Pushing it out of the Way: Interactive Visual Navigation

by   Kuo-Hao Zeng, et al.

We have observed significant progress in visual navigation for embodied agents. A common assumption in studying visual navigation is that the environments are static; this is a limiting assumption. Intelligent navigation may involve interacting with the environment beyond just moving forward/backward and turning left/right. Sometimes, the best way to navigate is to push something out of the way. In this paper, we study the problem of interactive navigation where agents learn to change the environment to navigate more efficiently to their goals. To this end, we introduce the Neural Interaction Engine (NIE) to explicitly predict the change in the environment caused by the agent's actions. By modeling the changes while planning, we find that agents exhibit significant improvements in their navigational capabilities. More specifically, we consider two downstream tasks in the physics-enabled, visually rich, AI2-THOR environment: (1) reaching a target while the path to the target is blocked (2) moving an object to a target location by pushing it. For both tasks, agents equipped with an NIE significantly outperform agents without the understanding of the effect of the actions indicating the benefits of our approach.


page 1

page 6

page 8

page 11

page 13

page 14

page 18

page 19


What do navigation agents learn about their environment?

Today's state of the art visual navigation agents typically consist of l...

VTNet: Visual Transformer Network for Object Goal Navigation

Object goal navigation aims to steer an agent towards a target object ba...

Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics

A common assumption when training embodied agents is that the impact of ...

How to Train PointGoal Navigation Agents on a (Sample and Compute) Budget

PointGoal navigation has seen significant recent interest and progress, ...

Learning Robust Agents for Visual Navigation in Dynamic Environments: The Winning Entry of iGibson Challenge 2021

This paper presents an approach for improving navigation in dynamic and ...

Visual Reaction: Learning to Play Catch with Your Drone

In this paper we address the problem of visual reaction: the task of int...

Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instances

We consider the problem of embodied visual navigation given an image-goa...

Please sign up or login with your details

Forgot password? Click here to reset