Skip to content

Commit

Permalink
Initial commit
Browse files Browse the repository at this point in the history
  • Loading branch information
@DavoodSZ1993
DavoodSZ1993 committed Jan 30, 2025
1 parent aff2db4 commit 08bf194
Showing 1 changed file with 21 additions and 53 deletions.
74 changes: 21 additions & 53 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,10 @@
<head>
<meta charset="utf-8">
<meta name="description"
content="Challenges and Opportunities of Using Deep Learning in Safe-Critical Robotic Manipulator Planning.">
content="SIMPNet: Spatial-informed Motion Planning Network.">
<meta name="keywords" content="">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Challenges and Opportunities of Using Deep Learning in Safe-Critical Robotic Manipulator Planning</title>
<title>SIMPNet: Spatial-informed Motion Planning Network.</title>

<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-PYVRSFMDRL"></script>
Expand Down Expand Up @@ -50,54 +50,19 @@
<span aria-hidden="true"></span>
</a>
</div>
<!--
<div class="navbar-menu">
<div class="navbar-start" style="flex-grow: 1; justify-content: center;">
<a class="navbar-item" href="https://keunhong.com">
<span class="icon">
<i class="fas fa-home"></i>
</span>
</a>
<div class="navbar-item has-dropdown is-hoverable">
<a class="navbar-link">
More Research
</a>
<div class="navbar-dropdown">
<a class="navbar-item" href="https://hypernerf.github.io">
HyperNeRF
</a>
<a class="navbar-item" href="https://nerfies.github.io">
Nerfies
</a>
<a class="navbar-item" href="https://latentfusion.github.io">
LatentFusion
</a>
<a class="navbar-item" href="https://photoshape.github.io">
PhotoShape
</a>
</div>
</div>
</div>
</div>-->
</nav>


<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title">Challenges and Opportunities of Using Deep Learning in Safe-Critical Robotic Manipulator Planning</h1>
<h1 class="title is-1 publication-title">SIMPNet: Spatial-informed Motion Planning Network.</h1>
<div class="is-size-5 publication-authors">
<span class="author-block">
<a href="https://zh.engr.tamu.edu/people-2/">Davood Soleymanzadeh</a><sup>1</sup>,</span>
<span class="author-block">
<a href="https://haosu-robotics.github.io/people">Ivan Lopez-Sanchez</a><sup>2</sup>,</span>
<span class="author-block">
<a href="https://mae.ncsu.edu/people/hao-su/">Hao Su</a><sup>2</sup>,
</span>
<a href="https://engineering.tamu.edu/civil/profiles/liang-xiao.html">Xiao Liang</a><sup>2</sup>,</span>
<span class="author-block">
<a href="https://engineering.tamu.edu/mechanical/profiles/zheng-minghui">Minghui Zheng</a><sup>1</sup>,
</span>
Expand All @@ -112,15 +77,15 @@ <h1 class="title is-1 publication-title">Challenges and Opportunities of Using D
</head>

<div class="is-size-5 author-affiliation">
<span class="author-block"><sup>1</sup> <a href="https://www.tamu.edu" target="_blank">Texas A&M University </a>,</span>
<span class="author-block"><sup>2</sup> <a href="https://www.ncsu.edu/" target="_blank">North Carolina State University</a></span>
<span class="author-block"><sup>1</sup> <a href="https://www.tamu.edu" target="_blank">J. Mike Walker '66 Department of Mechanical Engineering, Texas A&M University.</a>,</span>
<span class="author-block"><sup>2</sup> <a href="https://www.ncsu.edu/" target="_blank">Zachry Department of Civil and Environmental Engineering, Texas A&M University.</a></span>
</div>

<div class="column has-text-centered">
<div class="publication-links">
<!-- PDF Link. -->
<span class="link-block">
<a href="https://arxiv.org/pdf/2011.12948"
<a href="https://arxiv.org/pdf/2408.12831"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
Expand All @@ -129,7 +94,7 @@ <h1 class="title is-1 publication-title">Challenges and Opportunities of Using D
</a>
</span>
<span class="link-block">
<a href="https://arxiv.org/abs/2011.12948"
<a href="https://arxiv.org/abs/2408.12831"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="ai ai-arxiv"></i>
Expand All @@ -139,12 +104,12 @@ <h1 class="title is-1 publication-title">Challenges and Opportunities of Using D
</span>
<!-- Code Link. -->
<span class="link-block">
<a href="https://github.com/google/nerfies"
<a href="https://github.com/DavoodSZ1993/SIMPNet"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Paper List in the Survey</span>
<span>Code</span>
</a>
</span>
</div>
Expand All @@ -163,13 +128,16 @@ <h1 class="title is-1 publication-title">Challenges and Opportunities of Using D
<div class="column is-four-fifths">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
Deep learning frameworks have shown tremendous promise in planning for robotic manipulators. This is due to their fast inference capabilities,
inherent inductive biases, and proficiency in handling multi-modal distributions and datasets. However, there are also limitations associated
with utilizing deep learning for robotic manipulator planning, including the need for expensive datasets and challenges to generalize to out-of-distribution
settings. This review explores state-of-the-art research on leveraging deep learning modules to replace or enhance traditional planning algorithms.
This paper evaluates the contributions of deep learning frameworks to traditional planning algorithms, emphasizing both the benefits and limitations
of these methods. Also, this paper explores future directions to provide a clear path for researchers planning to utilize these models for the planning
of robotic manipulators.
Current robotic manipulators require fast and efficient motion-planning algorithms to operate in cluttered environments.
State-of-the-art sampling-based motion planners struggle to scale to high-dimensional configuration spaces and are inefficient
in complex environments. This inefficiency arises because these planners utilize either uniform or hand-crafted sampling
heuristics within the configuration space. To address these challenges, we present the Spatial-informed Motion Planning Network (SIMPNet).
SIMPNet consists of a stochastic graph neural network (GNN)-based sampling heuristic for informed sampling within the configuration space.
The sampling heuristic of SIMPNet encodes the workspace embedding into the configuration space through a cross-attention mechanism.
It encodes the manipulator's kinematic structure into a graph, which is used to generate informed samples within the framework of
sampling-based motion planning algorithms. We have evaluated the performance of SIMPNet using a UR5e robotic manipulator operating
within simple and complex workspaces, comparing it against baseline state-of-the-art motion planners. The evaluation results show the
effectiveness and advantages of the proposed planner compared to the baseline planners.
</div>
</div>
</div>
Expand All @@ -180,7 +148,7 @@ <h2 class="title is-3">Abstract</h2>
<div class="column is-four-fifths">
<h2 class="title is-3">Video</h2>
<div class="publication-video">
<iframe src="https://www.youtube.com/embed/MrKrnHhk8IA?rel=0&amp;showinfo=0"
<iframe src="https://youtu.be/msmV1sUrcmA&amp;showinfo=0"
frameborder="0" allow="autoplay; encrypted-media" allowfullscreen></iframe>
</div>
</div>
Expand Down

0 comments on commit 08bf194

Please sign in to comment.