Faculty Spotlight: Daniel Asmar
MSFEA conducted a short interview with Dr. Daniel Asmar, associate professor at MSFEA's Department of Mechanical Engineering
- Do you have an analogy to help readers understand your work?
- When we walk into an unfamiliar area, intuitively we visually scan it, create an internal representation of the area around us, and localize ourselves within that area while moving between waypoints. When you go to the bathroom at night and don't turn on the lights, you partly rely such a representation to get you there. The internal maps we create are topological in nature, and include objects, signs, and any visual landmarks that we try to familiarize. We move by localizing ourselves within these virtual maps that are conceived in our brains. Simultaneous Localization and Mapping (SLAM) is the equivalent of this procedure in a machine. The SLAM problem is frequently posed as a chicken and egg problem: if one had a map of an environment, robot localization could be achieved by triangulating to known landmarks within the map; alternatively, if one knew the location of the robot at all time, a map could be built by situating landmarks with respect to the robot. It is when both the map and the location of the robot are unknown that the problem becomes convoluted; in such situations, all unknowns must be solved concurrently under the framework of SLAM.
- Many people think that doing research in a country like Lebanon is irrelevant. What do you think about that?
- I think it is a matter of perspective. When some people look at Lebanon, they see the scarcity of technologies such as robotics and artificial intelligence. I see this scarcity as an opportunity for research and development. Let me give you an example. The autonomous driving systems being researched and developed around the world rely for their successful solution on the presence of a structured infrastructure, with marked lanes, and people obeying the law. The problem becomes much more difficult in the absence of such structure, and the violation of vehicle laws. The driving conditions in Lebanon pose challenges which if solved could lead to more robust systems.
- What excites you about your work?
- Although our work includes research, teaching, and services, I would say it is the research aspect that is most exciting. I believe, the liberty of it all is what makes our work so exciting. We pose our own research questions, we investigate and hypothesize the possible solutions, we experiment to validate our hypotheses, and then discover the outcomes. For me, it is this entire process that is exciting. I am thrilled to be doing what I am doing and would not choose anything else to do for a living.
Dr. Daniel Asmar received his Bachelors degree in Mechanical Engineering from the University of Waterloo in 1993. He later earned his Master's degree in Mechanical Engineering from the American University of Beirut in 2002, and his Ph.D. in Systems Design Engineering from the University of Waterloo in 2006. Daniel's research interests are in visual perception, autonomous robot navigation and mapping, environment representation and recognition, augmentation techniques in archeology, and segmentation methods in Computer Vision. Daniel is an ASME member, a senior member in IEEE, and was the founder of the joint IEEE Lebanese chapter in Robotics and Automation, Instrumentations and Measurements, and Control Systems. Daniel is a member of the World Economic Forum (WEF) council on Artificial Intelligence, Robotics, and Virtual and Augmented Reality. Learn more about Dr. Asmar's research on the Vision and Robotics lab website.