A team of computer scientists from Rice University are working on a indoor location detection by using existing sensors in mobile devices. The navigational location detection system began as a solution for mobile device users inside large indoor spaces like office complexes or shopping malls where GPS navigation falters under poor signals that quickly deplete battery life.
Their results were presented in a paper at last month’s 2017 Design, Automation and Test in Europe (DATE) Conference in Lausanne, Switzerland. Six months ago, the same researchers had published a paper on their first technology for a new indoor mobile positioning system called CaPSuLe.
Both CaPSuLe and the DATE paper technology rely on machine learning for location detection. Both increase the speed of calculations and decrease energy expenditure in comparison with existing location technologies. But, while CaPSuLe depends on image matching techniques and uploaded data, the new technology taps into sensors that already exist in most mobile devices.
Although, the team were not satisfied with the initial performance metrics of the sensor-driven technology, as the use of gyroscope and accelerometer data for indoor-location detection returned poor results. But after they had added in some mapping information to the model, the performance improved significantly.
The scientists wanted to build a solution that uses cheap existing sensors, such as gyroscope and accelerometer. These sensors track acceleration and rotation, but the location signals are ‘noisy’ because of irrelevant movements. For example, one can use information from these sensors to track walking movements, but the sensors also pick up swinging arms and waving hands. So when physical laws of motion are applied to compute the final location, the result is an accumulation of errors.
In addition to sensor data, the scientists also drew on studies of standard human movements. Human motion has a lot of structure that enables them to utilize the otherwise-noisy sensors to produce accurate estimations. Humans don’t typically make erratic movements and walk in a near-straight line. For the 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 idea of estimating answers rather than working with precise calculations is a novel energy-efficient approach and one Krishna Palem, Rice’s Kenneth and Audrey Kennedy Professor of Computing, first began exploring in 2003. He later joined Anshumali Shrivastava, the Assistant Professor of Computer Science at Rice and Chen Luo, a first-year graduate student to work together on energy-saving approaches to computing problems. It was then, when the team found out that Luo’s previous work in time-series mining could benefit the research. Time-series mining is used for analyzing data with temporal order information. The research presented in the DATE paper required analysis of the gyroscope and accelerometer data and each of the data sets is exactly time-series data. The team later was joined by one, Juan Jose Gonzalez Espana, a graduate student in the Department of Electrical and Computer Engineering who was intrigued by Palem’s work.
According to Jose Espana, Palem’s work in ‘clever’ inexactness has multiple important applications in daily life. The kernel of current location detection solution can have wide applications for daily use across a variety of fields including marketing, health care and pet care among others. 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.
By aggregating all the information, the team has demonstrated a solution that is twice as accurate as GPS services, while being around 27 times cheaper in terms of energy, which directly translates into longer battery life.
The Rice research team’s international collaborators included Moon Yongshik, Soonhyun Noh, Daedong Park and Seongsoo Hong, all of Seoul National University in South Korea. The research was also supported in part by the U.S. Defense Advanced Research Projects Agency.
The 2017 DATE paper, “Location Detection for Navigation Using IMUs with a Map Through Coarse-Grained Machine Learning,” is currently available upon request.
