About Me
I am Federico Nesti, currently a Researcher (RTD-A) at Retis lab (Tecip Institute, Scuola Superiore Sant'Anna). My research bridges academic innovation with real-world applications, focusing on the trustworthiness of machine learning models in autonomous systems, including photo-realistic simulation systems, software architectures for safe AI deployment, and adversarial attacks.
Academic background: I received my BSc in Electronics Engineering in 2015 and my MSc in Robotics and Automation Engineering in 2018 from the University of Pisa. I completed my PhD funded by the Department of Excellence in Robotics & AI at the Scuola Superiore Sant'Anna. I participated in the U-PHOS project (2015–2017), interned at Fermilab (USA) in 2017, and completed my MSc thesis at TU Delft in 2018. I was also a visiting student at the University of Alicante in 2022.
Industrial experience: I worked as an R&D robotics engineer at Roboticom, and as an Algorithm Engineer at VisLab srl (an Ambarella Company). I consulted for several companies to help set up navigation systems and industrial robotics and automation plants.
Don't hesitate to get in touch for academic collaborations, M.Sc. thesis supervision, and opportunities in the industry.
News
July 2025: Our work SimPRIVE: a Simulation framework for Physical Robot Interaction with Virtual Environments was accepted for publication and will be presented at IEEE ITSC 2025 in November in Gold Coast, Australia. Find more information at https://retis-ai.github.io/SimPRIVE/
June 2025: Our work Towards Railway Domain Adaptation for LiDAR-based 3D Detection: Road-to-Rail and Sim-to-Real via SynDRA-BBox was accepted for publication at IEEE ICIRT 2025. More info here
Tools and Datasets
Check out our research on simulators at Retis Lab!
SimPRIVE
A plugin for Unreal Engine 5 to enable vehicle-in-the-loop simulation
SynDRA and SynDRA-BBox
Datasets for semantic segmentation and obstacle detection in railway environments
CARLA-GeAR
Tool and dataset for adversarial robustness evaluation in CARLA.