Think like an Amateur, Do as an Expert: Fun Research in Computer Vision and Robotics
Abstract of the lecture
Most researchers, when asked their fondest desire, respond that they want to do good research. If further queried as to what constitutes “good research,” they often find it difficult to give a clear answer. For myself, I believe that good research derives from solving real-world problems, thus delivering useful results to society, whereby researchers themselves enjoy doing so. Such research has its own story to tell, as well as power to persuade other people. “Think like an amateur, do as an expert” is my research motto: When conceptualizing a problem and its possible solution, think simply and openly, as a novice in that field, without preconceived notions. When implementing a solution, on the other hand, do so thoroughly, meticulously, and with expert skill.
As a roboticist, I have been extremely fortunate to participate in developing a wide range of computer-vision systems and autonomous robots, including human-face recognition, autonomously-driven cars, computer-assisted surgical robots, robot helicopters, biological live cell tracking through a microscope, and EyeVision for Super Bowl broadcast. In these projects, I met and worked with many people from diverse backgrounds, and also encountered many challenges. While reviewing the technical content of these projects, I will also try to sprinkle anecdotal experiences that highlight the appealing and enjoyable aspects of a researcher’s life—those that occur accidentally or inevitably as my “Think like an amateur, do as an expert” maxim interacts with problems and people.