Update research

_data/research.yaml

@@ -59,7 +59,7 @@
     While larger language models (LLMs) and vision-language models (VLMs) have demonstrated remarkable proficiency in comprehending natural language and translating human instructions into detailed plans for straightforward robotic tasks, they encounter significant difficulties when tackling long-horizon complex tasks. 
     In particular, the challenges of sub-task identification and allocation become especially complicated in scenarios involving cooperative teams of heterogeneous robots. 
     To address these challenges, we have <strong>proposed a novel multi-agent task planning framework designed to excel in long-horizon tasks, which integrates the reasoning capabilities of LLMs with traditional heuristic search planning, which achieves high success rates and efficiency while demonstrating robust generalization across various tasks.</strong> 
-    This research not only contributes to the advancement of task planning for heterogeneous robot teams but also lays the groundwork for future explorations in multi-agent collaboration.
+    This research not only contributes to the advancement of task planning for heterogeneous robotic teams but also lays the groundwork for future explorations in multi-agent collaboration.
     <br><br>
 
     **Related Publications:** <br>
@@ -76,6 +76,35 @@
     - Cooperative Planning
 
 
+- title: Cooperative Perception, Prediction, and Planning for Multi-Agent Systems
+  # subtitle: a subtitle
+  # group: featured
+  image: research_images/cooperative_pred_plan.png
+  # link: https://github.com/
+  description: |
+    Mobile robots and autonomous vehicles rely heavily on onboard sensors for perceiving and understanding the surroundings, 
+    and thereby learning safe and efficient planning strategies. While deep learning-based perception methods demonstrate impressive abilities in various tasks, 
+    including 2D/3D object detection, occupancy prediction, segmentation, tracking, such dependency is vulnerable to situations with occlusions, impaired visibility, and long-range perception. 
+    With the advancement of multi-agent communication, connected and automated vehicles (CAVs) can overcome the inherent limitations of single autonomous vehicle and mobile robots can collaboratively navigate complex environments. 
+    Our research <strong>firstly demonstrates enhanced situational awareness by sharing information between CAVs on both perception and motion prediction modules. 
+    Our framework design is robust to tolerate realistic V2X bandwidth limitations and transmission delays. Through extensive experiments and ablation studies on both simulated 
+    and real-world V2V datasets, we demonstrate the effectiveness of our method in cooperative perception, tracking, and motion prediction.</strong> 
+    This work advances multi-agent cooperation in robotics and autonomous driving systems.
+    <br><br>
+
+    **Related Publications:** <br>
+    1. [CMP: Cooperative Motion Prediction with Multi-Agent Communication](https://arxiv.org/abs/2403.17916), submitted to IEEE Robotics and Automation Letters, under review. <br>
+  # repo: greenelab/lab-website-template
+
+  tags:
+    - Cooperative Perception
+    - Cooperative Prediction
+    - Cooperative Planning
+    - Multi-Agent/Robot Systems
+    - Trajectory Prediction
+    - Connected and Automated Vehicles
+
+
 - title: Vision Language Reasoning for Scene Understanding in Autonomous Driving
   # subtitle: a subtitle
   # group: featured