Sri Anumakonda

I'm an autonomous vehicle researcher building in the intersection between computer vision and self-driving cars.

Current: student researcher at UIUC, member @Masason Foundation, doing generative modelling research to create adversarial systems to train more robust autonomous vehicle policies. updates coming soon!

Prev @tks.world where I worked with Shell, the United Nations, and Instacart. Also am one of the youngest certified self-driving car engineers in the world, was featured on Udacity for the work I'm doing.

Email  /  Linkedin  /  Twitter  /  Github  /  Medium /  CV /  2021 Annual Letter

My primary research interests are in the field of autonomous vehicles, more specifically towards computer vision for vision-based autonomy. You can find some of my projects in this space below. This is just an overview of the work I'm doing. For a full list, please check my Github.

Leveraging CUDA + OpenCV + PyTorch's C++ API (LibTorch) using TorchScript to run semantic segmentation at the highest FPS possible

Leveraged Reinforcement Learning algorithms to help train a self-driving agent to drive in a highway environment [using discrete controls].

Used Deep Convolutional Networks to control self-driving steering, read more than 60 papers in the space, and met some really smart people from the wayve.ai + comma.ai team!

Using DC-GANs to create synthetic data that can be used to train + validate the robustness of autonomous vehicles. End goal is to apply to extrapolate the data pool we have for adverse driving scenarios/any situations where limited data is available.

Implemented this paper from scratch with just my knowledge of Python and stackoverflow. Focusing on managing spatio-temporal image data for successful training of lane detection. Lanes don't change every single frame, so why can't we take in a few input frames and be able to successfully predict lane lines? Note: Github repository is not up to date as I have been unable to locate some of the files as part of training but the ConvLSTM model and training loop is created (and formatted nicely!).

Used my knowledge throughout the Udacity Self-Driving Nanodegree [from perception and sensor fusion of LiDAR and radar sensors to polynomial trajectory generation] to create my capstone project; an autonomous vehicle capable of driving in simulation (using waypoitns). I built trajectory algorithms, localization algorithnms, and kalman filters to name a few of the projects I built!

Creating a custom lane detection pipeline w/ Gaussian Filters + Polynomial fitting along with object detection using sliding windows w/ SVMs with the use of pure Machine Learning.

Want them in your inbox? Add your email here.

• January 2022
• December 2021

Template from Jon Barron