Intelligent Perception and Mapping: Machine Learning for Mobile Robotics

Abstract:
This talk explores a collection of my recent works on robotic perception and mapping. I will highlight key challenges enabling robots to perceive, interpret, and adapt to dynamic environments. Topics include robust object detection, out-of-distribution and change detection, and cross-view localization. 

Short bio:
Dr. Feras Dayoub is a Senior Lecturer with the Australian Institute of Machine Learning (AIML) at the University of Adelaide, specializing in robotic vision and machine learning for robotic perception. He is also an Adjunct Senior Lecturer at Queensland University of Technology (QUT) and serves as the AI theme lead for the University of Adelaide in its partnership with the University of Surrey. His research focuses on enabling the reliable deployment of computer vision and machine learning on mobile robots in real-world environments. With expertise in applied robotic vision, Dr. Dayoub has led projects that harness machine learning for agricultural innovation, environmental conservation, and infrastructure monitoring through vision-based autonomous systems.