[1Q3-OS-7a] 統合AIへの展望

[1Q3-OS-7a-05] Implement and Validation of a Probabilistic Generative Model Inspired by Hippocampal Formation

〇Shunsuke Otake¹, Katsuyoshi Maeyama¹, Shoichi Hasegawa¹, Takeshi Nakashima¹, Akira Taniguchi¹, Tadahiro Taniguchi¹, Hiroshi Yamakawa^2,3 (1. Ritsumeikan University, 2. The Whole Brain Architecture Initiative, 3. The University of Tokyo)

Keywords:Brain reference architecture, Hippocampal formation, Probabilistic generative model, Simultaneous localization and mapping, Recurrent state space model

We construct and implement a concrete computational model based on a hippocampal formation-inspired probabilistic generative model (HF-PGM) and evaluate the effectiveness of the proposed model. HF-PGM does not specify the architecture or probability distribution of the model. In this study, we propose a probabilistic generative model consistent with HF-PGM by integrating the Recurrent State-Space Model (RSSM), one of the world models, and Simultaneous Localization and Mapping (SLAM)'s model based on the occupancy grid map. Global localization was performed in a simulated environment to evaluate its performance in experiments. We showed that the proposed model improves performance over conventional self-localization methods. We also evaluated the performance of the integrated world model concerning location categorization using a latent space representation.