Karnik Ram

Hello! I am a Research Associate in the Robotics Institute at Carnegie Mellon University and I am supervised by Prof. Kris Kitani. I am broadly interested in localization and mapping, and I am currently working on a generalizable indoor localization system for blind person navigation.

Previously, I was an MS by Research student at IIIT Hyderabad, supervised by K. Madhava Krishna in the Robotics Research Center, where I worked on improving the robustness of visual-inerital odometry algorithms in dynamic environments among others.

Even earlier, I worked as a student developer for MRPT as part of GSoC, and Navstik labs. I completed my bachelor's at SSN College of Engineering, Anna University in 2017.

Email | CV | Github | LinkedIn | Blog

What's new
  • June 2021: Our work on RP-VIO has been accepted for IROS 2021 in Prague Online.
  • December 2019: I served as the head student instructor for the Mobile Robotics course at IIIT-H.
  • July 2019: I participated in the ETH Robotics Summer School in Zurich.
  • June 2019: Our work INFER was accepted for IROS 2019 in Macau.
  • July 2018: I started as a master's student in the Robotics Research Center at IIIT-H.

RP-VIO: Robust Plane-based Visual-Inertial Odometry for Dynamic Environments
Karnik Ram, Chaitanya Kharyal, Sudarshan Harithas, K. Madhava Krishna  |  Spring 2020-21
In proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021.

We present a monocular visual-inertial odometry (VIO) system that uses only planar features and their induced homographies, during both initialization and sliding-window estimation, for increased robustness and accuracy in dynamic environments. We evaluate on diverse sequences, including our own highly-dynamic simulated dataset, and show significant improvement over a state-of-the-art monocular VIO algorithm in dynamic environments.

Project page

INFER: Intermediate Representations for Future Prediction
Shashank Srikanth, Junaid Ahmed Ansari, Karnik Ram, Sarthak Sharma, J. Krishna Murthy, K. Madhava Krishna  |  Spring 2019
In proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019.

We have developed an autoregressive model to accurately predict future trajectories of traffic participants (vehicles). We demonstrate that using semantics provides a significant boost and allows the model generalize to completely different datasets, collected across several cities, and also across countries where people drive on opposite sides of the road (left-handed vs right-handed driving).

Preprint | Video

CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks
Ganesh Iyer, Karnik Ram, J. Krishna Murthy, K. Madhava Krishna  |  Spring 2018
In proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018.

We developed a self-supervised deep network, CalibNet, capable of automatically estimating the 6-DoF rigid body transformation between a 3D LiDAR and a 2D camera in real-time. The network alleviates the need for any calibration targets, thereby reducing significant calibration efforts.

Preprint | Video

ARTPARK Robotics Challenge
Suraj Bonagiri, Viswanarayanan S, Sreeharsha P, Ashwin Rao, Karnik Ram  |  Summer 2021

Mentored and worked with a team of students to implement a janitorial robot to autonomously navigate and clean a washroom environment in simulation. The team has progressed to the top 4 out of 30 teams in the challenge and has been selected for the final round with funding to work on a realworld implementation.

Challenge page

Automatic Calibration of Sensor Extrinsics
Karnik Ram  |  Summer 2018

An end-to-end application with a graphical user interface for easily calibrating the extrinsics between range and visual sensors was developed during GSoC 2018. Automatic and target-less calibration algorithms based on plane-matching and line-matching were integrated into the app, allowing the calibration to be performed in any generic scene setting without the need for any specific targets.

Code | Video | Report

Direct Dense Image Registration
Karnik Ram, J. Krishna Murthy  |  Fall 2017

Estimated the camera motion between two frames by minimizing the photometric error between them. Implemented in matlab using a vanilla Levenberg-Marquardt non-linear least squares (approx.) solver.


Motion-based Camera-IMU Extrinsic Calibration
Karnik Ram, Kunal Chelani  |  Fall 2017

Implemented a pipeline to estimate the rigid body pose between an IMU and a camera by applying the Kabsch algorithm to their motion estimates. Based on Zachary Taylor and Juan Nieto's work on Motion-Based Calibration of Multimodal Sensor Arrays.

Report | Code

Automated Stock Counting Using a Quadcopter
Karnik Ram, Harish S, Apeksha Avinash  |  Winter 2016

Developed a visual odometry module based on optic flow for the localization of a custom-built quadcopter and incorporated it into the PX4 navigation stack, enabling autonomous indoor navigation. All the computations were performed on-board, on an Odroid XU4. A stock counting module was implemented using ArUco markers.

Report | Code

Motion Capture using a Kinect
Karnik Ram  |  Fall 2016

Used SimpleOpenNI to track body joint angles and mapped it to a model in blender. This was developed as a part of a body posture tracking project during my time as an intern at HTIC.

Code | Video

Person Tracking for a Drone
Karnik Ram  |  Summer 2016

Developed and evaluated a person tracking application for a drone using a CUDA accelerated monocular HOG detector, and another using disparity maps generated from a custom stereo rig. Both were tested on a Jetson TX1. This was developed during my time as an intern at Navstik Labs.

Visual Servoing of a Mobile Robot
Karnik Ram, Yash Oza  |  Spring 2016

Developed a simple navigation stack for controlling the motion of a differential drive mobile robot using visual feed-back from an overhead camera. The stack consisted of a color based localization module and a PID controller for issuing steering commands to the motors.

Code | Video

Low-Cost Flight Controller for a Quadcopter
Karnik Ram, Harish S, Aadithya V, Ashwin V, Harshwardhan  |  Fall 2015

Built and programmed a flight controller for stabilizing a custom built quadcopter, using the ATmega328. Utilized interrupt service routines, I2C comm, PWM and PID rate control loops.


Karnik Ram, Shankar S, Prashanth TV  |  Summer 2015

Developed an Android app that enabled students to share their course textbooks among each other easily. This app has got close to a thousand installations and has also been featured in a prominent weekly magazine, and in the top 10 of the Apps for Chennai contest.

Code | Store | Press | Press

The SSN App
Karnik Ram, Adithya J, Varun R, Muthu CT  |  Winter 2014

Ideated and developed an Android application to notify students and faculty about important events, announcements and other campus related information like bus routes and dining menus. It has close to two thousand users today and is the official app of SSN.

Code | Store | Appreciation

Built using Hugo and Jon's styling
Last updated: Dec, 2021