Search-based Planning for Higher-dimensional Robotic Systems

Prof. Maxim Likhachev
Robotics Institute, Carnegie Mellon University

April. 28, 2023 (Friday), 12:00 – 1:00 pm
In-person: Room 220, Building C

Abstract: Search-based Planning refers to planning by constructing a graph from systematic discretization of the state- and action-space of a robot and then employing a heuristic search to find an optimal path from the start to the goal vertex in this graph. This paradigm works well for low-dimensional robotic systems such as mobile robots and provides rigorous guarantees on solution quality. However, when it comes to planning for higher-dimensional robotic systems such as mobile manipulators, humanoids and ground and aerial vehicles navigating at high-speed, Search-based Planning has been typically thought of as infeasible. In this talk, I will describe some of the research that my group has done into changing this thinking.  In particular, I will focus on two different principles. First, constructing multiple lower-dimensional abstractions of robotic systems, solutions to which can effectively guide the overall planning process using Multi-Heuristic A*. Second, using offline preprocessing to provide online planning algorithms that provably guarantee to return solutions within a (small) constant time for repetitive planning tasks. I will present algorithmic frameworks that utilize these principles, describe their theoretical properties, and demonstrate their applications to a wide range of physical high-dimensional robotic systems.

Bio: Maxim Likhachev is an Associate Professor at Carnegie Mellon University, directing Search-based Planning Laboratory (SBPL), and a Senior Staff Software Engineer at Waymo. His group at CMU researches heuristic search, decision-making and planning algorithms, all with applications to the control of robotic systems including unmanned ground and aerial vehicles, mobile manipulation platforms, humanoids, and multi-robot systems. Maxim obtained his Ph.D. in Computer Science from Carnegie Mellon University with a thesis called “Search-based Planning for Large Dynamic Environments.” He has over 150 publications in top journals and conferences on AI and Robotics and numerous paper awards. His work on Anytime D* algorithm, an anytime planning algorithm for dynamic environments, has been awarded the title of Influential 10-year Paper at International Conference on Automated Planning and Scheduling (ICAPS) 2017, the top venue for research on planning and scheduling. Other awards include selection for 2010 DARPA Computer Science Study Panel that recognizes promising faculty in Computer Science and being on a team that won 2007 DARPA Urban Challenge and on a team that won the Gold Edison award in 2013.  Maxim founded RobotWits, a company devoted to developing advanced planning and decision-making technologies for self-driving vehicles and recently acquired by Waymo, and co-founded TravelWits, an online travel tech company that brings AI to make travel logistics easier. Finally, Maxim is an executive co-producer of regional Emmy-nominated The Robot Doctor TV series aimed at showing the use of mathematics in Robotics and inspiring high-school students to pursue careers in science and technology.

Formal methods for Cyber Physical Systems: State of the Art and Future Challenges

Prof. Necmiye Ozay

Electrical Engineering and Computer Science, University of Michigan

April. 14, 2023 (Friday), 12:00 – 1:00 pm

In-person: Room 220, Building C

Abstract: Modern cyber-physical systems, like high-end passenger vehicles, aircraft, or robots, are equipped with advanced sensing, learning, and decision making modules. On one hand these modules render the overall system more informed, possibly providing predictions into the future. On the other hand, they can be unreliable due to problems in information processing pipelines or decision making software. Formal methods, from verification and falsification to correct-by-construction synthesis hold the promise to detect and possibly eliminate such problems at design-time and to provide formal guarantees on systems’ correct operation. In this talk, I will discuss several recent advances in control synthesis and corner case generation for cyber-physical systems with a focus on scalability, and what role data and learning can play in this process. I will conclude the talk with some thoughts on challenges and interesting future directions.   Bio: Necmiye Ozay received her B.S. degree from Bogazici University, Istanbul in 2004, her M.S. degree from the Pennsylvania State University, University Park in 2006 and her Ph.D. degree from Northeastern University, Boston in 2010, all in electrical engineering. She was a postdoctoral scholar at the California Institute of Technology, Pasadena between 2010 and 2013. She joined the University of Michigan, Ann Arbor in 2013, where she is currently an associate professor of Electrical Engineering and Computer Science, and Robotics. Dr. Ozay’s research interests include hybrid dynamical systems, control, optimization and formal methods with applications in cyber-physical systems, system identification, verification & validation, autonomy and dynamic data analysis. Her papers received several awards. She has received the 1938E Award and a Henry Russel Award from the University of Michigan for her contributions to teaching and research, and five young investigator awards, including NSF CAREER, DARPA Young Faculty Award, ONR Young Investigator Award, and NASA Early Career Faculty Award. She is also a recent recipient of the Antonio Ruberti Young Researcher Prize from the IEEE Control Systems Society for her fundamental contributions to the control and identification of hybrid and cyber-physical systems.

Overview of the Dynamics, Control, and Systems Diagnosis Program at NSF

Prof. Eva Adnan Kanso

NSF Program Manager, Zohrab A. Kaprielian Fellow in Engineering, and Professor of Aerospace and Mechanical Engineering, University of Southern California

March. 3, 2023 (Friday), 1:15 – 2:00 pm

In-person: Room 220, Building C

Abstract: Prof. Kanso will present a brief overview of the Dynamics, Control, and Systems Diagnosis Program in the CMMI division at NSF, point out funding opportunities such as the EAGER, RAISE, and other mechanisms, and bring to your attention strategic priorities across the engineering directorate at NSF.

Bio: Eva Kanso joined the Division of Civil, Mechanical & Manufacturing Innovation (CMMI) of NSF in Fall 2021 as an IPA rotator from the University of Southern California, where she is a professor and the Z.H. Kaprielian Fellow in Aerospace and Mechanical Engineering. Prior to joining USC in 2005, Kanso held a two-year postdoctoral position in Computing and Mathematical Sciences at Caltech. She received a Ph.D. degree in 2003 and an M.S. degree in 1999 in Mechanical Engineering, as well as an M.A. degree in 2002 in Mathematics, all from the University of California at Berkeley. She obtained her Bachelor of Engineering degree from the American University of Beirut with distinction. Kanso held visiting positions at Princeton University in 2004, the Laboratoire LadHyX at the Ecole Polytechnique in 2015, the Courant Institute of Mathematical Sciences in 2016-2017, the Simons Foundation in 2016-2017, and the Ecole Supérieure de Physique et de Chimie Industrielles in 2021. Her research interests concern fundamental problems in the biophysics of cellular and subcellular processes and the physics of animal behavior, both at the individual and collection levels. A central theme in her work is the role of the mechanical environment, specifically the fluid medium and fluid-structure interactions, in shaping and driving biological functions.

Safety through Agility: What can you learn from Autonomous Racing?

Prof. Rahul Mangharam

Department of Electrical and Systems Engineering, University of Pennsylvania

Feb. 3, 2023 (Friday), 12:00 – 1:00 pm
In-person: Room 220, Building C

Abstract: Balancing performance and safety are crucial to deploying autonomous vehicles in multi-agent environments. In particular, autonomous racing is a domain that penalizes safe but conservative policies, highlighting the need for robust, adaptive strategies. Current approaches either make simplifying assumptions about other agents or lack robust mechanisms for online adaptation. In this talk we will explore research themes on perception, planning and control at the limits of performance. We explore:
(1) How to generate the most competitive agents who dynamically balance safety and assertiveness by using distributionally robust online adaptation;
(2) How to build the most efficient autonomous racecar with Multi-domain optimization across vehicle design, planning and control;
(3) How to combine previous system designs to auto-complete new designs with new requirements, and
(4) Understand the value of Cooperation in Multi-Agent Games.
We realize all our research in the https://f1tenth.org autonomous racecar platform that is 10th the size, but 10x the fun! The main takeaway from this talk is how you can get involved in very exciting research on safe autonomous systems. I will also present projects on AV Gokart that we are doing in the Autoware Center of Excellence for Autonomous Driving at Pennovation.

Bio: Rahul’s builds safe autonomous systems at the intersection of formal methods, machine learning and controls. He applies his work to safety-critical autonomous vehicles, urban air mobility, life-critical medical devices, IoT4Agriculture, and AI Co-designers for complex systems. He is the Penn Director for the Department of Transportation’s $14MM Mobility21 National University Transportation Center which focuses on technologies for safe and efficient movement of people and goods. Rahul received the 2016 US Presidential Early Career Award (PECASE) from President Obama for his work on Life-Critical Systems. He also received the 2016 Department of Energy’s CleanTech Prize (Regional), the 2014 IEEE Benjamin Franklin Key Award, 2013 NSF CAREER Award, 2012 Intel Early Faculty Career Award and was selected by the National Academy of Engineering for the 2012 and 2017 US Frontiers of Engineering. He has won several ACM and IEEE best paper awards in Cyber-Physical Systems, controls, machine learning, and education.
Website: https://www.seas.upenn.edu/~rahulm/