Robot Perception & Localisation
My research in Robot Perception & Localisation focuses on probabilistic localisation, mapping, and perception algorithms that enable autonomous robots to operate reliably in complex, GPS-denied, and dynamic environments.
Research Areas
- Simultaneous Localisation and Mapping (SLAM)
- Collaborative SLAM
- Visual SLAM
- LiDAR SLAM
- Multi-Robot Localisation
- Sensor Fusion
- GPS-Denied Navigation
- Probabilistic Mapping
Research Projects
Random Finite Set Based 3D Visual SLAM
A probabilistic 3D Visual SLAM framework based on Random Finite Set theory for robust localisation and mapping in GPS-denied environments.
Collaborative LiDAR SLAM
A probabilistic collaborative LiDAR SLAM framework enabling multiple autonomous robots to jointly localise and construct a shared map using Random Finite Set theory.
Collaborative SLAM with Moving Object Tracking
Joint probabilistic estimation of robot trajectories, static maps, and moving objects using Random Finite Set theory.
Marine Robotics Dataset Collection
Design and collection of real-world datasets for validating probabilistic localisation and mapping algorithms in marine environments.
AprilTag-Based Multi-Robot Localisation
A ROS2-based localisation framework using AprilTags for cooperative localisation of autonomous aerial robots.
Distributed Perception for Autonomous Robot Teams
Developing decentralised probabilistic perception algorithms that enable teams of autonomous robots to collaboratively understand complex environments.