Talks and presentations

Conference Talks at ICAPS 2024

June 01, 2024

Conference proceedings and doctoral consortium, 34th International Conference on Automated Planning and Scheduling (ICAPS 2024), Banff, Canada

Presented two contributions at ICAPS 2024:

Previously Published Paper Track: [When Prolog Meets Generative Models: A New Approach for Managing Knowledge and Planning in Robotic Applications] — a framework combining probabilistic logic programming and generative models to create flexible, scalable robot planning systems.
Doctoral Consortium: Adaptive and Scalable Knowledge Management for Robotic Applications via Probabilistic Logic Languages — highlighting ongoing PhD work on logic-based adaptive task planning.

Conference Talk at IEEE ICRA 2024

May 20, 2024

Conference proceedings talk, IEEE International Conference on Robotics and Automation (ICRA 2024), Tokyo, Japan

Presented the paper [When Prolog Meets Generative Models: A New Approach for Managing Knowledge and Planning in Robotic Applications], showing how Large Language Models (LLMs) can be paired with Prolog-based symbolic reasoning to automatically generate and refine robotic knowledge bases for planning and control.

Doctoral Consortium Talk at SoCS 2023

July 18, 2023

Doctoral consortium presentation, 16th International Symposium on Combinatorial Search (SoCS 2023), Prague, Czech Republic

Presented the extended abstract Multi-Agent Open Framework: Developing a Holistic System to Solve MAPF, describing an open-source framework that integrates Multi-Agent Path Finding (MAPF) algorithms and task allocation mechanisms for scalable robotic coordination.

Conference Talk at AIxIA 2022

November 23, 2022

Conference proceedings talk, 21st International Conference of the Italian Association for Artificial Intelligence (AIxIA 2022), Udine, Italy

Presented the paper Comparing Multi-Agent Path Finding Algorithms in a Real Industrial Scenario, benchmarking several MAPF algorithms on a factory logistics environment, bridging academic MAPF solutions with real-world robotic systems.

Conference Proceeding Talk at IEEE COMPSAC 2021

July 13, 2021

Conference proceedings talk, IEEE COMPSAC 2021, Madrid, Spain (online)

In this work, we introduce a GPU-parallel implementation of the Iterative Dynamic Programming (IDP) algorithm for solving the multi-point Markov–Dubins problem, which seeks the shortest bounded-curvature path through several waypoints. Unlike traditional optimization methods (NLP/MINLP), this approach is inherently parallelizable and significantly improves accuracy, speed, and energy efficiency, making it well suited for embedded and real-time applications. Follow the title link for more info.