AirLoop: Lifelong Loop Closure Detection
This addresses the incremental learning challenge for loop closure detection in robotics, enabling models to adapt to new environments without degrading performance on previously learned data.
The paper tackles the problem of catastrophic forgetting in loop closure detection for SLAM systems when models are incrementally trained on new environments, and presents AirLoop, a lifelong learning method that minimizes forgetting, demonstrating effectiveness on TartanAir, Nordland, and RobotCar datasets.
Loop closure detection is an important building block that ensures the accuracy and robustness of simultaneous localization and mapping (SLAM) systems. Due to their generalization ability, CNN-based approaches have received increasing attention. Although they normally benefit from training on datasets that are diverse and reflective of the environments, new environments often emerge after the model is deployed. It is therefore desirable to incorporate the data newly collected during operation for incremental learning. Nevertheless, simply finetuning the model on new data is infeasible since it may cause the model's performance on previously learned data to degrade over time, which is also known as the problem of catastrophic forgetting. In this paper, we present AirLoop, a method that leverages techniques from lifelong learning to minimize forgetting when training loop closure detection models incrementally. We experimentally demonstrate the effectiveness of AirLoop on TartanAir, Nordland, and RobotCar datasets. To the best of our knowledge, AirLoop is one of the first works to achieve lifelong learning of deep loop closure detectors.