Biography

My research spans robotics, computer vision, and machine learning. I have a keen interest and extensive experience in place recognition, localization, navigation, retrieval, and scene understanding.

I am currently on a full-time parenting break!
(Emails sent to fn.ln@adelaide.edu.au after 22 Apr were not received. Please contact at firstname dot sahaji at gmail.)

[2023-25] Research Fellow [robot navigation] at AIML, Uni. Adelaide.
[2020-23] Research Fellow [localisation] at QCR, QUT.
[2016-19] PhD [place recognition & retrieval] at ACRV, QUT.
[2012-15] Robotics researcher [object detection & tracking] at TCS Research.

News

 

Recent Publications

Quickly discover relevant content by filtering publications.
RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation
RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation
Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning
Vehicle localization
Anyloc: Towards universal visual place recognition
Anyloc: Towards universal visual place recognition
DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions
DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditions
GDIP: gated differentiable image processing for object detection in adverse conditions
Hierarchical Unsupervised Topological SLAM
Locking On: Leveraging Dynamic Vehicle-Imposed Motion Constraints to Improve Visual Localization