Abstract: A method for generating a synthetic skin model includes: accessing an image of a user; generating a facial landmark container including facial landmarks extracted from the region of the image depicting a face of a user; initializing a set of test skin models, each populated with a set of model coefficients selected from a first set of possible model coefficient values and defining parameters for constructing a synthetic face unique within the first set of test skin models; injecting the set of test skin models and the facial landmark container into a synthetic face generator to generate a set of synthetic skin images, each representing a synthetic face, unique within the set of synthetic skin images, according to facial landmarks extracted from the region of the image; and rendering the set of synthetic skin images within a user interface.

Abstract: A method for generating a synthetic skin model includes: accessing an image of a user; generating a facial landmark container including facial landmarks extracted from the region of the image depicting a face of a user; initializing a set of test skin models, each populated with a set of model coefficients selected from a first set of possible model coefficient values and defining parameters for constructing a synthetic face unique within the first set of test skin models; injecting the set of test skin models and the facial landmark container into a synthetic face generator to generate a set of synthetic skin images, each representing a synthetic face, unique within the set of synthetic skin images, according to facial landmarks extracted from the region of the image; and rendering the set of synthetic skin images within a user interface.

Abstract: A method for generating a synthetic skin model includes: accessing an image of a user; generating a facial landmark container including facial landmarks extracted from the region of the image depicting a face of a user; initializing a set of test skin models, each populated with a set of model coefficients selected from a first set of possible model coefficient values and defining parameters for constructing a synthetic face unique within the first set of test skin models; injecting the set of test skin models and the facial landmark container into a synthetic face generator to generate a set of synthetic skin images, each representing a synthetic face, unique within the set of synthetic skin images, according to facial landmarks extracted from the region of the image; and rendering the set of synthetic skin images within a user interface.

Abstract: An artificial multiped is constructed (either in simulation or embodied) in such a way that its natural body dynamics allow the lower part of each leg to swing naturally under the influence of gravity. The upper part of each leg is actively actuated in the sagittal plane. The necessary input to drive the above-mentioned actuators is derived from a neural network controller. The latter is arranged as two bi-directionally coupled chains of neural oscillators, the number of which equals twice that of the legs to be actuated. Parameter optimisation of the controllers is achieved by evolutionary computation in the form of a genetic algorithm.

Abstract: An artificial multiped is constructed (either in simulation or embodied) in such a way that its natural body dynamics allow the lower part of each leg to swing naturally under the influence of gravity. The upper part of each leg is actively actuated in the sagittal plane. The necessary input to drive the above-mentioned actuators is derived from a neural network controller. The latter is arranged as two bi-directionally coupled chains of neural oscillators, the number of which equals twice that of the legs to be actuated. Parameter optimisation of the controllers is achieved by evolutionary computation in the form of a genetic algorithm.

Abstract: An artificial multiped is constructed (either in simulation or embodied) in such a way that its natural body dynamics allow the lower part of each leg to swing naturally under the influence of gravity. The upper part of each leg is actively actuated in the sagittal plane. The necessary input to drive the above-mentioned actuators is derived from a neural network controller. The latter is arranged as two bi-directionally coupled chains of neural oscillators, the number of which equals twice that of the legs to be actuated. Parameter optimisation of the controllers is achieved by evolutionary computation in the form of a genetic algorithm.