Ruta Desai

I am a Research Scientist and Tech Lead at Meta Reality Labs Research in Redmond. At Reality Labs, I lead an embodied AI team whose vision is to develop contextual Augmented Reality (AR) systems that can extend their users' capabilities. We adopt an embodied AI framing for contextual AR assistance. In particular, we model the AR system as an intelligent agent that perceives the user and their environment through various sensors and outputs actions in service of the user's goals, aligned with the user's preferences.

Prior to joining Meta, I obtained my PhD at the Robotics Institute, Carnegie Mellon University working with Stelian Coros and Jim McCann. For my thesis, I devised human-AI systems that enabled casual users to build and program robots — towards increasing accessibility of robotics. In the past, I have also had not-so-brief stints in the area of human motor control and biomechanical simulations with Hartmut Geyer and Jessica K. Hodgins.


Please get in touch if you're interested in applying for an internship at the Reality Labs.


Email: rutadesai[at]fb.com

CV  /  Thesis  /  Google Scholar

Research Highlights

Embodied AI for AR

My current research focuses on leveraging representation learning, planning, and reinforcement learning techniques — combined with an embodied AI framing — for developing AR assistance models. Our embodied AI framing allows us to break down the problem of computing AR/VR assistance into two main parts — a) Inferring the goals and context of the user given a sequence of multi-modal sensor observations and b) Learning goal-conditioned system-action policies.

Goal and Context Inference for AR Assistance

We leverage self-supervised learning and multi-modal sensors (egocentric video + IMU) to understand user's goals and context such as current task and actions in AR.


ICCV EPIC Workshop 2021


Towards Goal-Conditioned Assistance in VR

We compute assistance policies for house-cleaning task in VR and evaluate it at-scale by deploying these policies in a web-based version of the AI Habitat simulator.


Preprint available!


Episodic Memory Question Answering for AR Assistance

Can we develop egocentic AI models that can respond to a user's queries about their spatiotemporal history?



Coming soon at CVPR 2022!
In collaboration with Georgia Tech.


Human-AI Systems for Robot Design

My PhD research aimed at making robotics more accessible to casual users by reducing the domain knowledge required in designing and building robots. Towards this end, I developed several interactive human-in-the-loop AI systems that enable the design of desired structure and behavior of diverse robots.

Interactive AI System for Articulated Robot Design

This tool allows novices to create custom articulated robots such as manipulators and walking robots. It supports both manual and automatic design, and enables design testing using physics-based simulation.


ICRA 2017

Featured on Techcrunch and ACM!

Try it out!


Interactive AI System for Non-articulated Robot Design

This tool enables novices to create smart IoT devices with embedded sensors using digital fabrication. It automatically finds assembly-aware packing of components within the device, and exports necessary geometries for 3D printing.


UIST 2018


Semantic Design of Expressive Robot Behaviors

Can we design complex robot behaviors such as robot walking based on the emotion that the behavior evokes?



CHI 2019

Best paper award!
In collaboration with Autodesk Research, Toronto.


Publications

Embodied AI for AR

Egocentric Scene Context for Human-centric Environment Understanding from Video
Tushar Nagarajan, Santhosh Kumar Ramakrishnan, Ruta Desai, James Hillis, and Kristen Grauman
In review at European Conference on Computer Vision (ECCV) (2022).                         

arXiv coming soon!

Episodic Memory Question Answering
Samyak Datta, Sameer Dharur, Vincent Cartellier, Ruta Desai, Mukul Khanna, Dhruv Batra, and Devi Parikh
Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, USA (2022).                         

arXiv coming soon!

How You Move Your Head Tells What You Do: Self-supervised Video Representation Learning with Egocentric Cameras and IMU Sensors
Satoshi Tsutsui, Ruta Desai, and Karl Ridgeway
International Conference on Computer Vision (ICCV), EPIC Workshop (2021).                         

PDF | bib | Video

Optimal Assistance for Object-Rearrangement Tasks in Augmented Reality
Benjamin Newman, Kevin Carlberg, and Ruta Desai
arXiv Preprint (2020).                         

PDF | bib | Video

Towards Inferring Cognitive State Changes from Pupil Size Variations in Real World Conditions
Naga Venkata Kartheek Medathati, Ruta Desai, and James Hillis
ACM Symposium on Eye Tracking Research and Applications (ETRA), Stuttgart, Germany (2020).                         
PDF | bib

Human-AI Collaborative and Mixed-Initiative Systems, Robotics

Cross-Domain Imitation Learning via Semantic Skills
Karl Pertsch, Ruta Desai, Franziska Meier, Vikash Kumar, Dhruv Batra, and Akshara Rai
Submitted to International Conference on Machine Learning (ICML) (2022).                         

arXiv coming soon!

Geppetto: Enabling Semantic Design of Expressive Robot Behaviors
Ruta Desai, Fraser Anderson, Justin Matejka, Stelian Coros, James McCann, George Fitzmaurice, and Tovi Grossman
ACM Conference on Human Factors in Computing Systems (CHI), Glasgow, UK (2019).                         
Best paper award (top 1%) [Details]
PDF | bib | Video | Fastforward | Supplementary (PDF)

Assembly-aware Design of Printable Electromechanical Devices
Ruta Desai, James McCann, and Stelian Coros
ACM User Interface Software and Technology Symposium (UIST), Berlin, Germany (2018).                           
PDF | bib | Video | Fastforward

Skaterbots: Optimization-based Design and Motion Synthesis for Robotic Creatures with Legs and Wheels
Moritz Geilinger, Roi Poranne, Ruta Desai, Bernhard Thomaszewski, and Stelian Coros
ACM Transactions on Graphics (Proc. ACM SIGGRAPH), Vancouver, Canada (2018).                           

PDF | bib | Video

Automatic Design of Task-specific Robotic Arms
Ruta Desai, Margarita Safonova, Katharina Muelling, and Stelian Coros
ICRA Workshop on Autonomous Robot Design, Brisbane, Australia (2018).                           

arXiv | bib | Slides | Video

Interactive Co-Design of Form and Function for Legged Robots using the Adjoint Method
Ruta Desai, Beichen Li, Ye Yuan, and Stelian Coros
International Conference on Climbing and Walking Robots (CLAWAR), Panama city, Panama (2018).  

Best technical paper (second place)  
arXiv Preprint | Video

Computational Abstractions for Interactive Design of Robotic Devices
Ruta Desai, Ye Yuan, and Stelian Coros
IEEE International Conference on Robotics and Automation (ICRA), Singapore (2017).                          
PDF | bib | Slides | Video | Code
Robot models for fabrication: car, walking robot


3D Printing Pneumatic Device Controls with Variable Activation Force Capabilities
Marynel Vazquez, Eric Brockmeyer, Ruta Desai, Chris Harrison and Scott E. Hudson
ACM Conference on Human Factors in Computing Systems (CHI), Seoul, Korea, (2015).

PDF | bib | Poster | Video


Human Motion Modeling, Human Motor Control, Biomechanics
A Simple Model of Skill Acquisition in a Dynamic Balance Task
Ruta Desai and Jessica K. Hodgins
Dynamic Walking, Columbus, USA (2015).

PDF | bib | Poster | Video
Virtual Model Control for Dynamic Lateral Balance
Ruta Desai, Hartmut Geyer, and Jessica K. Hodgins
IEEE International Conference on Humanoid Robots (Humanoids), Madrid, Spain (2014).

PDF | bib
Integration of an Adaptive Swing Control into a Neuromuscular Human Walking Model
Seungmoon Song, Ruta Desai, and Hartmut Geyer
IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan (2013).

PDF | bib | Video

Muscle-Reflex Control of Robust Swing Leg Placement
Ruta Desai and Hartmut Geyer
IEEE International Conference on Robotics and Automation (ICRA), Karlsruhe, Germany (2013).

PDF | bib

Robust Swing Leg Placement under Large Disturbances
Ruta Desai and Hartmut Geyer
IEEE International Conference on Robotics and Biomimetics (ROBIO), Guangzhou, China (2012).

PDF | bib | Video

Patents and Articles
Generative design techniques for robot behavior
Fraser Anderson, Stelian Coros, Ruta Desai, Tovi Grossman, Justin Matejka, George Fitzmaurice
US Patent 20200030988 A1 (2020).                                                                                                                 

PDF

Robust swing leg controller under large disturbances
Ruta Desai and Hartmut Geyer
US Patent 20150066156 A1 (2014).                                                                                                                 

PDF

A Brief Overview of Human and Robot Motor Learning
Ruta Desai
RI CMU Technical Report                                                                                                                 

PDF

Academic Service

Conference Program Committee Chair and Reviewer
  • Program committee, ACM UIST 2019, 2020.
  • Associate Chair (AC), ACM CHI 2020, 2021.
  • Reveiwer for IEEE IROS, IEEE ICRA, ACM TOCHI, ACM UIST, ACM CHI, ACM GI, IEEE WHC (2015-2021).
Talks

Outreach

Women in Technology

I am always looking to support and contribute towards encouraging women in science and technology. In the past:

  • I have led roadshows and volunteered in teaching middle school girls at Technights at CMU. We have smashed computers, fought combats in code, and have even gazed stars through apps!
  • I helped organize OurCS 2015, a conference to encourage undergraduate women in research. I was also a part of Google Anita Borg Scholars Alumni Planning committee.

Selected Press

  • Techcrunch, New toolkit makes it easy to drag and drop your own robot, 2017.
  • ACM Communications, Robot Design For Dummies, 2017.
  • EurekAlert, CMU's interactive tool helps novices and experts make custom robots, 2017.
  • NSF, Graduate Student Earns Prestigious Scholarships for Women - Ruta Desai, 2012.
  • CMU SCS, Five SCS Students Named Siebel Scholars, 2012.

Last updated: March 2022

Webpage adapted from Jon Barron.