Hello, I am Athindran. I am currently a machine learning engineer in Behavior Planning at Aurora Innovation in Pittsburgh, PA.
What do I do?
I was a sixth-year PhD student in the Department of Electrical and Computer Engineering at Princeton University. I am fortunate to be advised by Prof. Peter Ramadge. My research was focused on designing safety fallback mechanisms for autonomous systems with provable guarantees. I utilize various tools, ranging from classical control to model-based optimization, to enable these filters to satisfy desirable properties such as smooth handover and robustness to imperfect models. My general research focus over the past few years has been on applying optimization and learning methods to control applications.
Resume Github Profile Google Scholar Old Website
Projects with Code
Fast, smooth, and safe Probabilistic Safety with GP
Talks and Presentations
| Control theory and practice | Deep learning |
|---|---|
| ECE General Exam | ORFE Deep Learning Theory Seminar |
| ACC 2021 | CSML Reading Group GNN part 1 |
| CISS 2021 | CSML Reading Group GNN part 2 |
Journal Papers
- A. R. Kumar, K. -C. Hsu, P. J. Ramadge and J. F. Fisac, “Fast, Smooth, and Safe: Implicit Control Barrier Functions through Reach-Avoid Differential Dynamic Programming,” in IEEE Control Systems Letters, doi: 10.1109/LCSYS.2023.3292132 Link to paper
- Liang Heng, Athindran Ramesh Kumar and Grace Xingxin Gao, Location Hash: Private Proximity Detection Using Partial GPS Information, IEEE Transactions on Aerospace and Electronic Systems. Dec. 2016. Link to paper
Conference and Workshop Papers
- Ting-Han Fan, Athindran Ramesh Kumar, Peter J. Ramadge. “Safety Control for Prime Focus Spectrograph.” In 2022 56th Annual Conference on Information Sciences and Systems (CISS) (pp. 269-274). IEEE Link to paper
- Athindran Ramesh Kumar*, Sulin Liu*, Jaime F. Fisac, Ryan P. Adams, Peter J. Ramadge. “ProBF: Probabilistic Safety Certificates with Barrier Functions.” Presented at SafeRL workshop at NeurIPS 2021. Link to paper
- Athindran Ramesh Kumar, Balaraman Ravindran, and Anand Raghunathan. “Pack and detect: Fast object detection in videos using region-of-interest packing.” Proceedings of the ACM India Joint International Conference on Data Science and Management of Data. 2019. Link Featured in TechXplore
For a complete list, please visit Google Scholar
Work Experience
Software Engineer, Behavior Planning at Aurora Innovation. Oct 2023 - Present
Development and fail-safe testing of motion control/fault management techniques for self-driving tractor-trailers
Machine learning modeling for motion planning of self-driving vehicles
Software Intern, Control at Aurora Innovation. May - Aug 2022
Implementation of a feature to improve longitudinal control of self-driving trucks
Research Intern, Nokia Bell Labs. June - Aug 2021
Reinforcement learning for a robotic arm
Research Engineer, Center of Excellence in Wireless Technology. April 2016 - June 2018
Frequency assignment techniques and path loss models for rural environments
Tech Intern, Google StreetView. May - August 2014
Carrier phase positioning with GPS to achieve centimeter accurate positioning of StreetView cars
Outside Work
Back in my undergraduate days, I played quite a bit of tennis as a serious extra-curricular and represented the institute at the inter-IIT sports meet and the inter-collegiate sports fest. I was also part of the gold medal winning team of Tapti hostel in Schroeter 2012. I was also into app development in my undergraduate days. I helped build Android apps for the institute technical and cultural festivals, Shaastra and Saarang.
Contact
You can reach me through email at r[dot]athindran[at]gmail[dot]com