Webinar (New Date): Safety and robustness guarantees with learning in the loop - Speaker: Prof. Dr. Nikolai Matni, UPenn - Organizer: IEEE joint Control, Robotics, and Cybernetics Chapter of the Vancouver Section

---

---

Please note new date of the event.

 

Dear All, 

The event is postponed to November 26th, 4pm due to organizational reasons. We apologize for any inconvenience. To those already registered the new link will be emailed. There is still time to register.

This free webinar is open to everyone. Please feel free to invite your friends and colleagues. We would appreciate everyone to register using the link from this notice. The link to webinar will be shared to all registrants prior to the event.

Thank you,

IEEE Joint CS - RAS - SMC Chapter of Vancouver Section

_____________________________________________________________________________________________________________________

Title: Safety and robustness guarantees with learning in the loop

Speaker: Prof. Dr. Nikolai Matni, University of Pennsylvania

 

Abstract:
We present recent progress towards developing learning-based control strategies for the design of safe and robust autonomous systems. Our approach is to recognize that machine learning algorithms produce inherently uncertain estimates or predictions, and that this uncertainty must be explicitly quantified (e.g., using non-asymptotic guarantees of contemporary high-dimensional statistics) and accounted for (e.g., using robust control and optimization) when designing safety critical systems. In the first half of the talk, we consider the optimal control of an unknown dynamical system, and show that by integrating modern tools from high-dimensional statistics and robust control, we can provide end-to-end finite data robustness, safety, and performance guarantees for learning and control. In the second half of the talk, motivated by vision based control of autonomous vehicles, we consider the complementary problem of controlling a known dynamical system for which partial state information, such as vehicle position, can only be extracted from high-dimensional data, such as an image. Our approach is to learn a perception map from high-dimensional data to partial-state observation, as well as its corresponding error profile, and then design a robust controller. We show that jointly learning the perception map and error profile can be cast as a robust regression problem, and that this allows us to treat the perception map as a noisy position sensor, which can then be integrated into a novel robust control synthesis procedure that has favorable safety and generalization properties. We conclude with our thoughts on future challenges and opportunities in the broad area of safe learning and control.

Bio:
Nikolai Matni is an Assistant Professor in the Department of Electrical and Systems Engineering at the University of Pennsylvania, where he is also a member of the Department of Computer and Information Sciences (by courtesy), the GRASP Lab, the PRECISE Center, and the Applied Mathematics and Computational Science graduate group. Prior to joining Penn, Nikolai was a postdoctoral scholar in EECS at UC Berkeley. He has also held a position as a postdoctoral scholar in the Computing and Mathematical Sciences at Caltech. He received his Ph.D. in Control and Dynamical Systems from Caltech in June 2016. He also holds B.A.Sc. and M.A.Sc. in Electrical Engineering from the University of British Columbia, Vancouver, Canada. His research interests broadly encompass the use of learning, optimization, and control in the design and analysis of safety-critical and data-driven cyber-physical systems. Nikolai was awarded the IEEE CDC 2013 Best Student Paper Award (first ever sole author winner) and the IEEE ACC 2017 Best Student Paper Award (as co-advisor).

 

---

---

---

---

Thursday November 26th, 4pm-5:30pm

Webinar. Free Event. Registration required.

Webinar Link Info to be emailed upon registration. 

---