Detecting Landmark Misrecognition in Pose-Graph SLAM via Minimum Cost Multicuts

Pose-graph SLAM is the de facto standard framework for constructing large-scale maps from multisession experiences of relative observations and motions during visual robot navigations. It has received increasing attention in the context of recent advanced SLAM frameworks such as graph neural SLAM. One remaining challenge is landmark misrecognition errors (i.e., incorrect landmark edges) that can have catastrophic effects on the inferred pose-graph map. In this study, we present comprehensive criteria to maximize global consistency in the pose graph using a new robust graph cut technique. Our key idea is to formulate the problem as a minimum-cost multicut that enables us to optimize not only landmark correspondences but also the number of landmarks while allowing for a varying number of landmarks. This makes our proposed approach invariant against the type of landmark measurement, graph topology, and metric information, such as the speed of the robot motion. Specifically, we implement a new consistency metric that relies only on the order of observed landmarks. The proposed metric is invariant against the type of landmark measurements, graph topology, and metric information such as the speed of robot motion. The proposed graph cut technique was integrated into a practical SLAM framework and verified experimentally using the public NCLT dataset.