First update in fall semester

h2r · Sep 23, 2024 · 6f32e57 · 6f32e57
1 parent be7cd38
commit 6f32e57
Show file tree

Hide file tree

Showing 3 changed files with 53 additions and 1 deletion.
diff --git a/index.md b/index.md
@@ -10,7 +10,55 @@ layout: all
 
 Brown Robotics Talks consists of BigAI talks and lab talks ([CIT](https://www.google.com/maps/place/Department+of+Computer+Science/@41.826953,-71.4021589,17z/data=!3m1!4b1!4m6!3m5!1s0x89e4453b5275469d:0xc48a812b6cfb273!8m2!3d41.826953!4d-71.3995786!16s%2Fg%2F1hhwdn5zz?entry=ttu) 115). From spring 2024, this website is created to track both talk series. All confirmed schedule will be posted, together with recordings of past talks (you'll need a Brown account to access the recordings).
 
-### Schedule for Spring 2024
+<h3>Schedule for Fall 2024</h3>
+
+<table>
+<thead>
+  <tr>
+    <th>Date</th>
+    <th>Talk</th>
+    <th>Speaker</th>
+  </tr>
+</thead>
+<tbody>
+  <tr>
+    <td>10/11</td>
+    <td><b>TBD</b></td>
+    <td>Pulkit Verma</td>
+  </tr>
+  <tr>
+    <td>10/18</td>
+    <td><b>TBD</b></td>
+    <td>Roberto Martin-Martin</td>
+  </tr>
+  <tr>
+    <td>10/25</td>
+    <td><b>TBD</b></td>
+    <td>Alex LaGrass</td>
+  </tr>
+  <tr>
+    <td>11/01</td>
+    <td><b>TBD</b></td>
+    <td>Jason Ma</td>
+  </tr>
+  <tr>
+    <td>11/08</td>
+    <td><b>TBD</b></td>
+    <td>Neil Dantam</td>
+  </tr>
+  <tr>
+    <td>11/15</td>
+    <td><b>TBD</b></td>
+    <td>Linfeng Zhao</td>
+  </tr>
+</tbody>
+</table>
+
+
+
+<h3>Spring 2024</h3>
+
+
 
 <table>
 <thead>

diff --git a/pasttalks.md b/pasttalks.md
@@ -56,6 +56,9 @@ permalink: /pasttalks/
   <tr>
     <td><b>[internal] <a href='https://alpera.xyz/' target="_blank">Alper Ahmetoglu</a>, <a href='https://ewinge.me/' target="_blank">Eric Ewing</a></b> [<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=a97965b0-3d00-4608-a4b9-b16c011eb356' target='_blank'>recording</a>]</td><td></td>
   </tr>
+  <tr>
+    <td><b>[internal] A few attempts to learn generalizable manipulation skills - An imitation learning view</b>[<a href='abstracts/mingxijia.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=dd473ccc-2b2c-4cf1-81e3-b1e301200dea' target='_blank'>recording</a>]</td><td><a href='https://saulbatman.github.io/' target="_blank">Mingxi Jia</a></td>
+  </tr>
 </tbody>
 </table>
 

diff --git a/pasttalks/abstracts/mingxijia.txt b/pasttalks/abstracts/mingxijia.txt
@@ -0,0 +1 @@
+Controlling robots to do different tasks in unstructured environments is pivotal for real-world robotic applications. However, achieving this capability poses significant challenges due to the need for a system that can generalize from limited data to a wide range of tasks and environments. Existing methods rely on large, costly datasets and struggle with generalization. In this talk, I will talk about several successful cases and one ongoing effort using imitation learning and generative models for training generalizable robot manipulation skills. The approaches include using symmetry-constrained models for few-shot learning, encoding semantic priors for zero-shot manipulation, and utilizing video generation for multi-task robot manipulation.
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		Controlling robots to do different tasks in unstructured environments is pivotal for real-world robotic applications. However, achieving this capability poses significant challenges due to the need for a system that can generalize from limited data to a wide range of tasks and environments. Existing methods rely on large, costly datasets and struggle with generalization. In this talk, I will talk about several successful cases and one ongoing effort using imitation learning and generative models for training generalizable robot manipulation skills. The approaches include using symmetry-constrained models for few-shot learning, encoding semantic priors for zero-shot manipulation, and utilizing video generation for multi-task robot manipulation.