Add many posts

_pages/projects_page/index.html

@@ -6,10 +6,8 @@
   overlay_filter: 0.5
 excerpt: "Projects"
 --- 
-<p>Projects</p>
-{% for post in site.my_posts %}
-<div class="post">
-    <h2><a href="{{ post.url }}">{{ post.title }}</a></h2>
-    <div>{{ post.content }}</div>
-</div>
-{% endfor %}
+<h3 class="archive__subtitle">Projects</h3>
+
+{% for post in site.categories.Projects %}
+{% include archive-single.html type='post' %}
+{% endfor %}

_pages/research_page/index.html

@@ -2,8 +2,8 @@
 layout: archive
 author_profile: true
 header:
-overlay_image: assets/image/thumbnail/homepage_thumbnail.jpeg
-overlay_filter: 0.5
+    overlay_image: assets/image/thumbnail/homepage_research.jpeg
+    overlay_filter: 0.3
 excerpt: "Research"
 ---
 
@@ -19,7 +19,7 @@ <h3 class="archive__subtitle">Publications</h3>
 
 <br>
 <br>
-<p class="archive__subtitle">2nd Author</p>
+<h1 class="archive__subtitle">2nd Author</h1>
 
 {% for post in site.categories.2ndAuthor %}
 {% include archive-single.html type='post' %}

_posts/2020-05-31-icra_boseong.md

@@ -5,7 +5,7 @@ categories:
 tags:
  - Aerial Tracking
 header:
-  teaser: /assets/image/thumbnail/tro2023.gif
+  teaser: /assets/image/thumbnail/homepage_boseong-icra_gif.gif
 authors: Boseong Jeon, <u>Yunwoo Lee*</u>, and H. Jin Kim
 links:
 - paper:
@@ -14,7 +14,7 @@ links:
 - bibtex:
   name: "Bibtex"
 ---
-{% include video id="zxpBws6kxNI" provider="youtube" %}
+{% include video id="_JSwXBwYRl8" provider="youtube" %}
 
 **Abstract:** This work suggests an integrated approach for a drone (or multirotor) to perform an autonomous videography task in a 3-D obstacle environment by following a moving object. The proposed system includes 1) a target motion prediction module which can be applied to dense environments and 2) a hierarchical chasing planner. Leveraging covariant optimization, the prediction module estimates the future motion of the target assuming it efforts to avoid the obstacles. The other module, chasing planner, is in a bi-level structure composed of preplanner and smooth planner. In the first phase, we exploit a graph-search method to plan a chasing corridor which incorporates safety and visibility of target. In the subsequent phase, we generate a smooth and dynamically feasible trajectory within the corridor using quadratic programming (QP). We validate our approach with multiple complex scenarios and actual experiments. The source code and the experiment video can be found in https://github.com/icsl-Jeon/traj_gen_vis and https://www.youtube.com/watch?v=_JSwXBwYRl8.
 

_posts/2020-10-24-iros2020.md

@@ -5,7 +5,7 @@ categories:
 tags:
  - Aerial Tracking
 header:
-  teaser: /assets/image/thumbnail/tro2023.gif
+  teaser: /assets/image/thumbnail/homepage_iros2020_cut_gif.gif
 authors: Youngseok Jang*, <u>Yunwoo Lee*</u>, and H. Jin Kim
 links:
 - paper:

_posts/2021-03-19-multislam.md

@@ -5,7 +5,7 @@ categories:
 tags:
  - Multi Robot System
 header:
-  teaser: /assets/image/thumbnail/tro2023.gif
+  teaser: /assets/image/thumbnail/homepage_multislam_7x_comp_crop.gif
 authors: Youngseok, Changsuk Oh, <u>Yunwoo Lee*</u>, and H. Jin Kim
 links:
 - paper:
@@ -14,7 +14,7 @@ links:
 - bibtex:
   name: "Bibtex"
 ---
-{% include video id="zxpBws6kxNI" provider="youtube" %}
+{% include video id="aaVWl64vYxQ" provider="youtube" %}
 
 **Abstract:** Multirobot simultaneous localization and mapping (SLAM) requires technical ingredients such as systematic construction of multiple SLAM systems and collection of information from each robot. In particular, map fusion is an essential process of multirobot SLAM that combines multiple local maps estimated by team robots into a global map. Fusion of multiple local maps is usually based on interloop detection that recognizes the same scene visited by multiple robots, or robot rendezvous where a member(s) of a robot team is observed in another member's images. This article proposes a collaborative monocular SLAM including a map fusion algorithm that utilizes rendezvous, which can happen when multirobot team members operate in close proximity. Unlike existing rendezvous-based approaches that require additional sensors, the proposed system uses a monocular camera only. Our system can recognize robot rendezvous using nonstatic features (NSFs) without fiducial markers to identify team robots. NSFs, which are abandoned as outliers in typical SLAM systems for not supporting ego-motion, can include relative bearing measurements between robots in a rendezvous situation. The proposed pipeline consists of the following: first, a feature identification module that extracts the relative bearing measurements between robots from NSFs consisting of anonymous bearing vectors with false positives, and second, a map fusion module that integrates the map from the observer robot with the maps from the observed robots using identified relative measurements. The feature identification module can operate quickly using the proposed alternating minimization algorithm formulated by two subproblems with closed-form solutions. The experimental results confirm that our collaborative monocular SLAM system recognizes rendezvous rapidly and robustly, and fuses local maps of team robots into a global map accurately.
 

_posts/2021-09-23-atypical_proj.md

@@ -0,0 +1,11 @@
+---
+title: "Autonomous Driving, Ministry of Science and Technoloy of Korea"
+categories:
+ - Projects
+tags:
+ - Autonomous Driving
+header:
+  teaser: /assets/image/thumbnail/homepage_atypical_proj_2x_gif_comp.gif
+---
+
+<b>Autonomous Driving</b> in <b>Rural</b> environments

_posts/2021-10-01-iros2021.md

@@ -5,7 +5,7 @@ categories:
 tags:
  - Aerial Tracking
 header:
-  teaser: /assets/image/thumbnail/tro2023.gif
+  teaser: /assets/image/thumbnail/homepage_iros2021_cut_gif.gif
 authors: <u>Yunwoo Lee</u>, Jungwon Park, Boseong Jeon, and H. Jin Kim
 links:
 - paper:

_posts/2021-10-04-dual_access.md

@@ -5,7 +5,7 @@ categories:
 tags:
  - Aerial Tracking
 header:
-  teaser: /assets/image/thumbnail/tro2023.gif
+  teaser: /assets/image/thumbnail/homepage_dualtarget_gif.gif
 authors: Boseong Jeon, <u>Yunwoo Lee*</u>, Jeongjun Choi, Jungwon Park, and H. Jin Kim
 links:
 - paper:

_posts/2022-09-23-kai_proj.md

@@ -0,0 +1,11 @@
+---
+title: "Drone swarm, Korean Aerospace Industry, Korea"
+categories:
+ - Projects
+tags:
+ - Multi-rotor
+header:
+  teaser: /assets/image/thumbnail/homepage_kai_proj_5d5x_gif_comp.gif
+---
+
+<b>Quadrotor Swarm</b>, upto 10 agents

_posts/2023-06-01-dlsc.md

@@ -6,7 +6,7 @@ tags:
  - multi-agent trajectory planning
  - distributed robot system
 header:
-  teaser: /assets/image/thumbnail/tro2023.gif
+  teaser: /assets/image/thumbnail/homepage_dlsc_crop.gif
 authors: Jungwon Park, <u>Yunwoo Lee</u>, Inkyu Jang, and H. Jin Kim
 links:
 - paper:

_posts/2023-09-23-mooin_proj.md

@@ -0,0 +1,11 @@
+---
+title: "Unmanned Aerial/Ground Vehicle, Ministry of Science and Technology of Korea"
+categories:
+ - Projects
+tags:
+ - Multi-rotor
+header:
+  teaser: /assets/image/thumbnail/homepage_mooin_proj_4x_gif_comp.gif
+---
+
+<b>Monocular depth estimation</b> and <b>Path planning</b> in unstructured environments 

_posts/2024-05-28-monocameraonly.md

@@ -1,11 +1,11 @@
 ---
-title: "(R-AL) Mono-Camera-Only Target Chasing for a Drone in a Dense Environment by Cross-Modal Learning"
+title: "(RA-L) Mono-Camera-Only Target Chasing for a Drone in a Dense Environment by Cross-Modal Learning"
 categories:
  - 2ndAuthor
 tags:
  - deep learning
 header:
-  teaser: /assets/image/thumbnail/tro2023.gif
+  teaser: /assets/image/thumbnail/homepage_monocamera_gif.gif
 authors: Seungyeon Yoo, Seungwoo Jung, <u>Yunwoo Lee</u>, Dongsek Shim, and H. Jin Kim
 links:
 - paper:

_posts/2024-09-23-qp_chaser.md

@@ -6,7 +6,7 @@ categories:
 tags:
  - Aerial Tracking
 header:
-  teaser: /assets/image/thumbnail/homepage_thumbnail.jpeg
+  teaser: /assets/image/thumbnail/homepage_qp_chaser_4x_compressed_gif_comp.gif
 journals: RA-L
 authors: <u>Yunwoo Lee</u>, Jungwon Park,S eungwoo Jung, Boseong Jeon, Dahyun Oh, and H. Jin Kim
 links:
@@ -15,3 +15,15 @@ links:
   name: "Paper"
 ---
 
+<br>
+<br>
+<br>
+
+
+**Abstract:** Maintaining the visibility of the target is one of the major objectives of aerial tracking missions.
+This paper proposes a target-visible trajectory planning pipeline using quadratic programming (QP).
+Our approach can handle various tracking settings, including 1) single- and dual-target following and 2) both static and dynamic environments, unlike other works that focus on a single specific setup.
+In contrast to other studies that fully trust the predicted trajectory of the target and consider only the visibility of the target’s center, our pipeline considers error in target path prediction and the entire body of the target to maintain the target visibility robustly. 
+First, a prediction module uses a sample-check strategy to quickly calculate the reachable sets of moving objects, which represent the areas their bodies can reach, considering obstacles.
+Subsequently, the planning module formulates a single QP problem, considering path topology, to generate a tracking trajectory that maximizes the visibility of the target's reachable set among obstacles.
+The performance of the planner is validated in multiple scenarios, through high-fidelity simulations and real-world experiments.

_posts/2024-09-25-bpmp_tracker.md

@@ -6,12 +6,28 @@ categories:
 tags:
  - Aerial Tracking
 header:
-  teaser: /assets/image/thumbnail/homepage_thumbnail.jpeg
+  teaser: /assets/image/thumbnail/homepage_bpmp-tracker_2x_gif.gif
 journals: RA-L
 authors: <u>Yunwoo Lee</u>, Jungwon Park, Boseong Jeon, Seungwoo Jung, and H. Jin Kim
 links:
 - paper:
   link: https://arxiv.org/pdf/2408.04266
   name: "Paper"
 ---
+{% include video id="rTf4HyOwnOA" provider="youtube" %}
 
+**Abstract:** This work presents a distributed trajectory planning method for multi-agent aerial tracking. The proposed method uses a Dynamic Buffered Voronoi Cell (DBVC) and a Dynamic Inter-Visibility Cell (DIVC) to formulate the distributed trajectory generation. Specifically, the DBVC and the DIVC are time-variant spaces that prevent mutual collisions and occlusions among agents, while enabling them to maintain suitable distances from the moving target. We combine the DBVC and the DIVC with an efficient Bernstein polynomial motion primitive-based tracking trajectory generation method, which has been refined into a less conservative approach than in our previous work. The proposed algorithm can compute each agent's trajectory within several milliseconds on an Intel i7 desktop. We validate the tracking performance in challenging scenarios, including environments with dozens of obstacles.
+
+## Bibtex <a id="bibtex"></a>
+```
+@ARTICLE{bpmp_tracker2024,
+  author={Lee, Yunwoo and Park, Jungwon and Jeon, Boseong and Jung, Seungwoo and Kim, H. Jin},
+  journal={IEEE Robotics and Automation Letters}, 
+  title={BPMP-Tracker: A Versatile Aerial Target Tracker Using Bernstein Polynomial Motion Primitives}, 
+  year={2024},
+  volume={9},
+  number={12},
+  pages={10938-10945},
+  keywords={Trajectory;Drones;Polynomials;Target tracking;Trajectory planning;Planning;Pipelines;Ellipsoids;Cameras;Aerodynamics;Reactive and sensor-based planning;visual servoing;motion and path planning},
+  doi={10.1109/LRA.2024.3475879}}
+```

_posts/2024-11-06-dmvc_tracker.md

@@ -5,8 +5,16 @@ categories:
 tags:
  - Aerial Tracking
 header:
-  teaser: /assets/image/thumbnail/homepage_thumbnail.jpeg
+  teaser: /assets/image/thumbnail/homepage_dmvc_tracker_2x_gif_comp.gif
 journals: RA-L
 authors: <u>Yunwoo Lee</u>, Jungwon Park, and H. Jin Kim
 ---
 
+
+
+<br>
+<br>
+<br>
+
+
+**Abstract:** This work presents a distributed trajectory planning method for multi-agent aerial tracking. The proposed method uses a Dynamic Buffered Voronoi Cell (DBVC) and a Dynamic Inter-Visibility Cell (DIVC) to formulate the distributed trajectory generation. Specifically, the DBVC and the DIVC are time-variant spaces that prevent mutual collisions and occlusions among agents, while enabling them to maintain suitable distances from the moving target. We combine the DBVC and the DIVC with an efficient Bernstein polynomial motion primitive-based tracking trajectory generation method, which has been refined into a less conservative approach than in our previous work. The proposed algorithm can compute each agent's trajectory within several milliseconds on an Intel i7 desktop. We validate the tracking performance in challenging scenarios, including environments with dozens of obstacles.

_sass/minimal-mistakes/_archive.scss

@@ -124,10 +124,10 @@
   overflow: hidden;
   -webkit-transition: $global-transition;
   transition: $global-transition;
-  margin-top: 5px;
-  margin-bottom: 0px;
+  margin-top: 10px;
+  margin-bottom: 5px;
   margin-left: 0px;
-  margin-right: 14px;
+  margin-right: 20px;
   width: 150px;
 
   @include breakpoint($medium) {
@@ -167,7 +167,7 @@
 
 .feature__item>.archive__item:hover {
   .archive__item-teaser>img {
-    filter: brightness(50%);
+    filter: brightness(70%);
   }
 }
 

index.html

@@ -6,4 +6,5 @@
   overlay_filter: 0.5
 excerpt: "Toward Fully Autonomous Mobile Robot System"
 ---
-<p>Hi, I am a Ph.D candidate at Lab for Autonomous Robotics Research (<a href="https://larr.snu.ac.kr/" target="_blank">LARR</a>), Seoul National University, South Korea. My research interests is mobile robot trajectory planning, in particular Aerial Tracking and Multi-Robot System.</p>
+<p>Hi, I am a Ph.D candidate at Lab for Autonomous Robotics Research (<a href="https://larr.snu.ac.kr/" target="_blank">LARR</a>), Seoul National University, South Korea. My research interests is mobile robot trajectory planning, in particular <b>Aerial Tracking</b> and <b>Multi-Agent System</b>.</p>
+<p>You can see my works through these links: <a href="/_pages/research_page/index.html" target="_blank">RESEARCH</a> and <a href="/_pages/projects_page/index.html" target="_blank">PROJECTS</a>!</p>