This work proposes an algorithm for scalpel region detection using color segmentation and edge detection. The input images are obtained with a fixed camera that has a line of view perpendicular to the scalpel plane. Three squares of red, green and blue colors were added to the scalpel in order to serve as fiducials. For the detection of those marks, the use of two methods was evaluated: One based on the application of thresholds to the color components, and the other based on the use of a fuzzy rule machine. The experimentation shows that both approaches provide similar results. Some morphological operations are then applied in order to detect the scalpel region. The algorithm was successfully tested in several cases, and some examples of the results are presented and analyzed. © 2020 IEEE.

Robot manipulators are designed to interact with their surroundings. Even if a task does not specifically involve interaction, the robot may collide with unknown obstacles during its motion. To overcome these problems, it is necessary to consider possible interactions inside the control system. This paper aims to design a controller that allows the manipulator to reach a final pose, even if it interacts with an unforeseen object during its trajectory. This design is composed of two stages: A feedback linearization system that allows to eliminate intrinsic nonlinearities of the robot, and the imposition of a dynamic behavior to keep delicate interactions without using external 6D force/torque sensors. The proposed controller was tested on an UR5 robot, but can be extended to any robotic manipulator. The results show the comparison between the behavior achieved by a standard feedback-linea...