Rajitha de Silva
Postdoctoral Research Assistant in robotic perception and navigation at the University of Lincoln. My research focuses on vision-based autonomy for robots operating in outdoor and agricultural environments, with particular interest in crop-row navigation, long-term perception, and practical deployment on real robotic platforms.
I completed my PhD in Computer Science at the University of Lincoln in February 2024. My doctoral work, Vision-Based Autonomous Navigation System Development for Agri-Robots, explored robust crop-row detection, in-field navigation, and end-of-row behaviour using cost-effective vision sensors. Before moving to the UK, I worked as an Assistant Lecturer at the Sri Lanka Institute of Information Technology, where I taught robotics, embedded systems, IoT, and electronics while supervising undergraduate research projects.
🌱 I’m currently working on developing visual perception algorithms for agri-robots.
Research Interests
- Robotic perception for outdoor autonomy
- Agricultural robotics and field navigation
- Computer vision and feature matching
- ROS-based robot software systems
- Machine learning and deep learning for embodied systems
Current Work
I currently contribute to postdoctoral research projects including Agri Open Core (AOC) and GAIA: Ground-Aerial maps Integration for increased Autonomy outdoors. My recent work spans visual perception, localization, and navigation for robots that must perform reliably in dynamic, unstructured outdoor settings.
Selected Highlights
- Best Research Project (Impact), UKRI TAS Hub AI and Robotics Research Awards, 2025
- Best Paper Award, TIG-IV: Agri-Food Robotics Workshop at ICRA 2023
- Journal of Field Robotics paper recognized among the journal’s top 10 most-cited papers for 2023
- Funded PhD studentship through Lincoln Agri-Robotics and UKRI Research England’s Expanding Excellence in England programme
Selected Publications
- Keypoint Semantic Integration for Improved Feature Matching in Outdoor Agricultural Environments
- Vision based crop row navigation under varying field conditions in arable fields
- Deep learning-based crop row detection for infield navigation of agri-robots
- Leaving the Lines Behind: Vision-Based Crop Row Exit for Agricultural Robot Navigation