Tue, Sep 26, 2023 @ 12:00 PM - 01:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Lars Lindemann, Assistant Professor, USC Thomas Lord Department of Computer Science
Talk Title: Verifiable Control of Learning-Enabled Autonomous Systems
Abstract: Autonomous systems research shows great promise to enable many future technologies such as autonomous driving, intelligent transportation, and robotics. Accelerated by the computational advances in machine learning and AI, there has been tremendous success in the development of learning-enabled autonomous systems over the past years. At the same time, however, new fundamental questions arise regarding the safety and reliability of these increasingly complex systems that operate in dynamic and unknown environments. In this talk, I will provide new insights and discuss exciting opportunities to address these challenges.
In the first part of the talk, we focus on reasoning about uncertainty of learning-enabled components in an autonomy stack. Existing model-based techniques are usually too conservative or do not scale. I will instead advocate for conformal prediction as an accurate and computationally lightweight alternative. We will first use conformal prediction to design predictive runtime verification algorithms that quantify uncertainty of learning-enabled systems. These algorithms can effectively compute the probability of a task violation during the execution of the system. I will then show how to design probabilistically safe motion planning algorithms in dynamic environments using such uncertainty quantification. While existing data-driven approaches quantify uncertainty heuristically, we quantify uncertainty in a distribution-free manner. Using ideas from adaptive conformal prediction, we can even deal with distribution shifts, i.e., when test and training distributions are different. We illustrate the method on a self-driving car and a drone that avoids a flying frisbee. In the second part of the talk, I present an optimization framework to learn safe control laws from expert demonstrations. In most safety-critical systems, expert demonstrations in the form of system trajectories that showcase safe system behavior are readily available or can easily be collected. I will propose a constrained optimization problem with constraints on the expert demonstrations and the system model to learn control barrier functions for safe control. Formal guarantees are provided in terms of the density of the data and the smoothness of the system model. We then discuss how we can account for model uncertainty and hybrid system models, and how we can learn safe control laws from high-dimensional sensor data. Two case studies on a self-driving car and a bipedal robot illustrate the method.
Biography: Lars Lindemann is currently an Assistant Professor at the Department of Computer Science at the University of Southern California where he leads the Safe Autonomy and Intelligent Distributed Systems (SAIDS) lab. Prior to joining USC, he was a Postdoctoral Fellow in the Department of Electrical and Systems Engineering at the University of Pennsylvania from 2020 and 2022. He received the Ph.D. degree in Electrical Engineering from KTH Royal Institute of Technology in 2020. Prior to that, he received the M.Sc. degree in Systems, Control and Robotics from KTH in 2016 and two B.Sc. degrees in Electrical and Information Engineering and in Engineering Management from the Christian-Albrecht University of Kiel in 2014. His current research interests include systems and control theory, formal methods, and autonomous systems. Lars received the Outstanding Student Paper Award at the 58th IEEE Conference on Decision and Control and the Student Best Paper Award (as a co-author) at the 60th IEEE Conference on Decision and Control. He was a finalist for the Best Paper Award at the 2022 Conference on Hybrid Systems: Computation and Control and for the Best Student Paper Award at the 2018 American Control Conference.
Host: Dr. Rahul Jain, email@example.com
Webcast: Webcast: https://usc.zoom.us/j/99747592573?pwd=YmNGYkJCK1V5SEQwcU1jVllwQVFwZz09
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher