Manan Tayal

Hi! I am Manan, a Researcher working on problems at the intersection of Control, Optimization and Machine Learning, with a focus on safety enforced decision-making in dynamical systems. Developing methods that integrate learning with formal guarantees to ensure constraint satisfaction and robust performance in uncertain, data-driven environments.

I am PhD Scholar at Centre for Cyber Physical Systems, Indian Institute of Science (IISc) Bangalore, working on Safe Robot Learning in the Stochastic Robotics Lab under the guidance of Prof. Shishir N. Y. Kolathaya and Prof. Pushpak Jagtap.

I am actively collaborating with Prof. Somil Bansal at Stanford University and Prof. Andrew Clark at Washington University.

I completed my B.Tech from Indian Institute of Technology Bombay (IITB) in 2021.

Click here for my detailed CV .

Follow me on Google Scholar, X (earlier twitter) and LinkedIn to keep informed with my latest research and projects.

News

May 01, 2025	Our work titled A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems, has been accepted at the 42nd International Conference on Machine Learning (ICML) 2025, Vancouver, Canada! Check out the project page.
Sep 17, 2024	I am thrilled to announce that our paper, BiRoDiff: Diffusion policies for bipedal robot locomotion on unseen terrains, has been accepted at the Indian Control Conference (ICC) 2024, Bhopal, India! Check out the project page.
Jul 20, 2024	Our recent work titled Learning a Formally Verified Control Barrier Function in Stochastic Environment, has been accepted to 63rd IEEE Conference on Decision and Control (CDC) 2024, Milan, Italy! Check out the project page.
Mar 02, 2024	I am thrilled to announce that my paper, Polygonal Cone Control Barrier Functions (PolyC2BF) for safe navigation in cluttered environments, has been accepted at the European Control Conference (ECC) 2024, Stockholm, Sweden!
Jan 26, 2024	Two of our papers Control Barrier Functions in Dynamic UAVs for Kinematic Obstacle Avoidance: A Collision Cone Approach and Collision Cone Control Barrier Functions: Experimental Validation on UGVs for Kinematic Obstacle Avoidance are accepted at the American Control Conference (ACC) 2024, Toronto, Canada!

Selected Publications

ICML

A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems

Manan Tayal^*, Aditya Singh^*, Shishir Kolathaya, and Somil Bansal

In International Conference on Machine Learning (ICML), 2025

arXiv Bib Code Website

@inproceedings{tayal2025physics,
  title = {A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems},
  author = {Tayal, Manan and Singh, Aditya and Kolathaya, Shishir and Bansal, Somil},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025}
}

CDC

Learning a Formally Verified Control Barrier Function in Stochastic Environment

Manan Tayal, Hongchao Zhang, Pushpak Jagtap, Andrew Clark, and Shishir Kolathaya

In 2024 IEEE 63rd Conference on Decision and Control (CDC), 2024

DOI arXiv Bib Code Website

@inproceedings{tayal2024learning,
  author = {Tayal, Manan and Zhang, Hongchao and Jagtap, Pushpak and Clark, Andrew and Kolathaya, Shishir},
  booktitle = {2024 IEEE 63rd Conference on Decision and Control (CDC)},
  title = {Learning a Formally Verified Control Barrier Function in Stochastic Environment},
  year = {2024},
  pages = {4098-4104},
  keywords = {Training;Jacobian matrices;Sufficient conditions;Filters;Heuristic algorithms;Neural networks;Control systems;Safety;Collision avoidance;Autonomous vehicles},
  doi = {10.1109/CDC56724.2024.10886052}
}

ACC

Control Barrier Functions in Dynamic UAVs for Kinematic Obstacle Avoidance: A Collision Cone Approach

Manan Tayal, Rajpal Singh, Jishnu Keshavan, and Shishir Kolathaya

In 2024 American Control Conference (ACC), 2024

DOI arXiv Bib Website

@inproceedings{tayal2024control,
  author = {Tayal, Manan and Singh, Rajpal and Keshavan, Jishnu and Kolathaya, Shishir},
  booktitle = {2024 American Control Conference (ACC)},
  title = {Control Barrier Functions in Dynamic UAVs for Kinematic Obstacle Avoidance: A Collision Cone Approach},
  year = {2024},
  pages = {3722-3727},
  doi = {10.23919/ACC60939.2024.10644548},
}