Enabling Indoor positioning, localization, navigation, and tracking using wireless sensors.
Location services, fundamentally, rely on two components: a mapping system and a positioning system. The mapping system provides the physical map of the space, and the positioning system identifies the position within the map. Outdoor location services have thrived over the last couple of decades because of well-established platforms for both these components (e.g. Google Maps for mapping, and GPS for positioning). In contrast, indoor location services haven’t caught up because of the lack of reliable mapping and positioning frameworks, as GPS is known not to work indoors. There are many important problems to be solved to enable real-time positioning and tracking for INdoors that can enable aplications ranging from navigation and localization that demand sub-meter accuracy, to Robot Automatio, tracking, and last-mile delivery that require sub-10cm accuracy to VR Tracking and other Mixed Reality systems that need sub-cm accurate tracking of either the users, user devices, robots or IoT devices.
Two of the major issues for localization and navigation using wireless-sensors is the need to overcome two major issues with wireless transmissions: Multipath and Non-Line of Sight issues. My research focuses on solving these issues to achieve accurate indoor localization and navigation for Wi-Fi devices in DLoc and open-sourced the first largest dataset called WILD; also to achieve low-power localization using BLE devices in BLoc; and UWB based industrial assets localization based on the upcoming industrial FiRa standards in ULoc that achieves 14x better battery life while achiieving 5x times better localization accuracy and stability compared to the COTS devices.
References
2021
Uloc: Low-power, scalable and cm-accurate uwb-tag localization and tracking for indoor applications
A myriad of IoT applications demand centimeter-accurate localization that is robust to blockages from hands, furniture, or other occlusions in the environment. To address these needs, we developed ULoc, a scalable, low-power, and cm-accurate UWB localization and tracking system. ULoc’s builds a multi-antenna UWB anchor and develops a novel 3D tracking algorithm to deliver a stationary localization accuracy of less than 5 cm and a tracking accuracy of 10 cm in mobile conditions. Follow the demo links below to see ULoc in action. Furthermore, we have also open sourced our hardware design files and source code.
@article{zhao2021uloc,title={Uloc: Low-power, scalable and cm-accurate uwb-tag localization and tracking for indoor applications},author={Zhao, Minghui and Chang, Tyler and Arun, Aditya and Ayyalasomayajula, Roshan and Zhang, Chi and Bharadia, Dinesh},journal={Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},volume={5},number={3},pages={1--31},year={2021},publisher={ACM New York, NY, USA},url={https://dl.acm.org/doi/pdf/10.1145/3478124},}
Sound source localization based on multi-task learning and image translation network
Yifan Wu, Roshan Ayyalasomayajula, Michael J Bianco, Dinesh Bharadia, and Peter Gerstoft
The Journal of the Acoustical Society of America, 2021
@article{wu2021sound,title={Sound source localization based on multi-task learning and image translation network},author={Wu, Yifan and Ayyalasomayajula, Roshan and Bianco, Michael J and Bharadia, Dinesh and Gerstoft, Peter},journal={The Journal of the Acoustical Society of America},volume={150},number={5},pages={3374--3386},year={2021},publisher={AIP Publishing},}
Sslide: Sound source localization for indoors based on deep learning
Yifan Wu, Roshan Ayyalasomayajula, Michael J Bianco, Dinesh Bharadia, and Peter Gerstoft
In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
@inproceedings{wu2021sslide,title={Sslide: Sound source localization for indoors based on deep learning},author={Wu, Yifan and Ayyalasomayajula, Roshan and Bianco, Michael J and Bharadia, Dinesh and Gerstoft, Peter},booktitle={ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},pages={4680--4684},year={2021},organization={IEEE},url={https://doi.org/10.1109/ICASSP39728.2021.9415109},}
2020
Deep learning based wireless localization for indoor navigation
Location services, fundamentally, rely on two components- a mapping system and a positioning system. The mapping system provides the physical map of the space, and the positioning system identifies the position within the map. Outdoor location services have thrived over the last couple of decades because of well-establishedplatforms for both these components (e.g. Google Maps for mapping, and GPS for positioning). In contrast, indoor location services haven’t caught up because of the lack of reliable mapping and positioning frameworks, as GPS is known not to work indoors. WiFi positioning lacks maps and is also prone to environmental errors. In this paper, we present DLoc, a Deep Learning based wireless localization algorithm that can overcome traditional limitations of RF-based localization approaches (like multipath, occlusions, etc.). DLoc uses data from the mapping platform we developed, MapFind, that can construct location-tagged maps of the environment. Together, they allow off-the-shelf WiFi devices like smartphones toaccess a map of the environment and to estimate their position withrespect to that map. During our evaluation, MapFind has collected location estimates of over 120 thousand points under 10 different scenarios across two different spaces covering 2000 sq. Ft. DLoc outperforms state-of-the-art methods in WiFi-based localizationby 80% (median and 90th percentile) across the 2000 sq. ft. spanningtwo different spaces.
@inproceedings{ayyalasomayajula2020deep,title={Deep learning based wireless localization for indoor navigation},author={Ayyalasomayajula, Roshan and Arun, Aditya and Wu, Chenfeng and Sharma, Sanatan and Sethi, Abhishek Rajkumar and Vasisht, Deepak and Bharadia, Dinesh},booktitle={Proceedings of the 26th Annual International Conference on Mobile Computing and Networking},pages={1--14},year={2020},url={https://dl.acm.org/doi/pdf/10.1145/3372224.3380894},}
2018
BLoc: CSI-based accurate localization for BLE tags
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 this paper, we seek to investigate what are the challenges that prevent BLE from adopting CSI based localization methods. We identify fundamental differences at the PHY layer between BLE and Wi-Fi, that make it challenging to extend CSI based localization to BLE. We present our system, BLoc, that incorporates novel, BLE-compatible algorithms to overcome these challenges and enable an accurate, multipath-resistant localization system. Our empirical evaluation shows that BLoc can achieve a localization accuracy of 86 cm with BLE tags, a 3X improvement over a state-of-the-art baseline.
@inproceedings{ayyalasomayajula2018bloc,title={BLoc: CSI-based accurate localization for BLE tags},author={Ayyalasomayajula, Roshan and Vasisht, Deepak and Bharadia, Dinesh},booktitle={Proceedings of the 14th International Conference on emerging Networking EXperiments and Technologies},pages={126--138},year={2018},url={https://dl.acm.org/doi/pdf/10.1145/3281411.3281428},}
Sound source localization based on multi-task learning and image translation networkThe Journal of the Acoustical Society of America, 2021
