Our Lab
Welcome to the website of Fudan MagicLab (Multi-agent robotic systems lab). Our Lab is part of the College of Intelligent Robotics and Advanced Manufacturing.
Our group is primarily involved in the following areas:
- Spatial intelligence
- Decision intelligence
Specifically, including:
- Next-Gen SLAM
- Mapless Prediction and Planning
- Interaction-aware Decision-making
- Scene Understanding and Embodied AI
You can access the main page of our specific work by using the following pane.
Spatial intelligence 🌠
Decision intelligence 🌁
Spatial intelligence 🌠
Check the details of our works by clicking on the following link：
O₂V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation
VINGS-Mono: Visual-Inertial Gaussian Splatting Monocular SLAM in Large Scenes
HGS-Mapping: Online Dense Mapping Using Hybrid Gaussian Representation in Urban Scenes
Swift-Mapping: Online Neural Implicit Dense Mapping in Urban Scenes
Decision intelligence 🌁
Check the details of our works by clicking on the following link：
HGS-Planner: Hierarchical Planning Framework for Active Scene Reconstruction Using 3D Gaussian Splatting
Learning Occlusion-aware Decision-making from Agent Interaction via Active Perception
LMPOcc: 3D Semantic Occupancy Prediction Utilizing Long-Term Memory Prior from Historical Traversals
Unveiling the Surprising Efficacy of Navigation Understanding in End-to-End Autonomous Driving
