SwRI's RANGER localization technology allows precise automated driving

November 20, 2015, Southwest Research Institute
SwRI's RANGER localization technology allows precise automated driving
This image shows 10 automated loops around a slalom course using the 2015 R&D 100 award-winning RANGER technology. With RANGER, vehicle position (in green) varied by less than 5 centimeters, compared to GPS measurements (in yellow), which varied by as much as 2 meters. Southwest Research Institute developed and patented RANGER to provided precise position and orientation measurements for automated vehicles using a ground-facing camera and localization algorithms. Credit: Southwest Research Institute

Southwest Research Institute (SwRI) has developed RANGER, a patented approach to vehicle localization that enables precise navigation for automated vehicles. R&D Magazine recently recognized RANGER as one of the 100 most significant innovations for 2015.

RANGER is a relatively low-cost solution, which uses a ground-facing camera and localization algorithms to provide precise position and orientation measurements. RANGER images the unique "fingerprint" of road surfaces, allowing precise automated driving within 2 centimeters, similar to the most accurate (and most expensive) GPS systems. RANGER, however, can operate in areas or environments where GPS has poor performance or fails completely.

"Localization for is a significant challenge," said Dr. Kristopher Kozak, a principal engineer in SwRI's Automation and Data Systems Division who led RANGER's development. "GPS is very good; it's ubiquitous, everybody has GPS on their phones, but it's not always as accurate as you need it to be for automated vehicle localization. RANGER is a low-cost, high-precision localization system that overcomes a lot of problems affecting GPS systems."

RANGER works by matching thousands of distinguishing on the ground to corresponding features collected and stored in a map. These features include obvious large-scale characteristics like cracks, road markings, oil stains, etc., as well as small, subtle features such as exposed aggregate and contrast variations. The composition of features on every patch of ground is unique, like a "fingerprint," and RANGER needs only a small percentage of the features to match to accurately determine the location of the vehicle.

RANGER is a novel approach to localization for automated driving that performs well in all illumination conditions and typical adverse weather conditions, including rain and fog. While other sensor-based approaches are more common, none use a similar camera-based approach with controlled illumination, and none can match RANGER's precision.

Explore further: Rangers and visitors build links on park visits

Related Stories

Wallaby sighting in Kalbarri the first in 20 years

October 16, 2015

The WA nature conservation community is abuzz with excitement with the rediscovery of black-flanked rock-wallabies (Petrogale lateralis lateralis) in Kalbarri National Park after two decades of presumed local extinction.

Recommended for you

Team breaks world record for fast, accurate AI training

November 7, 2018

Researchers at Hong Kong Baptist University (HKBU) have partnered with a team from Tencent Machine Learning to create a new technique for training artificial intelligence (AI) machines faster than ever before while maintaining ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.