Skip to content

Commit 25bf906

Browse files
manthan99manthan99
authored
Add restructured tartanground and documentation
2 parents b6694d6 + 65e1a19 commit 25bf906

11 files changed

Lines changed: 36596 additions & 4614 deletions

‎docs/index.rst‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -41,6 +41,7 @@ Useful Links
4141

4242
installation
4343
examples
44+
tartanground
4445
usage
4546
modalities
4647
environments

‎docs/tartanground/index.html‎

Lines changed: 14 additions & 34 deletions
Original file line numberDiff line numberDiff line change
@@ -83,21 +83,21 @@ <h2 class="subtitle is-3">A Large-Scale Dataset for Ground Robot Perception and
8383
<div class="publication-links">
8484
<!-- Arxiv PDF link -->
8585
<span class="link-block">
86-
<a href="https://arxiv.org/pdf/2505.10696" target="_blank"
86+
<a href="https://arxiv.org/abs/2505.10696" target="_blank"
8787
class="external-link button is-normal is-rounded is-dark">
8888
<span class="icon">
8989
<i class="fas fa-file-pdf"></i>
9090
</span>
9191
<span>Paper</span>
9292
</a>
9393
</span>
94-
94+
9595
<!-- Supplementary PDF link -->
9696
<span class="link-block">
97-
<a href="https://tartanair.org/" target="_blank"
97+
<a href="https://tartanair.org/tartanground.html" target="_blank"
9898
class="external-link button is-normal is-rounded is-dark">
9999
<span class="icon">
100-
<i class="fas fa-file-pdf"></i>
100+
<i class="fas fa-database"></i>
101101
</span>
102102
<span>Dataset</span>
103103
</a>
@@ -108,20 +108,20 @@ <h2 class="subtitle is-3">A Large-Scale Dataset for Ground Robot Perception and
108108
<a href="https://github.com/castacks/tartanairpy" target="_blank"
109109
class="external-link button is-normal is-rounded is-dark">
110110
<span class="icon">
111-
<i class="fab fa-github"></i>
111+
<i class="fas fa-list-alt"></i>
112112
</span>
113113
<span>Code</span>
114114
</a>
115115
</span>
116116

117117
<!-- ArXiv abstract Link -->
118118
<span class="link-block">
119-
<a href="https://arxiv.org/abs/2505.10696" target="_blank"
119+
<a href="https://docs.google.com/spreadsheets/d/1d_px4Ss19OmrJrdOLwPsVNYe7Blcdmr6JKs0GdOORCg/edit?usp=sharing" target="_blank"
120120
class="external-link button is-normal is-rounded is-dark">
121121
<span class="icon">
122-
<i class="ai ai-arxiv"></i>
122+
<i class="fas fa-database"></i>
123123
</span>
124-
<span>arXiv</span>
124+
<span>MetaData</span>
125125
</a>
126126
</span>
127127
</div>
@@ -151,17 +151,17 @@ <h2 class="subtitle has-text-centered">
151151
<div class="columns is-multiline has-text-centered">
152152

153153
<div class="column is-one-quarter">
154-
<p class="title has-text-danger has-text-weight-bold" style="font-size: 4rem;">70+</p>
154+
<p class="title has-text-danger has-text-weight-bold" style="font-size: 4rem;">60+</p>
155155
<p class="subtitle is-6">Photorealistic Environments</p>
156156
</div>
157157

158158
<div class="column is-one-quarter">
159-
<p class="title has-text-danger has-text-weight-bold" style="font-size: 4rem;">910</p>
159+
<p class="title has-text-danger has-text-weight-bold" style="font-size: 4rem;">878</p>
160160
<p class="subtitle is-6">Trajectories</p>
161161
</div>
162162

163163
<div class="column is-one-quarter">
164-
<p class="title has-text-danger has-text-weight-bold" style="font-size: 4rem;">1.5 M</p>
164+
<p class="title has-text-danger has-text-weight-bold" style="font-size: 4rem;">1.4 M</p>
165165
<p class="subtitle is-6">Samples</p>
166166
</div>
167167

@@ -185,8 +185,8 @@ <h2 class="title is-3">Abstract</h2>
185185
environments. This dataset, collected in various photorealistic simulation environments includes multiple RGB stereo cameras for 360-degree
186186
coverage, along with depth, optical flow, stereo disparity, LiDAR point clouds, ground truth poses, semantic segmented images, and occupancy
187187
maps with semantic labels. Data is collected using an integrated automatic pipeline, which generates trajectories mimicking the motion
188-
patterns of various ground robot platforms, including wheeled and legged robots. We collect 910 trajectories across 70 environments,
189-
resulting in 1.5 million samples. Evaluations on occupancy prediction and SLAM tasks reveal that state-of-the-art methods trained on
188+
patterns of various ground robot platforms, including wheeled and legged robots. We collect 878 trajectories across 63 environments,
189+
resulting in 1.44 million samples. Evaluations on occupancy prediction and SLAM tasks reveal that state-of-the-art methods trained on
190190
existing datasets struggle to generalize across diverse scenes. TartanGround can serve as a testbed for training and evaluation of a broad
191191
range of learning-based tasks, including occupancy prediction, SLAM, neural scene representation, perception-based navigation, and more,
192192
enabling advancements in robotic perception and autonomy towards achieving robust models generalizable to more diverse scenarios.
@@ -303,7 +303,7 @@ <h4 class="title is-5">Camera Resampling</h4>
303303
<div class="container is-max-desktop content">
304304
<h2 class="title is-3 has-text-centered">Environments</h2>
305305
<p class="has-text-justified">
306-
The TartanGround dataset features 74 photorealistic simulation environments carefully selected to cover a wide range of real-world conditions.
306+
The TartanGround dataset features 63 photorealistic simulation environments carefully selected to cover a wide range of real-world conditions.
307307
These environments are categorized into six types: <strong>Indoor</strong>, <strong>Nature</strong>, <strong>Rural</strong>,
308308
<strong>Urban</strong>, <strong>Industrial/Infrastructure</strong>, and <strong>Historical/Thematic</strong>.
309309
This diversity supports robust generalization across varied terrain and lighting conditions.
@@ -445,25 +445,5 @@ <h2 class="title">BibTeX</h2>
445445
</div>
446446
</footer>
447447

448-
<!-- Statcounter tracking code -->
449-
450-
<!-- You can add a tracker to track page visits by creating an account at statcounter.com -->
451-
<!-- Default Statcounter code for RoadRunnner M&M
452-
https://leggedrobotics.github.io/roadrunner_mm/ -->
453-
<!-- <script type="text/javascript">
454-
var sc_project=13049032;
455-
var sc_invisible=0;
456-
var sc_security="9391df5a";
457-
var scJsHost = "https://";
458-
document.write("<sc"+"ript type='text/javascript' src='" + scJsHost+
459-
"statcounter.com/counter/counter.js'></"+"script>");
460-
</script>
461-
<noscript><div class="statcounter"><a title="Web Analytics"
462-
href="https://statcounter.com/" target="_blank"><img class="statcounter"
463-
src="https://c.statcounter.com/13049032/0/9391df5a/0/" alt="Web Analytics"
464-
referrerPolicy="no-referrer-when-downgrade"></a></div></noscript> -->
465-
<!-- End of Statcounter Code -->
466-
<!-- End of Statcounter Code -->
467-
468448
</body>
469449
</html>

0 commit comments

Comments
 (0)