Drone Path-Following in GPS-Denied Environments using Convolutional Networks (2019-05-05T00:00:00.000000Z)

TL;DR

His paper presents a simple approach for drone navigation to follow a predetermined path using visual input only without reliance on a Global Positioning System (GPS), and suggests possible enhancements for extending the approach to more difficult paths in real life.

Abstract

his paper presents a simple approach for drone navigation to follow a predetermined path using visual input only without reliance on a Global Positioning System (GPS). A Convolutional Neural Network (CNN) is used to output the steering command of the drone in an end-to-end approach. We tested our approach in two simulated environments in the Unreal Engine using the AirSim plugin for drone simulation. Results show that the proposed approach, despite its simplicity, has average cross track distance less than 2.9 meters in the simulated environment. We also investigate the significance of data augmentation in path following. Finally, we conclude by suggesting possible enhancements for extending our approach to more difficult paths in real life, in the hope that one day visual navigation will become the norm in GPS-denied zones.

Authors

M. Samy

1 papers

K. Amer

1 papers

M. Shaker

1 papers

TL;DR

Abstract

Authors

References30 items

Active Neural Localization

Convolutional Neural Network-Based Deep Urban Signatures with Application to Drone Localization

Vision-based object path following on a quadcopter for GPS-denied environments

AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles

Toward low-flying autonomous MAV trail navigation using deep neural networks for environmental awareness

How hard is it to cross the room? - Training (Recurrent) Neural Networks to steer a UAV

Relative Camera Pose Estimation Using Convolutional Neural Networks

VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem

DeepVO: Towards end-to-end visual odometry with deep Recurrent Convolutional Neural Networks

A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots

Target-driven visual navigation in indoor scenes using deep reinforcement learning

End to End Learning for Self-Driving Cars

Deep Neural Network for Real-Time Autonomous Indoor Navigation

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search

A vision-based line following strategy for an autonomous UAV

PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization

U-Net: Convolutional Networks for Biomedical Image Segmentation

Fast R-CNN

Adam: A Method for Stochastic Optimization

Very Deep Convolutional Networks for Large-Scale Image Recognition

Vision-based qualitative path-following control of quadrotor aerial vehicle

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Enhanced Target Tracking in UAV Imagery with P-N Learning and Structural Constraints

Robust Real-Time Tracking with Diverse Ensembles and Random Projections

Learning monocular reactive UAV control in cluttered natural environments

Distributed component-based framework for Unmanned Air Vehicle systems

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

ImageNet: A large-scale hierarchical image database

YOLO ) You Only Look Once : Unified , Real - Time Object Detection

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names