Dhruv Shah

I am a graduate student in EECS at UC Berkeley, where I am advised by Sergey Levine and Jitendra Malik. I am a part of the Berkeley Artifical Intelligence Research Lab (BAIR) and 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 Carnegie Mellon University, Imperial College London and the University of Sydney.

CV / Github / Twitter / LinkedIn


  • [May 2020]  Our work on hybrid control for aerial manipulation was accepted to RSS 2020 (pre-print coming soon)
  • [Apr 2020]  Presenting our work on ingredients of real-world RL as a Spotlight at ICLR 2020, virtually!
  • [Dec 2019]  I'm attending NeurIPS @ Vancouver, let's meet!
  • [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


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

arXiv / Talk / Virtual Presentation   (Spotlight Talk)

Swarm Aggregation Without Communication and Global Positioning

Dhruv Shah, Leena Vachhani
Robotics and Automation Letters (RA-L), 2019

Also at 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