Learning juggling by gradually increasing difficulty vs. learning the complete skill results in different learning patterns.

Motor learning is central to sports, medicine, and other health professions as it entails learning through practice. To achieve proficiency in a complex motor task, many hours of practice are required. Therefore, finding ways to speed up the learning process is important. This study examines the impact of different training approaches on learning three-ball cascade juggling. Participants were assigned to one of two groups: practicing by gradually increasing difficulty and elements of the juggling movement ("learning in parts") or training on the complete skill from the start ("all-at-once"). Results revealed that although the all-at-once group in the early stages of learning showed greater improvement in performance, the "learning in parts" group managed to catch up, even over a relatively short period of time. The lack of difference in performance between the groups at the end of the training session suggests that the choice of training regime (between all-at-once and learning in parts), at least in the short term, can be selected based on other factors such as the learner's preference, practical considerations, and cognitive style.

Correction: Learning efficient haptic shape exploration with a rigid tactile sensor array.

[This corrects the article DOI: 10.1371/journal.pone.0226880.].

Learning efficient haptic shape exploration with a rigid tactile sensor array.

Haptic exploration is a key skill for both robots and humans to discriminate and handle unknown objects or to recognize familiar objects. Its active nature is evident in humans who from early on reliably acquire sophisticated sensory-motor capabilities for active exploratory touch and directed manual exploration that associates surfaces and object properties with their spatial locations. This is in stark contrast to robotics. In this field, the relative lack of good real-world interaction models-along with very restricted sensors and a scarcity of suitable training data to leverage machine learning methods-has so far rendered haptic exploration a largely underdeveloped skill. In robot vision however, deep learning approaches and an abundance of available training data have triggered huge advances. In the present work, we connect recent advances in recurrent models of visual attention with previous insights about the organisation of human haptic search behavior, exploratory procedures and haptic glances for a novel architecture that learns a generative model of haptic exploration in a simulated three-dimensional environment. This environment contains a set of rigid static objects representing a selection of one-dimensional local shape features embedded in a 3D space: an edge, a flat and a convex surface. The proposed algorithm simultaneously optimizes main perception-action loop components: feature extraction, integration of features over time, and the control strategy, while continuously acquiring data online. Inspired by the Recurrent Attention Model, we formalize the target task of haptic object identification in a reinforcement learning framework and reward the learner in the case of success only. We perform a multi-module neural network training, including a feature extractor and a recurrent neural network module aiding pose control for storing and combining sequential sensory data. The resulting haptic meta-controller for the rigid 16 × 16 tactile sensor array moving in a physics-driven simulation environment, called the Haptic Attention Model, performs a sequence of haptic glances, and outputs corresponding force measurements. The resulting method has been successfully tested with four different objects. It achieved results close to 100% while performing object contour exploration that has been optimized for its own sensor morphology.