Social Links

New Interior Navigational Location Detection Technology Said to Be Twice as Accurate as GPS

April 27, 2017 By Finley Engineering in

Rice University computer scientists continue to push the envelope of interior navigational location detection technology. A new method just announced by a Rice research team improves on an initial effort presented in a research paper published just six months ago. 

Data collected in field trials showed that Rice’s solution to the problem of interior mobile device location and navigation is twice as accurate as GPS services and around 27 times cheaper in terms of energy, which translates directly into longer battery life, researchers said.

Interior Navigational Location Detection Technology

Rice’s new mobile device interior location detection-navigation technology improves on researchers’ initial methodology in that it takes advantage of low-energy sensors – accelerometers and gyroscopes – already built into smartphones and other mobile devices. The initial new methodology used novel application of more compute- and energy-intensive machine learning techniques, as well as uploading and comparative processing of images.

A lot more has gone into development of the new methodology. Of particular importance was the development of an innovative predictive analytic that can use inexact data fed into a model of interior location-navigation, which in turn is based on scientific analysis of human body motion and pedestrian tendencies, such as the tendency to walk in straight lines, Rice University News’ Jade Boyd reports.

“Human motion has a lot of structure that we were able to utilize with the otherwise-noisy sensors to produce accurate estimations,” Rice computer science professor Anshumali Shrivastava explained. “Humans don’t typically make erratic movements; they usually walk in a near-straight line.

“For our machine learning algorithm, this means that if the starting point is known, and there’s a precondition for traveling in a straight line with limited opportunities for possible left and right turns, then the location where someone stops can be accurately estimated even with noisy sensors.”

The team also had to find a way to filter out a lot in the way of “noise” – real-time data regarding human movement that can confuse and increase the computing power and time required for a sufficiently accurate determination of the mobile device user’s location within the context of their current indoor setting.

“These sensors track acceleration and rotation, but the location signals are ‘noisy’ because of irrelevant movements,” Shrivastava continued. “For example, we can use information from these sensors to track walking movements, but the sensors also pick up swinging arms and waving hands. So when we try to apply physical laws of motion to compute the final location, the result is an accumulation of errors.”

The new mobile device indoor location detection-navigation technology could have numerous applications in daily life – marketing, health care and pet care, among others, added research team member Juan Jose Gonzalez Espana, a graduate student in Rice’s Dept. of Electrical and Computer Engineering.

“For example, marketers could extend product offers based on the current location of the user or the places they frequent. In health care, the solution could be used to trigger alarms if patients approach potentially harmful areas. In pet care, missing dogs or cats could be located through this technology.”