Switchable constraints for robust pose graph SLAM

By Niko Sünderhauf, Peter Protzel. 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012

354 citations recorded by the source corpus.

Current SLAM back-ends are based on least squares optimization and thus are not robust against outliers like data association errors and false positive loop closure detections. Our paper presents and evaluates a robust back-end formulation for SLAM using switchable constraints. Instead of proposing yet another appearance-based data association technique, our system is able to recognize and reject outliers during the optimization. This is achieved by making the topology of the underlying factor graph representation subject to the optimization instead of keeping it fixed. The evaluation shows that the approach can deal with up to 1000 false positive loop closure constraints on various datasets. This largely increases the robustness of the overall SLAM system and closes a gap between the sensor-driven front-end and the back-end optimizers.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8a937906e2a4235a6509926322f3de88340fd4dc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Perception, Planning, Control, and Coordination for Autonomous Vehicles (2017, methodology): “Various extension to the current SLAM algorithm to make the loop closure detection more robust such as Switchable Constraint method [161], Max-Mixture Model [162], and Realizing, Reversing, Recovering techniques [163] have been proposed in recent literature.”
Factor Graphs for Robot Perception (2017, neutral): “[179, 180], max mixture [156], and “realizing, reversing, recovering” (RRR) [128].”
Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection (2019, methodology): “[43] M. Pfingsthorn and A. Birk, “Generalized graph SLAM: Solving local and global ambiguities through multimodal and hyperedge constraints,” Int.”
Improving RGB-D SLAM in dynamic environments: A motion removal approach (2017, methodology): “We introduce two tuning functions F(θ ) and G(θ ) in this paper, where G(θ ) has been described in [33].”
Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments (2021, background): “CC outperformed the others in challenging regions with few false positives (red), which can potentially be treated using existing robust back-ends [45, 48, 49].”
QuadricSLAM: Dual Quadrics From Object Detections as Landmarks in Object-Oriented SLAM (2018, methodology): “1For a discussion of SLAM methods robust to data association errors see the relevant literature such as [27], [28].”
Maplab: An Open Framework for Research in Visual-Inertial Mapping and Localization (2017, neutral): “The algorithm is similar to [37].”
Robust map optimization using dynamic covariance scaling (2013, methodology): “Recently, Sünderhauf and Protzel [8] published an effective method for optimizing graphs in the presence of outliers.”
Robust reconstruction of indoor scenes (2015, methodology): “) Independently, we substituted the robust optimization formulation presented in Section 5 with basic switchable constraints [57] or expectation maximization [40].”