I am an assistant professor in the ECE Department at the University of Southern California, where I lead the Safe and Intelligent Autonomy lab. Before joining USC, I spent a year as a Research Scientist at Waymo (formerly known as Google’s Self-Driving Car project).
We are looking for undergraduate and graduate students to join our research group. If you are interested in robotics, control, and/or machine learning, consider joining us!
I am broadly interested in robotics and autonomous systems. Specifically, my research focuses on understanding how machine learning methods can be combined with classical, model-based planning and control methods with the goal of:
(a) enabling robots to make intelligent decisions in a data-efficient manner, especially when they rely on perception and vision sensors;
(b) assuring robot safety while it relies on learning for decision-making.
somilban AT usc DOT edu
New paper on providing safety guarantees for DeepReach. The scalability of DeepReach along with the proposed verification algorithm allows us to compute high-confidence safe sets for high-dimensional systems.
New paper on quickly updating safety assurances for an autonomous system online as the system or the environment factors change.
We have released the code for DeepReach. You can check it out here.