Prediction of SLAM ATE Using an Ensemble Learning Regression Model and 1-D Global Pooling of Data Characterization
This work addresses the need for integrity measures in SLAM systems for autonomous robotics, offering a method to optimize evaluation with limited data, though it is incremental as it builds on existing SLAM and ensemble learning techniques.
The authors tackled the problem of predicting SLAM localization error by developing a random forest regression model using 1-D global pooled features from raw sensor data, achieving up to 94.7% prediction accuracy on ORB-SLAM3 across multiple datasets and modes.
Robustness and resilience of simultaneous localization and mapping (SLAM) are critical requirements for modern autonomous robotic systems. One of the essential steps to achieve robustness and resilience is the ability of SLAM to have an integrity measure for its localization estimates, and thus, have internal fault tolerance mechanisms to deal with performance degradation. In this work, we introduce a novel method for predicting SLAM localization error based on the characterization of raw sensor inputs. The proposed method relies on using a random forest regression model trained on 1-D global pooled features that are generated from characterized raw sensor data. The model is validated by using it to predict the performance of ORB-SLAM3 on three different datasets running on four different operating modes, resulting in an average prediction accuracy of up to 94.7\%. The paper also studies the impact of 12 different 1-D global pooling functions on regression quality, and the superiority of 1-D global averaging is quantitatively proven. Finally, the paper studies the quality of prediction with limited training data, and proves that we are able to maintain proper prediction quality when only 20 \% of the training examples are used for training, which highlights how the proposed model can optimize the evaluation footprint of SLAM systems.