Improving Visual Place Recognition Based Robot Navigation by Verifying Localization Estimates

Visual Place Recognition (VPR) systems often have imperfect performance, affecting the ‘integrity’ of position estimates and subsequent robot navigation decisions. Previously, SVM classifiers have been used to monitor VPR integrity. This research introduces a novel Multi-Layer Perceptron (MLP) integrity monitor which demonstrates improved performance and generalizability, removing per-environment training and reducing manual tuning requirements. We test our proposed system in extensive real-world experiments, presenting two real-time integrity-based VPR verification methods: a single-query rejection method for robot navigation to a goal zone (Experiment 1); and a history-of-queries method that takes a best, verified, match from its recent trajectory and uses an odometer to extrapolate a current position estimate (Experiment 2). Noteworthy results for Experiment 1 include a decrease in aggregate mean along-track goal error from $ \approx \!9.8\;{\text{m}}$ to $ \approx \!3.1\;{\text{m}}$, and an increase in the aggregate rate of successful mission completion from $\approx \!41\%$ to $\approx \!55\%$. Experiment 2 showed a decrease in aggregate mean along-track localization error from $ \approx \!2.0\;{\text{m}}$ to $ \approx \!0.5\;{\text{m}}$, and an increase in the aggregate localization precision from $\approx \!97\%$ to $\approx \!99\%$. Overall, our results demonstrate the practical usefulness of a VPR integrity monitor in real-world robotics to improve VPR localization and consequent navigation performance.