Towards Robust Human-Robot Interaction: A Quality Diversity Approach
Paul G. Allen School via YouTube
Learn the Skills Netflix, Meta, and Capital One Actually Hire For
Live Online Classes in Design, Coding & AI — Small Classes, Free Retakes
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore a cutting-edge approach to improving human-robot interactions in this 56-minute lecture by Stefanos Nikolaidis from USC. Delve into the concept of quality diversity for automatic scenario generation in HRI, learning how to discover diverse failure scenarios that encompass both environmental factors and human actions. Examine the application of standard quality diversity algorithms in shared autonomy, and discover a new class of these algorithms that significantly enhance scenario space exploration. Investigate the integration of these advanced algorithms with generative models to create complex, realistic scenarios. Gain insights into practical applications, including procedural content generation and human preference learning. This talk, presented at the Paul G. Allen School, offers valuable knowledge for researchers and practitioners in robotics, artificial intelligence, and human-computer interaction fields.
Syllabus
Towards Robust HRI: A Quality Diversity Approach (Stefanos Nikolaidis, USC)
Taught by
Paul G. Allen School