Learning complex robotic behaviors with optimal control - Munich AI Lectures
EVENTS |
Learning complex robotic behaviors with optimal control
Ludovic Righetti (NYU) | Munich AI Lectures | 18. June 2024, 17:00 – 18:00 CET
Location: Arcisstr. 21, 80333 Munich, Room 0790 (ground floor)
Ludovic Righetti
To the lecture series
More info on Prof. Righetti's work: https://engineering.nyu.edu/faculty/ludovic-righetti
Ludovic Righetti is an Associate Professor in the Electrical and Computer Engineering Department and in the Mechanical and Aerospace Engineering Department at the Tandon School of Engineering of New York University. He is also a member of the Center for Urban Science and Progress.
He leads the Machines in Motion Laboratory, where his research focuses on the planning and control of movements for autonomous robots, with a special emphasis on legged locomotion and manipulation. He is more broadly interested in questions at the intersection of decision-making, automatic control, optimization, applied dynamical systems and machine learning and their application to physical systems.
About the talk
Nonlinear model predictive control (MPC) is a reliable technology to generate a variety of robotic behaviors, from flying robots to humanoids. While MPC is a rigorous framework to generate, in principle, any kind of behaviors from a single algorithm, major limitations remain. For example, current approaches do not allow easy inclusion of multi-modal sensing, especially visual and force feedback, and algorithms struggle to optimize in real-time multi-contact behaviors necessary for complex manipulation or locomotion. On the other hand, learning-based methodologies, which heavily rely on offline compute, do not seem to struggle with these issues.
In this talk, I will present our recent work tackling those problems with a particular eye towards unifying learning and numerical optimal control. First, I will argue for the benefits of “textbook” numerical optimization methods to develop reliable solvers. Then I will discuss how to include multi-modal sensing and accelerate the generation complex behaviors through a mixture of machine learning and online optimization. Since the algorithms we design are intended for real applications that could change how we organize our societies, I will end the presentation with a broader discussion on the impacts of robotics research on society and the role engineers ought to play.
---
On a monthly basis, Munich AI Lectures invite top-level AI researchers to give a glimpse into their work and the future of AI. The Munich AI Lectures are a joint initiative of the baiosphere, Bavarian Academy of Science and Humanities (BAdW), Helmholtz Munich, Ludwig Maximilian University of Munich (LMU), Technical University of Munich (TUM), AI-HUB@LMU, ELLIS Chapter Munich, Konrad Zuse School of Excellence in Reliable AI (relAI), Munich Center for Machine Learning (MCML), Munich Data Science Institute (MDSI) at TUM, and Munich Institute of Robotics and Machine Intelligence (MIRMI).
The lectures consist of a short presentation followed by a Q&A to enable a lively discussion with our speakers. Each lecture lasts about one hour and will be streamed live on Munich AI Lectures' YouTube Channel. Recordings will be available afterwards.