Online Dynamic SLAM with Incremental Smoothing and Mapping

2025-09-09

AI Summary

To address the insufficient real-time performance of SLAM in dynamic scenes, this paper proposes the first incremental-optimization-oriented dynamic SLAM framework enabling joint online estimation of static backgrounds and dynamic objects. Our method introduces a lightweight factor graph structure and system architecture specifically designed for incremental solving, integrating dynamic object motion modeling, joint camera pose optimization, incremental smoothing mapping, and sparse structural analysis. The approach achieves significant efficiency gains without compromising accuracy: it matches or surpasses state-of-the-art methods in precision across multiple standard benchmarks while accelerating inference by 5×. To the best of our knowledge, this is the first dynamic SLAM solution that unifies high accuracy with real-time performance. Furthermore, the framework exhibits strong scalability and is suitable for online deployment in real-world environments.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Dynamic SLAM methods jointly estimate for the static and dynamic scene components, however existing approaches, while accurate, are computationally expensive and unsuitable for online applications. In this work, we present the first application of incremental optimisation techniques to Dynamic SLAM. We introduce a novel factor-graph formulation and system architecture designed to take advantage of existing incremental optimisation methods and support online estimation. On multiple datasets, we demonstrate that our method achieves equal to or better than state-of-the-art in camera pose and object motion accuracy. We further analyse the structural properties of our approach to demonstrate its scalability and provide insight regarding the challenges of solving Dynamic SLAM incrementally. Finally, we show that our formulation results in problem structure well-suited to incremental solvers, while our system architecture further enhances performance, achieving a 5x speed-up over existing methods.

Problem

• Online Dynamic SLAM for real-time scene estimation
• Reducing computational cost in dynamic SLAM systems
• Incremental optimization for joint static-dynamic mapping

Innovation

• Incremental optimization for Dynamic SLAM
• Novel factor-graph formulation design
• System architecture enabling online estimation