Summary

Aim

Methods in AI for robotic control, mobile platforms, and cognitive cyber-physical systems are developing rapidly. They tackle the challenging task of modeling real-world systems and environments through data, using machine vision, reinforcement learning for control, probabilistic machine learning, among many others. Such data-driven approaches have led to many concerns regarding the robustness, stability, and overall safety of these systems.

While data-driven approaches based on learning algorithms have seen huge success in the last decade, when applied to cyber-physical systems such as manufacturing applications and healthcare robotics, the lack of safety guarantees causes trust issues. A central challenge is defining and implementing robustness for different applications and providing methods for analyzing and verifying models. The focus of this session is to investigate the diverse meaning of robust AI and gathers a wide array of approaches to the problem.

The proposed invited session provides a forum for bringing together researchers from academia and industry to explore and present their findings in Robust Artificial Intelligence with theories, systems, technologies, and approaches for testing and validating them on challenging real-world, safety-critical applications.

Topics

Research papers on all aspects of Robust AI. Topics include, but are not limited to:

• Knowledge-driven models

• Reasoning-based methods

• Robustness analysis

• Trustworthiness

• Machine learning biases

• Adversarial attacks and security

• Cognitive models and bio-inspired AI

• Hybrid-models

• Explainable AI

Call for Papers

IMPORTANT DATES

• Paper submission deadline: 1 May 2022 15 May 2022

• Notification of acceptance: 15 May 2022 24 May 2022

• Camera ready: 3 June 2022

Invited session at the internal KES conference, Verona, Italy, 7-9 September 2022

Authors who submit and present their work will have their work published and indexed internationally by Elsevier's Procedia Computer Science.

Accepted Papers

• Towards Improved Visualization and Optimization of Aquaculture Production Process. Dr. Aya Saad, Dr. Finn Olav Bjørnson, Eng. Espen Eilertsen, Eng. Tore Norheim Hagtun, Eng. Oscar Nissen, Dr. Sveinung Johan Ohrem.

• RAMARL: Robustness Analysis with Multi-Agent Reinforcement Learning - Robust Reasoning in Autonomous Cyber-Physical Systems. Dr. Aya Saad, Prof Anne Håkansson

• The Handie system: Hand signs interaction with autonomous mobile cyber-physical systems. Prof Anne Håkansson.

Organizers

Aya Saad, Postdoctoral fellow, aya.saad.ntnu.no@gmail.com, The Norwegian University of Science and Technology, Høgskoleringen 1, 7491 Trondheim, Norway

Anne Håkansson, Professor, anne.hakansson@uit.no, UiT Norges arktiske universitet, Postboks 6050 Langnes, 9037 Tromsø, Norway

Email & Contact Details

Aya Saad, Postdoctoral fellow, aya.saad.ntnu.no@gmail.com, NTNU, Trondheim, Norway

Professor Anne Håkansson, anne.hakansson@uit.no, IFI, UIT, Tromsö, Norway

Archive

The International Robust AI Workshop - an invited session at KES2021, Szczecin, Poland.