Mechanical and Civil Engineering Seminar

Mechanical and Civil Engineering Seminar Series

Title: Adaptable, Scalable, and Certifiable Localization and Mapping for Autonomous Mobile Robots

Abstract: In this talk I will present recent advances in localization and mapping for mobile robots that achieve the precision, computational efficiency, and operational reliability needed for real-time control and autonomy in diverse environments. Central to our approach is the insight that the localization and mapping pipeline is composed of decision-making processes that must be informed by environment characteristics made through observations to maximize performance and resiliency. In essence, these decision-making processes enable adaptive behaviors that act as proactive safeguards to achieve long-term operational reliability and performance across different operating environments. I will show that localization and mapping algorithms designed around this key insight are at the precipice of achieving the level of safety and consistency required for the deployment of autonomous robots in diverse, challenging environments. I will also examine the current and future role of contraction theory within the context of developing certifiable localization and mapping approaches and the potential for modeling these algorithms as a feedback combination to guide future development and analysis. Open research questions on scalability, adaptability, and the role of learning will also be discussed.

Bio: Brett Lopez is an Assistant Professor in the Mechanical and Aerospace Engineering Department at the University of California, Los Angeles. He received his Ph.D. and S.M. from MIT with a specialization in controls and robotics, and his B.S. in Aerospace Engineering from UCLA. He is recipient of the UCLA Faculty Career Development Award, the UCLA MAE Outstanding Teaching Award, and the NSF Graduate Research Fellowship. Prior to joining UCLA, he was a postdoctoral fellow at NASA-JPL where he led the development of NASA-JPL's drone autonomy stack for the DARPA Subterranean Challenge. His broad research interests include nonlinear and optimal control theory; localization and mapping; trajectory optimization; and autonomy with application to aerospace systems. He is particularly interested in developing principled approaches that improve the reliability and performance of autonomous aerospace systems operating in diverse or uncertain conditions.

NOTE: At this time, in-person Mechanical and Civil Engineering Lectures are open to all Caltech students/staff/faculty/visitors.