Improving Visual Place Recognition Based Robot Navigation Through Verification of Localization Estimates

Visual Place Recognition (VPR) systems often have imperfect performance, which affects robot navigation decisions. This research introduces a novel Multi-Layer Perceptron (MLP) integrity monitor for VPR which demonstrates improved performance and generalizability over the previous state-of-the-art SVM approach, removing per-environment training and reducing manual tuning requirements. We test our proposed system in extensive real-world experiments, where we also present two real-time integrity-based VPR verification methods: an instantaneous rejection method for a robot navigating to a goal zone (Experiment 1); and a historical method that takes a best, verified, match from its recent trajectory and uses an odometer to extrapolate forwards to a current position estimate (Experiment 2). Noteworthy results for Experiment 1 include a decrease in aggregate mean along-track goal error from  9.8m to  3.1m in missions the robot pursued to completion, and an increase in the aggregate rate of successful mission completion from  41 decrease in aggregate mean along-track localization error from  2.0m to  0.5m, and an increase in the aggregate precision of localization attempts from  97 to  99 integrity monitor in real-world robotics to improve VPR localization and consequent navigation performance.