ProbPer-LiLo: Probabilistic Persistency Modeling for Life-Long Mapping
Waqas Ali, Yixi Cai, Patric Jensfelt, Thien-Minh Nguyen
AI summary
Problem
Existing lifelong mapping methods struggle to distinguish quasi-static objects from static structures, rely on binary change detection, and fail to scale to large environments due to computationally prohibitive point-wise analysis.
Approach
The authors introduce ProbPer-LiLo, which leverages a factor graph to model object persistence using semantic labels and temporal consistency across multiple mapping sessions, enabling accurate static map extraction and semantic-geometric change detection for map refinement.
Key results
- Novel factor graph-based probabilistic model for accurate static and quasi-static object classification
- Scalable map refinement pipeline that fuses semantic and geometric information across multi-session maps
- State-of-the-art change detection and map update performance on large-scale real-world environments
- Public release of the complete framework and a new multi-campus lifelong mapping dataset
Why it matters
Provides a robust, scalable solution for maintaining accurate long-term 3D maps, critical for autonomous navigation, infrastructure inspection, and urban planning applications.
Abstract
3D mapping is vital for a broad range of applications that rely on a consistent and accurate representation of the environment. Change is an ever-persistent force in our world and with the evolution of a scene its 3D map becomes outdated. Thus, a mapping framework that can adapt and refine the 3D maps with the changes in the scene is necessary. In this paper, we propose a lifelong mapping framework where map maintenance is based on two objectives including the preservation of static structures and the refinement of the 3D map. To preserve only the static structures, we classify the object’s state and remove the dynamic objects and the quasi-static objects, i.e., objects which temporarily appear static. For classifying the state of objects, we propose a discrete probabilistic solution utilizing a factor graph. Using this classification, we generate static maps from multiple sessions which are used for map refinement. The refinement is based on change detection and map update, leveraging semantic and geometric information. For the evaluation, we collect a multi- campus lifelong dataset as an extension of the MCD datasets from KTH and NTU campuses. The proposed approach is capable of accurately detecting quasi-static objects even in highly dynamic environments. Our system demonstrates state of the art performance in large scale environments. Furthermore, our approach can handle both SLAM-generated and survey-grade maps.