Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
5
datasets available to search
ShareScore release 0.9.0
Dataset results
5 results for “Driving Scenario”
DeepScenario: An Open Driving Scenario Dataset for Autonomous Driving System Testing
<p>With the rapid development of autonomous driving systems (ADSs), testing ADSs under various driving conditions has become a key method to ensure the successful deployment of ADS in the real-world. However, it is impossible to test all the scenarios due to the inherent complexity and uncertainty of ADSs and the driving tasks. Further, testing of ADSs is expensive regarding time and computational resources. Therefore, a large-scale driving scenario dataset consisting of various driving conditions is needed. To this end, we present an open driving scenario dataset <em>DeepScenario</em>, containing over 30<em>K</em> <em>executable</em> driving scenarios, which are collected by 2880 test executions of three driving scenario generation strategies. Each scenario in the dataset is labeled with six attributes characterizing test results. We further show the attribute statistics and distribution of driving scenarios. For example, there are 1050 collision scenarios, in 917 scenarios there were collisions with other vehicles, 105 and 28 with pedestrians and static obstacles, respectively.</p> <p>This dataset contains:</p> <ol> <li><strong><a href="https://github.com/Simula-COMPLEX/DeepScenario/tree/main/deepscenario-dataset">deepscenario-dataset</a></strong> - DeepScenario dataset, which includes driving scenarios generated by executing three scenario generation strategies: <em>Reinforcement Learning (RL)-based Strategy</em>, <em>Random-based Strategy</em>, <em>Greedy-based Strategy</em>;</li> <li><strong><a href="https://github.com/Simula-COMPLEX/DeepScenario/tree/main/deepscenario-toolset">deepscenario-toolset</a></strong> - The toolset for <em>DeepScenario</em> dataset, including <em>ScenarioCollector</em> that can automatically collect driving scenarios, and <em>ScenarioRunner</em> that can support replaying driving scenarios. We also provide <a href="https://github.com/Simula-COMPLEX/DeepScenario/tree/main/deepscenario-toolset/lgsvl/scenariotoolset">source code</a> and <a href="https://github.com/Simula-COMPLEX/DeepScenario/tree/main/deepscenario-toolset#usage">usage examples</a> for the toolset. </li> </ol> <p>More information about DeepScenario dataset is available in our Github repository: <a href="https://github.com/Simula-COMPLEX/DeepScenario">https://github.com/Simula-COMPLEX/DeepScenario</a>.</p>
Database of 3D rendered freeway driving scenarios
<p>The <code>videos.tar</code> file contains a set of 418 one-minute video clips depicting 128 driving scenarios on a Brazilian freeway. These clips were generated using the Vissim traffic simulation software and are encoded in MP4 format.</p> <p>The videos were created to support a survey on drivers' perceptions of freeway driving under a range of traffic and road conditions. Detailed information about the video creation process can be found in the following publications:</p> <ul> <li>Journal Article: "Using Traffic Simulation for Level of Service Traveller Perception Studies" (Promet - Traffic & Transportation, doi:10.7307/ptt.v34i2.3965)</li> <li>PhD Dissertation: Fernando Piva's PhD dissertation (doi:10.11606/T.18.2022.tde-10012023-155328)</li> </ul> <p>Each video clip is named according to the following format:</p> <div> <div> <div> <pre><code>output_G1_L4_S100_T20_D48_R3.mp4 </code></pre> </div> </div> </div> <p>where:</p> <ul> <li>G1: Grade magnitude (1% uphill)</li> <li>L4: Number of traffic lanes (4 lanes)</li> <li>S100: Posted speed limit (100 km/h)</li> <li>T20: Percentage of trucks in traffic (20%)</li> <li>D48: Average traffic density (4.8 vehicles/hour/lane)</li> <li>R3: Scenario replication identifier (third replication)</li> </ul> <p>Each scenario was replicated at least three times.</p> <p>The following traffic and road conditions were simulated:</p> <table> <tbody> <tr> <td><strong>Factor</strong></td> <td><strong>Definition<br></strong></td> <td><strong>Numeric values</strong></td> </tr> <tr> <td><code>NL</code>:</td> <td>Number of lanes in the driving direction</td> <td>3 or 4 lanes</td> </tr> <tr> <td><code>G</code>:</td> <td>Grade magnitude</td> <td>1% (nearly level grade) or 4% (steep uphill grade)</td> </tr> <tr> <td><code>SL</code>:</td> <td>Posted speed limit</td> <td>90, 100, 110 or 120 km/h</td> </tr> <tr> <td><code>PT</code>:</td> <td>Percentage of trucks in the traffic stream</td> <td>0, 10, 20 or 30% trucks </td> </tr> <tr> <td><code>D</code>:</td> <td>Traffic density</td> <td>36, 48, 72, 84, 96, 108, 120, 132, 144, 156, 168, 180 or 192 (x 0.1 veh/km/ln)</td> </tr> <tr> <td><code>R</code>:</td> <td>Scenario replication identifier </td> <td>integer > 0</td> </tr> </tbody> </table> <p>If you find this dataset useful for your research, please let the authors know. We are open to collaborations and questions about the dataset.</p>
Exploring Human and Artificial Attention Mechanisms in Driving Scenarios
Open the record for dataset details and reuse information.
Validation of the Drug Impaired Driving Scenario (DIDS) on the CRCDS-miniSim
ClinicalTrials.gov study NCT04970342. IPD Sharing: NO. Countries: 1. Publications: 0.
Calibration of adaptive energy management strategies for fuel cell trucks using real-world driving scenarios
<p>Energy management strategies have a significant impact on the hydrogen economy of fuel cell trucks and the lifetime of battery and fuel cell systems. Usually, the strategy design and calibration involve a multi-objective optimization of performance indexes related to hydrogen consumption, fuel cell transients, battery thermal state, and battery charge control. This contribution presents the calibration of an energy management strategy that is adaptive to battery and ambient temperature. Indeed, fuel cell trucks face critical operating conditions due to high ambient temperatures or high loads on long uphill roads. However, the presented adaptive energy management strategy can effectively avoid thermal issues to preserve the battery life without hindering the hydrogen economy. The strategy calibration can be optimized using a simulation environment consisting of drivetrain components in AVL CRUISE M and vehicle control unit functions in MATLAB Simulink. Moreover, AVL CAMEO can systematically vary the adaptive strategy's curve parameters to find the best trade-off between the key performance indexes. The calibration considers real-world driving cycles of road freight vehicles, including measured speed, road elevation, and variable vehicle mass. The calibration is robust because the performance indexes are optimized over more than 9000 kilometers, covering an extensive range of real-world driving scenarios. Besides the benefits of optimal calibrations, this contribution also provides interesting insights into the energy and thermal management problem of fuel cell trucks.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.