Enabling Wireless Sensors via deisgning simulators, and novel perception models for aiding Next Generation Wireless Digital Twin models.
To facilitate the seamless integration of wireless sensors into our everyday applications, a critical element currently lacking is the availability of expansive datasets and real-time integrations within simulators tailored for large-scale deployments and assessments. Drawing inspiration from recent strides in Digital-Twin technologies across diverse domains, my research is poised to take the next leap forward. This involves crafting a sophisticated framework for efficient perception, simulator design, and the delivery of real-time feedback from the digital twin of the simulator to real-world environments.
For localization across all kinds of different environments for example we would need large models and larger datasets, Which demands for readily available RF-simulators, and the current simulators are still lacking. So, I would like to develop physics inspired ML models like the diffusion models to create wireless simulators that are closer to the real world scenarios. Which could help for a more wider deployment of these sensors by the design of ML-based digital twins by making them readily integrable into simulators like unity and gazebo
References
2020
LocAP: Autonomous millimeter accurate mapping of WiFi infrastructure
Indoor localization has been studied for nearly two decades fueled by wide interest in indoor navigation, achieving the necessary decimeter-level accuracy. However, there are no real-world deployments of WiFi-based user localization algorithms, primarily because these algorithms are triangulation based and therefore assume the location of the Access Points, their antenna geometries, and deployment orientations in the physical map. In the real world, such detailed knowledge of the location attributes of the Access Point is seldom available, thereby making WiFi localization hard to deploy. In this paper, for the first time, we establish the accuracy requirements for the location attributes of access points to achieve decimeter level user localization accuracy. Surprisingly, these requirements for antenna geometries and deployment orientation are very stringent, requiring millimeter level and sub-10 degree of accuracy respectively, which is hard to achieve with manual effort. To ease the deployment of real-world WiFi localization, we present LocAP, which is an autonomous system to physically map the environment and accurately locate the attributes of existing infrastructure AP in the physical space down to the required stringent accuracy of 3 mm antenna separation and 3degree deployment orientation median errors, whereas state-of-the-art report 150 mm and 25degrees respectively.
@inproceedings{ayyalasomayajula2020locap,title={LocAP: Autonomous millimeter accurate mapping of WiFi infrastructure},author={Ayyalasomayajula, Roshan and Arun, Aditya and Wu, Chenfeng and Rajagopalan, Shrivatsan and Ganesaraman, Shreya and Seetharaman, Aravind and Jain, Ish Kumar and Bharadia, Dinesh},booktitle={17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)},pages={1115--1129},year={2020},url={https://www.usenix.org/conference/nsdi20/presentation/ayyalasomayajula},}
