Aditya Narayanan

I am an Electrical and Computer Engineering student at The University of Texas at Austin. I work in Dr. Sandeep Chinchali's Swarm Robotics Lab, where I've worked on ML and robotics systems research.

I'm currently applying for a PhD in Machine Learning and Robotics, where I hope to work on efficient ML systems.

Email: adityan [at] utexas [dot] edu
CV  /  Google Scholar  /  Github  /  LinkedIn

profile photo

News

  • Oct 2024: I presented my work, PEERNet, at IROS 2024 in Abu Dhabi! Check out the blog post I wrote about PEERNet here.
  • Sep 2024: I began working as a Machine Learning Engineer at Synthefy.
  • Aug 2024: My paper, "PEERNet: An End-to-End Profiling Tool for Real-Time Networked Robotic Systems" was accepted to IROS 2024! Check out the arxiv version here.
  • Sep 2023: I completed an internship at Mathworks, where I was part of the Engineering Development Group.

Research

My research aim is to combine systems engineering and modern machine learning to build efficient Robotic and ML systems.

Currently, I'm working on generating synthetic timeseries data using diffiuson models. Specifically, I'm aiming to improve the zero-shot generalization of diffusion models for synthetic timeseries data using contrastively-learned embeddings of timeseries data.

In the past, I've worked on networked robotic systems research, where I explored efficient deployment of robotic systems through systematic benchmarking and profiling. Our work on this thread, PEERNet, was accepted at IROS 2024, where I presented the project in an oral-pitch and poster session.

PEERNet: An End-to-End Profiling Tool for Real-Time Networked Robotic Systems
Aditya Narayanan, Pranav Kasibhatla, Minkyu Choi, Po-han Li, Ruihan Zhao, Sandeep Chinchali
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024

Online Foundation Model Selection in Robotics
Po-han Li, Oyku Selin Toprak, Aditya Narayanan, Ufuk Topcu, Sandeep Chinchali
Under review, 2024

This website is based on Jon Barron's source code. His website can be found here.