Cristiano Saltori
Papers
2
Total Citations
17
H-Index
1
About
Cristiano Saltori is a leading researcher in embodied AI and autonomous systems, with key contributions in LiDAR semantic segmentation, domain generalization, and end-to-end driving. His most cited work, “Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation” (2023, 16 citations), addresses a critical challenge in robotics: enabling LiDAR-based perception systems to generalize across diverse, unseen environments. By systematically investigating domain shifts in point cloud data, Saltori’s work provides foundational insights for deploying safe, robust robots in the real world. More recently, his 2025 paper “Efficient Multi-Camera Tokenization With Triplanes for End-to-End Driving” pioneers a novel tokenization strategy using triplane representations for multi-camera inputs, pushing the boundaries of autoregressive transformer policies for autonomous vehicles. This work aims to leverage internet-scale pretraining for scalable, generalizable driving policies. Saltori’s research sits at the intersection of computer vision, robotics, and machine learning, directly impacting the development of embodied intelligent agents that can operate reliably across varied domains. His contributions are essential reading for students and researchers working on domain adaptation, 3D perception, and autonomous navigation.
Research Focus
Key Achievements
Top Papers
- 1
- 2