ICRA 2023 WS: Explainable Robotics

Scope

There is a growing interest in the research and development of AI algorithms capable of generating explanations for their output. Explanations could play an essential role in robot systems to improve predictability, user-friendliness, debugging effectiveness, and overall transparency and trustworthiness of robots. This workshop aims to put forth a diversity of viewpoints from experts in robotics, from AI and technical to social perspectives. The workshop will provide a venue for robotics and AI researchers, philosophers, psychologists, and social scientists to exchange research, ideas, and opinions on the use of explanations in robotics, from methods and requirements to metrics, interaction, and qualitative findings. In this workshop, we aim to bring together researchers to explore 1) how HRI researchers seek to design human-interpretable or legible robot behaviors, 2) how xAI researchers have applied their techniques to robotics, 3) how robotics researchers generate explanations that allow robots to operate at different levels of autonomy, and 4) how roboticists have needed to augment or develop their own xAI techniques especially suited for robotics (xAI for "agents" may not be good for "robots”).

Invited speakers

All times are London (UK) time.

Seongun Kim

Korea Advanced Institute of Science and Technology, South Korea
Subramanian Ramamoorthy

University of Edinburgh, UK
Silvia Rossi

Università degli Studi di Napoli Federico II, Italy
Lars Kunze

University of Oxford, UK
Tathagata Chakraborti

IBM Research AI, USA
Bradley Hayes

University of Colorado, Boulder, USA
Karinne Ramirez Amaro

Chalmers University of Technology, Sweden

Accepted papers

Konstantinos Gavriilidis, Andrea Munafo, Wei Pang, Helen F. Hastie, "A Surrogate Model Framework for Explainable Autonomous Behaviour" [PDF]

Sam Thellman, Maartje M.A. De Graaf, "The challenges of first- and second-order belief reasoning in explainable human-robot interaction" [PDF]

Lennart Wachowiak, Andrew Coles, Oya Celiktutan, Gerard Canal, "A Survey of Evaluation Methods and Metrics for Explanations in Human–Robot Interaction (HRI)" [PDF]

Justin Kottinger, Shaull Almagor, Morteza Lahijanian, "Explainable Multi-Robot Motion Planning via Segmentation" [PDF]

Efimia Panagiotaki, Daniele De Martini, Lars Kunze, "Towards Semantic Interpretation and Validation of Graph Attention-based Explanations" [PDF]

Marwen Belkaid, "Explanation through behavior: a human-inspired framework for explainable robotics" [PDF]

Gabriele Trovato, Yueh-Hsuan Weng, Yegang Du, "'Never complain, never explain': why robots may not have to be explicable after all" [PDF]

Marta Lagomarsino, Marta Lorenzini, Merryn Dale Constable, Elena De Momi, Cristina Becchio, Arash Ajoudani, "Maximising Coefficiency of Human-Robot Handovers through Reinforcement Learning" [PDF]

Anna Collins, "Argumentation for Evaluative Explanations of PDDL Plans" [PDF]

Kerstin Haring, Pilyoung Kim, Daniel Pittman, "Explainable Robot Design Based on a Robot Theory of Mind: A Web-Based Platform to systematically evaluate Robot Designs" [PDF]

Schedule

9:15 - 9:30	Opening (organizers)
9:30 - 10:00	Seongun Kim	"Explaining the Decisions of Deep Policy Networks for Robotic Manipulation and Robot Navigation"
10:00 - 10:30	Subramanian Ramamoorthy	"Why Explain, and Steps towards Design for Trustworthiness"
10:30 - 11:00	Poster session
11:00 - 11:30	Coffee break
11:30 - 12:00	Silvia Rossi	"Transparency in Human-Robot Interaction - Open Challenges in Modeling and Evaluation of the Robot's Behavior"
12:00 - 12:30	Lars Kunze	"Making Robots Explainable and Trustworthy"
12:30 - 14:00	Lunch
14:00 - 14:30	Tathagata Chakraborti	"Planning with Mental Models - Explanations versus Explainable Behavior"
14:30 - 15:00	Bradley Hayes	"How to Generate and Utilize Justifications to Make Robot Explanations Useful"
15:00 - 15:30	Karinne Ramirez Amaro	"Explainable AI meets Robotics - Robots that Learn and Reason from Experiences"
15:30 - 16:00	Coffee break and poster session
16:00 - 17:00	Short presentations (Accepted papers)
17:00 - 18:00	Panel discussion

Organizers

Senka Krivic (Corresponding organizer) www

University of Sarajevo, Bosnia and Herzegovina
Gerard Canal www

King's College London, UK
Martim Brandao www

King's College London, UK
Anais Garrell www

CSIC-UPC, Spain
Matthew Gombolay www

Georgia Institute of Technology, US
Jean Oh www

Carnegie Mellon University, US
Rohan Paleja www

Georgia Institute of Technology, US
Silvia Tulli www

Instituto Superior Técnico, Portugal; Sorbonne University, France
Miguel Faria www

GAIPS@INESC-ID and Instituto Superior Técnico, Portugal
Tanmay Shankar www

Carnegie Mellon University, US