AAAI 2022 Spring Symposia

Submissions

We welcome contributions focused on understanding, modeling, and improving the efficacy of (a) communicating proficiency from human to robot and (b) communicating intent from a human to a robot.

We are requesting 2 page (position) and 6 page (regular) papers using the AAAI Symposium Series format. Anonymization is not required.

Regular papers should focus on research results. All submissions will be peer-reviewed and authors of accepted papers will be asked to do either a short or long podium presentation. At least one author of each accepted paper must register for the workshop.

We will send acceptance notifications by January 15.

Papers will appear in the workshop proceedings.

Submission Deadline: January 7, 2022, 23:59 Anywhere on Earth (AoE), via Easy Chair: https://easychair.org/conferences/?conf=sss22

Workshop Description

The proposed symposium focuses understanding, modeling, and improving the efficacy of (a) communicating proficiency from human to robot and (b) communicating intent from a human to a robot. For example, how should a robot convey predicted ability on a new task? How should it report performance on a task that was just completed? How should a robot adapt its proficiency criteria based on human intentions and values?

Communities in AI, robotics, HRI, and cognitive science have addressed related questions, but there are no agreed upon standards for evaluating proficiency and intent-based interactions. This is a pressing challenge for human-robot interaction for a variety of reasons. Prior work has shown that a robot that can assess its performance can alter human perception of the robot and decisions on control allocation. There is also significant evidence in robotics that accurately setting human expectations is critical, especially when proficiency is below human expectations. Moreover, proficiency assessment depends on context and intent, and a human teammate might increase or decrease performance standards, adapt tolerance for risk and uncertainty, demand predictive assessments that affect attention allocation, or otherwise reassess or adapt intent.

Schedule Outline

Each workshop day will have a subtheme. Day 1 will focus on system approaches to proficiency assessment and explanation of proficiency assessment, Day 2 will focus on human-centered approaches to matching intent to robot proficiency, and Day 3 will focus on integration. Break-out sessions on Day 2 and Day 3 will likewise focus on the subthemes, with a final group working session focused on integration. Accepted papers will be presented on the day that most closely aligns with the theme of the talk.

Invited speakers will be selected from two areas adjacent to the workshop theme: verification and validation in human-robot interaction and folk psychology of intent. The invited speakers will not be asked to invent or present work that precisely matches the workshop theme, but rather asked to talk about their own prior work in a way that informs workshop participants about how the theme fits into the broader research community. In addition to the invited speakers, we will have a panel of invited experts on the topic of explainability in AI.

Organizers

Jacob W. Crandall and Michael A. Goodrich, Brigham Young University: crandall@cs.byu.edu, mike@cs.byu.edu
Holly Yanco, University of Massachusetts, Lowell: holly@cs.uml.edu
Aaron Steinfeld, Carnegie Mellon University: steinfeld@cmu.edu

Acknowledgements

Organizational effort is supported under the SUCCESS MURI, a project funded by the Office of Naval Research (N00014-18-1-2503).