Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added .DS_Store
Binary file not shown.
163 changes: 142 additions & 21 deletions index.html
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
<!DOCTYPE html>
<html>
<head>
<title>DexSing</title>
<title>DexSinGrasp</title>

<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<meta name="author" content="Anonymous">
Expand Down Expand Up @@ -47,12 +47,12 @@
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title">Learning Synergistic Dexterous Singulation in Cluttered Environments</h1>
<h1 class="title is-1 publication-title">DexSinGrasp: Learning a Unified Policy for Dexterous Object Singulation and Grasping in Cluttered Environments</h1>

<div class="is-size-5 publication-authors">
<div>
Lixin Xu, Zhewei Gui, Zixuan Liu, Zeyu Jiang, Zixuan Liu, <br>
Jingxiang Guo, Zhixuan Xu, Chongkai Gao, Zhixuan Xu, Lin Shao
Lixin Xu, Zixuan Liu, Zhewei Gui, Jingxiang Guo, <br>
Zeyu Jiang, Zhixuan Xu, Chongkai Gao, Lin Shao
</div>
</div>

Expand All @@ -64,33 +64,34 @@ <h1 class="title is-1 publication-title">Learning Synergistic Dexterous Singulat
<span class="icon">
<i class="ai ai-arxiv"></i>
</span>
<span>arXiv</span>
<span>arXiv (Coming Soon)</span>
</a>
</span>
<span class="link-block">
<a href="#" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Paper</span>
<span>Paper (Coming Soon)</span>
</a>
</span>
<span class="link-block">
<!-- Appendix Link -->
<!-- <span class="link-block">
<a href="#" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Appendix</span>
</a>
</span>
</span> -->

<!-- Code Link -->
<span class="link-block">
<a href="#" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Code</span>
<span>Code (Coming Soon)</span>
</a>
</span>

Expand All @@ -100,7 +101,7 @@ <h1 class="title is-1 publication-title">Learning Synergistic Dexterous Singulat
<span class="icon">
<i class="fas fa-database"></i>
</span>
<span>Data</span>
<span>Dataset (Coming Soon)</span>
</a>
</span>
</div>
Expand All @@ -116,7 +117,7 @@ <h1 class="title is-1 publication-title">Learning Synergistic Dexterous Singulat
<div class="container is-max-desktop">
<div class="hero-body">
<video id="intro" controls playsinline height="100%">
<source src="./static/data/DexSing.mp4" type="video/mp4">
<source src="./static/data/DexSinGrasp.mp4" type="video/mp4">
</video>
</div>
</div>
Expand All @@ -131,34 +132,154 @@ <h1 class="title is-1 publication-title">Learning Synergistic Dexterous Singulat
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
Grasping objects in cluttered environments remains a fundamental yet challenging problem in robotic manipulation. While prior works have explored learning-based synergies for two-fingered grippers, few works leverage high degrees of freedom (DoF) of dexterous hands for synegistic singulation in cluttered environments. In this work, we propose DexSing, a synergistic dexterous singulation policy using reinforcement learning, which enables to perform singulation for grasping with high dexterity, thus significantly improving grasping efficiency in cluttered environments. We incorporate curriculum learning to enhance success rate and generalization across diverse clutter conditions and employ policy distillation to obtain a deployable vision-based grasping strategy. To evaluate our approach, we introduce a set of cluttered grasping tasks with varying object arrangements and occlusion levels. Experimental results demonstrate that our method outperforms baselines in terms of efficiency and grasping success rate, particularly in dense clutter.
Grasping objects in cluttered environments remains a fundamental yet challenging problem in robotic manipulation. While prior works have explored learning-based synergies between pushing and grasping for two-fingered grippers, few have leveraged the high degrees of freedom (DoF) in dexterous hands to perform efficient singulation for grasping in cluttered settings.
In this work, we introduce DexSinGrasp, a unified policy for dexterous object singulation and grasping. DexSinGrasp enables high-dexterity object singulation to facilitate grasping, significantly improving efficiency and effectiveness in cluttered environments. We incorporate curriculum learning to enhance success rates and generalization across diverse clutter conditions, while policy distillation enables a deployable vision-based grasping strategy.
To evaluate our approach, we introduce a set of cluttered grasping tasks with varying object arrangements and occlusion levels. Experimental results show that our method outperforms baselines in both efficiency and grasping success rate. Experimental results show that our method outperforms baselines in both efficiency and grasping success rate, particularly in dense clutter. Codes, appendix, and videos are available on our project website https://nus-lins-lab.github.io/dexsingweb/.
</p>
</div>
</div>
</div>
<!--/ Abstract -->




<!-- Overview -->
<!-- <div class="columns is-centered has-text-centered">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Pipeline Overview</h2>
<div class="content has-text-justified">
<figure>
<img src="./static/data/DexSing_overview.jpg" alt="Overview of DexSing framework image">
<figcaption style="font-style: normal; font-size: 0.95em;">Overview of DexSing TODO.</figcaption>
<img src="./static/data/overview.png" alt="Overview of DexSinGrasp framework image">
<figcaption style="font-style: normal; font-size: 0.95em;">Framework of DexSinGrasp. Firstly, we employ clutter arrangement curriculum learning to progressively improve our teacher policy's performance, and acquire two teacher policies at the end of this stage for dense and random arrangement tasks, respectively.
We then collect various state and action data along with pointcloud data from the trained two teachers to train a vision-based student policy via behavior cloning, which better facilitates real-world deployment.</figcaption>
</figure>
</div>
<div class="content has-text-justified">
<p>

</p>
</div>
</div>
</div> -->
</div>
<!--/ Overview -->

<!-- Cluttered Environments -->
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Cluttered Environments Generation</h2>
<div class="content has-text-justified">
<figure style="width: 80%; margin: 0 auto;">
<img src="./static/data/blocks2.png" alt="Overview of DexSinGrasp framework image">
<figcaption style="font-style: normal; font-size: 0.95em;">Dense and random arrangement settings. We introduce a cluttered
environment generation module to create diverse object settings, including
different obstacle quantities from 0 to 8, dense and random arrangements,
various poses, and block shapes. For simplicity, we only show obstacles
with numbers 4 to 8. </figcaption>
</figure>
</div>
<div class="content has-text-justified">
<p>

</p>
</div>
</div>
</div>
<!--/ Cluttered Environments -->


<!-- Simulation Results -->
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Simulation Experiments</h2>
<div class="content has-text-justified">
<!-- First row -->
<div class="columns is-centered is-gapless">
<div class="column">
<figure>
<img src="./static/data/d4.gif" alt="Dense 4 objects" style="width: 90%;">
<figcaption style="font-style: normal; font-size: 0.95em;">Dense arrangement with 4 obstacles</figcaption>
</figure>
</div>
<div class="column">
<figure>
<img src="./static/data/d6.gif" alt="Dense 6 objects" style="width: 90%;">
<figcaption style="font-style: normal; font-size: 0.95em;">Dense arrangement with 6 obstacles</figcaption>
</figure>
</div>
<div class="column">
<figure>
<img src="./static/data/d8.gif" alt="Dense 8 objects" style="width: 90%;">
<figcaption style="font-style: normal; font-size: 0.95em;">Dense arrangement with 8 obstacles</figcaption>
</figure>
</div>
</div>
<!-- Second row -->
<div class="columns is-centered is-gapless">
<div class="column">
<figure>
<img src="./static/data/r4.gif" alt="Random 4 objects" style="width: 90%;">
<figcaption style="font-style: normal; font-size: 0.95em;">Random arrangement with 4 obstacles</figcaption>
</figure>
</div>
<div class="column">
<figure>
<img src="./static/data/r6.gif" alt="Random 6 objects" style="width: 90%;">
<figcaption style="font-style: normal; font-size: 0.95em;">Random arrangement with 6 obstacles</figcaption>
</figure>
</div>
<div class="column">
<figure>
<img src="./static/data/r8.gif" alt="Random 8 objects" style="width: 90%;">
<figcaption style="font-style: normal; font-size: 0.95em;">Random arrangement with 8 obstacles</figcaption>
</figure>
</div>
</div>
</div>
<div class="content has-text-justified">
<p>

</p>
</div>
</div>
</div>
<!--/ Simulation Results -->

<!-- Real-World Results -->
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Real-World Experiments</h2>
<div class="content has-text-justified">
<figure style="width: 80%; margin: 0 auto;">
<img src="./static/data/real-world.gif" alt="Overview of DexSinGrasp framework image">
<figcaption style="font-style: normal; font-size: 0.95em;">We conduct real-world experiments using an xArm6 equipped with a LEAP Hand. Results show the efficacy of our vision-based student policy.</figcaption>
</figure>
</div>
<div class="content has-text-justified">
<p>

</p>
</div>
</div>
</div>
<!--/ Real-World Results -->

</div>
</section>


<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title is-3">BibTeX</h2>
<pre><code>@article{xu2025dexsingrasp,
title={DexSinGrasp: Learning a Unified Policy for Dexterous Object Singulation and Grasping in Cluttered Environments},
author={Xu, Lixin and Liu, Zixuan and Gui, Zhewei and Guo, Jingxiang and Jiang, Zeyu and Xu, Zhixuan and Gao, Chongkai and Shao, Lin},
journal={arXiv preprint},
year={2025}
}</code></pre>
</div>
</section>

<!-- BibTex -->
<!-- <section class="section" id="BibTeX"> -->
<!-- TODO -->
<!-- </section> -->
<!--/ BibTex -->

<!-- Footer -->
<footer class="footer", style="padding: 40px 0;">
Expand Down
Binary file added static/.DS_Store
Binary file not shown.
Binary file added static/data/.DS_Store
Binary file not shown.
Binary file added static/data/1.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/DexSinGrasp.mp4
Binary file not shown.
Binary file added static/data/blocks2.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/d4.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/d6.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/d8.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/dexsingrasp.pdf
Binary file not shown.
Binary file added static/data/framework.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/grasp.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/output.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/overview.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/quantitive.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/r4.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/r6.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/r8.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/real-world.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added static/data/teaser.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.