Education
2025
Albert-Ludwigs-Universität Freiburg
M.Sc.-Embedded Systems Engineering with specialisation in AI
2018
Jaypee Institute Of Information Technology
B.Tech-Electronics and Communication
Engineering
Work Experience
2019 – 2022
Junior Research Fellow
Centre For Airborne Systems
- Worked on project based on RADAR tracking and detection using Deep Neural Network architectures.
- Developed a single shot RADAR detector based on CNN model outperforming conventional techniques like CFAR.
Internships
2022 – present
Hiwi
Institute of Physiology, University of Freiburg
- Developing acquisition and simulation tools for neuroscience experiments, including VR systems for mice imaging and electrophysiological recordings of neuronal and behavior data.
2017 – 2018
Research Intern
IIIT-Delhi
- Implemented optimum frequency hopping strategy for wireless nodes giving better throughput while avoiding
jammers as compared to the naive approach using reinforcement learning.
Projects
Graph Neural Network based filtering method of Scene Graph
- Designed and trained GNN-based filtering method of scene graph before interfacing it with Large Language Models to reduce hallucinations.
Robot Air Hockey Challenge 2023
- Designed Model Predictive Control and Reinforcement Learning-based agent trained to play air hockey by controlling a 7DOF KUKA iiwa14 in MuJoCo based simulation game.
FreiCAR: Practical Autonomous Driving
- Designed controller and perception modules to navigate an RC car autonomously on the race track.
Single Shot Radar Target Detection and Localization using Deep Neural Network
- Designed single shot CNN-RNN based network for object detection in processed RD map.
Multi Modular Tracking using LSTM networks
- Designed LSTM-based filter, prediction, and association modules for tracking high-maneuvering airborne objects.
- The end-to-end GOSPA metric of our technique shows good improvement over conventional JPDA-IMM and GNN-IMM and does not require the knowledge of environment parameters like clutter density and detection probability.
Voice-Activated Vending Machine
- The project aims to replace the front desk cashier of food trucks and fast food joints with voice-activated vending machine, that can understand the order, checks for allergies, take payment, it takes help of facial recognition to remember customers thus increasing cost efficiency.
Quadcopter with auto leveling
- Developed PID algorithm and complementary filter code for quad copter capable of auto levelling.
Achievements
1st Place - Tree Segmentation Challenge, DL’22 Competition
3rd Place - Large Networks Track, DL’22 Competition
Winner (Automation & Optimizations) Voice AI Hardware Challenge (Hackster.io)
Publications
Modular Multitarget Tracking Using Long Short-Term Memory Networks Rishabh Verma, R. Rajesh, and M. S. Easwaran Journal of Aerospace Information Systems 0 0:0, 1-4
R. Verma, S. J. Darak, V. Tikkiwal, H. Joshi and R. Kumar , “Countermeasures Against Jamming Attack in Sensor Networks with Timing and Power Constraints,” in 11th International Conference on Communication Systems Networks (COMSNETS 2019: Poster) , India, Jan. 2019
D. Tm, R. Verma, R. Rajesh and S. Varughese, “Single Shot Radar Target Detection and Localization using Deep Neural Network,” 2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), Bangalore, India, 2022, pp. 1-9, doi: 10.1109/CONECCT55679.2022.9865801.