Bayesian Relational Memory for Semantic Visual Navigation
Citations Over TimeTop 10% of 2019 papers
Abstract
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 allows (1) capturing the layout prior from training environments, i.e., prior knowledge, (2) estimating posterior layout at test time, i.e., memory update, and (3) efficient planning for navigation, altogether. We develop a BRM agent consisting of a BRM module for producing sub-goals and a goal-conditioned locomotion module for control. When testing in unseen environments, the BRM agent outperforms baselines that do not explicitly utilize the probabilistic relational memory structure.
Related Papers
- → Introduction to the Special Issue: Toward an Explicit Technology for Generalizing Academic Behavior(2010)14 cited
- → On a Generalization of Yager’s Implications(2012)8 cited
- → Behavior therapy: Problems in Generalization(1971)19 cited
- Comparative Study of the New and Experienced Teachers' Differences in the General Teaching of Mathematical(2010)
- The New Segregation and Generalization of IMO42-2(2005)