Tathagata Mukherjee

Papers

Total Citations

H-Index

About

Tathagata Mukherjee is a researcher focused on advancing indoor positioning and robotic localization through innovative sensor fusion and deep learning techniques. His work primarily addresses the critical challenge of accurate spatial awareness in environments where GPS is unreliable, targeting applications in mobile robotics, IoT, smart cities, and virtual reality. Mukherjee’s key contributions include the development of RF-MSiP (Radio Frequency Multi-source Indoor Positioning), a framework that integrates multiple radio frequency signals to compute precise indoor location data, as detailed in his 2019 paper (5 citations). He also pioneered a distributed sensing approach for single-platform image-based localization, employing a modified PoseNet convolutional neural network with four non-stereo monocular cameras to regress robot positions, as described in his 2018 work (4 citations). This method enables robust re-localization for ground robots without reliance on expensive stereo systems. While his citation counts reflect the emerging nature of his research, Mukherjee’s work stands out for its practical, scalable solutions to real-world navigation problems, bridging the gap between theoretical computer vision and deployable autonomous systems. His contributions are particularly relevant for students and researchers exploring low-cost, high-accuracy localization in complex indoor environments.