Abstract: A method of training a neural network configured to obfuscate a facial image and an electronic device for performing the method are provided. The method includes obtaining, based on an input facial image, an output facial image in which the input facial image is obfuscated, extracting, based on the input facial image, a feature of the input facial image for reconstructing identification information included in the input facial image from the output facial image, extracting, based on the output facial image, a feature of the output facial image corresponding to the feature of the input facial image, and training the neural network based on a difference between the feature of the input facial image and the feature of the output facial image.

Abstract: A robot control apparatus to control an operation path of a robot includes an interpolator including a rough interpolation processor to output a rough velocity signal of no-acceleration and no-deceleration according to input commands, a plurality of acceleration/deceleration processors to receive the rough velocity signal from the rough interpolation processor and to perform acceleration and deceleration in sequence, and an inverse kinematics processor to transform the velocity signal received from the acceleration/deceleration processor into a joint velocity signal for the robot, and a controller to control the robot according to the accelerated/decelerated velocity signal received from the interpolator. In a robot control apparatus and a control method thereof, precision about an operation path of a robot is improved.

Abstract: A robot control apparatus to control an operation path of a robot includes an interpolator including a rough interpolation processor to output a rough velocity signal of no-acceleration and no-deceleration according to input commands, a plurality of acceleration/deceleration processors to receive the rough velocity signal from the rough interpolation processor and to perform acceleration and deceleration in sequence, and an inverse kinematics processor to transform the velocity signal received from the acceleration/deceleration processor into a joint velocity signal for the robot, and a controller to control the robot according to the accelerated/decelerated velocity signal received from the interpolator. In a robot control apparatus and a control method thereof, precision about an operation path of a robot is improved.