: 99%

Efficient Learning of Pre-attentive Steering in a Driving School Framework

Rudzits

Pugeault

2014

Künstl Intell

View full text Add to dashboard Cite

Autonomous driving is an extremely challenging problem and existing driverless cars use non-visual sensing to palliate the limitations of machine vision approaches. This paper presents a driving school framework for learning incrementally a fast and robust steering behaviour from visual gist only. The framework is based on an autonomous steering program interfacing in real time with a racing simulator (TORCS): hence the teacher is a racing program having perfect insight into its position on the road, whereas the student learns to steer from visual gist only. Experiments show that (i) such a framework allows the visual driver to drive around the track successfully after a few iterations, demonstrating that visual gist is sufficient input to drive the car successfully; and (ii) the number of training rounds required to drive around a track reduces when the student has experienced other tracks, showing that the learnt model generalises well to unseen tracks.

show abstract

VITS-a vision system for autonomous land vehicle navigation

Cited by 327 publications

References 20 publications

Vision for mobile robot navigation: a survey

Vision for mobile robot navigation: a survey

A 3-D Traffic Animation System with Storm Surge Response

Efficient Learning of Pre-attentive Steering in a Driving School Framework

Contact Info

Product

Resources

About