About Me

I am a PhD student at the University of Washington, advised by Dieter Fox. Previously, I was a researcher at NUS under David Hsu. My interests are in Human-Robot Interaction, Computer Vision, Natural Language Processing, and Machine Learning. I graduated with a Bachelors in Computer Eng. from NUS. During my stint as an undergrad, I spent a year at Stanford, and also interned at a YCombinator AR startup.

Contact: mshr ( at ) cs.uw.edu




ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks.
Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk,
Winson Han, Roozbeh Mottaghi, Luke Zettlemoyer, Dieter Fox
Computer Vision and Pattern Recognition (CVPR) 2020.
Website | Abstract | PDF | VideoCode | BibTex


exp_setup_v2.jpgInteractive Visual Grounding of Referring Expressions for Human-Robot Interaction.
Mohit Shridhar, David Hsu
Robotics: Science & Systems (RSS) 2018.
Abstract | PDF | VideoCode | Poster | Slides | BibTeX

rafflesXPose: Reinventing user interaction with flying cameras.
Ziquan Lan, Mohit Shridhar, David Hsu, Shengdong Zhao. 
Robotics: Science & Systems (RSS) 2017.
Best Systems Paper Award in Memory of Seth Teller
AbstractPDF | Video | Slides | BibTeX



INGRESS: Interactive Visual Grounding of Referring Expressions.
Mohit Shridhar, Dixant Mittal, David Hsu
International Journal of Robotics Research (IJRR) 2020.
To appear
PDF (coming soon)


liveframe_davidFree-Viewpoint Video Reconstruction for Immersive Telepresence 
Mohit Shridhar
Bachelor of Engineering Thesis, Dept. of Electrical and Computer Engineering 2016.
NUS 30th Annual Faculty Innovation and Research Award
PDF | Video



Meta California
Computer Vision & Graphics Engineer, Intern
Jan 2015 – Dec 2015
Worked on VI-SLAM and Holographic Skype for AR Headset (Hololens & MagicLeap competitor).
Part of CEO’s ensemble for building demo content during Series B ($50M round)

HopeTechnik Singapore
Robotics Engineer, Intern
May 2014 – Aug 2014
Worked on AGVs for transporting medical supplies inside hospitals
Built a multi-map planner for navigation across multiple floors

Engineering Design and Innovation Center (NUS) – Singapore
Researcher, Intern
May 2013 – Aug 2013
Built a functioning tribometer using just 3D-printed and laser-cut parts.
Autodesk University Panorama 2013 Finalist



shield_slam_small-e1505654738992.jpgShield SLAM (2015)   
Monocular SLAM for Android devices.
Paper | Code

dense_semantic-e1509871384650.pngDense-Semantic SLAM (2017) 
Combining Monocular SLAM with Dense Captioning for object retrieval

dropout_smallHiggs Boson Detection Challenge (2015)   
Deep-learning for classifying Higgs Boson to tau-tau signal events
Paper | PosterCode


multimapMulti-Map Manager 
(2014)   Video | Code
ROS package for managing multiple static maps (e.g: different floors)

oculusOculus-Rift Gazebo Navigator (2014)    Video | Code
Joystick based navigation tool for FPS navigation in Gazebo

quadsTextured Quads (2016)    Code
Rviz plugin for displaying images and videos

tascaTASCA (2013)    Video | Code
Java-based todo-list application

ardo2.jpgArduino Oscilloscope (2013)    Code
Cheap alternative to digital oscilloscopes


Some of my collaborative work has been featured in:

tc-techcrunch-e1508071918323.png             ted-logo-fb.png             IEEE-Spectrum.Horizontal              gazebo_hor             autodesk-university-2016-logo-2-line-color-black.png


My Erdos number is at most three.  But unfortunately my Erdos–Bacon–Sabbath number is undefined.

I am a fan of films, science fiction, and Oxford commas.