Dr. Waqar Shahid Qureshi is an applied AI researcher and engineer with over 22 years of professional experience across academia, research, and industry. His interdisciplinary expertise lies in artificial intelligence, computer vision, robotics, and intelligent sensing systems, with a strong emphasis on real-world deployment in precision agriculture, consumer electronics, and civil infrastructure.

Dr. Qureshi has played a pivotal role in advancing AI-enabled sensing and automation. He was the lead inventor of the 3D scanning software embedded in the world’s first full-colour 3D printer and scanner, commercialized by XYZPrinting Inc.

He co-founded Robotiqs Private Limited, an AgriTech pioneer in Pakistan, launching commercial aerial spraying drones for smart farming. His research in crop health, mango maturity devices maps provide smart toolkits for smallhold farmers.

Dr. Qureshi is also the inventor of an AI-based direct pavement surface assessment framework, which has been adopted by Industry through a License. His contributions span from deep-learning-based rating systems to sensor fusion pipelines linking vision, IMU, and LiDAR data for cycleway condition assessment.

He has collaborated with institutions such as the TU Dublin, NUST Pakistan, Central Queensland Australia, Kansas State University, Umm-al Qura University Saudi Arabia, Asian Institute of Technology, Taiwan Tech, Chinese Agricultural University, and Nottingham Trent University U. K. He has authored over 100 publications and led funded projects from SFI, Enterprise Ireland, HEC, and PARC, Pakistan.

Dr. Qureshi’s research interests lie in addressing fundamental questions across applied domains such as agri-tech, civil infrastructure, and health & discovery:

• How can multimodal deep learning models improve real-time perception in resource-constrained sensing systems, particularly in mobile robotics and edge-deployed platforms?

• Can ordinal classification frameworks better capture human-labelled uncertainty in subjective tasks such as pavement rating, fruit ripeness scoring, or behavioural interpretation?

• How do low-cost sensors and embedded AI pipelines enable scalable 3D reconstruction for infrastructure, crops, or consumer environments?

• What models are best suited for inferring human intention from egocentric vision, gaze tracking, or wearable IMU and GPS streams in assistive or driver-monitoring scenarios?

• How can satellite or drone-based remote sensing be used to detect spatiotemporal patterns in crops, soil, and land cover with minimal supervision?

• Can spectrometry-driven chemometric models enable reliable quality estimation of perishable agri-products?

• How can we design deployable, self-improving AI systems that learn robust representations from weak, noisy, or sparsely labelled data in the wild?

Computer Vision, Digital Image Processing, Applied Artificial Intelligence, Machine Learning, Computer Organisation and Design, Digital Design, Electronics, Data Structures, Object Oriented Programming, Programming Languages, Programming for Embedded Systems, Computing System, Data Analysis for Sustainable Research, Smart Grid