Vision-Based Autonomous Drone Control using Supervised Learning in Simulation release_6ocygp25qvci5psecvasf7oxei

by Max Christl

Released as a article .

2020  

Abstract

Limited power and computational resources, absence of high-end sensor equipment and GPS-denied environments are challenges faced by autonomous micro areal vehicles (MAVs). We address these challenges in the context of autonomous navigation and landing of MAVs in indoor environments and propose a vision-based control approach using Supervised Learning. To achieve this, we collected data samples in a simulation environment which were labelled according to the optimal control command determined by a path planning algorithm. Based on these data samples, we trained a Convolutional Neural Network (CNN) that maps low resolution image and sensor input to high-level control commands. We have observed promising results in both obstructed and non-obstructed simulation environments, showing that our model is capable of successfully navigating a MAV towards a landing platform. Our approach requires shorter training times than similar Reinforcement Learning approaches and can potentially overcome the limitations of manual data collection faced by comparable Supervised Learning approaches.
In text/plain format

Archived Files and Locations

application/pdf  1.0 MB
file_mrzi6ixhxbhxhipyhvhiehffji
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-09-09
Version   v1
Language   en ?
arXiv  2009.04298v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: c223dcc8-e9d2-41ba-b953-058f656b2155
API URL: JSON