Bluetooth Low Energy (BLE) tags have become very prevalent over the last decade for tracking applications in homes as well as businesses. These tags are used to track objects, navigate people, and deliver contextual advertisements. However, in spite of the wide interest in tracking BLE tags, the primary methods of tracking them are based on signal strength (RSSI) measurements. Past work has shown that such methods are inaccurate, and prone to multipath and dynamic environments. As a result, localization using Wi-Fi has moved to Channel State Information (CSI, includes both signal strength and signal phase) based localization methods.
In indoor environments, BLE tags are the methods of choice. They provide sufficiently long range indoors, are resistant to frequency selective fading and have low power operation. BLE tags are readable by off-the-shelf smartphones and access points, because of their co-existence in the 2.4 GHz Wi-Fi band. BLE tags are, therefore, getting very popular for tracking operations in homes, factory floors, etc. Google’s vision for physical web is based on extensive deployment of BLE beacons. It is in this context that localization for BLE devices becomes crucial.
Deep Neural Networks and Convolutional Neural Network techniques to overcome these limitations.
Researchers at UC San Diego in collaboration with a researcher from MIT have developed a CSI-based localization system for BLE tags (BLoc). BLoc includes novel algorithms to compute CSI for BLE packets, to increase bandwidth of BLE signals by combining the frequency hops and to isolate the direct path from multipath reflections. By doing so, BLoc achieves sub-meter localization accuracy in a real world environment.
BLoc will open new avenues for localization of tens of millions of already deployed BLE tags and will serve as a tool for the research community to test out CSI-based localization algorithms for BLE devices.
The goal of BLoc is to improve localization accuracy for the BLE tags that increasingly form a part of our daily lives. In summary, each communication protocol has different applications and different deployment scenarios, therefore localization of each protocol is important. BLoc is geared to advance the Bluetooth localization towards the indoor application scenario.
Working Prototype: tested and proved the performance of the algorithm on data collected in a real-world setup
The invention is patent-pending and is available for licensing and collaborations.