Hippocampal formation-inspired probabilistic generative model
This work addresses the challenge of building more efficient AI agents for navigation by referencing brain function, but it appears incremental as it builds on existing brain reference architecture and SLAM models without reporting concrete performance gains.
The authors tackled the problem of navigation in uncertain environments by proposing a hippocampal formation-inspired probabilistic generative model (HF-PGM) that integrates neuroscientific knowledge with robotics and AI techniques like SLAM, resulting in a model designed to be highly consistent with the anatomical structure and functions of the hippocampal formation.
In building artificial intelligence (AI) agents, referring to how brains function in real environments can accelerate development by reducing the design space. In this study, we propose a probabilistic generative model (PGM) for navigation in uncertain environments by integrating the neuroscientific knowledge of hippocampal formation (HF) and the engineering knowledge in robotics and AI, namely, simultaneous localization and mapping (SLAM). We follow the approach of brain reference architecture (BRA) (Yamakawa, 2021) to compose the PGM and outline how to verify the model. To this end, we survey and discuss the relationship between the HF findings and SLAM models. The proposed hippocampal formation-inspired probabilistic generative model (HF-PGM) is designed to be highly consistent with the anatomical structure and functions of the HF. By referencing the brain, we elaborate on the importance of integration of egocentric/allocentric information from the entorhinal cortex to the hippocampus and the use of discrete-event queues.