Sri Aditya Deevi

U R Rao Satellite Centre Bengaluru, Karnataka

I am a Scientist in the Mission Simulation Group (MSG) at U.R. Rao Satellite Centre, Indian Space Research Organization (ISRO). My work involves tackling diverse AI and robotics research challenges in aerospace systems. Currently, I am engaged in several notable projects, including pose estimation and tracking in uncooperative spacecraft rendezvous operations using monocular data, estimating the relative pose of space resident objects with LIDAR point cloud data, developing autonomous navigation algorithms for rovers, and creating vision-based solutions for the autonomous landing of unmanned aerial vehicles (UAVs).

Before joining ISRO, I graduated from Caltech with a Masters degree in Electrical Engineering, having earned the prestigious and fully funded Dr. Satish Dhawan Fellowship from the Department of Space, Government of India. At Caltech, I conducted research to develop efficacious multimodal deep sensor fusion methods for object detection in the Autonomous Robotics and Control Lab (ARCL) led by Prof. Soon-Jo Chung. Following my time at Caltech, I had the opportunity to intern at the Jet Propulsion Laboratory (JPL) in the Optical Communication Systems group. There, I collaborated with Dr. Sabino Piazzolla and spearheaded the development of short-term forecasting techniques to predict key atmospheric parameters helpful in characterizing the optical channel.

In a more general sense, I am interested in Machine Learning, Robotics and Computer Vision. I am particularly fascinated by the intersection of these fields and their applications in aerospace systems. I am always on the lookout for exciting research opportunities and collaborations, so feel free to reach out if you have any ideas or projects in mind.

news

Oct 15, 2024	Our paper accepted in International Conference on Ubiquitous Information Management and Communication (IMCOM) 2025.
Sep 30, 2024	Won the AI/ML challenge organized at U.R. Rao Satellite Centre, competing with over 250 scientists.
Aug 23, 2024	Presented interactive demos showcasing our research group’s work to school students on National Space Day.
Jul 20, 2024	Represented U.R. Rao Satellite Centre in the 9^th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG-2024).
Apr 04, 2024	Joined U.R. Rao Satellite Centre as a Scientist/Engineer - ‘SC’ in the Mission Simulation Group.
Feb 29, 2024	Presented our paper, RGB-X Object Detection via Scene-Specific Fusion Modules, in the AGI Leap Summit organized by SuperAGI.
Jan 10, 2024	Our paper published in the Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.
Oct 20, 2023	Completed Graduate Research Internship at NASA’s Jet Propulsion Laboratory.

selected publications

RGB-X Object Detection via Scene-Specific Fusion Modules

Sri Aditya Deevi, Connor Lee, Lu Gan , and 3 more authors

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2024

Abstract HTML Code Poster Slides

Multimodal deep sensor fusion has the potential to enable autonomous vehicles to visually understand their surrounding environments in all weather conditions. However, existing deep sensor fusion methods usually employ convoluted architectures with intermingled multimodal features, requiring large coregistered multimodal datasets for training. In this work, we present an efficient and modular RGB-X fusion network that can leverage and fuse pretrained single-modal models via scene-specific fusion modules, thereby enabling joint input-adaptive network architectures to be created using small, coregistered multimodal datasets. Our experiments demonstrate the superiority of our method compared to existing works on RGB-thermal and RGB-gated datasets, performing fusion using only a small amount of additional parameters. Our code is available at https://github.com/dsriaditya999/RGBXFusion.