5 papers
GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model
Peter Bohm, Saimunur Rahman, Abdelwahed Khamis +3
Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of ho…
Spatially Stratified Distillation for Heterogeneous Radar Place Recognition
Sagun Singh Shrestha, Samuel Harding, Abdelwahed Khamis +2
Scalable, all-weather place recognition increasingly relies on heterogeneous radar place recognition to bridge diverse hardware platforms. A notable application is matching queries…
Visual Place Recognition in Forests with Depth-Aware Distillation
Walter Nedov, Saimunur Rahman, Kavindie Katuwandeniya +3
Visual place recognition in natural forest environments remains challenging due to repetitive vegetation, weak structural cues, and significant appearance variation across traversa…
Point-PNG: Conditional Pseudo-Negatives Generation for Point Cloud Pre-Training
Sutharsan Mahendren, Saimunur Rahman, Piotr Koniusz +4
We propose Point-PNG, a novel self-supervised learning framework that generates conditional pseudo-negatives in the latent space to learn point cloud representations that are both…
A Deeper Look into Second-Order Feature Aggregation for LiDAR Place Recognition
Saimunur Rahman, Peyman Moghadam
Efficient LiDAR Place Recognition (LPR) compresses dense pointwise features into compact global descriptors. While first-order aggregators such as GeM and NetVLAD are widely used,…