Papers
2
Total Citations
20
H-Index
2
About
Adriana Amicarelli is a researcher in robotics and probabilistic artificial intelligence, specializing in simultaneous localization and mapping (SLAM) under uncertainty. Her work addresses a fundamental challenge in autonomous systems: how robots can build maps of unknown environments while tracking their own position, even when sensor data is noisy or incomplete. Amicarelli’s key contribution lies in reformulating SLAM as a Markov random field problem, enabling the use of iterated conditional modes—a powerful optimization technique—to solve it efficiently. Her 2018 paper on this approach, which has garnered 13 citations, introduced a method that outperforms traditional filtering-based SLAM in accuracy and robustness. A follow-up study in 2019 extended this framework to continuous probabilistic SLAM, achieving 7 citations and further demonstrating the versatility of her technique. Amicarelli’s work bridges graph theory and probabilistic inference, offering a computationally tractable solution for real-time robotic navigation. Her research is particularly relevant for autonomous vehicles, drones, and exploration robots operating in GPS-denied environments. By advancing the theoretical foundations of SLAM, she has provided a practical tool for engineers and a clear framework for students entering the field of robotic perception.
Research Focus
Key Achievements
Top Papers
- 1
- 2Continuous Probabilistic SLAM Solved via Iterated Conditional Modes7 citations · 2019