Heshan Fernando is a Postdoctoral Fellow at Ingenuity Labs, Queen’s University, Kingston, Canada. He is interested in the research and development of intelligent systems for industrial applications–robotic machines and autonomous systems that can learn and adapt to operate reliably in dynamic and complex environments. Heshan is currently working on the development of robotic systems and AI methods for rail infrastructure monitoring.  His previous research projects have involved the study and development of control and learning strategies for robotic excavation and intelligent sensing and condition monitoring methods automated assembly machines.

Heshan received the B.Eng (Honours, 2011) degree in Mechanical Engineering with a Mechatronics and Embedded Systems option from the University of Victoria, and both M.A.Sc. (2012) and Ph.D. (2021) degrees in Mechanical Engineering from Queen’s University. From 2016 to 2017, Heshan was a visiting researcher at the Centre for Applied Autonomous Sensor Systems (AASS) at  Örebro Universitet and the Rocktec Automation Division of Epiroc AB–both located in Örebro, Sweden.


Offroad Robotics at Ingenuity Labs
Queen’s University
Mitchell Hall 69 Union Street, Room 395
Kingston, ON K7L 3N6


External Links

TA Courses

Queen’s University

DM 822 – Mechatronics Systems (summer 2019)
APSC 200 – Engineering Design and Practice II (fall 2018)
MINE 471 – Mine-Mechanical Design Project (winter 2018)
MINE 472 – Mining Systems, Automation, and Control (winter 2016 to 2018, 2020)
MECH 350 – Automatic Controls Labs (winter 2013 to 2016)
MECH 452 – Mechatronics (fall 2012 to 2015, 2017-2018)


Journal Papers

H. Fernando and J. A. Marshall. What lies beneath: Material classification for autonomous excavators using proprioceptive force sensing and machine learning.  In Automation in Construction, vol. 119, November, 2020. DOI: 10.1016/j.autcon.2020.103374

H. Fernando, J. A. Marshall, and J. Larsson.  Iterative learning-based admittance control for autonomous excavation.  In Journal of Intelligent & Robotic Systems, vol. 96, no. 3-4, December 2019. DOI: 10.1007/s10846-019-00994-3

H. A. Fernando and B. W. Surgenor. An unsupervised artificial neural network versus a rule-based approach for fault detection and identification in an automated assembly machine. In Robotics and Computer Integrated Manufacturing, vol. 43, Special issue: extended papers selected from FAIM 2014, pp. 79–88, February 2017.

K. Hughes, H. A. Fernando, G. Szkilnyk., B. W. Surgenor and M. Greenspan. Video event detection for fault monitoring in assembly automation. In International Journal of Intelligent Systems Technologies and Applications, vol. 14, nos. 1 and 2, pp. 106-113, 2013.

Conference Papers (Fully Refereed)

U. Artan, H. Fernando, and J. A. Marshall. Automatic material classification via proprioceptive sensing and wavelet analysis during excavation.  To appear in Proceedings of the 2021 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), July 14, 2021.

H. A. Fernando, J. A. Marshall, H. Almqvist and J. Larsson. Towards controlling bucket fill factor in robotic excavation by learning admittance control setpoints. In 11th Conference on Field and Service Robotics, Zurich, September 2017.

H. A. Fernando and B. W. Surgenor. An artificial neural network based on adaptive resonance theory for fault classification on an automated assembly machine. In Proceedings of the 24th International Conference on Flexible Automation and Intelligent Manufacturing (FAIM), San Antonio, Texas, May 2014.

H. A. Fernando, V. Chauhan and B. W. Surgenor. Image-based versus signal-based sensors for machine fault detection and isolation. In Proceedings of the ASME 12th Biennial Conference on Engineering Systems Design and Analysis (ESDA), Copenhagen, Denmark, June 2014.

H. A. Fernando and B. W. Surgenor. An RFID-based automated warehouse project for a course in mechatronics. In Proceedings of the 2nd International Conference on Mechanical Engineering and Mechatronics (ICMEM), Toronto, Ontario, August 2013.

H. A. Fernando, K. Hughes, G. Szkilnyk., B. W. Surgenor and M. Greenspan. Video event fault detection with STVs: application to a high speed assembly machine. In Proceedings of the 41st North American Manufacturing Research Conference (NAMRC), Madison, Wisconsin, June 2013.

H. A. Fernando, J. Siriwardana and S. Halgamuge. Can a datacenter heat-flow model be scaled down? In Proceedings of the IEEE 6th International Conference Information and Automation for Sustainability (ICIAfS), Beijing, China, September 2012.

Conference Papers (Abstract Refereed)

H. A. Fernando, C. Lounsbury and B. W. Surgenor. Integrating RFID technology into a course in mechatronics. In Proceedings of the International Conference on Engineering Education and Research (ICEER), Hamilton, Ontario, August 2014.

V. Chauhan, H. A. Fernando and B. W. Surgenor. Effects of illumination techniques for machine vision inspection for automated assembly machines. In Proceedings of the Canadian Society for Mechanical Engineering (CSME) International Congress, Toronto, Ontario, June 2014.

Conference Presentations (Non-Author)

J. Waldie, B.W. Surgenor and B. Dehghan. Fuzzy PID and contour tracking as applied to position control of a pneumatic gantry robot. ASME/BATH Symposium on Fluid Power and Motion Control (FPMC), Sarasota, Florida, October 8, 2013.

Academic Thesis

H. Fernando,  Control and Learning for Robotic Excavation.  Ph.D. Thesis, Department of Mechanical and Materials Engineering, Queen’s University, January 2021 (advisor: Joshua Marshall).

H. Fernando, Artificial Neural Networks for Fault Detection and Identification on an Automated Assembly Machine, M.ASc. Thesis, Department of Mechanical Engineering, Queen’s University, Kingston, ON, May 2014 (advisor: Brian Surgenor).

H. Fernando, Alternative Wind Turbine Technologies, B.Eng (Hons) Thesis, Department of Mechanical Engineering, University of Victoria, Victoria, BC, May 2011 (advisor: Curran Crawford).