I am a Ph.D. student at the Paul G. Allen School of Computer Science and Engineering at the University of Washington, advised by Byron Boots. The primary focus of my research is to enable robots to safely operate in the real world while performing a diversity of tasks with minimal human intervention. I approach this by combining the strengths of planning & control with data-driven techniques. Specifically, my research topics include integrating model-predictive control with reinforcement learning, imitation learning for accelerated motion planning and differentiable trajectory optimization.

Before transferring to University of Washington, I spent a year as a Ph.D. Robotics student at School of Interactive Computing, Georgia Tech, prior to which I was a Robotics Engineer at Near Earth Autonomy, Inc. working on motion planning for UAVs. In 2017, I worked as a researcher at The Air Lab at The Robotics Institute, Carnegie Mellon University with Sanjiban Choudhury and Sebastian Scherer, focusing on reinforcement and imitation learning for robot motion planning. I graduated my M.S in Robotic Systems Development from RI in 2016. Before that, I received my B. Tech in Mechanical Engineering from Indian Institute of Technology, Varanasi.

I had the amazing opportunity to spend Fall 2020 and Summer 2019 as an intern at NVIDIA Seattle Robotics Lab working with Dieter Fox, Fabio Ramos and Byron Boots.

When not busy with research, you'll catch me doing stand-up and improv comedy or practicing Capoeira.

Curriculum Vitae (Updated December 2021).

Journal Publications

Leveraging Experience in Lazy Search
Autonomous Robots, 2021

M. Bhardwaj, S. Choudhury, B. Boots, S. Srinivasa
[Publication] [Arxiv]

Data-driven Planning via Imitation Learning
International Journal on Robotics Research, 2017

S. Choudhury, M. Bhardwaj, S. Arora, A. Kapoor, G. Ranade, S. Scherer and D. Dey
(Finalist for Paper of the Year) [Publication] [Arxiv]

Conference Publications

STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation
Conference on Robot Learning (CoRL), 2021

M. Bhardwaj, B. Sundaralingam, A. Mousavian, N. Ratliff, D. Fox, F. Ramos, B. Boots (Selected for Oral Talk - 6% Acceptance) [Proceedings][Arxiv] [Website] [Codebase][Poster]

Blending MPC & Value Function Approximation for Efficient Reinforcement Learning
International Conference on Learning Representations (ICLR), 2021

M. Bhardwaj, S. Choudhury, B.Boots [Arxiv]

Information Theoretic Model Predictive Q-Learning
Learning for Dynamics and Control, 2020

M. Bhardwaj, A. Handa, D.Fox, B.Boots
[Proceedings] [Arxiv] [Website]

Differentiable Gaussian Process Motion Planning
International Conference on Robotics and Automation, 2020

M. Bhardwaj, B. Boots and M. Mukadam
[Proceedings] [Arxiv] [Website] [Talk]

Leveraging Experience in Lazy Search
Robotics:Science and Systems, 2019

M. Bhardwaj, S. Choudhury, B. Boots and S. Srinivasa
[Proceedings] [Arxiv] [Presentation] [Poster] [Talk]

Learning Heuristic Search via Imitation
Conference on Robot Learning (CoRL), 2017

M. Bhardwaj, S. Choudhury and S. Scherer
[Proceedings] [Arxiv] [Website] [Presentation] [Talk]

Real-time dynamic singularity avoidance while visual servoing of a dual-arm space robot
Advances in Robotics (AIR), 2015

P. Mithun, V.V. Anurag, M. Bhardwaj, S.V. Shah