BioSLAM: A Bio-Inspired Lifelong Memory System for General Place Recognition

We present BioSLAM, a lifelong SLAM frame- work for learning various new appearances incrementally and maintaining accurate place recognition for previously visited areas. Unlike humans, artificial neural networks suffer from catastrophic forgetting and may forget the previously visited areas when trained with new arrivals. For humans, researchers discover that there exists a memory replay mechanism in the brain to keep the neuron active for previous events. Inspired by this discovery, BioSLAM designs a gated generative replay to control the robot’s learning behavior based on the feedback rewards. Specifically, BioSLAM provides a novel dual-memory mechanism for maintenance: 1) a dynamic memory to efficiently learn new observations and 2) a static memory to balance new-old knowledge. When the agent is encountered with different appear- ances under new domains, the complete processing pipeline can help to incrementally update the place recognition ability, robust to the increasing complexity of long-term place recognition. We demonstrate BioSLAM in three incremental SLAM sce- narios: 1) a 120km city-scale trajectories with LiDAR-based inputs, 2) a multi-visited 4.5km campus-scale trajectories with LiDAR-vision inputs, and 3) an official Oxford dataset with 10km visual inputs under different environmental conditions. We show that BioSLAM can incrementally update the agent’s place recognition ability and outperform the state-of-the-art incremental approach, Generative Replay, by 24% in terms of place recognition accuracy. To our knowledge, BioSLAM is the first memory-enhanced lifelong SLAM system to help incremental place recognition in long-term navigation tasks.