News
Research updates, publications and project milestones.
ISC-Perception was selected as the cover article for Buildings, Volume 16, Issue 17. The paper presents a hybrid dataset of real, photorealistic and synthetic imagery for robotic assembly of Intermeshed Steel Connections.
Publications, project milestones and selected technical work.
The paper introduces a hybrid vision dataset for robotic assembly of Intermeshed Steel Connections.
ConPose presents a jointly trained RGB framework for component detection and pose estimation in robotic structural assembly.
Through ISx4 AI Research, I co-authored work on trace-level observability for production LLM applications and operating practices for lean AI product teams.
The paper sets out a collaborative human-robot strategy and experimental platform for automated assembly of Intermeshed Steel Connections.
The paper develops self-supervised facial representation learning and patch-aware gaze estimation.
QUB-PHEO provides multi-view visual data for intention inference in collaborative assembly, covering 70 participants and 36 subtasks.