Computer Engineering Commons^™

Learning With Limited Labeled Data For Image And Video Understanding, Razieh Kaviani Baghbaderani

Doctoral Dissertations

Deep learning-based algorithms have remarkably improved the performance in many computer vision tasks. However, deep networks often demand a large-scale and carefully annotated dataset and sufficient sample coverage of every training category. However, it is not practical in many real-world applications where only a few examples may be available, or the data annotation is costly and require expert knowledge. To mitigate this issue, learning with limited data has gained considerable attention and is investigated thorough different learning methods, including few-shot learning, weakly/semi supervised learning, open-set learning, etc.

In this work, the classification problem is investigated under an open-world assumption to …

Task-Oriented Manipulation Planning: Teaching Robot Manipulators To Learn Trajectory Tasks, Yan Li

Doctoral Dissertations

As robot manipulator applications are conducted in more complex tasks and unstructured environments, traditional manual programming cannot match the growing requirements. However, human experts usually know how to operate robot manipulators to complete tasks, but they do not know how to manually program the robot for automatically executing tasks. From a general point of view, a robot manipulation task is composed of a series of consecutive robot actions and environment states which we call it trajectory task. Imitation learning, an emerging and popular technique of robot behavior programming, is a good way to tackle this line of work but still …

Model Based Force Estimation And Stiffness Control For Continuum Robots, Vincent A. Aloi

Doctoral Dissertations

Continuum Robots are bio-inspired structures that mimic the motion of snakes, elephant trunks, octopus tentacles, etc. With good design, these robots can be naturally compliant and miniaturizable, which makes Continuum Robots ideal for traversing narrow complex environments. Their flexible design, however, prevents us from using traditional methods for controlling and estimating loading on rigid link robots.

In the first thrust of this research, we provided a novel stiffness control law that alters the behavior of an end effector during contact. This controller is applicable to any continuum robot where a method for sensing or estimating tip forces and pose exists. …