Motivation
Reliable and precise robot localisation in agricultural environments remains a critical challenge for autonomous systems in horticulture. At the Lincoln Centre for Autonomous Systems (L-CAS), we are pioneering innovative approaches to hybrid localisation that combine multiple sensor modalities for robust operation in GPS-denied or GPS-degraded scenarios. This project focuses on developing advanced sensor fusion algorithms that integrate LiDAR, camera imagery, and inertial measurement unit (IMU) data to enable consistent and dependable robot localisation across diverse horticultural settings. By creating robust hybrid localisation solutions for wheeled agricultural platforms, we aim to enhance the reliability and operational efficiency of robotic systems even when RTK-GPS signals deteriorate or are unavailable. Your contribution will help shape the future of autonomous navigation in agricultural robotics, addressing a fundamental challenge that currently limits widespread adoption of autonomous systems in real-world farming operations.
Required Skills
- Strong programming skills in Python and/or C++
- Experience with ROS2 or willingness to learn quickly
- Knowledge of sensor fusion techniques and algorithms
- Understanding of computer vision and/or LiDAR processing methods
- Familiarity with IMU data integration and filtering
- Interest in agricultural robotics and its real-world challenges
- Problem-solving mindset and attention to detail
- Ability to work effectively within multidisciplinary research teams
Skills to Be Gained
This project offers an exceptional opportunity to develop expertise at the intersection of robotics, computer vision, and precision agriculture. You’ll gain hands-on experience implementing sophisticated sensor fusion algorithms that integrate multiple data streams (LiDAR, camera, IMU) to create robust localisation systems for agricultural robots. Working directly with real-world wheeled agricultural platforms, you’ll develop advanced skills in ROS2 navigation stack integration and performance optimisation for embedded systems. The project provides practical experience in deploying and testing algorithms in challenging field conditions, where you’ll learn to address issues like variable lighting, uneven terrain, and dynamic obstacles. You’ll collaborate closely with industry partners through our involvement in cutting-edge research projects JABAS and Agri-OpenCore, gaining valuable insights into the commercial aspects of agricultural robotics development. The expertise gained in sensor fusion, algorithm development, and real-world system integration will be highly valuable for careers in robotics research, autonomous system development, and agricultural technology innovation.
If you are interested to work on this as an intern fill out our Expression of Interest Form, choosing Professor Marc Hanheide as the researcher to supervise the project.