Shivang Patel


2020 - Present:     PhD, Computer Science; West Virginia University (Morgantown, WV)

2017 - 2019:           MEng, Robotics; University of Maryland (College Park, MD)

2013 - 2017:           BEng, Mechatronics; G. H. Patel College of Engineering (Vallabh Vidhyanagar, India)


Randhawa, Z. A., Patel, S., Adjeroh, D. A., & Doretto, G. (2022, December). Learning Representations for Masked Facial Recovery. In Advances in Visual Computing: 17th International Symposium, ISVC 2022, San Diego, CA, USA, October 3–5, 2022, Proceedings, Part I (pp. 22-35). Cham: Springer International Publishing.

Patel, S., Hariharan, S., Dhulipala, P., Lin, M. C., Manocha, D., Xu, H., & Otte, M. (2021, May). Multi-Agent Ergodic Coverage in Urban Environments. In 2021 IEEE International Conference on Robotics and Automation (ICRA) (pp. 8764-8771). IEEE.

Arul, S. H., Sathyamoorthy, A. J., Patel, S., Otte, M., Xu, H., Lin, M. C., & Manocha, D. (2019). LSwarm: Efficient collision avoidance for large swarms with coverage constraints in complex urban scenes. IEEE Robotics and Automation Letters, 4(4), 3940-3947.

Sheth, S., Ajmera, A., Sharma, A., Patel, S., & Kathrecha, C. (2018). Design and development of intelligent AGV using computer vision and artificial intelligence. In Soft Computing: Theories and Applications (pp. 337-349). Springer, Singapore.

Technical Skills

Proficient in C++, Python, ROS, ROS 2, Gazebo, Ignition, openCV, Tensorflow, Keras, PyTorch, GIT, Docker and Linux.

Experience (Academic)

Graduate Research Assistant, Vision and Learning Lab, WVU

Graduate Research Assistant, Aerospace Department, UMD

Graduate Research Assistant, Mechanical Department, UMD

Experience (Open Source)

Navigation 2


Self Driving Toy Car using Reinforcement Learning Technique

Smart AGV

Evaluation of Adversarial Attacks and Defenses for DNN

Traffic sign detection using feature detection methods and Machine learning routines

Simulating the Lane Departure Warnings through Lane Detection in a Self Driving car.

Trajectory estimation through Visual Odometry.