Spatio SLAM: An Integrated Strategy for Robot Autonomy in Variable Indoor Luminance

Perceiving and understanding dynamic scenes by a robot vision system requires crucial spatio-temporal knowledge and geometry to enable long-term autonomy. Existing Dynamic SLAM (Simultaneous Localization And Mapping) addresses definite portions of robot pose estimation to make it accurate. On the co...

Full description

Saved in:
Bibliographic Details
Main Authors: Rapti Chaudhuri, Suman Deb, Abhijit Das
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11112625/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849392661611413504
author Rapti Chaudhuri
Suman Deb
Abhijit Das
author_facet Rapti Chaudhuri
Suman Deb
Abhijit Das
author_sort Rapti Chaudhuri
collection DOAJ
description Perceiving and understanding dynamic scenes by a robot vision system requires crucial spatio-temporal knowledge and geometry to enable long-term autonomy. Existing Dynamic SLAM (Simultaneous Localization And Mapping) addresses definite portions of robot pose estimation to make it accurate. On the contrary scene understanding and rational integration with position is hard to find. In this context, a comprehensive realisation of a variable scene shared with other dynamic agents is still a challenge to execute within a shifting drift. This challenge is even increased when the environment is with variable luminance. To address these challenges, we propose a spatial-geometric SLAM (Spatio SLAM) solution that unifies the exiting connotations of long and short-term dynamics that constructs a real-time dense spatial-geometric map. The geometric representation of the scene gives the autonomous agent a prior map to factorize the navigation framework. In this work an end-to-end DA-SSOD (Domain Adaptive Single Stage Object Detection) deep network is introduced into the object detection module. This DA-SSOD introduction experimentally confirms the accurate prediction of obstacles in complex indoor surroundings with variable luminance. Geometric maps built by Spatio SLAM (as the real-time reconstruction of a 3D scene over an instance), results in 86.6%precision in static and 87.4%precision in varying environment (with dynamic obstacles). SOTA (State Of The Art) analysis presents the superiority of Spatio SLAM on other SLAM techniques implemented across multiple indoor structures.
format Article
id doaj-art-e8ca0b79d95f4ced8d61185f40c53a45
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e8ca0b79d95f4ced8d61185f40c53a452025-08-20T03:40:43ZengIEEEIEEE Access2169-35362025-01-011313689413690810.1109/ACCESS.2025.359557211112625Spatio SLAM: An Integrated Strategy for Robot Autonomy in Variable Indoor LuminanceRapti Chaudhuri0https://orcid.org/0000-0001-5732-2391Suman Deb1https://orcid.org/0000-0002-1457-4713Abhijit Das2https://orcid.org/0000-0001-5796-0748CSE Department, National Institute of Technology Agartala, Agartala, IndiaCSE Department, National Institute of Technology Agartala, Agartala, IndiaManipal Academy of Higher Education, Manipal Institute of Technology Bengaluru, Manipal, IndiaPerceiving and understanding dynamic scenes by a robot vision system requires crucial spatio-temporal knowledge and geometry to enable long-term autonomy. Existing Dynamic SLAM (Simultaneous Localization And Mapping) addresses definite portions of robot pose estimation to make it accurate. On the contrary scene understanding and rational integration with position is hard to find. In this context, a comprehensive realisation of a variable scene shared with other dynamic agents is still a challenge to execute within a shifting drift. This challenge is even increased when the environment is with variable luminance. To address these challenges, we propose a spatial-geometric SLAM (Spatio SLAM) solution that unifies the exiting connotations of long and short-term dynamics that constructs a real-time dense spatial-geometric map. The geometric representation of the scene gives the autonomous agent a prior map to factorize the navigation framework. In this work an end-to-end DA-SSOD (Domain Adaptive Single Stage Object Detection) deep network is introduced into the object detection module. This DA-SSOD introduction experimentally confirms the accurate prediction of obstacles in complex indoor surroundings with variable luminance. Geometric maps built by Spatio SLAM (as the real-time reconstruction of a 3D scene over an instance), results in 86.6%precision in static and 87.4%precision in varying environment (with dynamic obstacles). SOTA (State Of The Art) analysis presents the superiority of Spatio SLAM on other SLAM techniques implemented across multiple indoor structures.https://ieeexplore.ieee.org/document/11112625/Spatio SLAMspatial-geometric mapdynamic SLAMspatio-temporal knowledgedrift shift
spellingShingle Rapti Chaudhuri
Suman Deb
Abhijit Das
Spatio SLAM: An Integrated Strategy for Robot Autonomy in Variable Indoor Luminance
IEEE Access
Spatio SLAM
spatial-geometric map
dynamic SLAM
spatio-temporal knowledge
drift shift
title Spatio SLAM: An Integrated Strategy for Robot Autonomy in Variable Indoor Luminance
title_full Spatio SLAM: An Integrated Strategy for Robot Autonomy in Variable Indoor Luminance
title_fullStr Spatio SLAM: An Integrated Strategy for Robot Autonomy in Variable Indoor Luminance
title_full_unstemmed Spatio SLAM: An Integrated Strategy for Robot Autonomy in Variable Indoor Luminance
title_short Spatio SLAM: An Integrated Strategy for Robot Autonomy in Variable Indoor Luminance
title_sort spatio slam an integrated strategy for robot autonomy in variable indoor luminance
topic Spatio SLAM
spatial-geometric map
dynamic SLAM
spatio-temporal knowledge
drift shift
url https://ieeexplore.ieee.org/document/11112625/
work_keys_str_mv AT raptichaudhuri spatioslamanintegratedstrategyforrobotautonomyinvariableindoorluminance
AT sumandeb spatioslamanintegratedstrategyforrobotautonomyinvariableindoorluminance
AT abhijitdas spatioslamanintegratedstrategyforrobotautonomyinvariableindoorluminance