RoboCupSimData Files Overview
This page is part of the RoboCupSimData project hosted on bitbucket.
There are three sets of different sizes on this page. They are:
- a one game set, to explore the data before downloading the full set;
- a ten game set, for more exploring and simple
experiments; and finally
- the full dataset, split into 10 parts. This full dataset
also contains all the files that are part of (1) and (2).
All game datasets on this page come in two versions:
- A set of CSV files. For each game in the set, there is
one file with groundtruth data for all players, one file
with parameters of the game, and forty-four files
(two per player), with the local, incomplete, and noisy
"visual" percepts of each player: one file for
sensed moving objects, and one file for sensed landmarks. We
modified the soccer simulator to record these local percepts
for all players of both teams, the original soccer simulator
does not record these files.
- The original logfiles of the RoboCup Soccer Simulator,
together with the logfiles of the players' sensory inputs, generated with our
simulator patch (visual and "body" sensors). All CSV files above can be
recreated from the logfiles with the scripts that we release
together with our data.
Additionally, the file landmarks.csv contains positions of all landmarks
(flags, lines, goals), in global coordinates. Every game is using
this set of landmarks, and their "global" positions are known to all players.
One game example data
An example game between Gliders2016 and HELIOS2016, winner and
runner up of RoboCup 2016.
Ten games top 5 teams
For this ten games top 5 set, we determined the top 5
teams from all games run for our full dataset. We then selected 10
games from the full dataset, so that each team plays one of the
other top 5 once.
Full data set: Ten teams 25 rounds tournament
The full data set was created by playing 25 rounds of games with
10 teams (the top 6 teams from RoboCup 2017, and the top 4 teams
from RoboCup 2016). In each round, all teams play against each other,
resulting in 25 * 9 * 10 / 2 = 1125 games in total. The dataset is
split into 10 packages for easier downloading. Each package
contains all matches of a team playing on the "left" side of the
field, i.e. 4 or 5 matches (of 25 rounds each).
- CSV files: (total size: 17GB zipped, 229GB unzipped)
- 0-cyrus2017-csv.zip (1.8GB zipped, 24GB unzipped). Content listing: 0-cyrus2017-csv-ls-gGR
- 1-fra-united2017-csv.zip (1.6GB zipped, 24GB unzipped). Content listing: 1-fra-united2017-csv-ls-gGR
- 2-Gliders2016-csv.zip (1.5GB zipped, 21GB unzipped). Content listing: 2-Gliders2016-csv-ls-gGR
- 3-helios2017-csv.zip (1.9GB zipped, 26GB unzipped). Content listing: 3-helios2017-csv-ls-gGR
- 4-helios2016-csv.zip (1.5GB zipped, 21GB unzipped). Content listing: 4-helios2016-csv-ls-gGR
- 5-hfutengine2017-csv.zip (1.8 zipped, 23GB unzipped). Content listing: 5-hfutengine2017-csv-ls-gGR
- 6-mt2017-csv.zip (1.8GB zipped, 22GB unzipped). Content listing: 6-mt2017-csv-ls-gGR
- 7-oxsy2017-csv.zip (2.0GB zipped, 29GB unzipped). Content listing: 7-oxsy2017-csv-ls-gGR
- 8-ri-one-csv.zip (1.6GB zipped, 22GB unzipped). Content listing: 8-ri-one-csv-ls-gGR
- 9-yunlu-csv.zip (1.5GB zipped, 21GB unzipped). Content listing: 9-yunlu-csv-ls-gGR
- Original logs:
- 0-cyrus2017-rcx.tar.gz (2.7GB). Content listing: 0-cyrus2017-rcx-ls-gGR
- 1-fra-united2017-rcx.tar.gz (2.4GB). Content listing: 1-fra-united2017-rcx-ls-gGR
- 2-Gliders2016-rcx.tar.gz (2.1GB). Content listing: 2-Gliders2016-rcx-ls-gGR
- 3-helios2017-rcx.tar.gz (2.7GB). Content listing: 3-helios2017-rcx-ls-gGR
- 4-helios2016-rcx.tar.gz (2.1GB). Content listing: 4-helios2016-rcx-ls-gGR
- 5-hfutengine2017-rcx.tar.gz (2.6GB). Content listing: 5-hfutengine2017-rcx-ls-gGR
- 6-mt2017-rcx.tar.gz (2.6GB). Content listing: 6-mt2017-rcx-ls-gGR
- 7-oxsy2017-rcx.tar.gz (2.9GB). Content listing: 7-oxsy2017-rcx-ls-gGR
- 8-ri-one-rcx.tar.gz (2.3GB). Content listing: 8-ri-one-rcx-ls-gGR
- 9-yunlu-rcx.tar.gz (2.3GB). Content listing: 9-yunlu-rcx-ls-gGR