Welcome to the homepage of the Intelligent and Cognitive Engineering (ICE) Laboratory in the College of Engineering and Physical Sciences at the University of Guelph. The Principal Investigator (PI) of the ICE Lab is Dr. S. Andrew Gadsden, who is currently an Associate Professor in Mechanical Engineering.

Dr. Gadsden’s research background and expertise includes a broad consideration of control and estimation theory, artificial intelligence and machine learning, and smart or cognitive systems. Smart systems are found everywhere in our increasingly automated and interconnected world—from smart homes to self-driving vehicles. The next-generation smart system, known as a cognitive system, is a type of system that operates in an environment with a perceived amount of cognition. These are smart systems with a higher-level of intelligence that behave autonomously. A system is deemed cognitive when capable of five fundamental processes essential to human cognition: the perception-action cycle (PAC), memory, attention, intelligence, and language. A cognitive system is equipped to perceive and interact with the environment while it stores and learns from past experiences to adapt its operation which improves its efficiency, effectiveness, and robustness in unknown environments.

Fundamentally, the safe and reliable operation of a cognitive system is heavily dependent on its sensors, its understanding of the collected data, and its interaction with the environment. For example, estimation strategies that extract useful information from sensors must be robust to sensor failure or system uncertainties such as unmodeled dynamics. The inability to provide reliable information to the controller can lead to poor system performance, unsafe operating conditions, or failure. Based on the sensor data, a cognitive system may build its knowledge base and models using machine learning techniques. However, this generally creates models that are input-output driven with minimal information or user understanding on the dynamics of the system. Physics-based or mathematical modelling of the system are significantly more complex, but are not considered ‘black box’ models like those generated from advanced machine learning methods. This offers some advantages as the engineer or user may better understand how the system behaves. However, this raises an important question on the future of cognitive systems. Can we rely solely on a cognitive system for critical or unsafe tasks, or should they be regulated to passive actions and menial duties?

Dr. Gadsden and his research team are working towards answering this fundamental question. His team is focusing on novel and efficient ways of advancing the theory of cognitive systems while improving public confidence, acceptance, and trust in their application. In particular, he is working on developing robust estimation and control strategies to improve cognitive system performance within the perception-action cycle. Further, Dr. Gadsden and his team are fusing machine learning and physics-based modelling for improved system intelligence. Finally, he is working towards a cognitive system that is able to explain and reason its actions to improve user trust.

The ICE Lab has a number of different research application areas, which can be viewed here. Furthermore, members of the laboratory gain industry-relevant skills and training, and have found successful careers in academia, government laboratories, and industry.

Please browse our laboratory website and contact us if you have any questions or comments.