Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Luiza Mici

An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction

Mar 09, 2018
Luiza Mici, German I. Parisi, Stefan Wermter

Figure 1 for An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction

Figure 2 for An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction

Figure 3 for An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction

Figure 4 for An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction

During visuomotor tasks, robots must compensate for temporal delays inherent in their sensorimotor processing systems. Delay compensation becomes crucial in a dynamic environment where the visual input is constantly changing, e.g., during the interacting with a human demonstrator. For this purpose, the robot must be equipped with a prediction mechanism for using the acquired perceptual experience to estimate possible future motor commands. In this paper, we present a novel neural network architecture that learns prototypical visuomotor representations and provides reliable predictions on the basis of the visual input. These predictions are used to compensate for the delayed motor behavior in an online manner. We investigate the performance of our method with a set of experiments comprising a humanoid robot that has to learn and generate visually perceived arm motion trajectories. We evaluate the accuracy in terms of mean prediction error and analyze the response of the network to novel movement demonstrations. Additionally, we report experiments with incomplete data sequences, showing the robustness of the proposed architecture in the case of a noisy and faulty visual sensor.

Via

Access Paper or Ask Questions

A self-organizing neural network architecture for learning human-object interactions

Mar 02, 2018
Luiza Mici, German I. Parisi, Stefan Wermter

Figure 1 for A self-organizing neural network architecture for learning human-object interactions

Figure 2 for A self-organizing neural network architecture for learning human-object interactions

Figure 3 for A self-organizing neural network architecture for learning human-object interactions

Figure 4 for A self-organizing neural network architecture for learning human-object interactions

The visual recognition of transitive actions comprising human-object interactions is a key component for artificial systems operating in natural environments. This challenging task requires jointly the recognition of articulated body actions as well as the extraction of semantic elements from the scene such as the identity of the manipulated objects. In this paper, we present a self-organizing neural network for the recognition of human-object interactions from RGB-D videos. Our model consists of a hierarchy of Grow-When-Required (GWR) networks that learn prototypical representations of body motion patterns and objects, accounting for the development of action-object mappings in an unsupervised fashion. We report experimental results on a dataset of daily activities collected for the purpose of this study as well as on a publicly available benchmark dataset. In line with neurophysiological studies, our self-organizing architecture exhibits higher neural activation for congruent action-object pairs learned during training sessions with respect to synthetically created incongruent ones. We show that our unsupervised model shows competitive classification results on the benchmark dataset with respect to strictly supervised approaches.

Via

Access Paper or Ask Questions