Mahesh S. Patil

Papers

Total Citations

H-Index

About

Mahesh S. Patil is a researcher focused on advancing artificial intelligence for indoor environments, particularly in the domains of robotics and scene understanding. His work bridges deep learning and reinforcement learning to tackle the unique challenges of GPS-denied spaces. Patil’s most notable contribution is his pioneering application of deep reinforcement learning for indoor navigation, as detailed in his 2020 paper, which has garnered 11 citations. This work addresses a critical gap in robotics and drone technology, where traditional GPS fails. Additionally, his 2017 study on combining RGB and depth images for indoor scene classification (10 citations) tackles the high appearance variability of indoor settings, a key hurdle for mobile robotics. By fusing visual and depth data, Patil’s research enhances a robot’s ability to recognize and adapt to its surroundings, directly impacting applications from autonomous drones to assistive technologies. His work stands out for its practical focus on real-world deployment, offering scalable solutions for indoor autonomy. Though his citation counts reflect a growing field, Patil’s contributions are foundational for researchers seeking robust, learning-based approaches to indoor intelligence.