Skip to content
arXiv Robotics — research abstracts· Jiahui Fu, Yilun Du, Kurran Singh, Joshua B. Tenenbaum, John J. Leonard·· 2 days agoEditorial score60

NeuSE: Neural SE(3)-Equivariant Embedding for Long-Term Object-Based Simultaneous Localization and Mapping

NeuSE: Neural SE(3)-Equivariant Embedding for Long-Term Object-Based Simultaneous Localization and Mapping

Summary

The paper presents NeuSE, a novel neural SE(3)-equivariant embedding for objects that supports object-based SLAM. It enables consistent spatial understanding in dynamic environments by encoding full shape, scale, and transform information. NeuSE is evaluated on synthetic and real-world sequences, demonstrating improved localization and change-aware mapping consistency.

Source: arXiv Robotics — research abstracts · Read original article ↗

Loading article text…

Source:arXiv Robotics — research abstracts · arxiv.org

Timezone · UTC

Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).