Maulik Bhatt

I am a Ph.D. student in the Department of Mechanical Engineering at UC Berkeley, advised by Prof. Negar Mehr. I am part of the ICON Lab. I started my Ph.D. at UIUC in the Coordinated Science Laboratory, and moved to UC Berkeley with my advisor in January 2024.

In Summer 2025, I interned at Amazon Robotics, where I worked on learning-based motion planning for Proteus, a fully autonomous warehouse robot.

Previously, I graduated from IIT Bombay with an interdisciplinary dual degree (B.Tech in Aerospace Engineering + M.Tech in Systems and Control Engineering). I received the Panasonic Scholarship, Undergraduate Research Award, and Technical Hostel's Commendation.

Portrait of Maulik Bhatt

Research

I am interested in developing autonomous robots that can work alongside humans and other robots. My research focuses on enabling agents to reason about other agents in the environment and effectively coordinate their motion. To this end, I have worked on approaches grounded in diffusion models and game theory, developing scalable algorithms that achieve real-time performance and robust multi-agent coordination.

Selected Publications

MIMIC-D overview figure

MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies

Dayi Dong, Maulik Bhatt, Seoyeon Choi, Negar Mehr

Submitted to ICRA, 2026

arXiv Code Website

MIMIC-D is a framework for multi-agent coordination using only local observations that effectively captures multi-modality in expert data.

Human-robot motion experiments with restricted visual fields

Understanding and Imitating Human-Robot Motion with Restricted Visual Fields

Maulik Bhatt, Honghao Zhen, Monroe Kennedy III, Negar Mehr

IROS, 2025

arXiv Video Website

Our algorithm estimates agents' observation space and imitates their behavior under partial observability.

MultiNash-PF trajectory game example

MultiNash-PF: A Particle Filtering Approach for Computing Multiple Local Generalized Nash Equilibria in Trajectory Games

Maulik Bhatt, Iman Askari, Yue Yu, Ufuk Topcu, Huazhen Fang, Negar Mehr

IROS, 2025

arXiv

Our method reduces multi-modal equilibrium computation time by up to 50%.

Maximum-entropy dynamic game illustration

Maximum-Entropy Multi-Agent Dynamic Games: Forward and Inverse Solutions

Negar Mehr, Mingyu Wang, Maulik Bhatt, Mac Schwager

Transactions on Robotics, 2023

Paper Video

We introduce noisy Nash equilibrium and provide forward and inverse methods for learning agent objectives from demonstrations.

Constrained multi-agent trajectory optimization experiment

Efficient Constrained Multi-Agent Trajectory Optimization using Dynamic Potential Games

Maulik Bhatt, Yixuan Jia, Negar Mehr

IROS, 2023

arXiv Video Code

Our constrained trajectory planner is 20 times faster than prior state-of-the-art methods.

Autonomous multi-agent racing experiment setup

RAPID: Autonomous Multi-Agent Racing using Constrained Potential Dynamic Games

Yixuan Jia, Maulik Bhatt, Negar Mehr

European Control Conference, 2023

arXiv Video Code

Our algorithm outperforms prior methods in autonomous multi-agent racing.

Earlier Publications

Rigid body pose estimation result

Discrete-time Rigid Body Pose Estimation based on Lagrange-d'Alembert Principle

Maulik Bhatt, Srikant Sukumar, Amit K Sanyal

Journal of Nonlinear Science

Paper

This is the first discrete-time pose estimator proven almost globally asymptotically stable.

Multi-rate rigid body attitude estimation illustration

Asymptotically Stable Optimal Multi-rate Rigid Body Attitude Estimation based on Lagrange-d'Alembert Principle

Maulik Bhatt, Amit K Sanyal, Srikant Sukumar

CDC 2020 and Journal of Geometric Mechanics

CDC Paper JGM Paper

The method proves almost global asymptotic stability in discrete-time with multi-rate measurements.

Obstacle-avoiding Hilbert curve visualization

Modification of Hilbert's Space-Filling Curve to Avoid Obstacles: A Robotic Path-Planning Strategy

Anant Joshi, Maulik Bhatt, Arpita Sinha

Indian Control Conference, 2019

Paper Experiment 1 Experiment 2

Developed an exploration algorithm for unknown environments with obstacle avoidance.

Autonomous drone landing on moving vehicle

Autonomous Landing of Drones on Moving Ground Vehicles

Maulik Bhatt, David Saussie

Implemented a dynamic image-based visual servo control strategy for safe autonomous drone landing on moving ground vehicles.

Hobbies

Climbing, Hiking, Cooking, Flute