Skip to content

Commit

Permalink
Adding more stuff
Browse files Browse the repository at this point in the history
  • Loading branch information
@SimeonOA
SimeonOA committed Mar 31, 2024
1 parent c5e1bba commit ae7cb6b
Show file tree
Hide file tree
Showing 6 changed files with 155 additions and 72 deletions.
218 changes: 147 additions & 71 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -76,42 +76,46 @@
<h1 class="title is-1 publication-title">Automating Deformable Gasket Assembly</h1>
<div class="is-size-5 publication-authors">
<span class="author-block">
<a href="https://simeonoa.github.io">Simeon Adebola</a><sup>1</sup>,</span>
<a href="https://simeonoa.github.io">Simeon Adebola*</a><sup>1</sup>,</span>
<span class="author-block">
Tara Sadjadpour</a><sup>1</sup>,</span>
Tara Sadjadpour*</a><sup>1</sup>,</span>
<span class="author-block">
Karim El-Refai</a><sup>1</sup>,
Karim El-Refai*</a><sup>1</sup>,
</span>
<span class="author-block">
Will Panitch</a><sup>1</sup>,
</span>
<span class="author-block">
Zehan Ma</a><sup>1</sup>,
Zehan Ma</a><sup>1</sup>,
</span>
<span class="author-block">
Roy Lin</a><sup>1</sup>,
Roy Lin</a><sup>1</sup>,
</span>
<span class="author-block">
Tianshuang Qiu</a><sup>1</sup>
Tianshuang Qiu</a><sup>1</sup>
</span>
<span class="author-block">
Shreya Ganti</a><sup>1</sup>,
Shreya Ganti</a><sup>1</sup>,
</span>
<span class="author-block">
Charlotte Le</a><sup>1</sup>,
Charlotte Le</a><sup>1</sup>,
</span>
<span class="author-block">
Jaimyn Drake</a><sup>1</sup>,
Jaimyn Drake</a><sup>1</sup>,
</span>
<span class="author-block">
<a href="https://goldberg.berkeley.edu">Ken Goldberg</a><sup>1</sup>
<a href="https://goldberg.berkeley.edu"> Ken Goldberg</a><sup>1</sup>
</span>
</div>

<div class="is-size-5 publication-authors">
<span class="author-block"><sup>1</sup>The AUTOLab at UC Berkeley</span>
<!-- <span class="author-block"><sup>2</sup>Google Research</span> -->
</div>
<div class="is-size-5 publication-authors">
<span class="author-block"><sup>*</sup>Equal Contribution</span>
</div>


<div class="column has-text-centered">
<div class="publication-links">
Expand Down Expand Up @@ -172,24 +176,125 @@ <h1 class="title is-1 publication-title">Automating Deformable Gasket Assembly</
</div>
</section>

<section class="hero teaser">
<section class="publication-body">
<div class="container is-max-desktop">
<div class="hero-body">
<video id="teaser" autoplay muted loop playsinline height="100%">
<source src="./static/videos/teaser.mp4"
type="video/mp4">
</video>
<h2 class="subtitle has-text-centered">
<span class="dnerf">Nerfies</span> turns selfie videos from your phone into
free-viewpoint
portraits.
</h2>
<div class="publication-body">
<img id="publication" autoplay muted loop playsinline height="100%">
<img src="./static/images/actuation.png"
type="images/png">
</img>
<p>
For the <span class="dgask">Gasket Assembly</span>, task, we present a learned diffusion policy and three procedural algorithms.
The procedural algorithms consist of gasket/channel detection, template matching and then actuation. The Gasket/Channel Detection box shows
gasket segmentation (above) and channel segmentation (below). The Template Matching box shows the three templates for the curved, straight and trapezoid
channels. The Straight/Curved Actuation box shows selection and actuation strategies for the straight and curved channels: (a) is Unidirectional insertion,
(b) is Binary search insertion, and (c) is Hybrid insertion. The numbers of the points on the channels represent the order and location where robot attempts
to place and press the gasket into. The arrows indicate the direction(s) of the slide(s). The half-points and quartile-points in binary insertion are labeled as
(2,3) and (4,6,7,5) respectively. In Hybrid insertion they’re labeled (4,5) and (6,8,9,5) respectively. For the trapezoid channel, we treat each segment of the
trapezoid as an instance of the straight channel. In the unidirectional approach (d) we process each segment in a counterclockwise manner, starting at the
blue segment. For hybrid and binary (e), we evaluate the blue segment, then the cyan segments, and finally the red segment. The learned policy proceeds
directly from the initial state to actuation (f). The Final State box shows the final assembled gasket.
</p>
</div>
</div>
</section>

<section class="section">
<div class="container is-max-desktop">
<!-- Abstract. -->
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
In <span class="dgask">Gasket Assembly</span>, a deformable gasket must be
aligned and pressed into a narrow channel. This task is common
for sealing surfaces in the manufacturing of automobiles,
appliances, electronics, and other products. <span class="dgask">Gasket Assembly</span> is
a long-horizon, high-precision task and the gasket must align
with the channel and be fully pressed in to achieve a secure
fit. We present and compare 4 methods for <span class="dgask">Gasket Assembly</span>:
one policy from deep imitation learning and three procedural
algorithms. We evaluate each using 3D printed channels with
100 physical trials. Results suggest that deep imitation learning
can fail (lowest quartile of alignment and insertion performance)
on a straight channel in 2 of 10 trials, whereas a hybrid
procedural algorithm achieves highest quartile performance in
all 10 trials. The procedural algorithm also performs reliably
on a curved channel but poorly on a closed trapezoidal channel.
</p>
</div>
</div>
</div>
<!--/ Abstract. -->


<section class="publication-body">
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="publication-body">
<h3 class="title is-4">Channel Types</h3>
<p>
We present three channel types: open straight, open curved and closed trapezoid. See the link at page top for CAD files.

</p>
<img id="publication" autoplay muted loop playsinline height="100%">
<img src="./static/images/channels_bigger2.png"
type="images/png">
</img>
<p>
Each channel is shown here with a gasket fully inserted. The straight channel (A) and the curved channel (B) are both open-ended channels whereas
the trapezoid channel (C) is closed. This means that for all channels, the gasket endpoints (g0, g1) and channel endpoints (c0, c1)
lie nearly on top of each other, but in the trapezoid case, c0 and c1 also lie nearly on top of each other
</p>
</div>
</div>
</div>
</section>

<section class="hero is-light is-small">
<br>
<br>
<br>

<section class="publication-body">
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="publication-body">
<h2 class="title is-3">Physical Trials & Results</h2>
<p>
We carry out 100 physical trials: 10 for the learned diffusion policy on the straight channel,
10 for each procedural algorithm on each channel: straight, curved and trapezoid.
</p>
<img id="publication" autoplay muted loop playsinline height="100%">
<img src="./static/images/alignment_results.png"
type="images/png">
</img>
<p><span class = "bold">Alignment Results for all four approaches: learned diffusion mode, unidirectional, binary search and hybrid.
</span></p>
</div>
</div>
</div>
</section>


<section class="publication-body">
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="publication-body">
<img id="publication" autoplay muted loop playsinline height="100%">
<img src="./static/images/insertion_results.png"
type="images/png">
</img>
<p> <b>
Insertion Results for all four approaches: learned diffusion mode, unidirectional, binary search and hybrid.
</b></p>
</div>
</div>
</div>
</section>


<!-- <section class="hero is-light is-small">
<div class="hero-body">
<div class="container">
<div id="results-carousel" class="carousel results-carousel">
Expand Down Expand Up @@ -244,59 +349,30 @@ <h2 class="subtitle has-text-centered">
</div>
</div>
</div>
</section>

</section> -->

<section class="section">
<div class="container is-max-desktop">
<!-- Abstract. -->
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
In <span class="dnerf">Gasket Assembly</span>, a deformable gasket must be
aligned and pressed into a narrow channel. This task is common
for sealing surfaces in the manufacturing of automobiles,
appliances, electronics, and other products. <span class="dnerf">Gasket Assembly</span> is
a long-horizon, high-precision task and the gasket must align
with the channel and be fully pressed in to achieve a secure
fit. We present and compare 4 methods for <span class="dnerf">Gasket Assembly</span>:
one policy from deep imitation learning and three procedural
algorithms. We evaluate each using 3D printed channels with
100 physical trials. Results suggest that deep imitation learning
can fail (lowest quartile of alignment and insertion performance)
on a straight channel in 2 of 10 trials, whereas a hybrid
procedural algorithm achieves highest quartile performance in
all 10 trials. The procedural algorithm also performs reliably
on a curved channel but poorly on a closed trapezoidal channel.
</p>
</div>
</div>
</div>
<!--/ Abstract. -->

<!-- Paper video. -->
<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">Video</h2>
<div class="publication-video">
<iframe src="https://www.youtube.com/embed/MrKrnHhk8IA?rel=0&amp;showinfo=0"
frameborder="0" allow="autoplay; encrypted-media" allowfullscreen></iframe>
</div>
</div>
</div>
</div> -->
<!--/ Paper video. -->
</div>
</section>
<!-- </div>
</section> -->


<section class="section">
<!-- <section class="section">
<div class="container is-max-desktop">
<div class="columns is-centered">
<!-- Visual Effects. -->
Visual Effects.
<div class="column">
<div class="content">
<h2 class="title is-3">Visual Effects</h2>
Expand All @@ -309,11 +385,11 @@ <h2 class="title is-3">Visual Effects</h2>
type="video/mp4">
</video>
</div>
</div>
</div> -->
<!--/ Visual Effects. -->

<!-- Matting. -->
<div class="column">
<!-- <div class="column">
<h2 class="title is-3">Matting</h2>
<div class="columns is-centered">
<div class="column content">
Expand All @@ -329,15 +405,15 @@ <h2 class="title is-3">Matting</h2>
</div>
</div>
</div>
</div> -->
<!--/ Matting. -->

<!-- Animation. -->
<div class="columns is-centered">
<!-- <div class="columns is-centered">
<div class="column is-full-width">
<h2 class="title is-3">Animation</h2>
<!-- Interpolating. -->
Interpolating.
<h3 class="title is-4">Interpolating states</h3>
<div class="content has-text-justified">
<p>
Expand Down Expand Up @@ -368,14 +444,14 @@ <h3 class="title is-4">Interpolating states</h3>
<p class="is-bold">End Frame</p>
</div>
</div>
<br/>
<br/> -->
<!--/ Interpolating. -->

<!-- Re-rendering. -->
<!-- Re-rendering.
<h3 class="title is-4">Re-rendering the input video</h3>
<div class="content has-text-justified">
<p>
Using <span class="dnerf">Nerfies</span>, you can re-render a video from a novel
Using <span class="dgask">Nerfies</span>, you can re-render a video from a novel
viewpoint such as a stabilized camera by playing back the training deformations.
</p>
</div>
Expand All @@ -390,17 +466,17 @@ <h3 class="title is-4">Re-rendering the input video</h3>
type="video/mp4">
</video>
</div>
<!--/ Re-rendering. -->
/ Re-rendering.
</div>
</div>
<!--/ Animation. -->
/ Animation.
</div>
</section>
</section> -->


<section class="section" id="BibTeX">
<!-- <section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title">BibTeX</h2>
<pre><code>@article{park2021nerfies,
Expand All @@ -410,7 +486,7 @@ <h2 class="title">BibTeX</h2>
year = {2021},
}</code></pre>
</div>
</section>
</section> -->


<footer class="footer">
Expand Down
9 changes: 8 additions & 1 deletion static/css/index.css
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,8 @@
.bold {
font-weight: bold;
}


body {
font-family: 'Noto Sans', sans-serif;
}
Expand All @@ -13,7 +18,7 @@ body {
margin-bottom: 5px;
}

.dnerf {
.dgask {
font-variant: small-caps;
}

Expand Down Expand Up @@ -108,6 +113,8 @@ body {
}

.publication-body img {
width: 100%;
border-radius: 5px;
}

.results-carousel {
Expand Down
Binary file added static/images/actuation.png
View file
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/images/alignment_results.png
View file
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/images/channels_bigger2.png
View file
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/images/insertion_results.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit ae7cb6b

Please sign in to comment.