PageSourceSearch

https://seungchan-kim.github.io/

html seungchan-kim.github.io collected 2026-10-03 09:55:51 UTC 42,978 bytes, 593 lines download raw bytes

1<!DOCTYPE HTML>
2<html lang="en"><head>
3  <!-- If you fork or copy this repo, please delete the two 
3<script> tags below; otherwise my google analytics will track your page -->
4  <!-- %%%%%% Please delete from here.. -->
5  <!-- Global site tag (gtag.js) - Google Analytics -->
vendor: 66 bytes, lines 5-6
5
6  <script async src="https://www.googletagmanager.com/gtag/js?id=
6G-26LSMFKDDQ
vendor: 14 bytes, lines 6-7
6"></script>
7  
7<script>
8	  
vendor: 136 bytes, lines 8-11
8window.dataLayer = window.dataLayer || [];
9	  function gtag(){dataLayer.push(arguments);}
10	  gtag('js', new Date());
11	  gtag('config', '
11G-26LSMFKDDQ
vendor: 6 bytes, lines 11-12
11');
12  
12</script>
12
13  <!-- to here. Thanks! %%%%%%% -->
14
15  <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
16  <title>Seungchan Kim</title>
17  
18  <meta name="author" content="Seungchan Kim">
19  <meta name="viewport" content="width=device-width, initial-scale=1">
20  
21  <link rel="stylesheet" type="text/css" href="stylesheet.css">
22  
23
24</head>
25<body>
26  <table style="width:100%;max-width:800px;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"><tbody>
27    <tr style="padding:0px">
28      <td style="padding:0px">
29        <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"><tbody>
30          <tr style="padding:0px">
31            <td style="padding:2.5%;width:63%;vertical-align:middle">
32              <p style="text-align:center">
33                <name>Seungchan Kim</name>
34              </p>
35              <p style="text-align:center">
36                <strong> email: </strong><em> [email protected] </em>
37              </p>
38              <p>
39              I am a Ph.D. candidate in the <a href="https://www.ri.cmu.edu/" target="_blank">Robotics Institute</a> at <a href="https://www.cmu.edu/" target="_blank">Carnegie Mellon University</a>, advised by <a href="https://www.ri.cmu.edu/ri-faculty/sebastian-scherer/" target="_blank">Sebastian Scherer</a>. My research focuses on spatial reasoning and semantic representations for autonomous mobile robot exploration and navigation. I was also a robotics research intern at <a href="https://www.fieldai.com/" target="_blank">Field AI</a>. 
40              </p>
41              <p>
42                Previously, I earned a B.S. in Applied Mathematics & Computer Science and a M.S. in Computer Science from <a href="https://cs.brown.edu/" target="_blank">Brown University</a>, where I was advised by <a href="http://cs.brown.edu/people/gdk/" target="_blank">George Konidaris</a> and <a href="https://www.littmania.com/" target="_blank">Michael Littman</a>. At Brown, my research centered on deep reinforcement learning.
43              </p>
44              <p style="text-align:center">
45                <a href="https://seungchan-kim.github.io/CV_Seungchan_Kim.pdf" target="_blank">CV</a> &nbsp/&nbsp
46                <a href="https://publications.ri.cmu.edu/storage/publications/2026/08/Seungchan_Kim_PhD_Thesis_Dissertation_20260812145310.pdf" target="_blank">PhD Thesis</a> &nbsp/&nbsp
47                <a href="https://github.com/seungchan-kim/" target="_blank">GitHub</a> &nbsp/&nbsp
48                <a href="https://scholar.google.com/citations?user=hcm1rYQAAAAJ&hl=en" target="_blank">Google Scholar</a> &nbsp/&nbsp
49                <a href="https://x.com/seungchankim25" target="_blank">X</a> &nbsp/&nbsp
50            		<a href="https://www.linkedin.com/in/seungchankim25/" target="_blank">LinkedIn</a> &nbsp/&nbsp
51            		<a href="https://www.youtube.com/@seungchan-kim" target="_blank">YouTube</a>
52              </p>
53            </td>
54            <td style="padding:2.5%;width:40%;max-width:40%">
55              <a href=""><img style="width:80%;max-width:100%" width="206" height="200" alt="profile photo" src="images/profile2025.png" class="hoverZoomLink"></a>
56            </td>
57          </tr>
58        </tbody></table>
59        <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;">
60          <tbody>
61            <tr>
62              <td style="padding:20px;width:100%;vertical-align:middle">
63                <heading>News</heading>
64                <ul id="news-list" style="margin-bottom: 0; padding-left: 20px;">
65                  <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">09/2026: Co-organizing <a href="https://www.ai-meets-autonomy.com/iros-workshop-2026" target="_blank">vision-language autonomy</a> and <a href="https://frostlab.byu.edu/IIG-workshop/" target="_blank">intelligent information gathering</a> workshops at IROS 2026</li>
66                  <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">06/2026: I successfully defended my PhD Thesis!</li> 
67                  <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">
6704/2026: Visited UC San Diego, UC Berkeley, and Stanford for invited talks</li> 
68                  <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">01/2026: A paper on outdoor semantic navigation, <a href="https://raven-semantic.github.io/" target="_blank">RAVEN</a>, was accepted to ICRA 2026. See you at Vienna! </li>
69
70                  <div id="more-news" style="display:none;">
71                  	<li style="list-style-position:inside;margin:0;padding:0;text-align:left;">09/2025: I started research internship at Field AI. </li> 
72                    <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">06/2025: Two papers, <a href="https://rayfronts.github.io/" target="_blank">RayFronts</a> and <a href="https://pipe-planner.github.io/" target="_blank">PIPE Planner</a>, were accepted to IROS 2025.</li>
73                    <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">05/2025: Attended ICRA 2025 to present <a href="https://mapex-explorer.github.io" target="_blank">MapEx</a>. Also participated in ICRA 2025 Doctoral Consortium. </li> 
74                    <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">12/2024: I passed my PhD Thesis Proposal! You can watch the recording of my presentation <a href="https://youtu.be/4u9M1TVYTpU?si=y-GSfZErHpkmMfuA" target="_blank">here</a>. </li>
75                    <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">05/2024: Attended ICRA 2024 and presented my work on <a href="https://arxiv.org/pdf/2307.15202" target="_blank">multi-robot exploration</a>. </li>
76                    <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">12/2023: Survey on foundation models and robotics was released. Check out <a href="https://arxiv.org/abs/2312.08782" target="_blank">here</a>! </li>
77                    <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">11/2023: Attended CoRL 2023. Here are the <a href="https://seungchan-kim.github.io/notes/CoRL_2023_Note.pdf" target="_blank">notes</a> on the sessions that I joined.</li>
78                    <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">07/2022: Two papers on few-shot object detection were accepted at ECCV 2022 and IROS 2022. </li>
79                    <li style="list-style-position:inside;margin:0;padding:0;text-align:left;">09/2020: Started PhD in Robotics at Carnegie Mellon University! </li> 
80                  </div>
81                </ul>
82                
83                <div style="margin-top: 1px; margin-left: 38px;">
84                  <a href="javascript:void(0)" id="news-toggle-btn" onclick="toggleNews()" style="text-decoration: none; font-size: 0.95em; color: #1772d0; font-weight: bold;">+ Show More</a>
85                </div>
86
87                
87<script>
88                  function toggleNews() {
89                    var moreNews = document.getElementById("more-news");
90                    var btnText = document.getElementById("news-toggle-btn");
91
92                    if (moreNews.style.display === "none") {
93                      moreNews.style.display = "block";
94                      btnText.innerHTML = "- Show Less";
95                    } else {
96                      moreNews.style.display = "none";
97                      btnText.innerHTML = "+ Show More";
98                    }
99                  }
100                </script>
100
101              </td>
102            </tr>
103          </tbody>
104        </table>
105
106        <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;">
107		  <tbody>
108		    <tr>
109		      <td style="padding:20px;width:100%;vertical-align:middle">
110		        <heading>Invited Talks</heading>
111		        
112		        <ul style="margin-top: 10px; margin-bottom: 0px;">
113		          <li style="margin-bottom: 8px;">
114		            <strong>3D Representations for Robotics: Geometry, Efficiency, and Semantics</strong><br>
115		            <span style="color: #444; padding-left: 10px; display: block;">
116		              Guest Lecture, CS479: Machine Learning for 3D Data @ KAIST <span style="color: #888;">(hosted by Minhyuk Sung, May 2026)</span><br>
117		            </span>
118		          </li>
119		          <li style="margin-bottom: 8px;">
120		            <strong>Predictive Semantic World Models for Long-Horizon Mobile Robot Autonomy</strong><br>
121		            <span style="color: #444; padding-left: 10px; display: block;">
122		              CogAI Group @ Stanford <span style="color: #888;">(hosted by Jiajun Wu, Apr 2026)</span><br>
123		            </span>
124		          </li>
125		          <li style="margin-bottom: 8px;">
126		            <strong>Predictive Semantic Foresight for Mobile Robot Autonomy</strong><br>
127		            <span style="color: #444; padding-left: 10px; display: block;">
128		              Kanazawa AI Research Lab @ UC Berkeley <span style="color: #888;">(hosted by Angjoo Kanazawa, Apr 2026)</span><br>
129		              Co-PI Seminar on Optimization, Control, and Learning @ UCSD <span style="color: #888;">(hosted by Nikolay Atanasov, Apr 2026)</span><br>
130		              Interactive and Trustworthy Robotics Lab @ CMU <span style="color: #888;">(hosted by Andrea Bajcsy, Apr 2026)</span>
131		            </span>
132		          </li>
133		          <li style="margin-bottom: 8px;">
134		            <strong>Predictive Mapping and Semantic Reasoning for Autonomous Mobile Robots</strong><br>
135		            <span style="color: #444; padding-left: 10px; display: block;">
136		              Scalable Spatial Intelligence Lab @ U Michigan <span style="color: #888;">(hosted by Yulun Tian, Mar 2026)</span><br>
137		              Robot Learning Seminar @ U Buffalo / Georgia Tech / Penn State <span style="color: #888;">(hosted by Chen Wang, Mar 2026)</span>
138		            </span>
139		          </li>
140
141		          <g id="more-talks" style="display:none;">
142		            <li style="margin-bottom: 8px;">
143		              <strong>Spatial Reasoning and Semantic Representations for Intelligent Multi-Robot Exploration and Navigation</strong><br>
144		              <span style="color: #444; padding-left: 10px; display: block;">
145		                Artificial Intelligence for Robot Coordination at Scale Lab @ CMU <span style="color: #888;">(hosted by Jiaoyang Li, Jul 2025)</span><br>
146		                Resilient Intelligent Systems Lab @ CMU <span style="color: #888;">(hosted by Wennie Tabib, Nov 2024)</span>
147		              </span>
148		            </li>
149		          </g>
150		        </ul>
151
152		        <div style="margin-top: 4px; margin-left: 24px;">
153		          <a href="javascript:void(0)" id="talks-toggle-btn" onclick="toggleTalks()" style="text-decoration: none; font-size: 0.95em; color: #1772d0; font-weight: bold;">+ Show More</a>
154		        </div>
155
156		        
156<script>
157		          function toggleTalks() {
158		            var moreTalks = document.getElementById("more-talks");
159		            var btnText = document.getElementById("talks-toggle-btn");
160
161		            if (moreTalks.style.display === "none") {
162		              moreTalks.style.display = "contents"; 
163		              btnText.innerHTML = "- Show Less";
164		            } else {
165		              moreTalks.style.display = "none";
166		              btnText.innerHTML = "+ Show More";
167		            }
168		          }
169		        </script>
169
170		      </td>
171		    </tr>
172		  </tbody>
173		</table>
174        
175
176        <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"><tbody>
177          <tr>
178          <td style="padding:20px;width:100%;vertical-align:middle">
179            <heading>Publications</heading>
180          </td>
181         </tr>
182        </tbody></table>  
183        <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"><tbody>
184  <tr>
185            <td style="padding:20px;width:25%;vertical-align:middle">
186              <img src="images/supermap.gif" alt="" width="160" style="border-style: none">
187            </td> 
188            <td width="75%" valign="middle">
189              <a href="https://www.roboticsproceedings.org/rss22/p052.pdf" id="" target="_blank">
190                <papertitle>SuperMap: A Spatio-Temporal SLAM System for Visual-Language Navigation</papertitle>
191              </a>
192              <br>
193              <a href="https://shibowing.github.io/" target="_blank">Shibo Zhao</a>*, <a href="https://gfchen01.cc/" target="_blank">Guofei Chen</a>*, <a href="https://adrienzhh.github.io/honghao/" target="_blank">Honghao Zhu</a>, <a href="https://zl3466.github.io/" target="_blank">Zhiheng Li</a>, <a href="https://www.chad-yao.com/" target="_blank">Changwei Yao</a>, <a href="https://nzantout.github.io" target="_blank">Nader Zantout</a>, 
194              <br>
195              <strong>Seungchan Kim</strong>, <a href="https://theairlab.org/team/wenshan/" target="_blank">Wenshan Wang</a>, <a href="https://frc.ri.cmu.edu/~zhangji/" target="_blank">Ji Zhang</a>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>
196              <br>
197              <em> Robotics: Science and Systems (RSS) 2026</em>
198              <br>
199              <a href="https://www.roboticsproceedings.org/rss22/p052.pdf" id="" target="_blank">paper</a> |
200              <a href="https://arxiv.org/abs/2608.22896" target="_blank">arXiv</a> | 
201              <a href="https://superodometry.com/supermap" target="_blank">project page</a> |
202              <a href="https://youtu.be/TQjTTqEewNQ?si=ItOG5bXvwsfbXIcT" id="" target="_blank">video</a>
203            </td>
204          </tr>
205  <tr>
206            <td style="padding:20px;width:25%;vertical-align:middle">
207              <img src="images/proid.gif" alt="" width="160" style="border-style: none">
208            </td> 
209            <td width="75%" valign="middle">
210              <a href="https://arxiv.org/pdf/2604.10433" id="" target="_blank">
211                <papertitle>PRoID: Predicted Rate of Information Delivery in Multi-Robot Exploration and Relaying</papertitle>
212              </a>
213              <br>
214              <strong>Seungchan Kim</strong>, <a href="https://seungjaebk.github.io/" target="_blank">Seungjae Baek</a>, <a href="https://www.micahcorah.com/" target="_blank">Micah Corah</a>, <a href="https://profiles.uts.edu.au/Graeme.Best" target="_blank">Graeme Best</a>, <a href="https://bradymoon.com/" target="_blank">Brady Moon</a>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>
215              <br>
216              <em> arXiv preprint arXiv:2604.10433 (2026). Under Review </em>
217              <br>
218              <a href="https://arxiv.org/pdf/2604.10433" id="" target="_blank">paper</a> |   
219              <a href="https://arxiv.org/abs/2604.10433" target="_blank">arXiv</a>
220            </td>
221          </tr>
222  <tr>
223            <td style="padding:20px;width:25%;vertical-align:middle">
224              <img src="images/radseg.png" alt="" width="160" style="border-style: none">
225            </td> 
226            <td width="75%" valign="middle">
227              <a href="https://arxiv.org/pdf/2511.19704" id="" target="_blank">
228                <papertitle>RADSeg: Unleasing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models</papertitle>
229              </a>
230              <br>
231              <a href="https://oasisartisan.github.io" target="_blank">Omar Alama</a>*, <a href="https://www.linkedin.com/in/darshil-jariwala/" target="_blank">Darshil Jariwala</a>*, <a href="https://avigyanbh.github.io" target="_blank">Avigyan Bhattacharya</a>*, <strong>Seungchan Kim</strong>, <a href="https://theairlab.org/team/wenshan/" target="_blank">Wenshan Wang</a>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>
232              <br>
233              <em> IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026 Findings</em>
234              <br>
235              <em> CVPR 2026 Workshop on Open-World 3D Scene Understanding and Representations </em>
236              <br>
237              <a href="papers/2026cvprfindings-radseg.pdf" id="" target="_blank">paper</a> |   
238              <a href="https://arxiv.org/abs/2511.19704" target="_blank">arXiv</a> |
239              <a href="http://radseg-ovss.github.io/" target="_blank">project page</a> |
240              <a href="https://github.com/RADSeg-OVSS/RADSeg" target="_blank">
240code</a>
241            </td>
242          </tr>
243  <tr>
244            <td style="padding:20px;width:25%;vertical-align:middle">
245              <img src="images/raven-intro.gif" alt="" width="160" style="border-style: none">
246            </td> 
247            <td width="75%" valign="middle">
248              <a href="https://arxiv.org/pdf/2509.23563" id="" target="_blank">
249                <papertitle>RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory and Behavior Adaptation</papertitle>
250              </a>
251              <br>
252              <strong>Seungchan Kim</strong>, <a href="https://oasisartisan.github.io" target="_blank">Omar Alama</a>, <a href="https://scholar.google.com/citations?hl=en&user=91gM0vQAAAAJ" target="_blank">Dmytro Kurdydyk</a>, <a href="https://theairlab.org/team/johnk/" target="_blank">John Keller</a>, <a href="https://nik-v9.github.io/" target="_blank">Nikhil Keetha</a>, <a href="https://theairlab.org/team/wenshan/" target="_blank">Wenshan Wang</a>, <a href="https://yonatanbisk.com/" target="_blank">Yonatan Bisk</a>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>
253              <br>
254              <em> IEEE International Conference on Robotics and Automation (ICRA) 2026 </em>
255              <br>
256              <font color="red"><strong>(Oral Presentation, 8.3% of Accepted Papers)</strong></font>
257              <br>
258              <em> IROS 2025 Active Perception Workshop</em>, <font color="red"><strong>Best Paper Finalist (Spotlight Presentation)</strong></font>
259              <br>
260              <a href="papers/2026icra-raven.pdf" id="" target="_blank">paper</a> |   
261              <a href="https://arxiv.org/abs/2509.23563" target="_blank">arXiv</a> | 
262              <a href="https://raven-semantic.github.io/" target="_blank">project page</a> |
263              <a href="https://github.com/castacks/RAVEN" target="_blank">code</a> |
264              <a href="https://youtu.be/slLuZv3-zIs?si=ly2X8Tlyi3Qlqgp9" target="_blank">video</a> | 
265              <a href="https://youtu.be/OL5CfAdYYcQ" target="_blank">presentation video</a>
266            </td>
267          </tr>
268  <tr>
269            <td style="padding:20px;width:25%;vertical-align:middle">
270              <img src="images/mapexrl-thumbnail.png" alt="" width="160" style="border-style: none">
271            </td> 
272            <td width="75%" valign="middle">
273              <a href="https://arxiv.org/pdf/2503.01548" id="" target="_blank">
274                <papertitle>MapExRL: Human-Inspired Indoor Exploration with Predicted Environment Context and Reinforcement Learning</papertitle>
275              </a>
276              <br>
277              <a href="https://narekharutyu.github.io/" target="_blank">Narek Harutyunyan</a>*, <a href="https://bradymoon.com/" target="_blank">Brady Moon</a>*, <strong>Seungchan Kim</strong>, <a href="https://cherieho.com/" target="_blank">Cherie Ho</a>, <a href="https://adamhung60.github.io/" target="_blank">Adam Hung</a>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>
278              <em> IEEE International Conference on Advanced Robotics (ICAR) 2025 </em>
279        <br> 
280        <em> ICRA 2025 Workshop on Structured Learning for Efficient, Reliable, and Transparent Robots</em>
281              <br>
282              <a href="papers/2025icar-mapexrl.pdf" id="" target="_blank">paper</a> |   
283              <a href="https://arxiv.org/abs/2503.01548" target="_blank">arXiv</a> | 
284              <a href="https://mapexrl.github.io/" target="_blank">project page</a> |
285              <a href="https://ieeexplore.ieee.org/document/11338661" target="_blank">DOI</a> |
286              <a href="https://youtu.be/aprE3y0vcpY" target="_blank">video</a>
287            </td>
288          </tr>
289  <tr>    
290            <td style="padding:20px;width:25%;vertical-align:middle">
291              <img src="images/rayfronts-teaser.gif" alt="" width="160" style="border-style: none">
292            </td> 
293            <td width="75%" valign="middle">
294              <a href="https://arxiv.org/pdf/2504.06994" id="" target="_blank">
295                <papertitle>RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration</papertitle>
296              </a>
297              <br>
298              <a href="https://oasisartisan.github.io" target="_blank">Omar Alama</a>, <a href="https://avigyanbh.github.io" target="_blank">Avigyan Bhattacharya</a>, <a href="https://purenothingness24.github.io/" target="_blank">Haoyang He</a>, <strong>Seungchan Kim</strong>, <a href="https://haleqiu.github.io/" target="_blank">Yuheng Qiu</a>, <a href="https://theairlab.org/team/wenshan/" target="_blank">Wenshan Wang</a>, <a href="https://cherieho.com/" target="_blank">Cherie Ho</a>, <a href="https://nik-v9.github.io/" target="_blank">Nikhil Keetha</a>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>
299              <br>
300              <em> IEEE/RSJ International Conference on Intelligent Robots and Systems (I
300ROS) 2025 </em>
301              <br>
302              <em> RSS 2025 Workshop on Semantic Reasoning and Goal Understanding in Robotics</em>
303              <br>
304              <em> RSS 2025 Workshop on Learned Robot Representations </em>
305              <br>
306		          <a href="papers/2025iros-rayfronts.pdf" id="" target="_blank">paper</a> |   
307		          <a href="https://arxiv.org/abs/2504.06994" target="_blank">arXiv</a> | 
308		          <a href="https://rayfronts.github.io/" target="_blank">project page</a> | 
309		          <a href="https://github.com/RayFronts/RayFronts" target="_blank">code</a> |
310              <a href="https://ieeexplore.ieee.org/document/11245813" target="_blank">DOI</a> |  
311		          <a href="https://youtu.be/fFSKUBHx5gA?si=yPHBV7LxLirVjtYg" target="_blank">video</a>
312            </td>
313          </tr>
314	<tr>
315            <td style="padding:20px;width:25%;vertical-align:middle">
316              <img src="images/PIPE_animation.gif" alt="" width="160" style="border-style: none">
317            </td> 
318            <td width="75%" valign="middle">
319              <a href="https://arxiv.org/pdf/2503.07504" id="" target="_blank">
320                <papertitle>PIPE Planner: Pathwise Information Gain with Map Predictions for Indoor Robot Exploration</papertitle>
321              </a>
322              <br>
323              <a href="https://seungjaebk.github.io/" target="_blank">Seungjae Baek</a>*, <a href="https://bradymoon.com/" target="_blank">Brady Moon</a>*, <strong>Seungchan Kim</strong>*, <a href="https://caomuqing.github.io/" target="_blank">Muqing Cao</a>, <a href="https://cherieho.com/" target="_blank">Cherie Ho</a>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>, <a href="https://rml-unist.notion.site/" target="_blank">Jeong hwan Jeon</a>
324              <br>
325		(*: Equal Contributions)
326	      <br>
327              <em> IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025 </em>
328              <br>
329		<a href="papers/2025iros-pipe.pdf" id="" target="_blank">paper</a> |   
330		<a href="https://arxiv.org/abs/2503.07504" target="_blank">arXiv</a> | 
331		<a href="https://pipe-planner.github.io/" target="_blank">project page</a> |
332    <a href="https://github.com/castacks/pipe-planner" target="_blank">code</a> |
333    <a href="https://ieeexplore.ieee.org/document/11246190" target="_blank">DOI</a> | 
334		<a href="https://youtu.be/oZEqbCBRn-I" target="_blank">video</a>
335            </td>
336          </tr>
337	<tr>
338            <td style="padding:20px;width:25%;vertical-align:middle">
339              <img src="images/mapex-v2.gif" alt="" width="160" style="border-style: none">
340            </td> 
341            <td width="75%" valign="middle">
342              <a href="https://arxiv.org/pdf/2409.15590" id="" target="_blank">
343                <papertitle>MapEx: Indoor Structure Exploration with Probabilistic Information Gain from Global Map Predictions</papertitle>
344              </a>
345              <br>
346              <a href="https://cherieho.com/" target="_blank">Cherie Ho</a>*, <strong>Seungchan Kim</strong>*, <a href="https://bradymoon.com/" target="_blank">Brady Moon</a>, <a href="https://www.linkedin.com/in/aditya-parandekar-ab9aa0218/" target="_blank">Aditya Parandekar</a>, <a href="https://narekharutyu.github.io/" target="_blank">Narek Harutyunyan</a>, <a href="https://sairlab.org/chenw" target="_blank">Chen Wang</a>, <a href="https://www.cs.cmu.edu/~sycara/" target="_blank">Katia Sycara</a>, <a href="https://profiles.uts.edu.au/Graeme.Best" target="_blank">Graeme Best</a>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>
347              <br>
348		(*: Equal Contributions)
349	      <br>
350              <em> IEEE International Conference on Robotics and Automation (ICRA) 2025 </em>
351              <br>
352          		<a href="papers/2025icra-mapex.pdf" id="" target="_blank">paper</a> |   
353          		<a href="https://arxiv.org/abs/2409.15590" target="_blank">arXiv</a> |
354          		<a href="https://mapex-explorer.github.io" target="_blank">project page</a> | 
355          		<a href="https://github.com/castacks/MapEx" target="_blank">
355code</a> | 
356              <a href="https://ieeexplore.ieee.org/document/11128862/" target="_blank">DOI</a> | 
357          		<a href="https://youtu.be/awvBnLQi3zg?si=CRmQqOR7HFvTLzQN" target="_blank">video</a> | 
358          		<a href="https://youtu.be/s2f8nCrVZAk" target="_blank">presentation video</a>
359            </td>
360          </tr>
361	<tr>
362            <td style="padding:20px;width:25%;vertical-align:middle">
363              <img src="images/fm-rob-survey.png" alt="" width="160" style="border-style: none">
364            </td> 
365            <td width="75%" valign="middle">
366              <a href="https://arxiv.org/pdf/2312.08782.pdf" id="" target="_blank">
367                <papertitle>Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis</papertitle>
368              </a>
369              <br>
370              <a href="https://jeffreyyh.github.io/" target="_blank">Yafei Hu</a>*, <a href="https://quantingxie.github.io/" target="_blank">Quanting Xie</a>*, <a href="https://vidhijain.github.io/" target="_blank">Vidhi Jain</a>*, <a href="https://jonfranc.com/" target="_blank">Jonathan Francis</a>, <a href="https://www.jaypatrikar.me/" target="_blank">Jay Patrikar</a>, <a href="https://nik-v9.github.io/" target="_blank">Nikhil Keetha</a>, <strong>Seungchan Kim</strong>, <a href="https://yaqi-xie.me/" target="_blank">Yaqi Xie</a>, <a href="https://tyz1030.github.io/" target="_blank">Tianyi Zhang</a>, <a href="https://fang-haoshu.github.io/" target="_blank">Hao-Shu Fang</a>, <a href="https://shibowing.github.io/" target="_blank">Shibo Zhao</a>, <a href="https://www.linkedin.com/in/shayegan/" target="_blank">Shayegan Omidshafiei</a>, <a href="https://dkkim93.github.io/" target="_blank">Dong-Ki Kim</a>, <a href="https://www.linkedin.com/in/ali-agha-7aa5212a/" target="_blank">Ali-akbar Agha-mohammadi</a>, <a href="https://www.cs.cmu.edu/~sycara/" target="_blank">Katia Sycara</a>, <a href="https://droplab.ri.cmu.edu/" target="_blank">Matthew Johnson-Roberson</a>, <a href="https://faculty.cc.gatech.edu/~dbatra/" target="_blank">Dhruv Batra</a>, <a href="https://xiaolonw.github.io/" target="_blank">Xiaolong Wang</a>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>, <a href="https://sairlab.org/chenw" target="_blank">Chen Wang</a>, <a href="https://faculty.cc.gatech.edu/~zk15/" target="_blank">Zsolt Kira</a>, <a href="https://fxia22.github.io/" target="_blank">Fei Xia</a>, <a href="https://yonatanbisk.com/" target="_blank">Yonatan Bisk</a>
371              <br>
372              <em> arXiv preprint arXiv:2312.08782 (2023). </em>
373              <br>
374          		<a href="https://arxiv.org/pdf/2312.08782.pdf" id="" target="_blank">paper</a> |
375          		<a href="https://arxiv.org/abs/2312.08782" target="_blank">arXiv</a> | 
376          		<a href="https://robotics-fm-survey.github.io/" target="_blank">project page</a>
377            </td>
378        </tr>	
379	<tr>
380            <td style="padding:20px;width:25%;vertical-align:middle">
381              <img src="images/mrmr.gif" alt="" width="160" style="border-style: none">
382            </td>
383            <td width="75%" valign="middle">
384              <a href="https://arxiv.org/pdf/2307.15202.pdf" id="" target="_blank">
385                <papertitle>Multi-Robot Multi-Room Exploration with Geometric Cue Extraction and Circular Decomposition</papertitle>
386              </a>
387              <br>
388              <strong>Seungchan Kim</strong>, <a href="https://www.micahcorah.com/" target="_blank">Micah Corah</a>, <a href="https://theairlab.org/team/johnk/" target="_blank">John Keller</a>, <a href="https://profiles.uts.edu.au/Graeme.Best" target="_blank">Graeme Best</a>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>
389              <br>
390              <em> IEEE Robotics and Automation Letters (RA-L) 2023 </em>
391          		<br>
392          		<em>Presentation at IEEE International Conference on Robotics and Automation (ICRA) 2024</em>
393              <br>
394      		    <a href="papers/2023ral-mrmr.pdf" id="" target="_blank">paper</a> |
395      		    <a href="https://arxiv.org/abs/2307.15202" target="_blank">arXiv</a> |
396      		    <a href="https://seungchan-kim.github.io/multi-robot-multi-room" target="_blank">project page</a> |
397      		    <a href="https://ieeexplore.ieee.org/document/10356832" target="_blank">DOI</a> | 
398      		    <a href="https://www.youtube.com/watch?v=zUtK1hh2Tpo" target="_blank">video</a> | 
399      		    <a href="https://youtu.be/DFoL3MGQwbE?si=zFEQKhjwbX2hU8Y_" target="_blank">presentation video</a>
400            </td>
401          </tr>
402          
403          <tr>
404            <td style="padding:20px;width:25%;vertical-align:middle">
405              <img src="images/airdet.png" alt="" width="160" style="border-style: none">
406            </td> 
407            <td width="75%" valign="middle">
408              <a href="https://arxiv.org/pdf/2112.01740.pdf" id="" target="_blank">
409                <papertitle>AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration</papertitle>
410              </a>
411              <br>
412              <a href="https://jaraxxus-me.github.io/" target="_blank">Bowen Li</a>, <a href="https://sairlab.org/chenw" target="_blank">Chen Wang</a>, <a href="https://pranay-ar.github.io/" target="_blank">Pranay Reddy</a>, <strong>Seungchan Kim</strong>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>
413              <br>
414              <em> European Conference on Computer Vision (ECCV) 2022 </em>
415              <br>
416      	      <a href="papers/2022eccv-airdet.pdf" id="" target="_blank">paper</a> | 
417      	      <a href="https://arxiv.org/abs/2112.01740" target="_blank">arXiv</a> |
418              <a href="https://jaraxxus-me.github.io/ECCV2022_AirDet/" target="_blank">project page</a> |
419              <a href="https://github.com/Jaraxxus-Me/AirDet" target="_blank">
419code</a> | 
420          		<a href="https://link.springer.com/chapter/10.1007/978-3-031-19842-7_25">DOI</a>
421            </td>
422          </tr>
423          
424          <tr>
425            <td style="padding:20px;width:25%;vertical-align:middle">
426              <img src="images/airinteraction.png" alt="" width="160" style="border-style: none">
427            </td> 
428            <td width="75%" valign="middle">
429              <a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9981461" id="" target="_blank">
430                <papertitle>Robotic Interestingness via Human-Informed Few-Shot Object Detection</papertitle>
431              </a>
432              <br>
433              <strong>Seungchan Kim</strong>, <a href="https://sairlab.org/chenw" target="_blank">Chen Wang</a>, <a href="https://jaraxxus-me.github.io/" target="_blank">Bowen Li</a>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>
434              <br>
435              <em> IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022 </em>
436              <br>
437				<a href="papers/2022iros-interestingness.pdf" target="_blank">paper</a> | <a href="https://arxiv.org/abs/2208.01084" target="_blank"> arXiv </a> | <a href="https://ieeexplore.ieee.org/abstract/document/9981461" target="_blank"> DOI </a> | <a href="https://youtu.be/-GugFxs6ubg?si=6ZnIj1ibFnmeqjjO" target="_blank">video</a>
438            </td>
439          </tr>
440          
441          <tr>
442            <td style="padding:20px;width:25%;vertical-align:middle">
443              <img src="images/online-learning.png" alt="" width="160" style="border-style: none">
444            </td> 
445            <td width="75%" valign="middle">
446              <a href="https://arxiv.org/pdf/2111.09793.pdf" id="" target="_blank">
447                <papertitle>Unsupervised Online Learning for Robotic Interestingness with Visual Memory</papertitle>
448              </a>
449              <br>
450              <a href="https://sairlab.org/chenw" target="_blank">Chen Wang</a>, <a href="https://haleqiu.github.io/" target="_blank">Yuheng Qiu</a>, <a href="https://theairlab.org/team/wenshan/" target="_blank">Wenshan Wang</a>, <a href="https://jeffreyyh.github.io/" target="_blank">Yafei Hu</a>, <strong>Seungchan Kim</strong>, <a href="https://theairlab.org/team/sebastian/" target="_blank">Sebastian Scherer</a>
451              <br>
452              <em> IEEE Transactions on Robotics (T-RO) 2021 </em>
453              <br>
454          		<a href="papers/2021tro-unsupervised.pdf" id="" target="_blank">paper</a> | <a href="https://arxiv.org/abs/2111.09793" target="_blank"> arXiv </a> | <a href="https://sairlab.org/interestingness/" target="_blank"> project page </a> | <a href="https://github.com/sair-lab/interestingness" target="_blank"> code </a> | <a href="https://ieeexplore.ieee.org/abstract/document/9653144">DOI</a>
455            </td>
456          </tr>
457          
458           <tr>
459            <td style="padding:20px;width:25%;vertical-align:middle">
460              <img src="images/playroom.png" alt="" width="160" style="border-style: none">
461            </td> 
462            <td width="75%" valign="middle">
463              <a href="https://psyarxiv.com/gq4rt/" id="" target="_blank">
464                <papertitle>Using Computational Analysis of Behavior to Discover Developmental Change in Memory-Guided Attention Mechanisms in Childhood</papertitle>
465              </a>
466              <br>
467              <a href="https://psychology.columbia.edu/content/dima-amso" target="_blank">Dima Amso</a>, Lakshmi Govindarajan, Pankaj Gupta, Diego Placido, Heidi Baumgartner, Andrew Lynn, Kelley Gunther, Tarun Sharma, Vijay Veerabadran, Kalpit Thakkar, <strong>Seungchan Kim</strong>, <a href="https://serre-lab.clps.brown.edu/person/thomas-serre/" target="_blank">Thomas Serre</a>
468              <br>
469              <em> PsyArXiv. doi:10.31234/osf.io/gq4rt </em>
470              <br>
471		<a href="https://doi.org/10.31234/osf.io/gq4rt" target="_blank">DOI</a>
472            </td>
473          </tr>
474          
475          <tr>
476            <td style="padding:20px;width:25%;vertical-align:middle">
477              <img src="images/multi-step.png" alt="" width="160" style="border-style: none">
478            </td> 
479            <td width="75%" valign="middle">
480              <a href="https://arxiv.org/pdf/1905.13320.pdf" id="" target="_blank">
481                <papertitle>Combating the Compounding-Error Problem with a Multi-step Model</papertitle>
482              </a>
483              <br>
484              <a href="https://cs.brown.edu/people/kasadiat/" target="_blank">Kavosh Asadi</a>, <a href="https://dipendramisra.com/" target="_blank">Dipendra Misra</a>, <strong>Seungchan Kim</strong>, <a href="https://www.littmania.com/" target="_blank">Michael Littman</a>
485              <br>
486              <em> arXiv preprint arXiv:1905.13320 (2019). </em>
487              <br>
488		<a href="papers/2019arxiv-compoundingerror.pdf" id="" target="_blank">paper</a> | <a href="https://arxiv.org/abs/1905.13320" target="_blank"> arXiv </a>
489            </td>
490          </tr>
491          
492          <tr>
493            <td style="padding:20px;width:25%;vertical-align:middle">
494              <img src="images/seaquest.png" alt="" width="160" style="border-style: none">
495            </td>
496            <td width="75%" valign="middle">
497              <a href="https://www.ijcai.org/Proceedings/2019/0379.pdf" id="" target="_blank">
498                <papertitle>DeepMellow: Removing the Need for a Target Network in Deep Q-Learning</papertitle>
499              </a>
500              <br>
501              <strong>Seungchan Kim</strong>, <a href="https://cs.brown.edu/people/kasadiat/" target="_blank">Kavosh Asadi</a>, <a href="https://www.littmania.com/" target="_blank">Michael Littman</a>, <a href="http://cs.brown.edu/people/gdk/" target="_blank">George Konidaris</a>
502              <br>
503              <em> International Joint Conference on Artificial Intelligence (IJCAI) 2019</em>
504              <br>
505              <em> Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2019</em>
506              <br>
507              <a href="papers/2019ijcai-deepmellow.pdf" target="_blank">paper</a> | <a href="https://github.com/seungchan-kim/DeepMellow" target="_blank">
507code</a> | <a href="https://par.nsf.gov/biblio/10180061">DOI</a>
508            </td>
509          </tr>
510          
511          <tr>
512            <td style="padding:20px;width:25%;vertical-align:middle">
513              <img src="images/mellowmax.png" alt="" width="160" style="border-style: none">
514            </td>
515            <td width="75%" valign="middle">
516              <a href="http://www.ifaamas.org/Proceedings/aamas2019/pdfs/p2060.pdf" id="" target="_blank">
517                <papertitle>Removing the Target Network from Deep Q-Networks with the Mellowmax Operator</papertitle>
518              </a>
519              <br>
520              <strong>Seungchan Kim</strong>, <a href="https://cs.brown.edu/people/kasadiat/" target="_blank">Kavosh Asadi</a>, <a href="https://www.littmania.com/" target="_blank">Michael Littman</a>, <a href="http://cs.brown.edu/people/gdk/" target="_blank">George Konidaris</a>
521              <br>
522              <em> International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2019</em>, <strong>Extended Abstract</strong>
523	      <br>
524		<a href="papers/2019aamas-mellowmaxdqn.pdf" id="" target="_blank">paper</a>
525            </td>
526          </tr>          
527          
528        <table width="100%" align="center" border="0" cellspacing="0" cellpadding="20"><tbody>
529          <tr>
530            <td style="padding-bottom: 5px;">
531              <heading>Teaching</heading>
532            </td>
533          </tr>
534        </tbody></table>
535        <table width="100%" align="center" border="0" cellpadding="20"><tbody>
536          <tr>
537            <td width="100%" valign="center" style="padding-top: 8px;">
538              <strong>Carnegie Mellon University Robotics Institute</strong>
539              <br>
540              <a href="" target="_blank">16-711 Kinematics, Dynamics, Control</a>, Teaching Assistant, Spring 2023
541              <br>
542              <a href="https://www.cs.cmu.edu/~kaess/teaching/16833/Spring2021/" target="_blank">16-833 Robot Localization and Mapping</a>, Teaching Assistant, Spring 2022
543              <br><br>
544              <strong>Brown University</strong>
545              <br>
546              <a href="https://cs.brown.edu/courses/csci1430/2019_Spring/index.html" target="_blank">CSCI1430 Computer Vision</a>, Teaching Assistant, Spring 2019
547              <br>
548              <a href="http://cs.brown.edu/courses/csci0040/" target="_blank">CSCI0040 Intro to Scientific Computing and Problem Solving</a>, Teaching Assistant, Spring 2015
549            </td>
550          </tr>
551         </tbody></table>
552        
553        
554        <table width="100%" align="center" border="0" cellspacing="0" cellpadding="20"><tbody>
555          <tr>
556            <td style="padding-bottom: 5px;">
557              <heading>Service & Outreach</heading>
558            </td>
559          </tr>
560        </tbody></table>
561        <table width="100%" align="center" border="0" cellpadding="20"><tbody>
562          <tr>
563            <td width="75%" valign="center" style="padding-top: 8px;">
564              <strong>Associate Editor:</strong> ICRA
565              <br>
566              <strong>Organizer:</strong>
567              <ul style="margin-top: 6px; margin-bottom: 10px;">
568                <li><a href="https://www.ai-meets-autonomy.com/iros-workshop-2026" target="_blank">IROS 2026 Workshop on AI Meets Autonomy: Vision, Language, and Autonomous Systems</a></li>
569                <li><a href="https://frostlab.byu.edu/IIG-workshop/" target="_blank">IROS 2026 Workshop and Competition on Intelligent Information Gathering for Single and Multi-Robot Systems</a></li>
570                <li><a href="https://theairlab.org/tartanplanningseries/" target="_blank">Tartan Planning Series Spring 2023</a></li>
571              </ul>
572              <strong>Journal Reviewer:</strong> IJRR, T-RO, T-ASE, RA-L
573              <br>
574              <strong>Conference Reviewer:</strong> ICRA, IROS, CoRL, CASE, MRS, ICAR, ICLR, NeurIPS, AAAI, ICML
575              <br>
576            </td>
577          </tr>
578         </tbody></table>
579        
580        <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"><tbody>
581          <tr>
582            <td style="padding:0px">
583              <br>
584              <p style="text-align:right;font-size:small;">
585                <a href="https://github.com/jonbarron/jonbarron_website" target="_blank"> Website Template</a>
586              </p>
587            </td>
588          </tr>
589        </tbody></table>
590
591</body>
592  
593</html>

Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.