"GO Stanford" Dataset 4

"GO Stanford 4" (GS4) are dataset of visual images from the view point of the mobile robot. These dataset are collected at the Stanford University campus and the simulator, Gibson Environment. Different from prior dataset, GS1, GS2, and GS3, new dataset, GS4 includes not only the front side view but also the back side view from 360-degree camera, RICOH THETA-S.

Download "GO Stanford 4"

We open our dataset, "GO Stanford 4".

GO Stanford 4 (GS4)

GS4 includes 360-degree camera view from Ricoh THETA S and, corresponding robot linear and angular velocities. The list file for the real environment in Stanford campus is "dataset_"A"_no"B"vc.txt". And, the dataset from simulator is "dataset_"A"_sim"C"h.txt". "A" is "360all"(360-dgree view image) or "refresall"(corresponding robot velocities). "B" is the indentification number for the real environment dataset. And, "C" is identification number for the simulator's dataset.

GS4 Download

Real environment

We teleoperate the mobile robot and collect the fisheye camera images in 12 buildings. Total time length is 10.3 hours. The collected dataset includes not only 360-degree images, which is pair of front and back fish eye image, but also wheel encoder signals and joypad inputs.








Different from the dataset of the real environment, this dataset includes a lot of home environments. We are using the calibrated fish eye camera model to render the front and back image view of 360-dgree camera.








The datasets provided on this page are published under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 License. This means that you must attribute the work in the manner specified by the authors, you may not use this work for commercial purposes and if you alter, transform, or build upon this work, you may distribute the resulting work only under the same license. If you are interested in commercial usage you can contact us for further options.