Object Memory Transformer for Object Goal Navigation

by   Rui Fukushima, et al.
National Institute of Advanced Industrial Science and Technology
Tokyo Institute of Technology
Mitsubishi Electric Corporation

This paper presents a reinforcement learning method for object goal navigation (ObjNav) where an agent navigates in 3D indoor environments to reach a target object based on long-term observations of objects and scenes. To this end, we propose Object Memory Transformer (OMT) that consists of two key ideas: 1) Object-Scene Memory (OSM) that enables to store long-term scenes and object semantics, and 2) Transformer that attends to salient objects in the sequence of previously observed scenes and objects stored in OSM. This mechanism allows the agent to efficiently navigate in the indoor environment without prior knowledge about the environments, such as topological maps or 3D meshes. To the best of our knowledge, this is the first work that uses a long-term memory of object semantics in a goal-oriented navigation task. Experimental results conducted on the AI2-THOR dataset show that OMT outperforms previous approaches in navigating in unknown environments. In particular, we show that utilizing the long-term object semantics information improves the efficiency of navigation.


page 1

page 3

page 6


MemoNav: Selecting Informative Memories for Visual Navigation

Image-goal navigation is a challenging task, as it requires the agent to...

Object Goal Navigation using Data Regularized Q-Learning

Object Goal Navigation requires a robot to find and navigate to an insta...

A Contextual Bandit Approach for Learning to Plan in Environments with Probabilistic Goal Configurations

Object-goal navigation (Object-nav) entails searching, recognizing and n...

Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks

Many robotic applications require the agent to perform long-horizon task...

Incremental Object Database: Building 3D Models from Multiple Partial Observations

Collecting 3D object datasets involves a large amount of manual work and...

Hierarchical Object-to-Zone Graph for Object Navigation

The goal of object navigation is to reach the expected objects according...

Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport

We address key challenges in long-horizon embodied exploration and navig...

Please sign up or login with your details

Forgot password? Click here to reset