Julian Zilly

Papers

Total Citations

H-Index

About

Julian Zilly is a researcher at the intersection of robotics, autonomous systems, and multi-modal perception. His work focuses on enabling robots to robustly perceive and act in complex, uncertain environments through the integration of heterogeneous sensor data. Zilly’s major contribution is the development of cross-modal learning filters, a novel approach for fusing information from diverse sensor types—such as RGB cameras and neuromorphic sensors—to enhance robotic perception and decision-making. His paper "Cross-Modal Learning Filters for RGB-Neuromorphic Wormhole Learning" (2019, 10 citations) introduces a framework that allows robots to leverage complementary sensor modalities, improving their ability to navigate and interact in dynamic, populated settings. This work is particularly relevant to autonomous driving, where vehicles rely on lidar, radar, sonar, and cameras to operate safely. Zilly also contributed to "The AI Driving Olympics at NeurIPS 2018" (2 citations), a competition that advanced the state of the art in autonomous driving through AI. His research is pivotal for developing more resilient and adaptable robotic systems, making him a notable figure in the fields of robotics and multi-modal learning.