docs: udpate soar & apexnav

Author: Gy920

assets/imgs/projects/soar.gif

@@ -1649,7 +1649,7 @@ <h1 class="page-title" title="Projects" itemprop="headline">
               incremental topological graph built directly on point clouds for efficient, real-time path planning.
               Combined in a hierarchical structure, these components enable agile, energy-efficient trajectories,
               achieving faster exploration with significantly reduced memory and computation compared to
-              state-of-the-art methods in diverse environments. (Estimate: ~120 words, likely around 200 characters).
+              state-of-the-art methods in diverse environments.
               [<a
                 href="https://www.bilibili.com/video/BV1nrx5eaESY/?spm_id_from=333.999.0.0&vd_source=07945b0b56417e213633c9332f4f4716">Video:Bilibili</a>]
             </p>
@@ -1662,6 +1662,29 @@ <h1 class="page-title" title="Projects" itemprop="headline">
 
             <hr class="wp-block-separator has-alpha-channel-opacity is-style-wide" />
 
+            <p>
+              Unmanned Aerial Vehicles (UAVs) have gained significant popularity in scene reconstruction. This paper
+              presents SOAR, a LiDAR-Visual heterogeneous multi-UAV system specifically designed for fast autonomous
+              reconstruction of complex environments. Our system comprises a LiDAR-equipped explorer with a large
+              field-of-view (FoV), alongside photographers equipped with cameras. To ensure rapid acquisition of the
+              scene’s surface geometry, we employ a surface frontier-based exploration strategy for the explorer. As the
+              surface is progressively explored, we identify the uncovered areas and generate viewpoints incrementally.
+              These viewpoints are then assigned to photographers through solving a Consistent Multiple Depot Multiple
+              Traveling Salesman Problem (Consistent-MDMTSP), which optimizes scanning efficiency while ensuring task
+              consistency. Finally, photographers utilize the assigned viewpoints to determine optimal coverage paths
+              for acquiring images. We present extensive benchmarks in the realistic simulator, which validates the
+              performance of SOAR compared with classical and state-of-the-art methods.
+              [<a
+                href="https://www.bilibili.com/video/BV1G1421Q79m/?spm_id_from=333.1387.homepage.video_card.click">Video:Bilibili</a>]
+            </p>
+
+            <figure class="wp-block-image aligncenter size-large is-resized">
+              <img decoding="async" width="898" height="1024" src="./assets/imgs/projects/soar.gif" alt=""
+                class="wp-image-548" style="aspect-ratio: 0.876953125; width: 665px; height: 356px"
+                sizes="(max-width: 898px) 100vw, 898px" />
+            </figure>
+
+
             <p>
               This paper tackles the challenge of autonomous target search
               using unmanned aerial vehicles (UAVs) in complex unknown

projects.html

@@ -1571,7 +1571,7 @@ <h5 class="wp-block-heading">
             </p>
 
             <p>
-              <strong>ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion</strong><br />Mingjie Zhang, Yuheng Du, Jinni Zhou, Zhenchao Qi, Jun Ma, Boyu Zhou<sup>#</sup><br />Submitted to <em>IEEE Robotics and Automation Letters</em>
+              <strong>ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion</strong><br />Mingjie Zhang, Yuheng Du, Chengkai Wu, Jinni Zhou, Zhenchao Qi, Jun Ma, Boyu Zhou<sup>#</sup><br />Submitted to <em>IEEE Robotics and Automation Letters</em>
               (<strong>RAL</strong> 2025)
             </p>