Dataset for MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots
4TU.ResearchDatavia 4TU.ResearchData (via DataCite) · bijgewerkt 24 juni 2026
Wat erin zit
MobileOcc is a human-aware 3D semantic occupancy dataset created to support dense occupancy perception for mobile robots operating in crowded, pedestrian-rich environments. The dataset was produced through an annotation pipeline that combines static-object occupancy labels with a mesh-optimization framework for modeling deformable human geometry: human shapes are first reconstructed from 2D images and then refined using associated LiDAR point-cloud data. MobileOcc provides labeled occupancy data together with established benchmarks and baseline implementations for two occupancy prediction and pedestrian velocity prediction.
Bestanden en diensten
- DataCite REST API (JSON)api.datacite.orgOpenen
Vergelijkbare datasets
Dataset: Video recordings of human-robot interactions with a Nao robot controlled via the SONAR adaptive control architecture for social norm aware robots4TU.ResearchDataData underlying the research of: human trustworthiness in 2D grid-world human-AI team interaction4TU.ResearchDataData underlying the MSc. thesis: An Evaluation of the Merging Interaction between Humans and Interaction-Aware Vehicles4TU.ResearchDataData underlying the study on the effects of task allocation using human’s willingness in trust and teamwork.4TU.ResearchDataCode accompanying the paper "Validating human driver models for interaction-aware automated vehicle controllers: A human approach”4TU.ResearchDataData underlying the MSc Thesis: Toward Occlusion Capable Human Trajectory Prediction4TU.ResearchDataControlled synthetic video dataset for auditing skin-tone shortcuts in human action recognition4TU.ResearchDataIdentification and Formalization of Human-Machine Collaboration Patterns, data underlying the publication: Ontology-based Reflective Communication for Shared Human-AI Recognition of Emergent Collaboration Patterns4TU.ResearchData
Meer van 4TU.ResearchData6.749 datasets
Research Data and Code Supporting the PhD Dissertation: Learning Interpretable Robot Dynamics for Control — From Physical Structure to Latent CoordinatesCode for thesis chapter "Suitability assessment of GNN-based metamodels for BGI allocation"Data and scripts underlying the dissertation: Sodium Borohydride as Granular fuel: Experimental Characterisation and DEM ModellingData supporting the publication: Vision-Informed Short-Horizon Prediction for the Squeeze Flow of Soft MaterialsData for thesis chapter "Suitability assessment of GNN-based metamodels for BGI allocation"Data underlying Chapter 3 of the PhD thesis: Organic acids and bipolar membrane electrodialysis for enhanced ammonia recovery from scrubber effluents.