Interview with Amar Halilovic: Explainable AI for robotics

On this interview collection, we’re assembly a number of the AAAI/SIGAI Doctoral Consortium individuals to seek out out extra about their analysis. The Doctoral Consortium offers a chance for a gaggle of PhD college students to debate and discover their analysis pursuits and profession goals in an interdisciplinary workshop along with a panel of established researchers. On this newest interview, we hear from Amar Halilovic, a PhD pupil at Ulm College.

Inform us a bit about your PhD – the place are you finding out, and what’s the subject of your analysis?

I’m at present a PhD pupil at Ulm College in Germany, the place I deal with explainable AI for robotics. My analysis investigates how robots can generate explanations of their actions in a means that aligns with human preferences and expectations, significantly in navigation duties.

Might you give us an outline of the analysis you’ve carried out up to now throughout your PhD?

To this point, I’ve developed a framework for environmental explanations of robotic actions and choices, particularly when issues go improper. I’ve explored black-box and generative approaches for the technology of textual and visible explanations. Moreover, I’ve been engaged on planning of various rationalization attributes, akin to timing, illustration, period, and so forth. Recently, I’ve been engaged on strategies for dynamically choosing the right rationalization technique relying on the context and consumer preferences.

Is there a side of your analysis that has been significantly fascinating?

Sure, I discover it fascinating how folks interpret robotic conduct in a different way relying on the urgency or failure context. It’s been particularly rewarding to review how rationalization expectations shift in several conditions and the way we will tailor rationalization timing and content material accordingly.

What are your plans for constructing in your analysis up to now throughout the PhD – what facets will you be investigating subsequent?

Subsequent, I’ll be extending the framework to include real-time adaptation, enabling robots to be taught from consumer suggestions and modify their explanations on the fly. I’m additionally planning extra consumer research to validate the effectiveness of those explanations in real-world human-robot interplay settings.

Amar along with his poster on the AAAI/SIGAI Doctoral Consortium at AAAI 2025.

What made you need to examine AI, and, specifically, explainable robotic navigation?

I’ve all the time been within the intersection of people and machines. Throughout my research, I spotted that making AI programs comprehensible isn’t only a technical problem—it’s key to belief and value. Robotic navigation struck me as a very compelling space as a result of choices are spatial and visible, making explanations each difficult and impactful.

What recommendation would you give to somebody considering of doing a PhD within the area?

Decide a subject that genuinely excites you—you’ll be residing with it for a number of years! Additionally, construct a help community of mentors and friends. It’s simple to get misplaced within the technical work, however collaboration and suggestions are important.

Might you inform us an fascinating (non-AI associated) reality about you?

I’ve lived and studied in 4 completely different nations.

About Amar

Amar is a PhD pupil on the Institute of Synthetic Intelligence of Ulm College in Germany. His analysis focuses on Explainable Synthetic Intelligence (XAI) in Human-Robotic Interplay (HRI), significantly how robots can generate context-sensitive explanations for navigation choices. He combines symbolic planning and machine studying to construct explainable robotic programs that adapt to human preferences and completely different contexts. Earlier than beginning his PhD, he studied Electrical Engineering on the College of Sarajevo in Sarajevo, Bosnia and Herzegovina, and Laptop Science at Mälardalen College in Västerås, Sweden. Outdoors academia, Amar enjoys travelling, pictures, and exploring connections between expertise and society.