Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Stanford University

Towards Robust Human-Robot Interaction - A Quality Diversity Approach

Stanford University via YouTube

Overview

Explore the challenges and advancements in human-robot interaction through this Stanford seminar featuring Stefanos Nikolaidis, Assistant Professor in computer science at the University of Southern California. Delve into the application of quality diversity algorithms for generating diverse failure scenarios in human-robot interaction simulations. Learn about the development of new quality diversity algorithms that enhance scenario space exploration and their integration with generative models. Discover applications in procedural content generation and human preference learning. Gain insights into topics such as MapElites, diversity measures, gradient-based approaches, and benchmark domains in robotics and autonomous systems. This 45-minute talk, given on March 4, 2022, offers valuable knowledge for those interested in improving the robustness and efficiency of human-robot interaction systems.

Syllabus

Introduction
MapElites
Diversity Measures
MapElite
Measure Space Distortion
Failure Cases
Limitations
Map Elites
Gradients
The Hearthstone
Overcooked
Environment Generation
Video Game Levels
Gradient Information
Gradient Ascend
Gradient Arborescence
Benchmark Domains
Sample Images
pyrips
tutorials
learning human preferences
assembly task
robotics class
students

Taught by

Stanford Online

Reviews

Start your review of Towards Robust Human-Robot Interaction - A Quality Diversity Approach

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.