This paper formalises Object–Action Complexes (OACs) as a basis for symbolic representations of sensory–motor experience and behaviours. OACs are designed to capture the interaction between objects and associated actions in artificial cognitive systems. We give a formal definition of OACs, provide examples of their use for autonomous cognitive robots, and enumerate a number of critical learning problems in terms of OACs.
COBISS.SI-ID: 25079335
The paper presents a novel method to obtain the basic frequency of an unknown periodic signal with an arbitrary waveform, which can work online with no additional signal processing or logical operations. The method originates from nonlinear dynamical systems for frequency extraction, which are based on adaptive frequency oscillators in a feedback loop. The novel method presented here uses a Fourier series representation in the feedback loop combined with a single oscillator. The proposed method can be used for the control of rhythmic robotic tasks, where only the extraction of the basic frequency is crucial. For demonstration several highly nonlinear and dynamic periodic robotic tasks are shown, including also a task where an EMG signal is used in a feedback loop.
COBISS.SI-ID: 25108775
The contribution presents the overall results of the research done within the field of robotic skill synthesis on the basis of human sensorimotor learning. The main scientific contribution is the implementation of the skill transfer from a human to a robot, where the human by his sensorimotor learning capacity, takes over the role of the cognitive apparatus of the robotic system and therefore teaches the robotic system how to autonomously execute novel tasks.
COBISS.SI-ID: 24969767