About

Visual Navigation is the problem of navigating an agent, e.g. a mobile robot, in an environment using camera input only. The agent is given a target image (an image it will see from the target position), and its goal is to move from its current position to the target by applying a sequence of actions, based on the camera observations only.

Source: Vision-based Navigation Using Deep Reinforcement Learning

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Latest papers without code

On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning

4 May 2021

Using a set of carefully designed baseline conditions, we find that the majority of the lottery ticket effect in reinforcement learning can be attributed to the identified mask.

VISUAL NAVIGATION

Visual Navigation with Spatial Attention

20 Apr 2021

This combination of the "what" and the "where" allows the agent to navigate toward the sought-after object effectively.

VISUAL NAVIGATION

SOON: Scenario Oriented Object Navigation with Graph-based Exploration

31 Mar 2021

In this task, an agent is required to navigate from an arbitrary position in a 3D embodied environment to localize a target following a scene description.

VISUAL NAVIGATION

MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation

21 Mar 2021

Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics.

SEMANTIC SEGMENTATION VISUAL NAVIGATION

A Survey of Embodied AI: From Simulators to Research Tasks

8 Mar 2021

Finally, based upon the simulators and a pyramidal hierarchy of embodied AI research tasks, this paper surveys the main research tasks in embodied AI -- visual exploration, visual navigation and embodied question answering (QA), covering the state-of-the-art approaches, evaluation and datasets.

EMBODIED QUESTION ANSWERING QUESTION ANSWERING VISUAL NAVIGATION

A Pose-only Solution to Visual Reconstruction and Navigation

2 Mar 2021

Visual navigation and three-dimensional (3D) scene reconstruction are essential for robotics to interact with the surrounding environment.

3D SCENE RECONSTRUCTION MOTION ESTIMATION VISUAL NAVIGATION

Learning for Visual Navigation by Imagining the Success

28 Feb 2021

ForeSIT is trained to imagine the recurrent latent representation of a future state that leads to success, e. g. either a sub-goal state that is important to reach before the target, or the goal state itself.

VISUAL NAVIGATION

Gaze-Informed Multi-Objective Imitation Learning from Human Demonstrations

25 Feb 2021

In the field of human-robot interaction, teaching learning agents from human demonstrations via supervised learning has been widely studied and successfully applied to multiple domains such as self-driving cars and robot manipulation.

EYE TRACKING HUMAN ROBOT INTERACTION IMITATION LEARNING SELF-DRIVING CARS VISUAL NAVIGATION

Scene Retrieval for Contextual Visual Mapping

25 Feb 2021

The second contribution is an algorithm `DMC' that combines our scene classification with distance and memorability for visual mapping.

CLASSIFICATION IMAGE RETRIEVAL SCENE CLASSIFICATION SCENE RECOGNITION VISUAL NAVIGATION

Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching

8 Feb 2021

Successful visual navigation depends upon capturing images that contain sufficient useful information.

SIMULTANEOUS LOCALIZATION AND MAPPING VISUAL NAVIGATION VISUAL ODOMETRY