Bayesian Relational Memory for Semantic Visual Navigation
2983335573, pp. 2769-2779, 2019.
We introduce a new memory architecture, Bayesian Relational Memory (BRM), to improve the generalization ability for semantic visual navigation agents in unseen environments, where an agent is given a semantic target to navigate towards. BRM takes the form of a probabilistic relation graph over semantic entities (e.g., room types), which...More
PPT (Upload PPT)