Research
We are building state-of-the-art intelligent robot systems
Indoor relocalization is vital for both robotic tasks like autonomous exploration and civil appli...
Line detection is widely used in many robotic tasks such as scene recognition, 3D reconstruction,...
Autonomous exploration has many important applications. However, classic information gain-based o...
AirVO is an illumination-robust and accurate stereo visual odometry system based on point and lin...
Video Object Identification
Graph neural networks (GNNs) are powerful models for many graph-structured tasks. Existing models...
Dynamic Object-aware SLAM (DOS) exploits object-level information to enable robust motion estimat...
I publish papers in both robotics and computer vision.
Object encoding and identification is crucial for many robotic tasks such as autonomous explorati...
After deployment to the wild, the robot may benefit if it can incrementally learn from the workin...
We propose a real-time semantic RGB-D SLAM system for dynamic environments that is capable of det...
FLOAM was included in the ROS Noetic update, which is now available!
The problem of visual interestingness detection, which is crucial for many practical applications...