The Robot-at-Home dataset (Robot@Home, paper here) is a collection of raw and processed data from five domestic settings compiled by a mobile robot equipped with 4 RGB-D cameras and a 2D laser scanner. Its main purpose is to serve as a testbed for semantic mapping algorithms through the categorization of objects and/or rooms.

This dataset is unique in three aspects:

The provided data were captured with a rig of 4 RGB-D sensors with an overall field of view of 180°H. and 58°V., and with a 2D laser scanner.

It comprises diverse and numerous data: sequences of RGB-D images and laser scans from the rooms of five apartments (87,000+ observations were collected), topological information about the connectivity of these rooms, and 3D reconstructions and 2D geometric maps of the visited rooms.

The provided ground truth is dense, including per-point annotations of the categories of the objects and rooms appearing in the reconstructed scenarios, and per-pixel annotations of each RGB-D image within the recorded sequences

During the data collection, a total of 36 rooms were completely inspected, so the dataset is rich in contextual information of objects and rooms. This is a valuable feature, missing in most of the state-of-the-art datasets, which can be exploited by, for instance, semantic mapping systems that leverage relationships like pillows are usually on beds or ovens are not in bathrooms.

Robot@Home2

Robot@Home2, is an enhanced version aimed at improving usability and functionality for developing and testing mobile robotics and computer vision algorithms. It consists of three main components. Firstly, a relational database that states the contextual information and data links, compatible with Standard Query Language. Secondly,a Python package for managing the database, including downloading, querying, and interfacing functions. Finally, learning resources in the form of Jupyter notebooks, runnable locally or on the Google Colab platform, enabling users to explore the dataset without local installations. These freely available tools are expected to enhance the ease of exploiting the Robot@Home dataset and accelerate research in computer vision and robotics.

If you use Robot@Home2, please cite the following paper:

Gregorio Ambrosio-Cestero, Jose-Raul Ruiz-Sarmiento, Javier Gonzalez-Jimenez, The Robot@Home2 dataset: A new release with improved usability tools, in SoftwareX, Volume 23, 2023, 101490, ISSN 2352-7110, https://doi.org/10.1016/j.softx.2023.101490.

@article{ambrosio2023robotathome2,title = {The Robot@Home2 dataset: A new release with improved usability tools},author = {Gregorio Ambrosio-Cestero and Jose-Raul Ruiz-Sarmiento and Javier Gonzalez-Jimenez},journal = {SoftwareX},volume = {23},pages = {101490},year = {2023},issn = {2352-7110},doi = {https://doi.org/10.1016/j.softx.2023.101490},url = {https://www.sciencedirect.com/science/article/pii/S2352711023001863},keywords = {Dataset, Mobile robotics, Relational database, Python, Jupyter, Google Colab}}

Version historyv1.0.1 Fixed minor bugs.v1.0.2 Fixed some inconsistencies in some directory names. Fixes were necessary to automate the generation of the next version.v2.0.0 SQL based dataset. Robot@Home v1.0.2 has been packed into a sqlite database along with RGB-D and scene files which have been assembled into a hierarchical structured directory free of redundancies. Path tables are also provided to reference files in both v1.0.2 and v2.0.0 directory hierarchies. This version has been automatically generated from version 1.0.2 through the toolbox.v2.0.1 A forgotten foreign key pair have been added.v.2.0.2 The views have been consolidated as tables which allows a considerable improvement in access time.v.2.0.3 The previous version does not include the database. In this version the database has been uploaded.v.2.1.0 Depth images have been updated to 16-bit. Additionally, both the RGB images and the depth images are oriented in the original camera format, i.e. landscape.

This digital elevation model (DEM) is a part of a series of DEMs produced for the National Oceanic and Atmospheric Administration Coastal Services Center's Sea Level Rise and Coastal Flooding Impacts Viewer (www.csc.noaa.gov/slr/viewer). This metadata record describes the DEM for Mobile County in Alabama and Escambia, Santa Rosa, and Okaloosa (southern coastal portion only) Counties in Florida. The DEM includes the best available lidar data known to exist at the time of DEM creation for the coastal areas of Mobile County in Alabama and Escambia, Santa Rosa, and Okaloosa (portion) counties in Florida, that met project specification.This DEM is derived from the USGS National Elevation Dataset (NED), US Army Corps of Engineers (USACE) LiDAR data, as well as LiDAR collected for the Northwest Florida Water Management District (NWFWMD) and the Florida Department of Emergency Management (FDEM). NED and USACE data were used only in Mobile County, AL. NWFWMD or FDEM data were used in all other areas. Hydrographic breaklines used in the creation of the DEM were obtained from FDEM and Southwest Florida Water Management District (SWFWMD). This DEM is hydro flattened such that water elevations are less than or equal to 0 meters.This DEM is referenced vertically to the North American Vertical Datum of 1988 (NAVD88) with vertical units of meters and horizontally to the North American Datum of 1983 (NAD83). The resolution of the DEM is approximately 5 meters. This DEM does not include licensed data (Baldwin County, Alabama) that is unavailable for distribution to the general public. As such, the extent of this DEM is different than that of the DEM used by the NOAA Coastal Services Center in creating the inundation data seen in the Sea Level Rise and Coastal Impacts Viewer (www.csc.noaa.gov/slr/viewer).The NOAA Coastal Services Center has developed high-resolution digital elevation models (DEMs) for use in the Center's Sea Level Rise And Coastal Flooding Impacts internet mapping application. These DEMs serve as source datasets used to derive data to visualize the impacts of inundation resulting from sea level rise along the coastal United States and its territories.The dataset is provided "as is," without warranty to its performance, merchantable state, or fitness for any particular purpose. The entire risk associated with the results and performance of this dataset is assumed by the user. This dataset should be used strictly as a planning reference and not for navigation, permitting, or other legal purposes.

Tree diameter and coordinate data obtained by iPhone, iPad, and conventional survey methods in a 1 ha forest plot in Hokkaido, Japan (42°59'57" N, 141°23'29" E). Tatsumi, Yamaguchi, Furuya (in press) ForestScanner: A mobile application for measuring and mapping trees with LiDAR-equipped iPhone and iPad. Methods in Ecology and Evolution.

Web mapping application containing where mobile food vendors are allowed to operate within the city limits of Sioux Falls, South Dakota.

The dataset contains lidar, imu and wheel odometry measurements collected using an all-electric 4 wheel robotic vehicle (Gator) in a forest environment at the Queensland Centre for Advanced Technologies (QCAT - CSIRO) in Brisbane, Australia. The dataset also contains a heightmap image constructed from aerial lidar data of the same forest. This dataset allows users to run the Forest Localisation software and evaluate the results of the presented localisation method. Lineage: The ground view data was collected utilising an all-electric 4 wheel robotic vehicle equipped with a Velodyne VLP-16 laser mounted on a servo-motor, with a 45 degree inclination, spinning around the vertical axis at 0.5Hz. In addition to the lidar scans, imu and wheel odometry measurements were also recorded. The above canopy map (heightmap) was constructed from aerial lidar data captured using a drone also equipped with a spinning mobile lidar sensor.

Code and data for replicating the application study. See S1 Appendix for further details. (ZIP)

This forest health dataset includes flightlines from 2023. Along these flightlines, surveyors from the Alaska Division of Forestry & Fire Protection and USDA Forest Service - Forest Health Protection document insect, disease, and abiotic damage in the forest from about 1000 feet altitude using a digital mobile sketch-mapping tablet and software. The aerial survey covers about 15% of the forests statewide each year. Note that much of the forest damage documented during these surveys does not typically result in tree or shrub mortality. Aerial survey data disclaimer: USDA Forest Service - Forest Health Protection and the Alaska Division of Forestry & Fire Protection make every attempt to accurately identify and locate forest damage. The data is offered "as is".

This forest health dataset includes both polygon and point data from 2023. Points have a buffered area based on tree number. Surveyors from the Alaska Division of Forestry & Fire Protection and USDA Forest Service - Forest Health Protection document insect, disease, and abiotic damage in the forest from about 1000 feet altitude using a digital mobile sketch-mapping tablet and software. The aerial survey covers about 15% of the forests statewide each year. Note that much of the forest damage documented during these surveys does not typically result in tree or shrub mortality. Aerial survey data disclaimer: USDA Forest Service - Forest Health Protection and the Alaska Division of Forestry & Fire Protection make every attempt to accurately identify and locate forest damage. The data is offered "as is".

This forest health dataset includes both polygon and point data from 2021. Points have a buffered area based on tree number. Surveyors from the Alaska Division of Forestry & Fire Protection and USDA Forest Service - Forest Health Protection document insect, disease, and abiotic damage in the forest from about 1000 feet altitude using a digital mobile sketch-mapping tablet and software. The aerial survey covers about 15% of the forests statewide each year. Note that much of the forest damage documented during these surveys does not typically result in tree or shrub mortality. Aerial survey data disclaimer: USDA Forest Service - Forest Health Protection and the Alaska Division of Forestry & Fire Protection make every attempt to accurately identify and locate forest damage from the air. A very small percentage of the mapped data can be ground-checked and it is possible that errors in the data exist. These data are offered 'as is'.

The Atlas of Living Australia (ALA) ACT and Southern Tablelands Weedspotter web portal and mobile phone weed mapping application (weed mapping app)

WHAT IS IT? The web portal and associated weed mapping application allows individuals, industry, government and community groups to:

Electronically map weed infestations in the field, including:
  What the weed species was,
  Where it was seen,
  When it was seen,
  How many plants were seen, and
  How dense the infestation was
Record weed control activities, including:
  What type of control,
  When it was controlled,
  Which species were targeted, and
  How effective the control effort was
Store that information on the Weedspotter web portal,
View, manage, review and analyse this information and generate maps and reports on this information to help in future weed management planning.

WHY DO WE NEED IT?

If you are passionate about controlling weeds in our region, you know how to identify and/or control weeds and you want to be part of the solution - to protect farm lands and nature conservation areas from weeds - then register and become involved.

The Weedspotter web portal and weed mapping app helps us to collaborate more and be more effective in controlling weeds in our region, by allowing all users to:

provide an early warning of new and emerging weeds coming into our region
track changes in weed occurrence over time and at different sites;
track weed control effort - where it has occurred, what weeds have been targeted and how effective this work has been;

By understanding what is happening to weeds in our region - individuals (such as farmers), groups (such as Landcare and ParkCare groups) and government can:

prevent new and emerging weeds from becoming a problem.
prioritise weed control effort in their area of interest, and

Identifying and controlling new and emerging weeds is particularly important in a changing climate, as weeds that previously could not survive in our climate, are starting to appear in our region and are at risk of becoming invasive and becoming the next problem weed.

WHAT IS ON THE WEBSITE AND APP? Weed species of interest

This section includes:

Weed species of interest to the 10 local government areas and the ACT government. These are lists of weeds that NSW local government areas (LGAs) and the ACT government have identified as weeds that could become a problem, are starting to become a problem or are already widespread in our region (the weeds of interest vary across the different LGAs and in the ACT). The ACT and NSW LGAs are particularly interested in new and emerging weeds that are at risk of becoming invasive and becoming the next problem weed
Species profiles - each species listed in the weeds of interest will include detailed information and photos to assist users to identify weed species in the field (using the app) or when they are on the website.
Identification Tool - a Weed Identification Tool that assists all users to identify those hard to pick weeds (this will include look-alikes that are not weeds including native look-alike plants) in the field (using the app) or on the website.

Mapping - How to contribute There are three mapping tools on the website and available through the app. Each of these mapping tools allows users to photograph weeds of interest, weed infestations of interest or weed control effort and lodge them on the portal. This will assist in confirming weed identification and also tracking change over time.

A general weed mapping tool - which allows users to digitally record in the field or through the portal, a single weed species at a single site.
A more advanced weed mapping tool - which allows users to digitally record (field based and directly into the website portal) a weed infestation - including multiples species, the infestation area and the infestation density at one site.
A tool for recording weed treatment/management information at a particular site.

To use the mapping tools - register for the site.

Weed sightings to date This area of the website allows users to look at what they have mapped, what else has been mapped in the region - by location, species, date and type of record (single species, multi-species of weed control effort); analyse this data, develop a report and maps and print these documents. This also provides a link to the broader Atlas of Living Australia website and all the biodiversity data that can be accessed through the ALA website.

HOW DO I GET HOLD OF THE MOBILE PHONE APP? The Atlas of Living Australia (ALA) ACT and Southern Tablelands Weedspotter mobile phone applications are available in IPhone and Android Smart phones from the Apple iTunes Store or from Google Play.