Engineering AI Systems and AI for Engineering: Language, Compositionality, and Physics in Learning-Driven Robot Autonomy
May 29 @ 3:30 pm - 5:00 pm
How can we transform artificial intelligence (AI) and machine learning capabilities into reliable, autonomous robotic systems? How can we engineer AI systems within budget constraints, certify them with respect to stakeholder requirements, and ensure that they meet the needs of the end user? Answering these questions necessitates new engineering methodologies for AI systems, as well as AI algorithms that leverage the unique characteristics of engineering problems. In this talk, I will begin by presenting methods that integrate foundation models such as large language models and vision-language-action models with frameworks and algorithms for verifiable sequential decision-making. I will then present compositional approaches to reinforcement learning, which enable independent development and testing of separate learning-enabled modules and facilitate the reliable deployment of their compositions in practice. Finally, I will present control-oriented learning algorithms that combine data with prior physics knowledge, yielding learning-enabled systems that effectively control hardware after mere minutes of data collection and training. Experiments on robotic hardware, ranging from manipulators to ground vehicles to hexacopters, demonstrate the important role that these algorithms play in the fast and reliable transfer of learning-driven algorithms to their target, real-world operating <a href="http://environments.
Co-sponsored” target=”_blank” title=”environments.
Co-sponsored”>environments.
Co-sponsored by: Ryozo Nagamune | nagamune@mech.ubc.ca | Dejan Kihas | kihas@<a href="http://ieee.org
Speaker(s):” target=”_blank” title=”ieee.org
Speaker(s):”>ieee.org
Speaker(s): Cyrus Neary
Agenda:
Event Start: 3:30pm
Talk and Q&A: 3:40pm
Event End: 5:00pm
Bldg: MacLeod Building , Room MCLD 3038
, 2356 Main Mall, Vancouver , British Columbia, Canada, V6T 1Z4, Virtual: https://events.vtools.ieee.org/m/559041