Towards an Autonomous Vision-based Inventory Drone

Research output: Contribution to conferencePosterResearch

Abstract

Inventory tracking is a time and cost intensive task in industry. Great expense is dedicated to performing inventory checks. To reduce this effort we present an inventory drone prototype developed to demonstrate the feasibility of vision‑based navigation inside industrial warehouses with highly repetitive visual structure.
In contrast to using LIDAR, we utilize model‑based visual localization against a precomputed map of the environment to estimate and compensate the drift of a commercially available odometry sensor and achieve cm‑accurate navigation. Our experiments showcase the capabilities of our prototype for vision‑based precise indoor navigation and autonomous inventory. All computations are performed on‑board the drone.
Original languageEnglish
Publication statusPublished - 22 May 2019
EventLogistikwerkstatt Graz 2019: Solution day – „update“ - Technische Universität Graz, Graz, Austria
Duration: 22 May 201922 May 2019
https://logistikwerkstatt-graz.at/

Conference

ConferenceLogistikwerkstatt Graz 2019
Abbreviated titleLoWe Graz
CountryAustria
CityGraz
Period22/05/1922/05/19
Internet address

Fingerprint

Navigation
Warehouses
Sensors
Drones
Costs
Industry
Experiments

Keywords

  • Aerial Robotics
  • Photogrammetrie
  • odometers
  • logistics
  • Industrial applications

Cite this

Pestana Puerta, J., Maurer, M., Fraundorfer, F., & Bischof, H. (2019). Towards an Autonomous Vision-based Inventory Drone. Poster session presented at Logistikwerkstatt Graz 2019, Graz, Austria.

Towards an Autonomous Vision-based Inventory Drone. / Pestana Puerta, Jesus; Maurer, Michael; Fraundorfer, Friedrich; Bischof, Horst.

2019. Poster session presented at Logistikwerkstatt Graz 2019, Graz, Austria.

Research output: Contribution to conferencePosterResearch

Pestana Puerta, J, Maurer, M, Fraundorfer, F & Bischof, H 2019, 'Towards an Autonomous Vision-based Inventory Drone' Logistikwerkstatt Graz 2019, Graz, Austria, 22/05/19 - 22/05/19, .
Pestana Puerta J, Maurer M, Fraundorfer F, Bischof H. Towards an Autonomous Vision-based Inventory Drone. 2019. Poster session presented at Logistikwerkstatt Graz 2019, Graz, Austria.
Pestana Puerta, Jesus ; Maurer, Michael ; Fraundorfer, Friedrich ; Bischof, Horst. / Towards an Autonomous Vision-based Inventory Drone. Poster session presented at Logistikwerkstatt Graz 2019, Graz, Austria.
@conference{96e1eee8e7034ac797f2b955feedb747,
title = "Towards an Autonomous Vision-based Inventory Drone",
abstract = "Inventory tracking is a time and cost intensive task in industry. Great expense is dedicated to performing inventory checks. To reduce this effort we present an inventory drone prototype developed to demonstrate the feasibility of vision‑based navigation inside industrial warehouses with highly repetitive visual structure. In contrast to using LIDAR, we utilize model‑based visual localization against a precomputed map of the environment to estimate and compensate the drift of a commercially available odometry sensor and achieve cm‑accurate navigation. Our experiments showcase the capabilities of our prototype for vision‑based precise indoor navigation and autonomous inventory. All computations are performed on‑board the drone.",
keywords = "Aerial Robotics, Photogrammetrie, odometers, logistics, Industrial applications",
author = "{Pestana Puerta}, Jesus and Michael Maurer and Friedrich Fraundorfer and Horst Bischof",
year = "2019",
month = "5",
day = "22",
language = "English",
note = "Logistikwerkstatt Graz 2019 : Solution day – „update“, LoWe Graz ; Conference date: 22-05-2019 Through 22-05-2019",
url = "https://logistikwerkstatt-graz.at/",

}

TY - CONF

T1 - Towards an Autonomous Vision-based Inventory Drone

AU - Pestana Puerta, Jesus

AU - Maurer, Michael

AU - Fraundorfer, Friedrich

AU - Bischof, Horst

PY - 2019/5/22

Y1 - 2019/5/22

N2 - Inventory tracking is a time and cost intensive task in industry. Great expense is dedicated to performing inventory checks. To reduce this effort we present an inventory drone prototype developed to demonstrate the feasibility of vision‑based navigation inside industrial warehouses with highly repetitive visual structure. In contrast to using LIDAR, we utilize model‑based visual localization against a precomputed map of the environment to estimate and compensate the drift of a commercially available odometry sensor and achieve cm‑accurate navigation. Our experiments showcase the capabilities of our prototype for vision‑based precise indoor navigation and autonomous inventory. All computations are performed on‑board the drone.

AB - Inventory tracking is a time and cost intensive task in industry. Great expense is dedicated to performing inventory checks. To reduce this effort we present an inventory drone prototype developed to demonstrate the feasibility of vision‑based navigation inside industrial warehouses with highly repetitive visual structure. In contrast to using LIDAR, we utilize model‑based visual localization against a precomputed map of the environment to estimate and compensate the drift of a commercially available odometry sensor and achieve cm‑accurate navigation. Our experiments showcase the capabilities of our prototype for vision‑based precise indoor navigation and autonomous inventory. All computations are performed on‑board the drone.

KW - Aerial Robotics

KW - Photogrammetrie

KW - odometers

KW - logistics

KW - Industrial applications

M3 - Poster

ER -