Learning to Encode Vision on the Fly in Unknown Environments: A Continual Learning SLAM Approach for Drones

Ali Safa, Tim Verbelen, Ilja Ocket, Andre Bourdoux, Hichem Sahli, Francky Catthoor, Georges G.E. Gielen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Learning to safely navigate in unknown environ-ments is an important task for autonomous drones used in surveillance and rescue operations. In recent years, a number of learning-based Simultaneous Localisation and Mapping (SLAM) systems relying on deep neural networks (DNNs) have been proposed for applications where conventional feature descriptors do not perform well. However, such learning-based SLAM systems rely on DNN feature encoders trained offline in typical deep learning settings. This makes them less suited for drones deployed in environments unseen during training, where continual adaptation is paramount. In this paper, we present a new method for learning to SLAM on the fly in unknown environments, by modulating a low-complexity Dictionary Learning and Sparse Coding (DLSC) pipeline with a newly proposed Quadratic Bayesian Surprise (QBS) factor. We experimentally validate our approach with data collected by a drone in a challenging warehouse scenario, where the high number of ambiguous scenes makes visual disambiguation hard.

Original languageEnglish
Title of host publication2022 Ieee International Symposium On Safety, Security, And Rescue Robotics (ssrr)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages373-378
Number of pages6
ISBN (Electronic)9781665456807
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event2022 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2022 - Sevilla, Spain
Duration: 8 Nov 202210 Nov 2022

Publication series

NameIeee International Symposium On Safety Security And Rescue Robotics

Conference

Conference2022 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2022
Country/TerritorySpain
CitySevilla
Period8/11/2210/11/22

Fingerprint

Dive into the research topics of 'Learning to Encode Vision on the Fly in Unknown Environments: A Continual Learning SLAM Approach for Drones'. Together they form a unique fingerprint.

Cite this