Amogh Joshi

My research interests lie in computer vision and graphics, especially for autonomous robotics.

At Princeton, I am part of the Computational Imaging Lab, and am advised by Professor Felix Heide. My primary work focuses on neural rendering and scene reconstruction, particularly for autonomous driving. I have also worked on a variety of projects across the spectrum of computational imaging, including computational photography and optics. Throughout my research, I have collaborated with Mercedes-Benz, Torc Robotics, and Colgate-Palmolive Research. Also at Princeton, I have conducted research with the Neuroscience of Cognitive Control Lab, where I worked on developing approaches grounded in computational cognitive science to better understand VLMs and LLMs.

I’m a member of the Data Generation team at Torc Robotics, where I work on scene reconstruction and generation for autonomous trucking environments. From 2022 to 2024, I worked as an autonomous driving engineer at Monarch Tractor. I was heavily involved in the development of the current Row Follow models in vineyards and dairy farms, and I principally developed the Invisible Bucket feature for operator awareness. I also worked on the Follow Me mode, multi-object and multi-person tracking, and briefly, on simulation for vineyards.

I am an affiliate researcher with the AI Institute for Next-Generation Food Systems, and I have principally led the development of AgML, the world’s largest software dedicated to agricultural machine learning data and models, since 2021. I’ve also been a member of the Plant AI and Biophysics Lab (advised by Mason Earles), where I’ve worked on improving data efficiency and generalizability of computer vision models for agricultural applications, as well as generative modeling of crops. Additionally, I have been a member of Project GEMINI, where I worked on procedural 3D crop modeling for sub-Saharan African crops.

In the more distant past, I was a member of the Information Ecosystems Lab at the University of Maryland (advised by Professor Cody Buntain) where I researched digital information sharing behaviors of U.S. and foreign politicians, with a focus on image content shared on social media.