Dhruv Shah

I am a graduate student in EECS at UC Berkeley and a student researcher at Google Brain Robotics, where I am advised by Sergey Levine. I am a part of the Berkeley Artifical Intelligence Research Lab (BAIR) and Berkeley Deep Drive (BDD). My research is supported by the Berkeley Fellowship for Graduate Study.

Earlier, I graduated with honors from IIT Bombay, where I received the Undergraduate Research Award 2019 and the Institute Academic Prize 2017-18. I have also been fortunate to spend time at Google Research, Carnegie Mellon University, Imperial College London and the University of Sydney.

CV / Scholar / Twitter / LinkedIn


  • [Nov 2021]  New pre-print on combining geometric costmaps with learned models out on arXiv
  • [Nov 2021]  I'll be presenting RECON in beautiful London at CoRL 2021, please stop by if you're attending
  • [Nov 2021]  New pre-print on using skill-centric state abstractions out on arXiv
  • [Oct 2021]  Check out this blog post by Sergey on data-driven robot learning, featuring some of my recent research
  • [Sep 2021]  Our paper on goal-directed exploration on mobile robots was accepted as an Oral Talk to CoRL 2021
  • [May 2021]  I'll be spending the summer at Google Brain Robotics, interning with Brian Ichter and Alex Toshev
  • [Apr 2021]  New pre-print on deploying robots in novel, unstructured environments for goal-directed exploration
  • [Feb 2021]  Our paper on navigating to visual goals in the real-world was accepted to ICRA 2021
  • [May 2020]  Our paper on hybrid control for aerial manipulation was accepted to RSS 2020
  • [Jan 2020]  Our paper on analyzing ingredients of real-world RL for robots was accepted to ICLR 2020
  • [Aug 2019]  I graduated from IIT Bombay, receiving the Undergraduate Research Award
  • [May 2019]  I'll be interning at the Australian Centre for Field Robotics over Summer 2019
  • [Apr 2019]  paper on projection design for source separation accepted to ICIP 2019
  • [Apr 2019]  I'll be joining UC Berkeley at BAIR as a PhD student in Fall 2019
  • [Mar 2019]  awarded the INAE Travel Grant to present at ICRA 2019, Montréal
  • [Jan 2019]  paper on swarm aggregation without communication will appear in RA-L and ICRA 2019
  • [Nov 2018]  awarded the INAE Travel Grant to present at GlobalSIP 2018, Anaheim
  • [Sep 2018]  paper on designing constrained projections for CS accepted to GlobalSIP 2018
  • [Aug 2018]  awarded the Institute Academic Prize 2017-18
  • [May 2018]  I'll be interning at Dyson Robotics Lab, Imperial College London over Summer 2018
  • [Mar 2018]  paper on 3D mapping in nuclear sites submitted to JFR
  • [Dec 2017]  paper on radiation localization accepted to WM2018


Hybrid Imitative Planning with Geometric and Predictive Costs in Off-road Environments

Nitish Dashora, Daniel Shin, Dhruv Shah, Henry Leopold, David Fan, Ali Agha-Mohammadi, Nicholas Rhinehart, Sergey Levine

Deep Reinforcement Learning Workshop at NeurIPS 2021
Robot Learning Workshop at NeurIPS 2021


Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning

Dhruv Shah, Peng Xu, Yao Lu, Ted Xiao, Alexander Toshev, Sergey Levine, Brian Ichter

Deep Reinforcement Learning Workshop at NeurIPS 2021


Rapid Exploration for Open-World Navigation with Latent Goal Models

Dhruv Shah, Benjamin Eysenbach, Nicholas Rhinehart, Sergey Levine

Conference on Robot Learning (CoRL) 2021   (Oral Talk)
Workshop on Never-Ending Reinforcement Learning at ICLR 2021   (Contributed Talk)

Blog Post / arXiv / Talk @ CoRL / Talk @ ICLR / Dataset

ViNG: Learning Open-World Navigation with Visual Goals

Dhruv Shah, Benjamin Eysenbach, Gregory Kahn, Nicholas Rhinehart, Sergey Levine

International Conference on Robotics and Automation (ICRA), 2021

arXiv / Video

Aerial Manipulation Using Hybrid Force and Position NMPC Applied to Aerial Writing

Dimos Tzoumanikas, Felix Graule, Qingyue Yan, Dhruv Shah, Marija Popovic, Stefan Leutenegger

Robotics: Science and Systems (RSS), 2020

arXiv / Talk / Cool Demos

The Ingredients of Real World Robotic Reinforcement Learning

Henry Zhu, Justin Yu, Abhishek Gupta, Dhruv Shah, Kristian Hartikainen, Avi Singh, Vikash Kumar, Sergey Levine

International Conference on Learning Representations (ICLR), 2020   (Spotlight Talk)
Workshop on Never-Ending Reinforcement Learning at ICLR 2021   (Contributed Talk)

Blog Post / arXiv / Talk / Virtual Presentation

Swarm Aggregation Without Communication and Global Positioning

Dhruv Shah, Leena Vachhani

Robotics and Automation Letters (RA-L), 2019
International Conference on Robotics and Automation (ICRA), 2019

Projection Design for Compressive Source Separation using Mean Errors and Cross-Validation

Dhruv Shah, Ajit Rajwade
International Conference on Image Processing (ICIP), 2019

Designing Constrained Projections for Compressed Sensing: Mean Errors and Anomalies with Coherence

Dhruv Shah, Alankar Kotwal, Ajit Rajwade
Global Conference on Signal and Information Processing (GlobalSIP), 2018

Combining 3D Mapping and Radiation Source Localization in Nuclear Sites

Weikun Zhen, Dhruv Shah, Michael Lee, Matthew Hanczor, Sebastian Scherer
Under Review

Multi-Agent Strategies for Pommerman

CS747: Foundation of Intelligent & Learning Agents

DPAC: Digitally Programmable Analog Computer

EE344: Electronics Design Laboratory

The IITB Mars Rover Project