Interview with Amar Halilovic: Explainable AI for robotics

On this interview sequence, we’re assembly a few of the AAAI/SIGAI Doctoral Consortium contributors to seek out out extra about their analysis. The Doctoral Consortium supplies a possibility for a bunch 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 matter of your analysis?

I’m at the moment a PhD pupil at Ulm College in Germany, the place I give attention to 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, notably in navigation duties.

May you give us an outline of the analysis you’ve carried out to date throughout your PhD?

Up to now, I’ve developed a framework for environmental explanations of robotic actions and choices, particularly when issues go flawed. 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 clarification attributes, similar to timing, illustration, period, and so forth. These days, I’ve been engaged on strategies for dynamically choosing the right clarification technique relying on the context and consumer preferences.

Is there a facet of your analysis that has been notably fascinating?

Sure, I discover it fascinating how folks interpret robotic habits in another way relying on the urgency or failure context. It’s been particularly rewarding to check how clarification expectations shift in numerous conditions and the way we are able to tailor clarification timing and content material accordingly.

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

Subsequent, I’ll be extending the framework to include real-time adaptation, enabling robots to study from consumer suggestions and alter 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 methods 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 pondering of doing a PhD within the discipline?

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

May you inform us an fascinating (non-AI associated) truth about you?

I’ve lived and studied in 4 totally different international locations.

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), notably how robots can generate context-sensitive explanations for navigation choices. He combines symbolic planning and machine studying to construct explainable robotic methods that adapt to human preferences and totally 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, images, and exploring connections between expertise and society.