In appearance-based localization and mapping, loop-closure detection is the process used to determinate if the current observation comes from a previously visited location or a new one. As the size of the internal map increases, so does the time required to compare new observations with all stored locations, eventually limiting online processing. This paper presents an online loop-closure detection approach for large-scale and long-term operation. The approach is based on a memory management method, which limits the number of locations used for loop-closure detection so that the computation time remains under real-time constraints. The idea consists of keeping the most recent and frequently observed locations in a working memory (WM) that is used for loop-closure detection, and transferring the others into a long-term memory (LTM). When a match is found between the current location and one stored in WM, associated locations that are stored in LTM can be updated and remembered for additional loop-closure detections. Results demonstrate the approach's adaptability and scalability using ten standard datasets from other appearance-based loop-closure approaches, one custom dataset using real images taken over a 2-km loop of our university campus, and one custom dataset (7 h) using virtual images from the racing video game “Need for Speed: Most Wanted”.

For large-scale and long-term simultaneous localization and mapping (SLAM), a robot has to deal with unknown initial positioning caused by either the kidnapped robot problem or multi-session mapping. This paper addresses these problems by tying the SLAM system with a global loop closure detection approach, which intrinsically handles these situations. However, online processing for global loop closure detection approaches is generally influenced by the size of the environment. The proposed graph-based SLAM system uses a memory management approach that only consider portions of the map to satisfy online processing requirements. The approach is tested and demonstrated using five indoor mapping sessions of a building using a robot equipped with a laser rangefinder and a Kinect.

For robots navigating using only a camera, illumination changes in indoor environments can cause re-localization failures during autonomous navigation. In this paper, we present a multi-session visual SLAM approach to create a map made of multiple variations of the same locations in different illumination conditions. The multi-session map can then be used at any hour of the day for improved re-localization capability. The approach presented is independent of the visual features used, and this is demonstrated by comparing re-localization performance between multi-session maps created using the RTAB-Map library with SURF, SIFT, BRIEF, BRISK, KAZE, DAISY, and SuperPoint visual features. The approach is tested on six mapping and six localization sessions recorded at 30 min intervals during sunset using a Google Tango phone in a real apartment.

Background: Home adaptation processes enhancing occupational engagement rely on identifying environmental barriers, generally during time-consuming home visits performed by occupational therapists (OTs). Relevance of a 3D model to the OT’s work has been attested, but a convenient and consumer-available technology to map the home environment in 3D is currently lacking. For instance, such a technology would support the exploration of home adaptations for a person with disability, with or without an OT visit. Objective: The aim of this study was to document the development and acceptability of a 3D mapping eHealth technology, optimizing its contribution to the OT’s work when conducting assessments in which home representations are essential to fit a person’s needs. Methods: A user-centered perspective, embedded in a participatory design framework where users are considered as research partners (not as just study participants), is reported. OTs, engineers, clinicians, researchers, and students, as well as the relatives of older adults contributed by providing ongoing feedback (eg, demonstrations, brainstorming, usability testing, questionnaires, prototyping). System acceptability, as per the Nielsen model, is documented by deductively integrating the data. Results: A total of 24 stakeholders contributed significantly to MapIt technology’s co-design over a span of 4 years. Fueled by the objective to enhance MapIt’s acceptability, 11 iterations lead to a mobile app to scan a room and produce its 3D model in less than 5 minutes. The app is available for smartphones and paired with computer software. Scanning, visualization, and automatic measurements are done on a smartphone equipped with a motion sensor and a camera with depth perception, and the computer software facilitates visualization, while allowing custom measurement of architectural elements directly on the 3D model. Stakeholders’ perception was favorable regarding MapIt’s acceptability, testifying to its usefulness (ie, usability and utility). Residual usability issues as well as concerns about accessibility and scan rendering still need to be addressed to foster its integration to a clinical context. Conclusions: MapIt allows to scan a room quickly and simply, providing a 3D model from images taken in real-world settings and to remotely but jointly explore home adaptations to enhance a person’s occupational engagement.