Advances in Cognitive Robotics: Image Processing, Tactile Sensing, and Hyperspectral Systems

Applicants may choose to focus on one of three embedded projects:

Project 1: Advanced Image Processing for Resilient Automation

This project develops robust computer vision architectures to process high-resolution visual data in real-time. It focuses on overcoming challenges in visually complex, dynamic environments (e.g., variable lighting, occlusion) to enable spatial mapping, and autonomous navigation in unstructured industrial settings.

Project 2: Novel Multi-Modal Sensing (Tactile and RGB-D)

Focused on human-robot parity in manipulation, this work fuses visual data (RGB-D) with advanced tactile sensor arrays. By creating a unified perception framework, it equips robotic end-effectors with a human-like sense of touch, allowing for the delicate, adaptive handling of fragile or irregularly shaped objects in dynamic environments.

Project 3: Hyperspectral Imaging for Enhanced Material Analysis

This project leverages hyperspectral sensors and deep learning to analyse material compositions far beyond the visible light spectrum. The research aims to deploy these systems for rapid, non-destructive quality control and classification, directly targeting applications in advanced manufacturing and precision agri-food sorting.

Funding Notes

OPEN TO HOME AND REPUBLIC OF IRELAND STUDENTS ONLY

References

Czimmermann, Tamás, et al. "Visual-based defect detection and classification approaches for industrial applications - a survey." Sensors 20.5 (2020): 1459.
Calandra, Roberto, et al. "More than a feeling: Learning to grasp and regrasp using vision and touch." IEEE Robotics and Automation Letters 3.4 (2018): 3300-3307.
Lu, B., Dao, P. D., Liu, J., He, Y., & Shang, J. (2020). Recent advances of hyperspectral imaging technology and applications in agriculture. Remote sensing, 12(16), 2659.