TY - GEN
T1 - Learning to Encode Vision on the Fly in Unknown Environments
T2 - 2022 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2022
AU - Safa, Ali
AU - Verbelen, Tim
AU - Ocket, Ilja
AU - Bourdoux, Andre
AU - Sahli, Hichem
AU - Catthoor, Francky
AU - Gielen, Georges G.E.
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85147538498&partnerID=8YFLogxK
U2 - 10.1109/SSRR56537.2022.10018713
DO - 10.1109/SSRR56537.2022.10018713
M3 - Conference contribution
AN - SCOPUS:85147538498
T3 - Ieee International Symposium On Safety Security And Rescue Robotics
SP - 373
EP - 378
BT - 2022 Ieee International Symposium On Safety, Security, And Rescue Robotics (ssrr)
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 8 November 2022 through 10 November 2022
ER -