OASIS-Map: Object-Level Change Detection in Multi-Session Mapping using Semantic Correspondence Matching
Robotics
Summary
The authors developed OASIS-Map, a system that helps robots keep track of objects in places that change over time, like stores or parking lots. Instead of relying only on fixed maps, their system compares detailed parts of objects seen at different times to figure out what has changed and match objects across visits. This helps the robot notice when things move, disappear, or get replaced, even if the robot sees them from different angles or partially hidden. They tested their method in real-world scenarios, showing it can successfully detect changes and associate objects with good accuracy.
Authors
Haedam Oh, Yifu Tao, Nived Chebrolu, Maurice Fallon
Abstract
Map representations which are consistent across repeated visits to a real-world semi-static environment are very useful for long-term robotic inspection. In such settings, the scene may evolve while the robot is absent, with objects appearing, disappearing, moving, or being replaced, quickly making a static map outdated. Existing change-detection methods reason through geometry, category-level semantics, or object persistence. However, achieving reliable object association across revisits remains a key challenge, especially under partial views, occlusion, and imperfect segmentation. In this work, we propose OASIS-Map, a multi-session mapping system that maintains a spatio-temporally consistent object-level map by establishing dense patch-level semantic correspondences between temporal observations. These correspondences detect where the scene has changed and incrementally associate objects across revisits as the robot re-observes the environment. We demonstrate OASIS-Map on three challenging real-world scenarios: object rearrangements in 3RScan, visually similar car replacements in a car park, and large-scale scene changes in an outdoor market. We achieve 0.783 F1 on change detection in a car replacement scenario in a car park and 0.667 F1 on moved object association in 3RScan. https://dynamic.robots.ox.ac.uk/projects/oasis-map/