Extracting useful and accurate information from scanned geologic and other earth science maps is a time-consuming and laborious process involving manual human effort. To address this limitation, the USGS partnered with the Defense Advanced Research Projects Agency (DARPA) to run the AI for Critical Mineral Assessment Competition, soliciting innovative solutions for automatically georeferencing and extracting features from maps. The competition opened for registration in August 2022 and concluded in December 2022. Training, validation, and evaluation data from the competition are provided here, as well as competition details and baseline solutions. The data are derived from published sources and are provided to the public to support continued development of automated georeferencing and feature extraction tools. References for all maps are included with the data. First Posted - December 27, 2023 Revised - July 21, 2025

The global map app market is booming, projected to reach $45 billion by 2033 with a 12% CAGR. Explore key trends, drivers, and restraints shaping this dynamic industry, including the rise of AR, AI integration, and the competition among leading players like Google Maps and Waze. Discover market segmentation, regional analysis, and future growth projections.

<<< This dataset is not released yet. Release date: 1st September, 2025. >>>

The Semantic Segmentation Map Dataset (Semap) contains 1,439 manually annotated map samples. Specifically, the dataset compiles 356 image patches from the Historical City Maps Semantic Segmentation Dataset (HCMSSD, [1]), 78 samples extracted from 19th century European cadastres [2–4], three from Paris city atlases [5], and 1,002 newly annotated samples, drawn from the Aggregated Dataset on the History of Cartography (ADHOC Images, [6]).

Additionally, it comprises 12,122 synthetically generated image samples and related labels.

Both datasets are part of the R. Petitpierre's PhD thesis [7]. Extensive details on annotation, and synthetical generation procedures are provided in the context of that work.

Organization of the data

To come soon.

Descriptive statistics

Number of semantic classes: 5 + background
Number of manually annotated image samples: 1,439
Number of synthetically-generated samples:
Image sample size:
min: 768 × 768 pixels
max: 1000 × 1000 pixels

Use and Citation

For any mention of this dataset, please cite :

@misc{semap_petitpierre_2025,
author = {Petitpierre, R{\'{e}}mi and Gomez Donoso, Damien and Kriesel, Ben},
title = {{Semantic Segmentation Map Dataset (Semap)}},
year = {2025},
publisher = {EPFL},
url = {https://doi.org/10.5281/zenodo.16164782}}

@phdthesis{studying_maps_petitpierre_2025,
author = {Petitpierre, R{\'{e}}mi},
title = {{Studying Maps at Scale: A Digital Investigation of Cartography and the Evolution of Figuration}},
year = {2025},
school = {EPFL}}

Corresponding author

Rémi PETITPIERRE - remi.petitpierre@epfl.ch - ORCID - Github - Scholar - ResearchGate

Work ethics

80% of the data were annotated by RP. The remainder were annotated by DGD and BK, two master's students from EPFL, Switzerland. The students were paid for their work using public funding, and were offered the possibility to be associated with the publication of the data.

License

This project is licensed under the CC BY 4.0 License.

Liability

We do not assume any liability for the use of this dataset.

References

1. Petitpierre, R. (2021). Historical City Maps Semantic Segmentation Dataset. V1.0. https://doi.org/10.5281/zenodo.5513639
2. di Lenardo I, Barman R, Pardini F, et al. (2021) Une approche computationnelle du cadastre napoléonien de Venise. Humanités numériques 3.
3. Petitpierre R, Rappo L and di Lenardo I (2023) Recartographier l’espace napoléonien. In: Humanistica 2023, Genève, Switzerland, June 2023. Géographie. Association francophone des humanités numériques. Available at: https://hal.science/hal-04109214.
4. Li S, Cerioni A, Herny C, et al. (2024) Vectorization of historical cadastral plans from the 1850s in the Canton of Geneva. Geneva, Switzerland: Swiss Territorial Data Lab. Available at: https://tech.stdl.ch/PROJ-CADMAP/.
5. Chazalon J, Carlinet E, Chen Y, et al. (2021) ICDAR 2021 Competition on Historical Map Segmentation. arXiv:2105.13265 [cs].
6. To come soon
7. Petitpierre R (2025) Studying Maps at Scale: A Digital Investigation of Cartography and the Evolution of Figuration. PhD thesis. École Polytechnique Fédérale de Lausanne.

The interactive map creation tools market is experiencing robust growth, driven by increasing demand for visually engaging data representation across diverse sectors. The market, estimated at $2.5 billion in 2025, is projected to witness a Compound Annual Growth Rate (CAGR) of 15% from 2025 to 2033, reaching approximately $7.8 billion by 2033. This expansion is fueled by several key factors. The rising adoption of location-based services (LBS) and geographic information systems (GIS) across industries like real estate, tourism, logistics, and urban planning is a major catalyst. Businesses are increasingly leveraging interactive maps to enhance customer engagement, improve operational efficiency, and gain valuable insights from geospatial data. Furthermore, advancements in mapping technologies, including the integration of AI and machine learning for improved data analysis and visualization, are contributing to market growth. The accessibility of user-friendly tools, coupled with the decreasing cost of cloud-based solutions, is also making interactive map creation more accessible to a wider range of users, from individuals to large corporations. However, the market also faces certain challenges. Data security and privacy concerns surrounding the use of location data are paramount. The need for specialized skills and expertise to effectively utilize advanced mapping technologies may also hinder broader adoption, particularly among smaller businesses. Competition among established players like Mapbox, ArcGIS StoryMaps, and Google, alongside emerging innovative solutions, necessitates constant innovation and differentiation. Nevertheless, the overall market outlook remains positive, with continued technological advancements and rising demand for data visualization expected to propel growth in the coming years. Specific market segmentation data, while unavailable, can be reasonably inferred from existing market trends, suggesting a strong dominance of enterprise-grade solutions, but with substantial growth expected from simpler, more user-friendly tools designed for individuals and small businesses.

The electronic cartography market is set to witness gradual growth between 2025 and 2035, fueled by the growing demand for sophisticated navigation systems, GIS-based analytics, and AI-based mapping solutions. The industry is expected to reach USD 32.26 billion in 2025 and expand to USD 48.74 billion by 2035, reflecting a compound annual growth rate (CAGR) of 10% during the forecast period.

Contract & Deals Analysis - Electronic Cartography Market

Company	Contract Value (USD Mn)
Garmin Ltd.	Approximately USD 90 - USD 100
Navionics (A Garmin Company)	Approximately USD 80 - USD 90
C-MAP (Navico Group)	Approximately USD 70 - USD 80
Maxar Technologies	Approximately USD 100 - USD 110

Country-wise Outlook

Country	CAGR (2025 to 2035)
USA	10.2%
China	10.9%
Germany	9.7%
Japan	10.1%
India	11.4%
Australia	9.9%

Competition Outlook

Company Name	Estimated Market Share (%)
Garmin Ltd.	20-25%
Navionics (Garmin)	15-20%
Maxar Technologies	10-15%
TomTom NV	8-12%
Honeywell Aerospace	5-10%
Thales Group	4-8%
Other Companies (combined)	30-38%

This dataset contains 82 annotated map samples from diverse historical city maps of Jerusalem and Paris, suitable for map text detection, recognition, and sequencing.

Organization of the data

The data in maptext_format.json is organized in the same way as in the General Data from the David Rumsey Collection from ICDAR 2024 Competition on Historical Map Text Detection, Recognition, and Linking [1].

The data is structured by image, and list of sequences (groups). The boolean attributes illegible and truncated are used to provide additional insight on the data quality.

Our interpretation of the truncated and illegible tags is the following:

• truncated refers to the case where part of a word is located outside the image crop, and is thus missing. In that case, the transcription stops at the image border, focusing only on the visible part of the word
• illegible is a subjective indication of (un)certainty in the transcription provided. Whenever possible, a best guess transcription is provided. Otherwise, the illegible letters are filled with blank spaces

The text corresponds to the diplomatic transcription, i.e. as it appears on the document. Text are transcribes with all latin characters, with cases, diacritics (e.g. ö, ḡ) and diagraphs (e.g. Œ).

Each word polygon consists of an even number of vertices arranged in clockwise order starting from the initial point to the top left. The first n/2 vertices represent the upper boundary line following the reading direction, while the second half represents the lower boundary line in the reverse direction. Here is an illustration:

Example structure

[
{
"image": "map_image_1.jpg",

# Here groups are what we call sequences.
"groups": [
{
"vertices": [[x1, y1], [x2, y2], ...],
"text": "Champs",
"illegible": "false",
"truncated": "false"
},
{
"vertices": [[x1, y1], [x2, y2], ...],
"text": "Elysées",
"illegible": "false",
"truncated": "false"
}
]
}
]


The file pandas_format.pkl contains the same data. It is only provided for convenience.

Image documents

The maps of Paris were taken from the Historical City Maps Semantic Segmentation Dataset [2]. The original documents were digitized by the Bibliothèque nationale de France (BnF), and the Bibliothèque Historique de la Ville de Paris (BHVP).

The maps of Jerusalem were curated from the collections of the National Library of Israel (NLI), and Wikimedia Commons.

Descriptive statistics

Number of words: 7528
Number of single-word sequences: 1757
Number of multi-word sequences: 1969
Statistics of multi-word sequences length:
mean: 2.93 words
std: 1.25 words
min: 2.00 words
med: 3.00 words
max: 15.00 words

Future updates

The transcribed text, corresponds to the diplomatic transcription, suitable for text recognition tasks. In future updates, we hope to complement it with an additional normalization attribute, which could extend abbreviations (e.g. "bvd." => "boulevard") and normalize transcriptions (e.g. "QVARTER" => "QUARTER").

Use and Citation

For any mention of this dataset, please cite :

@misc{paris_jerusalem_dataset_2025,
author = {Dai, Tianhao and Johnson, Kaede and Petitpierre, R{\'{e}}mi and Vaienti, Beatrice and di Lenardo, Isabella},
title = {{Paris and Jerusalem City Maps Text Dataset}},
year = {2025},
publisher = {Zenodo},
url = {https://doi.org/10.5281/zenodo.14982662}}

@article{recognizing_sequencing_2025,
author = {Zou, Mengjie and Dai, Tianhao and Petitpierre, R{\'{e}}mi and Vaienti, Beatrice and di Lenardo, Isabella},
title = {{Recognizing and Sequencing Multi-word Texts in Maps Using an Attentive Pointer}},
year = {2025}}

Corresponding author

Rémi PETITPIERRE - remi.petitpierre@epfl.ch - ORCID - Github - Scholar - ResearchGate

Work ethics

The data were annotated by two master's students from EPFL, Switzerland. The students were paid for their work using public funding, and were offered the possibility to be associated with the publication of the data.

License

This project is licensed under the CC BY 4.0 License.

Liability

We do not assume any liability for the use of this dataset.

References

1. Li Z., Lin Y., Chiang Y.-Y., Weinman J., Tual S., Chazalon J., Perret J., Duménieu B., Abadie N. (2024). ICDAR 2024 competition on historical map text detection, recognition, and linking. In Document Analysis and Recognition - ICDAR 2024: 18th International Conference, Athens, Greece, August 30–September 4, 2024, Proceedings, Part VI. Springer-Verlag, Berlin, Heidelberg, 363–380. https://doi.org/10.1007/978-3-031-70552-6_22
2. Petitpierre, R. (2021). Historical City Maps Semantic Segmentation Dataset. V1.0. https://doi.org/10.5281/zenodo.5513639

The self-driving 3D high-precision map market is experiencing rapid growth, driven by the escalating demand for autonomous vehicles and advanced driver-assistance systems (ADAS). The market's expansion is fueled by several key factors, including advancements in sensor technologies (LiDAR, radar, cameras), increasing investments in R&D by automotive manufacturers and technology companies, and the growing adoption of connected car technologies. The market is segmented by application (L1/L2+ Driving Automation, L3 Driving Automation, Others) and type (Crowdsourcing Model, Centralized Mode). The centralized mode currently dominates, leveraging sophisticated data processing and management systems, but crowdsourcing is gaining traction due to its cost-effectiveness and ability to rapidly update map data, particularly in dynamic urban environments. Leading players like TomTom, Google, and Baidu are strategically investing in enhancing their mapping capabilities and expanding their geographical coverage to capitalize on this burgeoning market. While challenges exist, such as high initial investment costs for infrastructure and data acquisition, and data security and privacy concerns, the long-term outlook remains exceptionally positive, driven by the inevitable shift towards autonomous driving technologies. The regional market exhibits significant variations. North America and Europe currently hold the largest market share, owing to the presence of established automotive and technology industries, and advanced regulatory frameworks supporting autonomous vehicle development. However, the Asia-Pacific region, particularly China and India, shows strong growth potential due to the rapid expansion of the automotive sector and significant government initiatives promoting autonomous driving technologies. Future market growth will be significantly influenced by advancements in artificial intelligence (AI) and machine learning (ML), enabling more accurate and dynamic map updates. Competition is intensifying, with both established mapping companies and emerging tech giants vying for market dominance through strategic partnerships, acquisitions, and technological innovations. Focus areas for future development include improving map accuracy, enhancing real-time updates, and addressing scalability challenges to support the increasing number of connected and autonomous vehicles.

Colombia Digital Map Market is expected to grow during 2025-2031

This raster layer canopy closure information for the Northern Tongass project area, prepared for the Northern portion of the Tongass National Forest to provide up-to-date and more complete information about vegetative communities, structure, and patterns across the Forest. Approximately 11.8 million acres, 8.6 million acres of which are terrestrial and inland waterbodies and rivers, were mapped through a partnership between the Geospatial Office (GO), Tongass National Forest, and the Alaska Regional Office. The Tongass National Forest and their partners prepared the regional classification system, identified the desired map units (map classes) and provided general project guidance. GO provided project support and expertise in vegetation mapping.The modeling units (mapping polygons) were characterized with the following vegetation attributes: 1) map group, 2) vegetation type, 3) tree canopy cover percent, 4) tree canopy cover class, 5) tree size class, 6) change percent, 7) change year, 8) biomass for trees ≥ 2” dbh, 9) crown competition factor, 10) gross board feet (GBF) for trees ≥ 9” dbh, 11) quadratic mean diameter (QMD) for trees ≥ 2” dbh, 12) quadratic mean diameter for trees ≥ 9” dbh, 13) rumple index, 14) stand density index (SDI) for trees ≥ 9” dbh, 15) trees per acre (TPA) for trees ≥ 1’ tall, 16) trees per acre for trees ≥ 6” diameter at breast height (dbh), and 17) acres. The minimum map feature depicted on the map is 0.25 acres. This map product was generated using imagery primarily acquired between 2020 – 2024, reference information collected in the summers of 2023 – 2024, and LiDAR data flown in 2015. Every effort was taken to ensure consistency in the final products and these can be considered indicative of the existing vegetation conditions found within the project boundary during the growing season of 2024. All map products were designed according to National Forest Service vegetation mapping standards and are stored in federal databases. For more detailed information on mapping methodology please see the Central and Northern Tongass Vegetation Mapping Report:Central and Northern Tongass Vegetation Mapping Report (in progress): Dangerfield, C.; Bellante, G.; Foss, J.; Lund, A.; Caster, A.; Mohatt, K.; Homan, K.; Wittwer, D.; Johnson, T.; Goetz, W.; Moody, R.; Vernier, M.; Hemingway, B.; Achtenhagen, A.; Ryerson, D.; Megown, K.. 2025. Tongass National Forest Existing Vegetation Map. Salt Lake City, UT. In progress.

Chile Digital Map Market is expected to grow during 2025-2031

Business location data for Maptitude mapping software are from Caliper Corporation and contain point locations for businesses.

ZIP Code business counts data for Maptitude mapping software are from Caliper Corporation and contain aggregated ZIP Code Business Patterns (ZBP) data and Rural-Urban Commuting Area (RUCA) data.

The global Car GPS Navigation System market, valued at $15.91 billion in 2025, is projected to experience robust growth, exhibiting a compound annual growth rate (CAGR) of 10.03% from 2025 to 2033. This expansion is fueled by several key factors. The increasing adoption of smartphones with advanced navigation capabilities and the integration of GPS systems into infotainment systems are significant drivers. Furthermore, the rising demand for enhanced safety features, including real-time traffic updates and advanced driver-assistance systems (ADAS), is boosting market growth. Consumer preference for seamless navigation experiences and the growing popularity of connected cars are also contributing to market expansion. The market is segmented into hardware and software/services components, with software and services witnessing faster growth due to the increasing demand for subscription-based services, map updates, and advanced features like voice control and augmented reality navigation. While the market faces challenges like the increasing prevalence of built-in navigation systems in vehicles and the rise of smartphone-based navigation apps, the continuous innovation in GPS technology, including the integration of high-definition maps and artificial intelligence (AI)-powered features, will continue to drive market growth across key regions including North America (particularly the US), Europe (Germany and France being major contributors), and APAC (with China and Japan leading the way). The competitive landscape is characterized by a mix of established automotive component suppliers, technology companies, and specialized map providers. Companies like Robert Bosch GmbH, TomTom NV, and Garmin Ltd. hold significant market share, leveraging their expertise in hardware and software development. Apple Inc. and Google (although not explicitly listed) exert indirect influence through their integrated navigation systems on smartphones and their mapping technologies. The market witnesses intense competition driven by product differentiation through features, pricing strategies, and partnerships with automotive manufacturers. Risks include potential disruptions from technological advancements, economic fluctuations impacting consumer spending, and the increasing regulatory landscape concerning data privacy and security. The ongoing evolution of autonomous driving technology may present both opportunities and challenges, potentially reshaping the future of the car GPS navigation system market in the long term.

The automotive map light market is experiencing steady growth, driven by increasing vehicle production and a rising demand for enhanced interior lighting features. While precise market size figures for 2025 are unavailable, considering a plausible CAGR of 5% (a conservative estimate given general automotive lighting growth trends) and estimating a 2025 market value of $500 million based on industry reports and analyses of related segments, we project a market size of approximately $700 million by 2033. This projected growth is fueled by several key factors. Technological advancements such as LED and ambient lighting systems are creating more sophisticated and energy-efficient map lights, leading to increased consumer adoption. Furthermore, rising safety concerns and regulations are prompting automakers to integrate improved lighting solutions into their vehicles, directly benefiting the map light market. The increasing prevalence of SUVs and luxury vehicles, segments known for incorporating advanced lighting features, also contributes to market expansion. However, the market faces challenges. Fluctuations in raw material prices and the overall economic climate can impact manufacturing costs and consumer spending. Competition from manufacturers in emerging economies offering cost-effective alternatives presents a potential restraint. Nevertheless, the ongoing trend towards vehicle personalization and improved in-cabin experiences suggests sustained growth in the coming years. Leading manufacturers such as GE Lighting, Osram Sylvania, and Philips are actively investing in research and development, fostering innovation and competition within the sector. This competitive landscape further enhances the overall market dynamism and its potential for future expansion.

The global mussel adhesive protein (MAP) market is experiencing significant growth, driven by increasing demand across diverse sectors. While precise market size figures for 2025 are not provided, considering typical CAGR values for emerging biotech markets (let's assume a conservative CAGR of 15% for illustration), and estimating a 2025 market size based on extrapolation from available information, we can project a global market value in the range of $150-$200 million. This robust expansion is fueled by the unique properties of MAP, including its strong adhesion in wet environments, biocompatibility, and biodegradability. Key application areas driving market growth include the medical field (tissue adhesives, drug delivery systems), cosmetics (wound healing products, skincare formulations), and research (biomaterial development, adhesive technology advancements). The market is segmented into natural and recombinant MAP, with recombinant MAP expected to witness faster growth due to its potential for scalability and consistent quality. However, challenges such as high production costs and regulatory hurdles associated with new biomaterials could act as restraints on market expansion. The market is geographically diverse, with North America and Europe currently holding significant shares. However, the Asia-Pacific region is projected to exhibit high growth potential, driven by increasing research activities and a burgeoning healthcare sector, particularly in countries like China and India. Major players in the industry include Jiangyin Usun Biochemical Technology, BD, Kollodis BioSciences, Biopolymer, JUYOU Bio-tech, Shenzhen Baiyin Biotechnology, and Gproan Biotechnologies(Suzhou), Inc., who are actively engaged in developing and commercializing MAP-based products. Competition is expected to intensify as new players enter the market and existing companies expand their product portfolios. Continued research and development efforts focused on improving MAP production efficiency and exploring novel applications will be crucial for the continued success of this promising market.

The global Monoammonium Phosphate (MAP) market is experiencing robust growth, driven by increasing demand across diverse sectors. While the exact market size for 2025 isn't provided, considering typical CAGR values for chemical markets (let's assume a conservative 5% for illustrative purposes, though this would need adjustment with actual data) and a hypothetical 2024 market size of $2 billion USD, the 2025 market size could be estimated around $2.1 billion USD. This growth is fueled primarily by the expanding food and beverage industry, where MAP serves as a crucial leavening agent and nutrient supplement. The agricultural sector, particularly animal feed and poultry farming, also contributes significantly to MAP demand due to its role as a phosphate fertilizer enhancing crop yields. Furthermore, the pharmaceutical and personal care industries utilize MAP in various formulations. The market is segmented by grade (food, pharma, fertilizer, industrial) and application, with the fertilizer grade commanding a substantial share. Key players like Mosaic Company, PotashCorp, and Mitsui Chemicals are driving innovation and expanding their market presence through strategic partnerships and capacity expansions. Geographic growth is uneven, with regions like Asia-Pacific (particularly China and India) exhibiting rapid expansion owing to burgeoning agricultural sectors and increasing disposable incomes. However, regulatory hurdles related to phosphate use and environmental concerns pose challenges to market expansion in certain regions. Looking ahead to 2033, continued growth is projected, albeit at a potentially moderating pace. Assuming a consistent CAGR of 5% (again, this requires refinement with actual data), the market could reach approximately $3.5 billion USD by 2033. Factors influencing future growth include technological advancements improving MAP production efficiency, stricter regulations necessitating higher-quality MAP, and evolving consumer preferences driving demand for healthier food products. Competition among established players and the emergence of new entrants could also significantly shape the market landscape during the forecast period. Understanding regional variations in regulations and market dynamics will be crucial for companies seeking to capitalize on future opportunities. The continued emphasis on food security and sustainable agricultural practices will remain key drivers of MAP demand in the years to come.

This flight dataset provided by the GRVC Robotics Lab of the University of Seville is derived from the euROBIN Nancy Robotics Competition (25-28 November 2024), as part of the paper "Fully Autonomous Dual Arm Aerial Delivery Robot for Intralogistics: the euROBIN Nancy Competition Flight Dataset" submitted to the IROS 2025 conference, whose authors are Alejandro Suarez, Jorge Pozas-Guerra, and Anibal Ollero.

The dataset comprises 42 folders sorted by date and time, corresponding to 54 flight tests. Note that some log files contain two flight tests. These log files were generated by Ardupilot, the open source flight control software [1][2] implemented on the CUAV v5 autopilot. A MATLAB script called DataViewer.m is provided on each folder, so users can easily visualize the data, including the time evolution of the multi-rotor position, velocity, attitude, angular rate, and differential PWM in pitch, as well as the 3D trajectory represented along with the 3D map of the scenario. The differential PWM corresponds to the difference between the duty cycle applied to the Electronic Speed Controllers (expressed in microseconds) of the front propellers with respect to the rear propellers. This differential signal is useful to identify when the arms move forward or when the parcel was grasped as it corresponds to the moment/torque in pitch exerted by the aerial platform controller to compensate the variation in the center of mass.

The 3D map is a point cloud (.PCD file) generated with FAST-LIO [3] using a Livox Mid-360 LiDAR, rotated 30 degrees downwards in pitch. The map was generated moving the aerial robot around the scenario by hand (not flying) before conducting the flight tests. The map included in this dataset (scanThursdayDroneArea.pcd) was generated on Thursday 28 November, corresponding to the scenario of the final demonstration. However, the position of the supply points from which the aerial robot grasped the parcels remained fixed during the four days of the competition. Only the delivery points changed between scenarios. A video from the aerial delivery operation performed by the robot can be seen in [4]. The aerial robot is an improved version of the platform employed for the euROBIN 1st Robotics Hackathon [5], achieving fully autonomous operation in the aerial parcel grasping and drop.

A detailed description of the euROBIN Nancy Robotics Competition can be found on the rulebook [6]. The aerial robot was evaluated in four variations of the scenario, with increasing level of complexity:

> 25 November: obstacle-free scenario
> 26 November: scenario with virtual obstacle
> 27 November: scenario with physical and virtual obstacle
> 28 November: scenario with two physical obstacles and one virtual obstacle

As said before, the two supply points were the same in the four scenarios, changing the location of the boxes used as drop points according to the location of the obstacles.

CREDITS

The GRVC Team Members participating in the euROBIN Nancy Robotics Competition were: Alejandro Suarez, Jorge Pozas-Guerra, Jose Antonio Hernandez, and Anibal Ollero.

CONTACT

Alejandro Suarez (asuarezfm@us.es)
GRVC Robotics Lab, University of Seville
https://grvc.us.es/

ACKNOWLEDGMENT

This work is supported by euROBIN, the European ROBotics and AI Network (Grant agreement 101070596), funded by the European Commission.

REFERENCES

[1] https://ardupilot.org/
[2] https://ardupilot.org/copter/docs/common-downloading-and-analyzing-data-logs-in-mission-planner.html
[3] https://github.com/hku-mars/FAST_LIO
[4] https://www.youtube.com/watch?v=Yg_AyYJrI28
[5] A. Suarez et al., "Door-to-Door Parcel Delivery From Supply Point to User’s Home With Heterogeneous Robot Team: The euROBIN First-Year Robotics Hackathon," in IEEE Robotics & Automation Magazine, doi: 10.1109/MRA.2024.3501954.
[6] https://www.eurobin-project.eu/images/2024/euROBIN_Nancy_Coopetition_RuleBook.pdf