Magazine article AI Magazine

The 2015 AAAI Fall Symposium Series Reports

Magazine article AI Magazine

The 2015 AAAI Fall Symposium Series Reports

Article excerpt

This article contains the reports of the AI for Human-Robot Interaction, Cognitive Assistance in Government and Public Sector Applications, Deceptive and Counter-Deceptive Machines, Self-Confidence in Autonomous Systems, and Sequential Decision Making for Intelligent Agents symposia, which were held November 12-14, 2015 in Arlington, Virginia.

**********

The Association for the Advancement of Artificial Intelligence presented the 2015 Fall Symposium Series on Thursday through Saturday, November 12-14, 2015, at the Westin Arlington Gateway in Arlington, Virginia. The titles of the six symposia were as follows: AI for Human-Robot Interaction, Cognitive Assistance in Government and Public Sector Applications, Deceptive and Counter-Deceptive Machines, Embedded Machine Learning, Self-Confidence in Autonomous Systems, and Sequential Decision Making for Intelligent Agents. This article contains the reports from five of the symposia.

AI for Human-Robot Interaction

Human-robot interaction (HRI) is a broad community encompassing robotics, artificial intelligence (AI), human-computer interaction (HCI), psychology, and social science. In this meeting, we sought to bring together and strengthen the subset of the HRI community that is focused on the AI challenges inherent to HRI. As a field, HRI aims to develop robots that are intelligent, autonomous, and capable of interacting with, modeling, and learning from humans--goals that are shared at the core of AAAI. While general HRI work is seen across a variety of venues, AI-HRI serves as a gathering point for the Al-focused community within HRI.

The central purpose of AI-HRI is to share the most exciting research in this area while cultivating a vibrant, interconnected research community. We built on the success of the community-building accomplished by last year's AI-HRI symposium with the introduction of a heavier emphasis on sharing cutting-edge research results and devoting more time to the presentation and discussion of current work in the field. Accordingly, AI-HRI featured 10 keynote lectures, 24 short paper presentations, and 10 long paper presentations.

A major theme of the symposium included plan understanding and negotiation between humans and robots. The contributions surrounding this theme focused on constructing systems capable of recognizing human intent and using it as a heuristic for symbolic and motion planning, performing open world reference resolution, recognizing the purpose of objects in a scene during task execution, adapting to plan breakdowns, generating precise language for task-oriented dialogue, and performing preference-based task allocation and scheduling across human-robot teams. A second major theme involved introducing autonomy to socially assistive robots, particularly in educational or therapeutic settings. Multiple contributed papers addressed issues of autonomously promoting social collaboration between children, generating effective academic curriculums for tutoring robotics, developing personalized approaches to reducing pain anxiety in children, and moderating multiparty interactions.

A diverse array of keynote speakers presented their latest work on a list of topics spanning intelligent interface design, activity recognition, learning from demonstration, motion planning, task understanding, manipulation, reinforcement learning, smart controls for medical robotics, and human-robot collaboration. Themes introduced by these keynotes spurred discussion regarding the development of proper evaluations for autonomous robot systems that interact with humans, as it is often intractable to simulate the human presence for such work and it is often infeasible to collect hundreds of samples for large-scale analysis. It became clear that participants harbor a variety of sometimes conflicting viewpoints about expectations and framing for Al-focused HRI work, but all share the same goal of broadening HRI's reach into the spotlight of each of the many fields it depends upon for fulfilling its ultimate goal: understanding and developing autonomous systems that interact with humans in meaningful and positive ways. …

Search by... Author
Show... All Results Primary Sources Peer-reviewed

Oops!

An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.