Stay Informed:
Baskin Engineering COVID-19 Information and Resources
Campus Roadmap to Recovery
Zoom Links: Zoom Help | Teaching with Zoom | Zoom Quick Guide

AM Seminar: Decision Making and Control for Advanced Driver Assistance Systems using Deep Reinforcement Learning

Speaker Name: 
Subramanya Nageshrao
Speaker Title: 
Research Engineer
Speaker Organization: 
Ford Motor Company
Start Time: 
Monday, February 10, 2020 - 4:00pm
End Time: 
Monday, February 10, 2020 - 5:00pm
Location: 
Baskin Engineering 372
Organizer: 
Abhishek Halder

Abstract

Most of the industrial applications rely on classical model-free control, primarily PID. One of the major bottlenecks in using advanced learning-based methods (such as reinforcement learning) for controls is the lack of interpretability of the trained agent. In this talk, we present a methodology for translating a trained reinforcement learning agent into a set of simple and easy to interpret if-then rules by using the proven universal approximation property of the rules with fuzzy predicates. Proposed methodology combines the optimality of reinforcement learning with interpretability of the theory of approximate reasoning, thus making reinforcement learning-based solutions more accessible to industrial practitioners. The framework presented in this work has the potential to help address the fundamental problem in widespread adoption of reinforcement learning in industrial applications.

Bio

Subramanya Nageshrao received his Ph.D. degree from the Delft University of Technology, Delft, The Netherlands in 2016. Upon graduation, he worked as a researcher for TNO, and then as a post-doc at the University of Michigan. He is now a research engineer in the Ford Motor Company. His primary research interests include driving policy, reinforcement learning, and advanced controls.

Event Type: 
Event