Published September 5, 2022 | Version v1
Dataset Open

Stochastic Occupancy Grid Map Prediction in Dynamic Scenes: Dataset

Creators

  • 1. Temple University

Description

Three occupancy grid map (OGM) datasets for the paper titled "Stochastic Occupancy Grid Map Prediction in Dynamic Scenes" by Zhanteng Xie and Philip Dames

1. OGM-Turtlebot2: collected by a simulated Turtlebot2 with a maximum speed of 0.8 m/s navigates around a lobby Gazebo environment with 34 moving pedestrians using random start points and goal points

2. OGM-Jackal: extracted from two sub-datasets of the socially compliant navigation dataset (SCAND), which was collected by the Jackal robot with a maximum speed of 2.0 m/s at the outdoor environment of the UT Austin

3. OGM-Spot: extracted from two sub-datasets of the socially compliant navigation dataset (SCAND), which was collected by the Spot robot with a maximum speed of 1.6 m/s at the Union Building of the UT Austin

The relevant code is available at: 
OGM prediction: https://github.com/TempleRAIL/SOGMP
OGM mapping with GPU: https://github.com/TempleRAIL/occupancy_grid_mapping_torch

Files

Files (392.5 MB)

Name Size Download all
md5:092e097761508b857a10285c059ce5c1
392.5 MB Download

Additional details

Funding

NRI: FND: COLLAB: Distributed, Semantically-Aware Tracking and Planning for Fleets of Robots 1830419
U.S. National Science Foundation

References

  • Karnan, Haresh, et al. "Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation." arXiv preprint arXiv:2203.15041 (2022).