A Robust Approach to High-Speed Navigation for Unrehearsed Desert Terrain

Urmson, Chris; Anhalt, Joshua; Bartz, Daniel; Clark, Michael; Galatali, Tugrul; Gutierrez, Alexander; Harbaugh, Sam; Johnston, Josh; Kato, Hiroki “Yu”; Koon, Phillip L.; Messner, William C.; Miller, Nick; Mosher, Aaron; Peterson, Kevin; Ragusa, Charlie; Ray, David C.; Smith, Bryon M.; Snider, Jarrod M.; Spiker, Spencer; Struble, Josh; Ziglar, Jason; Whittaker, William

doi:10.1007/978-3-540-73429-1_2

Cited by 55 publications

(16 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most reliable existing approach to vehicle localization is through the use of the Velodyne lidar sensor, which was widely used in DARPA challenges [16], [27], and is also used by the Google driverless car. One approach has been to build a 2D map of the environment by projecting the point cloud onto the road surface [10].…”

Section: Related Workmentioning

confidence: 99%

Light-weight localization for vehicles using road markings

Ranganathan

Ilstrup

2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Traditional vision-based localization methods such as visual SLAM suffer from practical problems in outdoor environments such as unstable feature detection and inability to perform location recognition under lighting, perspective, weather and appearance change. Additionally map construction on a large scale in these systems presents its own challenges. In this work, we present a novel method for precisely localizing vehicles on the road using signs marked on the road (road markings), which have the advantage of being distinct and easy to detect, their detection being robust under changes in lighting and weather. Our method uses corners detected on road markings to perform localization in global coordinates. The method consists of two phases -a mapping phase when a high-quality GPS device is used to automatically survey road marks and add them to a light-weight "map" or database, and a localization phase where road mark detection and look-up in the map, combined with visual odometry, produces precise localization. We present experiments using a real-time implementation operating in a car that demonstrates the improved localization robustness and accuracy of our system even when using road marks alone. However, in this case the trajectory between road marks has to be filled-in by visual odometry, which contributes drift. Hence, we also present a mechanism for combining roadmark-based maps with sparse feature-based maps that results in greater accuracy still. We see our use of road marks as a significant step in the general trend of using higher-level features for improved localization performance irrespective of environment conditions. 978-1-4673-6358-7/13/$31.00 ©2013 IEEE

show abstract

Section: Related Workmentioning

confidence: 99%

Light-weight localization for vehicles using road markings

Ranganathan

Ilstrup

2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…Still, vision-based localization methods for outdoor purposes are only at an evaluation stage. This was observed during the recent DARPA Urban Challenge events, in which none of the finalists used vision as its main localization sensor (Burdick et al, 2007;Leonard et al, 2007;Urmson et al, 2006). Similarly, the Mars Exploration Rovers use vision as a secondary localization sensor after the inertial navigation system (INS) (Cheng, Maimone, & Matthies, 2006).…”

Section: Introductionmentioning

confidence: 98%

Correlation‐based visual odometry for ground vehicles

Nourani-Vatani

Borges

2011

Journal of Field Robotics

View full text Add to dashboard Cite

Reliable motion estimation is a key component for autonomous vehicles. We present a visual odometry method for ground vehicles using template matching. The method uses a downward-facing camera perpendicular to the ground and estimates the motion of the vehicle by analyzing the image shift from frame to frame. Specifically, an image region (template) is selected, and using correlation we find the corresponding image region in the next frame. We introduce the use of multitemplate correlation matching and suggest template quality measures for estimating the suitability of a template for the purpose of correlation. Several aspects of the template choice are also presented. Through an extensive analysis, we derive the expected theoretical error rate of our system and show its dependence on the template window size and image noise. We also show how a linear forward prediction filter can be used to limit the search area to significantly increase the computation performance. Using a single camera and assuming an Ackerman-steering model, the method has been implemented successfully on a large industrial forklift and a 4×4 vehicle. Over 6 km of field trials from our industrial test site, an off-road area and an urban environment are presented illustrating the applicability of the method as an independent sensor for large vehicle motion estimation at practical velocities. C 2011 Wiley Periodicals, Inc.

show abstract

“…Global Positioning Systems (GPS, one kind of GNSS) should be the main navigation information source for autonomous vehicles, which was indicated from the famous DARPA GRAND CHALLENGE [7]. In the open sky field, namely eight satellites or more, the error standard deviation of differential mode GPS positioning is about 30 centimeters.…”

Section: Introductionmentioning

confidence: 99%

Correction of vehicle positioning error using 3D-map- GNSS and vision-based road marking detection

Hsu

Kamijo

2015

2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES)

View full text Add to dashboard Cite

Accurate and robust vehicle self-localization in the urban environment is a new challenge arising in the autonomous driving. GNSS positioning technique suffers from the effects of multipath and Non-Line-Of-Sight (NLOS) propagation in urban canyon. This paper proposes to employ an innovative GNSS positioning technique with the aid of 3D building map, to mitigate the error caused by multipath and NLOS. In addition, the road markings on road surface provide the significant visual information for driving, which can also be used for localization. Based on the lane marking detection, the lane keeping and changing behavior can be recognized and used for positioning. This paper integrates 3D-map-GNSS with vision-based road marking detection and 2D Map to reduce the vehicle positioning error. The experiment results demonstrate that the proposed method can provide sub-meter accuracy with respect to positioning error mean.

show abstract

A Robust Approach to High-Speed Navigation for Unrehearsed Desert Terrain

Cited by 55 publications

References 23 publications

Light-weight localization for vehicles using road markings

Light-weight localization for vehicles using road markings

Correlation‐based visual odometry for ground vehicles

Correction of vehicle positioning error using 3D-map- GNSS and vision-based road marking detection

Contact Info

Product

Resources

About