Alessandro Costantini
Papers
1
Total Citations
7
H-Index
1
About
Alessandro Costantini is a leading researcher at the intersection of secure robotics and robust perception, where his work addresses the critical challenge of deploying autonomous systems in uncertain and adversarial environments. His most-cited paper, "Robust object estimation using generative-discriminative inference for secure robotics applications" (2018, 7 citations), pioneers a hybrid generative-discriminative framework that enhances convolutional neural networks (CNNs) for object recognition. By integrating these inference paradigms, Costantini’s approach equips robots with the ability to maintain reliable perception even when faced with noisy, incomplete, or maliciously manipulated data—a key vulnerability in standard CNNs. This contribution is foundational for secure autonomous navigation, where trustworthiness is paramount. His research bridges machine learning and robotics, offering practical solutions for real-world deployment in domains like surveillance, autonomous driving, and industrial automation. With a focus on robustness and security, Costantini’s work is shaping the next generation of resilient robotic systems, making him a notable voice in the push toward truly autonomous and safe AI.
Research Focus
Key Achievements
Top Papers
- 1