Raunak Bhattacharyya

513-D, Academic Complex East

Indian Institute of Technology, Delhi

Hauz Khas, New Delhi

Welcome to my website!

My research is centered around the goal of enabling autonomous systems to make decisions safely and effectively in uncertain, real-world environments. Some representative research directions include imitation learning from human demonstrations, joint human-AI decision making, planning missions for autonomous inspection, and safe learning in autonomous agents. Towards these research threads, I leverage tools from reinforcement learning, generative modeling, and robotics.

I am currently teaching a course on Deep Reinforcement Learning.

Brief Bio: Previously, I was a postdoc at Oxford working with Nick Hawes. I obtained my PhD from Stanford under the guidance of Mykel Kochenderfer. I completed my MS from Georgia Tech and my BTech from IIT Bombay.

News

Mar 15, 2025	Our paper on human-AI joint decision making has been accepted to the ICLR 2025 workshop on Human-AI Coevolution.
Mar 07, 2025	HRI 2025, Melbourne
Jan 31, 2025	Journal papers accpted for publication in Robotics and Autonomous Systems and Transportation Research Part F.

Selected Publications

HRI
Group Decision-Making in Robot Teleoperation: Two Heads are Better Than One

Duc-An Nguyen, Raunak Bhattacharyya, Clara Colombatto, and 3 more authors

In ACM/IEEE International Conference on Human-Robot Interaction (HRI), Melbourne, Australia, 2025

Abs Bib PDF

Operators working with robots in safety-critical domains have to make decisions under uncertainty, which remains a challenging problem for a single human operator. An open question is whether two human operators can make better decisions jointly, as compared to a single operator alone. While prior work has shown that two heads are better than one, such studies have been mostly limited to static and passive tasks. We investigate joint decision-making in a dynamic task involving humans teleoperating robots. We conduct a human-subject experiment with N=100 participants where each participant performed a navigation task with two mobiles robots in simulation. We find that joint decision-making through confidence sharing improves dyad performance beyond the better-performing individual (p < 0.0001). Further, we find that the extent of this benefit is regulated both by the skill level of each individual, as well as how well-calibrated their confidence estimates are. Finally, we present findings on characterising the human-human dyad’s confidence calibration based on the individuals constituting the dyad. Our findings demonstrate for the first time that two heads are better than one, even on a spatiotemporal task which includes active operator control of robots.
@inproceedings{10.5555/3721488.3721550, author = {Nguyen, Duc-An and Bhattacharyya, Raunak and Colombatto, Clara and Fleming, Steve and Posner, Ingmar and Hawes, Nick}, title = {Group Decision-Making in Robot Teleoperation: Two Heads are Better Than One}, year = {2025}, publisher = {IEEE Press}, booktitle = {ACM/IEEE International Conference on Human-Robot Interaction (HRI)}, pages = {489–500}, numpages = {12}, keywords = {human-robot interaction, joint decision-making, teleoperation}, location = {Melbourne, Australia}, series = {HRI '25}, }

Preprint

CC-VPSTO: Chance-Constrained Via-Point-based Stochastic Trajectory Optimisation for Safe and Efficient Online Robot Motion Planning

Lara Brudermüller, Guillaume Berger, Julius Jankowski, and 2 more authors

arXiv preprint arXiv:2402.01370, 2024

Bib PDF

@article{brudermuller2024cc,
  title = {CC-VPSTO: Chance-Constrained Via-Point-based Stochastic Trajectory Optimisation for Safe and Efficient Online Robot Motion Planning},
  author = {Bruderm{\"u}ller, Lara and Berger, Guillaume and Jankowski, Julius and Bhattacharyya, Raunak and Hawes, Nick},
  journal = {arXiv preprint arXiv:2402.01370},
  year = {2024},
}

ECMR

Difficulty-Aware Time-Bounded Planning Under Uncertainty for Large-Scale Robot Missions

Michal Staniaszek, Lara Brudermüller, Raunak Bhattacharyya, and 2 more authors

In European Conference on Mobile Robots (ECMR), 2023

Bib PDF

@inproceedings{staniaszek2023difficulty,
  title = {Difficulty-Aware Time-Bounded Planning Under Uncertainty for Large-Scale Robot Missions},
  author = {Staniaszek, Michal and Bruderm{\"u}ller, Lara and Bhattacharyya, Raunak and Lacerda, Bruno and Hawes, Nick},
  booktitle = {European Conference on Mobile Robots (ECMR)},
  year = {2023},
  organization = {IEEE},
}

IEEE Transactions

Modeling human driving behavior through generative adversarial imitation learning

Raunak Bhattacharyya, Blake Wulfe, Derek J Phillips, and 4 more authors

IEEE Transactions on Intelligent Transportation Systems, 2022

Bib PDF

@article{bhattacharyya2022modeling,
  title = {Modeling human driving behavior through generative adversarial imitation learning},
  author = {Bhattacharyya, Raunak and Wulfe, Blake and Phillips, Derek J and Kuefler, Alex and Morton, Jeremy and Senanayake, Ransalu and Kochenderfer, Mykel J},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  volume = {24},
  number = {3},
  pages = {2874--2887},
  year = {2022},
  publisher = {IEEE},
}