Research Project Title:
Non-Line-of-Sight Obstacle Detection for Autonomous Vehicles
abstract:My proposed project will focus on developing the ability for autonomous vehicles to detect occluded obstacles. In my upcoming work, I will attempt to analyze shadows in camera feeds in order to anticipate and detect non-line-of-sight obstacles in well-illuminated environments. Once a shadow is detected, the manner in which these shadows change in a sequence of images will be used to deduct the motion of occluded objects. The work will first be evaluated on occluded objects around simulated corners. The results of this will then be fed into one of a Deep Learning, SVM, or Signals algorithm to generalize this approach to the real world. This generalized algorithm will be integrated into an autonomous wheelchair to conduct real-world experiments.
I have been interested in robotics and the autonomous vehicles space, for over six years. This project will allow me to develop the domain knowledge necessary to to excel in this field. I feel that my past internships at Uber, BMW, Microsoft Research, and the Carnegie Mellon Biorobotics Laboratory, as well as my enrollment in 6.141 and 6.036 have given me the necessary skills in autonomy and control to succeed with my upcoming research project.