A dataset for 2d path-planning. There are 172192 train instances, 51103 test instances and 15311 validation instances. Each sample contains: - map: a [100, 100] tensor representing an occupancy grid map. 0s are traversable cells, 1s are obstacles. - start: a [2,] tensor representing the coordinates of the starting point on the map - goal: a [2,] tensor representing the coordinates of the desired target point on the map - path: a [n, 2] tensor representing the ground truth optimal trajectory to follow from the start to the goal. The path is computed using the popular D* Lite algorithm, modified so to force a margin of 1 cell from any obstacle. Notice that there are samples in which the goal appears to be placed on an obstacle. In those cases, the trajectory ends with the last feasible (i.e. a cell which is not an obstacle, a 0 in the matrix map) position closest to the goal.

I'm sorry, but I messed up with python namespaces while saving the dataset samples. Check the related notebook for a quick and dirty fix. If you want to make your own dataset, follow the instructions on the github repo.

For an example of a possible application, have a look at my article on Medium.

2D Maps from CAMELS IllustrisTNG Simulations (Subset)

Author’s Note

This is my first dataset publication on Kaggle, and I’m very excited to share a small, manageable subset of the CAMELS Multifield (CMD) data to help the ML community practice image classification and astrophysical data analysis! Make sure to upvote, comment, and share if you enjoy or have suggestions for me. This subset is distributed under the MIT License with permission from the original author, Francisco Villaescusa-Navarro, and the CAMELS collaboration.

1. Overview

The CAMELS Multifield Dataset (CMD) is a massive collection of 2D maps and 3D grids derived from cosmological simulations that track the evolution of gas, dark matter, stars, black holes, and (in some suites) magnetic fields. These simulations vary important cosmological and astrophysical parameters, allowing researchers to explore and train machine learning models that could help us understand the universe’s fundamental properties.

Because the original CMD is extremely large, I’m providing a small subset from the IllustrisTNG suite, specifically from the LH (Latin Hypercube) set. This subset focuses on 2D maps at redshift z = 0.00, chosen randomly for demonstration and educational purposes.

2. About CAMELS & CMD

2.1 CAMELS Project

• CAMELS stands for Cosmology and Astrophysics with MachinE Learning Simulations.
• It aims to produce large datasets of cosmological simulations where diverse parameters (e.g., Ω_m, σ_8, supernova feedback, black-hole feedback) are systematically varied.

2.2 CMD (CAMELS Multifield Dataset)

• CMD contains hundreds of thousands of 2D maps and 3D grids from thousands of state-of-the-art hydrodynamic and N-body simulations.
• Data is organized by suite (IllustrisTNG, SIMBA, Astrid, or Nbody) and set (LH, CV, 1P, EX, BE, SB, etc.).
• Each 2D map or 3D grid is associated with a specific set of simulation parameters (the “labels”).

2.3 Suites

1. IllustrisTNG (MHD simulations): Gas, dark matter, stars, black holes, and magnetic fields.
2. SIMBA (Hydrodynamic): Similar to IllustrisTNG, but uses the SIMBA code.
3. Astrid (Hydrodynamic): Another code with its own feedback physics.
4. Nbody (Gravity-only): Follows only dark matter without astrophysical processes.

2.4 Sets

• LH (Latin Hypercube): Each simulation has unique values for all parameters, covering a broad range in parameter space.
• CV, 1P, EX, BE, SB: Other sets that vary parameters differently or keep some fixed.

3. This Subset

1. Suite & Set: IllustrisTNG – LH (Latin Hypercube sampling).
2. Field Example: Dark matter density (Mcdm), though you could encounter other fields if you download more from the official CMD resource.
3. Format: .npy files, each containing multiple 2D slices (maps).
4. Size: A small fraction of the full dataset (~5–10 maps or however many you decide to provide).
5. Coordinates: Each 2D map is a “slice” of the cosmological volume at redshift z = 0.00.
6. Parameter Labels:
   • Ω_m (matter density fraction),
   • σ_8 (root-mean-square amplitude of matter fluctuations),
   • A_SN1, A_SN2 (supernova feedback parameters),
   • A_AGN1, A_AGN2 (black-hole/AGN feedback parameters).

Because these maps are from the IllustrisTNG suite, they have non-zero values for all six parameters. If any user references the corresponding Nbody subset, note that only Ω_m and σ_8 apply there.

4. Why This Matters

The CAMELS data—especially 2D projections—are excellent for: - Machine Learning & Computer Vision: Classification, segmentation, or anomaly detection tasks. - Cosmology Research: Investigating how changes in Ω_m, σ_8, or feedback physics affect large-scale structure formation. - Educational Purposes: Students and newcomers can learn how real cosmological simulation data is structured and experiment with analysis or ML pipelines.

5. License & Attribution

This subset is shared under the MIT License granted by the original author, Francisco Villaescusa-Navarro, and the broader CAMELS collaboration. Please see the “License” section for the full text.

1. I am not the original author; I only provide a subset for educational and ML practice purposes.
2. All credits go to the CAMELS collaboration and the authors of the CMD.
3. If you publish results using this data, please cite the original sources appropriately and mention the CAMELS project.

6. References & Further Reading

-**CAMELS Project Overview**
-**IllustrisTNG Official Site**
-**[CMD Official Documentation](https://camels-multifield-dataset.read...

The raster datasets in this data release are maps of soil surface properties that were used in analyzing different approaches for digital soil mapping. They include maps of soil pH, electrical conductivity, soil organic matter, and soil summed fine and very fine sand contents that were created using both 2D and 3D modeling strategies. For each property a map was created using both 2D and 3D approaches to compare the mapped results.

2D Web Map depicting the "Smart Centres" at 700 Centre St, Thornhill, ON L4J 0A7. 43.811572597832004, -79.45177129969935, 207 MSL. Civil Engineering "Crack & Fracture" assessment of the Public Parking Areas and Aerial (Drone Photogrammetry) "Reality Capture" mission conducted by ACCESSiFLY between Friday, June 24, through Wednesday, June 29, 2022 during Transport Canada & NAVCanada approved "RPAS Flight".

The Navigation Electronic Map market is booming, projected to reach $3021 million by 2025 with a 25.4% CAGR. This report analyzes market drivers, trends, restraints, and key players, offering insights into 2D/3D maps across personal, commercial, and military applications. Explore regional market shares and future growth projections.

This is a platform that provides high-quality maps of Vworld for web and desktop in a mobile environment. It accepts various national spatial information of Vworld, and allows creation and editing of places, lines, polygons, and circles, and various map expression methods. It supports iOS and Android, and the Android Framework is based on Osmdroid and Java 1.7, so API 25 or lower is recommended.

2D Map For T1 distribution vs T2 distribution curve from Halliburton Logging. Measured in unitless.

1. This map is intended as a current snapshot of information that can be disclosed publicly regarding tax credit seismic surveys.2. Representation on this map does not guarantee public release and is subject to statutory requirements in effect at the time of acquisition and application for tax credit.3. Release is subject to public notice and permission of private oil and gas mineral estate owner where applicable. Some surveys require clipping to mineral ownership boundaries; actual map extents of released datasets may differ from those shown here. 4. Year label "Released" surveys denote actual release year. Year label "Eligible" and "Issued" denote the year in which the data is eligible for release and distribution under AS 43.55.025(f)(2)(c), most tax credit seismic projects are held confidential for 10 years from completion of initial seismic processing. 5. Map does not include surveys whose initial seismic processing was completed less than 10 years ago but prior to legislative adoption of the disclosure clause of AS 43.55.025(f)(5). Seismic surveys acquired with credits under AS 43.55.023 are not subject to disclosure under AS 43.55.025(f)(5), and cannot be represented here until their confidentiality period has expired.6. Additional qualifying surveys will be added to this map as new tax credit certificates are issued or as changes in confidentiality status allows.

A 2D background map created based on a continuous digital map, projecting the map to EPSG:3857. Provides graphic map/image map/midnight map/gray map/hybrid map map information. WMTS is an OGC international standard that can be used in libraries and tools that comply with the standard, such as openlayers, qgis, arcgis, cesium, and leaflet. For more details, see the attached file. If the sample does not run, receive an authentication key, change it, and then run it.

Number of tesserae in 2D distance map-based final pipeline segmentations.

The WMTS implementation standard provides a standards-based solution for serviing digital maps using predefined image tiles. Through the constructs of the specification, a WMTS service advertises imagery layers (e.g. imagery product) and defines the coordinate reference system, scale, and tiling grid available for access.

Stations in Hong Kong, Phillippines, Taiwan, and Wuhan of China, for the 2D TEC MAP

Discover the booming Simultaneous Localization and Mapping (SLAM) market, projected to reach [estimated 2033 market size in millions] by 2033, with a CAGR of 26.78%. Explore key drivers, trends, and restraints shaping this dynamic industry across autonomous vehicles, robotics, and AR/VR. Learn more about leading companies and regional market share. Recent developments include: November 2022 - Singapore based autonomous navigation solutions provider dConstruct introduced Ouster digital lidar to create highly accurate SLAMs and point cloud maps. Dconstruct creates these maps virtually and then studies the deployment of autonomous robots and the inspection and reconstruction of working environments. For instance - A map of a smart office building, The Galen, in Singapore was created on the cloud and was used to facilitate the deployment of autonomous robots ranging from cleaning robots to last-mile delivery robots., February 2023 - KUKA, the German manufacturer of industrial robots, launched Intralogistics Robot, with wheel sensors and laser scanners that let it safely move through its surroundings. The company claims this product is compatible to meets the highest safety requirements. It the specification such as 3D object detection, laser scanners, a payload of 1,322 pounds, and an automated guided vehicle system. The robot or the collision-free worker has been developed to work with logistics workers without the need for safety fencing. It employs eight safety zones in the front and back that can be adjusted for vehicle speeds and particular applications., July 2022 - Polymath Robotics, a start-up, developed an SDK-integrated plug-and-play software platform that enables businesses to quickly and affordably automate industrial vehicles. The start-up is developing fundamentally generalizable autonomy intending to automate the roughly 50 million industrial vehicles currently used in enclosed spaces.. Key drivers for this market are: Growing Penetration of Mapping Technologies in Domestic Robots and UAV, Advancements in Visual SLAM Algorithm; Increasing Application of SLAM in Augmented Reality. Potential restraints include: Growing Penetration of Mapping Technologies in Domestic Robots and UAV, Advancements in Visual SLAM Algorithm; Increasing Application of SLAM in Augmented Reality. Notable trends are: UAVs and Robots Will Experience Significant Growth in the Market.

Companion dataset of the manuscript: Fu Li, Umberto Villa, Seonyeong Park, Mark A. Anastasio. Three-dimensional stochastic numerical breast phantoms for enabling virtual imaging trials of ultrasound computed tomography. Arxiv preprint 2106.02744 (2021) This dataset includes a collection of 52 two-dimensional slices of numerical breast phantoms (NBPs) and corresponding ultrasound computed tomography (USCT) simulated measurement data. The anatomical structures of these NBPs were obtained by use of tools from the Virtual Imaging Clinical Trial for Regulatory Evaluation (VICTRE) project. More details on the modification and extension of the VICTRE NBPs for use in USCT studies can be found in the accompanying paper. The NBPs included in this dataset are representative of four ACR BI-RADS breast composition types: A. The breast is almost entirely fatty B. There are scattered areas of fibroglandular density C. The breasts is heterogeneously dense D. The breast is extremely dense Each NBP contains 2D maps of tissue labels, speed of sound, acoustic attenuation, density. A low-resolution speed-of-sound map is also provided to reproduce the FWI reconstruction results presented in the accompanying paper. Corresponding USCT measurement data were simulated by modeling 2D wave propagation in lossy heterogeneous media using a time explicit pseudospectral wave propagation solver. The dataset consists of three folders: The 2d_slices folder contains the 52 slices extracted from 3D NBPs. The measurements folder contains simulated measurement data corresponding to each slice. The imaging_system folder contains information about the 2D imaging system (excitation source, transducer coordinates) In addition, the following helper Matlab scripts are included: read_data.m: Helper function to load and visualize the excitation source and transducer locations. read_waveform_data.m: Helper function to read the .h5 files containing the measurement data. Each slice is saved as a binary MATLAB file (.mat) and contains the following variables label: tissue label map with [2560,2560] pixels and 0.1mm pixel size. Tissue types are denoted using the following labels: water (0), fat (1), skin (2), glandular (29), ligament (88), lesion (200). sos: speed of sound map (mm/μs) with [2560,2560] pixels and 0.1 mm pixel size. Data is stored as data type float32. aa: acoustic attenuation map (Np/m/MHzy) with [2560,2560] pixels and 0.1mm pixel size. Data is stored as data type float32. density: density map (kg/mm3) with [2560,2560] pixels and 0.1 mm pixel size. Data is stored as data type float32. sos_ini: low resolution speed of sound map (mm/μs) with [1280,1280] pixels and 0.2mm pixel size. Data is stored as data type float32. This is the initial guess used in the speed of sound reconstructions in our paper. y: attenuation exponent used for simulation. seed: phantom id type: breast composition type (A-D) The simulated measurement data is saved in hdf5 format. Measurement data corresponding the i-th emitting transducer is stored with hdf5 key equal to the transducer index as a two-dimensional array of size [1024,4250]. Here, the rows represent the receiver index, and the columns the time sample. The sampling frequency is 25MHZ. Because of file size limitations, measurement data for each slice has been divided into 8 chunks, containing data from 128 receivers each. The imaging_system folder contains information regarding the 2D imaging system. source300.mat describes the time profile of the exitation pulse. It consists of 300 time samples at a sampling frequency of 25Mhz. locations1024.mat provide the xy coordinates (mm)of the location of each transducer Data type is float32. Array size is [2x1024]. Warning: This is a very large dataset (~1TB). Please check out our download script written in python.

Three files consisting of a txt file dataset of gamma radiation count observations, with SLAM estimated position, and a 2D SLAM map of the Jožef Stefan Institute (JSI) TRIGA Mark II reactor hall.The JSI_radiation_data.txt consists of comma separated values, with a header row indicating the data types. Timestamp is with respect to Unix Epoch time (as is standard in ROS). Spatial coordinates of the robot x, y, z are in metres. As the robot is a ground level 2D robot, the SLAM estimate restricts the Z height to be roughly constant. Only x and y data are necessary. The counts data are in counts per second, indicating the number of events collected over a ~1 second time window by a CeBr3 scintillator detector and mixed field analyser.The map file (.pgm) is a trinary (three value) map generated by SLAM via ROS (Robot Operating System). The three values related to occupied (obstacles and physical features, such as walls), unoccupied (free-space), and unknown.The map metadata file (.yaml) provides values to convert pixel position of the map file into coordinates (in metres).Data was originally collected 31/01/2020 (in ROS bag format), which was interrogated to provide the data in the .txt file.This dataset is then post-processed to provide interpolated maps of gamma radiation, based on the point observations and maps in these files.

The WMTS implementation standard provides a standards-based solution for serviing digital maps using predefined image tiles. Through the constructs of the specification, a WMTS service advertises imagery layers (e.g. imagery product) and defines the coordinate reference system, scale, and tiling grid available for access.

DEEPEN stands for DE-risking Exploration of geothermal Plays in magmatic ENvironments. Part of the DEEPEN project involved developing and testing a methodology for a 3D play fairway analysis (PFA) for multiple play types (conventional hydrothermal, superhot EGS, and supercritical). This was tested using new and existing geoscientific exploration datasets at Newberry Volcano. This GDR submission includes images, data, and models related to the 3D favorability and uncertainty models and the 2D favorability and uncertainty maps. The DEEPEN PFA Methodology is based on the method proposed by Poux et al. (2020), which uses the Leapfrog Geothermal software with the Edge extension to conduct PFA in 3D. This method uses all available data to build a 3D geodata model which can be broken down into smaller blocks and analyzed with advanced geostatistical methods. Each data set is imported into a 3D model in Leapfrog and divided into smaller blocks. Conditional queries can then be used to assign each block an index value which conditionally ranks each block's favorability, from 0-5 with 5 being most favorable, for each model (e.g., lithologic, seismic, magnetic, structural). The values between 0-5 assigned to each block are referred to as index values. The final step of the process is to combine all the index models to create a favorability index. This involves multiplying each index model by a given weight and then summing the resulting values. The DEEPEN PFA Methodology follows this approach, but split up by the specific geologic components of each play type. These components are defined as follows for each magmatic play type: 1. Conventional hydrothermal plays in magmatic environments: Heat, fluid, and permeability 2. Superhot EGS plays: Heat, thermal insulation, and producibility (the ability to create and sustain fractures suitable for and EGS reservoir) 3. Supercritical plays: Heat, supercritical fluid, pressure seal, and producibility (the proper permeability and pressure conditions to allow production of supercritical fluid) More information on these components and their development can be found in Kolker et al., 2022. For the purposes of subsurface imaging, it is easier to detect a permeable fluid-filled reservoir than it is to detect separate fluid and permeability components. Therefore, in this analysis, we combine fluid and permeability for conventional hydrothermal plays, and supercritical fluid and producibility for supercritical plays. More information on this process is described in the following sections. We also project the 3D favorability volumes onto 2D surfaces for simplified joint interpretation, and we incorporate an uncertainty component. Uncertainty was modeled using the best approach for the dataset in question, for the datasets where we had enough information to do so. Identifying which subsurface parameters are the least resolved can help qualify current PFA results and focus future efforts in data collection. Where possible, the resulting uncertainty models/indices were weighted using the same weights applied to the respective datasets, and summed, following the PFA methodology above, but for uncertainty. There are two different versions of the Leapfrog model and associated favorability models: - v1.0: The first release in June 2023 - v2.1: The second release, with improvements made to the earthquake catalog (included additional identified events, removed duplicate events), to the temperature model (fixed a deep BHT), and to the index models (updated the seismicity-heat source index models for supercritical and EGS, and the resistivity-insulation index models for all three play types). Also uses the jet color map rather than the magma color map for improved interpretability. - v2.1.1: Updated to include v2.0 uncertainty results (see below for uncertainty model versions) There are two different versions of the associated uncertainty models: - v1.0: The first release in June 2023 - v2.0: The second release, with improvements made to the temperature and fault uncertainty models. ** Note that this submission is deprecated and that a newer submission, linked below and titled "DEEPEN Final 3D PFA Favorability Models and 2D Favorability Maps at Newberry Volcano" contains the final versions of these resources. **

This National Geographic Style Map (World Edition) web map provides a reference map for the world that includes administrative boundaries, cities, protected areas, highways, roads, railways, water features, buildings, and landmarks, overlaid on shaded relief and a colorized physical ecosystems base for added context to conservation and biodiversity topics. Alignment of boundaries is a presentation of the feature provided by our data vendors and does not imply endorsement by Esri, National Geographic or any governing authority.This basemap, included in the ArcGIS Living Atlas of the World, uses the National Geographic Style vector tile layer and the National Geographic Style Base and World Hillshade raster tile layers.The vector tile layer in this web map is built using the same data sources used for other Esri Vector Basemaps. For details on data sources contributed by the GIS community, view the map of Community Maps Basemap Contributors. Esri Vector Basemaps are updated monthly.Use this MapThis map is designed to be used as a basemap for overlaying other layers of information or as a stand-alone reference map. You can add layers to this web map and save as your own map. If you like, you can add this web map to a custom basemap gallery for others in your organization to use in creating web maps. If you would like to add this map as a layer in other maps you are creating, you may use the tile layers referenced in this map.

Mobile Robot Map Diff Tools Market Outlook

According to our latest research, the global Mobile Robot Map Diff Tools market size reached USD 1.27 billion in 2024, with a robust growth momentum supported by rapid advancements in robotics and automation. The market is projected to expand at a CAGR of 13.4% from 2025 to 2033, reaching an estimated USD 4.04 billion by 2033. Key drivers fueling this growth include the increasing adoption of mobile robots in industrial automation, the rising need for precise navigation solutions, and the proliferation of smart warehouses worldwide. As per our latest research, the market continues to evolve, integrating advanced mapping and map difference (diff) tools to enhance robot efficiency and operational reliability across diverse sectors.

A primary growth factor for the Mobile Robot Map Diff Tools market is the accelerating pace of industrial automation, particularly within manufacturing and logistics sectors. Companies are increasingly leveraging mobile robots to streamline operations, reduce labor costs, and improve safety standards. The need for advanced map diff tools arises from the necessity to ensure accurate navigation and localization in dynamic environments, where robots must continuously compare and update their internal maps to adapt to changes. This is especially critical in large-scale manufacturing plants and distribution centers, where even minor mapping discrepancies can lead to operational inefficiencies or safety hazards. The integration of artificial intelligence and machine learning into these tools further enhances their ability to detect and adapt to environmental changes in real-time, driving widespread adoption.

Another significant growth driver is the expansion of e-commerce and the resulting demand for smart warehouse management solutions. With the rise of online shopping, companies are investing heavily in automated storage and retrieval systems powered by mobile robots. Map diff tools play a crucial role in enabling these robots to navigate complex warehouse layouts efficiently while responding to frequent changes in inventory and infrastructure. The adoption of 2D, 3D, and hybrid map diff technologies allows for seamless integration of robots into existing warehouse management systems, enhancing overall productivity and reducing operational downtime. Furthermore, as companies strive to achieve higher levels of automation and scalability, the need for robust and reliable map diff solutions is expected to intensify, contributing to sustained market growth.

Technological advancements in sensor technologies, cloud computing, and edge processing also contribute significantly to the growth of the Mobile Robot Map Diff Tools market. The development of high-resolution LiDAR, advanced cameras, and real-time data processing capabilities enables more accurate mapping and faster map differentiation. Cloud-based deployment models are gaining traction, offering scalability, remote accessibility, and seamless updates for map diff tools. This technological evolution is not only making these solutions more affordable and accessible to small and medium enterprises but also expanding their application scope beyond traditional industrial settings to healthcare, defense, and research institutions. The convergence of these technologies is expected to further accelerate market expansion over the forecast period.

Regionally, Asia Pacific is emerging as a dominant force in the Mobile Robot Map Diff Tools market, driven by rapid industrialization, significant investments in robotics, and a burgeoning e-commerce sector. Countries such as China, Japan, and South Korea are leading the charge, supported by government initiatives and favorable regulatory frameworks. North America and Europe continue to be strong markets, benefiting from early adoption of advanced robotics and a strong presence of technology providers. Meanwhile, the Middle East & Africa and Latin America are gradually catching up, fueled by increasing awareness and investment in automation technologies. This global shift towards automation and smart robotics is expected to create substantial opportunities for map diff tool providers across all regions.

Product Type Analysis

The Mobile Robot Map Diff Tools market is segmented by product type into 2D Map Diff Tools, 3D Map Diff Tools, and Hybrid Map Diff Tools. The 2D Map Diff Tools segment has traditionally dominated the market due to its widespread use

Additional file 2: Supplementary file 1. Molecular mass and isoelectric point (pI) of chloroplast proteins.