Udit Singh Parihar

Deep Learning and SLAM Researcher

OLA Electric

Biography

Hey! I am currently at OLA Electric working on 3D scene representation of end-to-end autonomous driving agents and Mapping and Localization. Our work on deep feature matching has achieved a silver medal in the Kaggle Image Matching Challenge. I have been working on porting PyTorch model to the TensorRT for faster inference on resource-constraint devices and developing ROS2 wrapper around the deep learning pipeline.

Previously, I have done my master’s from IIITH from Robotics Research Center where I have been working on the intersection of SLAM, 3D computer vision, and deep learning with Prof Madhava Krishna. Our work on robust pose graph SLAM has been published at the ICRA conference and our work on Robust feature matching has been presented at the IROS conference. These works targets improving SLAM performance in feature-less regions and improving correspondence matching in high illumination and viewpoint variations.

Download my resumé.

Interests

SLAM / State Estimation
Differentiable Computer Vision
Optimization
Robotics

Education

MS by Research in CSE with specialization in Robotics, 2021
International Institute of Information Technology, Hyderabad
B.Tech in Mechanical, 2018
Indian Institute of Technology Jodhpur

Experience

Computer Vision and SLAM Research Engineer

OLA Electric

Jul 2021 – Jan 2023 Bangalore

Developed an end to end autonomous driving agent using cameras, GPS and IMU sensors. Ported the agent from Carla simulator to NuScenes Dataset.
Converted the pytorch model to TensorRT and developed a ROS wrapper to run on real Mahindra E2O car achieving final control prediction at 25 HZ, in a zero shot paradigm.
Won the silver medal in the Kaggle Image Matching Challenge 2022 by developing an Ensemble of Deep feature matching algorithm of SuperGlue and LoFTR.
Extended the Lidar based mapping and localization LeGO-LOAM SLAM for the Velodyne and Ouster lidars and ported ROS1 to ROS2 in C++.
Trained Self Supervised Depth estimation PackNet-SfM on Indian driving dataset and on Carla simulator dataset.

Graduate Research Assistant

Robotics Research Center, IIITH

Aug 2018 – Jul 2021 Hyderabad

Worked on the intersection of SLAM, Computer Vision, Deep Learning, and Robotics. Developed robust pose graph constraints using scene semantics and developed rotation invariant deep feature descriptors for feature matching.
Published in ICRA and IROS conferences.

Featured Publications

Udit Singh Parihar, Aniket Gujarathi, Kinal Mehta, Satyajit Tourani, Sourav Garg, Michael Milford, K. Madhava Krishna

October 2020 In IROS 2021

RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching

We achieve high viewpoint invariance local feature matching using rotation homographies during training and converting perspective image to orthographic for feature matching.

PDF Code Project Video

Sai Shubodh Puligilla, Satyajit Tourani, Tushar Vaidya, Udit Singh Parihar, Ravi Kiran Sarvadevabhatla, K. Madhava Krishna

April 2018 In ICRA 2020

Topological Mapping for Manhattan-like Repetitive Environments

Used semantics understanding to assist loop closure detection and localization in SLAM framework in challenging warehouse environment. Incorporated topological edges in a pose graph optimization.

PDF Code Video