Abstract

With robots poised to enter our daily environments, they will not only need to work for people, but also learn from them. An active area of investigation in the robotics, machine learning, and human-robot interaction communities is the design of teachable robots that can learn interactively from humans. To refer to these research efforts, we use the umbrella term Human-Interactive Robot Learning (HIRL). In the last two years, we began consolidating what defines HIRL in terms of long, medium, and short-term research problems and what the different communities can contribute to those problems. With this third installment of the HIRL workshop, we aim at further consolidating this community and, specifically this year, discuss how the recent widespread of Large Language Models (LLMs) will impact the teaching of robots and explore the opportunities and challenges presented by robots’ nature of embodied agents.