Clinical Evaluation of Next-generation, Multi-weight Hyaluronic Acid Plus Antioxidant Complex-based Topical Formulations with Targeted Delivery to Enhance Skin Rejuvenation

Introduction

Hyaluronic acid (HA) has become a commonly used ingredient in many topical products due to its strong humectant properties and essential role in skin hydration; however, limitations of delivery of HA to only the surface of skin has hindered leveraging the full capacity of HA biology necessary for skin rejuvenation. Here, we describe the clinical efficacy data of a set of novel next-generation, multi-weight HA plus antioxidant complex-based topical formulations with targeted skin delivery to enhance skin rejuvenation.

Methods

Four multi-weight HA plus antioxidant complex-based formulations: 1) Multi-Weight HA plus Antioxidant Complex Lotion with SPF 30 (Day Lotion); 2) Multi-Weight HA plus Antioxidant Complex Cream (Night Cream); 3) Multi-Weight HA plus Antioxidant Complex Gel Cream; and 4) Multi-Weight HA plus Antioxidant Complex Boost Serum were clinically evaluated for key attributes including moisturization via corneometer, with clinical grading of: dryness, roughness, fine lines and wrinkles, and following daily use of the individual products for up to eight weeks.

Results

Daily use of the multi-weight HA plus antioxidant complex-based formulations demonstrated significant improvements in all parameters evaluated compared to baselines, with changes in moisturization observed within 30 minutes of application, and changes in clinical grading parameters of dryness, roughness, fine lines and wrinkles observed as early as two weeks.

Conclusion

These data demonstrate the clinical benefits of daily use of multi-weight HA plus antioxidant complex-based moisturizers for overall improvement in skin health and appearance.

Evaluation of Antioxidants' Ability to Enhance Hyaluronic-acid Based Topical Moisturizers

Background

Hyaluronic acid (HA) is a unique molecule of the extracellular matrix with multiple biological activities. In skin, HA plays an essential role as a humectant, capable of binding up to 1,000 times its mass with water, providing skin with moisture and viscoelastic properties. HA concentration and synthesis decrease significantly in aging skin, due to exogenous and endogenous factors, including photoaging and HA metabolism. A key driver for HA degradation and reduced concentration is mediated via induction of reactive oxygen species (ROS) and other free radicals.

Objective

In this study, we evaluate antioxidant ingredients essential in the development of next-generation HA-based topical formulations aimed at leveraging HA's ability to maximize anti-aging properties.

Methods

Two antioxidants, glycine saponin (Glycine soja germ extract) and glycyrrhetinic acid (enoxolone), were evaluated for stimulation of endogenous HA production and inhibition of endogenous hyaluronidase activity, respectively.

Results

The antioxidant glycine saponin induced endogenous HA synthesis in fibroblasts, while the antioxidant glycyrrhetinic acid decreased the degradation rate of HA by 54 percent.

Conclusion

While HA has been included in numerous topical skin products, critical aspects of HA metabolism, especially in aging skin, have often been overlooked, including decreases in HA synthesis with increasing age, and increases in HA degradation mediated by exogenously induced reactive oxygen species and free radicals and increased enzymatic degradation by endogenous hyaluronidases. Here, we describe a unique approach to inclusion of two antioxidants essential for the development of the next generation of antioxidant complex-based topical skin formulations to limit the signs of aging skin.

Human-AI teams-Challenges for a team-centered AI at work

As part of the Special Issue topic "Human-Centered AI at Work: Common Ground in Theories and Methods," we present a perspective article that looks at human-AI teamwork from a team-centered AI perspective, i. e., we highlight important design aspects that the technology needs to fulfill in order to be accepted by humans and to be fully utilized in the role of a team member in teamwork. Drawing from the model of an idealized teamwork process, we discuss the teamwork requirements for successful human-AI teaming in interdependent and complex work domains, including e.g., responsiveness, situation awareness, and flexible decision-making. We emphasize the need for team-centered AI that aligns goals, communication, and decision making with humans, and outline the requirements for such team-centered AI from a technical perspective, such as cognitive competence, reinforcement learning, and semantic communication. In doing so, we highlight the challenges and open questions associated with its implementation that need to be solved in order to enable effective human-AI teaming.

Experimental Investigations into Using Motion Capture State Feedback for Real-Time Control of a Humanoid Robot

Regardless of recent advances, humanoid robots still face significant difficulties in performing locomotion tasks. Among the key challenges that must be addressed to achieve robust bipedal locomotion are dynamically consistent motion planning, feedback control, and state estimation of such complex systems. In this paper, we investigate the use of an external motion capture system to provide state feedback to an online whole-body controller. We present experimental results with the humanoid robot RH5 performing two different whole-body motions: squatting with both feet in contact with the ground and balancing on one leg. We compare the execution of these motions using state feedback from (i) an external motion tracking system and (ii) an internal state estimator based on inertial measurement unit (IMU), forward kinematics, and contact sensing. It is shown that state-of-the-art motion capture systems can be successfully used in the high-frequency feedback control loop of humanoid robots, providing an alternative in cases where state estimation is not reliable.

Errors in Human-Robot Interactions and Their Effects on Robot Learning

During human-robot interaction, errors will occur. Hence, understanding the effects of interaction errors and especially the effect of prior knowledge on robot learning performance is relevant to develop appropriate approaches for learning under natural interaction conditions, since future robots will continue to learn based on what they have already learned. In this study, we investigated interaction errors that occurred under two learning conditions, i.e., in the case that the robot learned without prior knowledge (cold-start learning) and in the case that the robot had prior knowledge (warm-start learning). In our human-robot interaction scenario, the robot learns to assign the correct action to a current human intention (gesture). Gestures were not predefined but the robot had to learn their meaning. We used a contextual-bandit approach to maximize the expected payoff by updating (a) the current human intention (gesture) and (b) the current human intrinsic feedback after each action selection of the robot. As an intrinsic evaluation of the robot behavior we used the error-related potential (ErrP) in the human electroencephalogram as reinforcement signal. Either gesture errors (human intentions) can be misinterpreted by incorrectly captured gestures or errors in the ErrP classification (human feedback) can occur. We investigated these two types of interaction errors and their effects on the learning process. Our results show that learning and its online adaptation was successful under both learning conditions (except for one subject in cold-start learning). Furthermore, warm-start learning achieved faster convergence, while cold-start learning was less affected by online changes in the current context.

Optimization of convolutional neural network hyperparameters for automatic classification of adult mosquitoes

The economic and social impacts due to diseases transmitted by mosquitoes in the latest years have been significant. Currently, no specific treatment or commercial vaccine exists for the control and prevention of arboviruses, thereby making entomological characterization fundamental in combating diseases such as dengue, chikungunya, and Zika. The morphological identification of mosquitos includes a visual exam of the samples. It is time consuming and requires adequately trained professionals. Accordingly, the development of a new automated method for realizing mosquito-perception and -classification is becoming increasingly essential. Therefore, in this study, a computational model based on a convolutional neural network (CNN) was developed to extract features from the images of mosquitoes and then classify the species Aedes aegypti, Aedes albopictus, and Culex quinquefasciatus. In addition, the model was trained to detect the mosquitoes of the genus Aedes. To train CNNs to perform the automatic morphological classification of mosquitoes, a dataset, which included 7,561 images of the target mosquitoes and 1,187 images of other insects, was acquired. Various neural networks, such as Xception and DenseNet, were used for developing the automatic-classification model based on images. A structured optimization process of random search and grid search was developed to select the hyperparameters set and increase the accuracy of the model. In addition, strategies to eliminate overfitting were implemented to increase the generalization of the model. The optimized model, during the test phase, obtained the balanced accuracy (BA) of 93.5% in classifying the target mosquitoes and other insects and the BA of 97.3% in detecting the mosquitoes of the genus Aedes in comparison to Culex. The results provide fundamental information for performing the automatic morphological classification of mosquito species. Using a CNN-embedded entomological tool is a valuable and accessible resource for health workers and non-taxonomists for identifying insects that can transmit infectious diseases.

BOLeRo: Behavior optimization and learning for robots

Reinforcement learning and behavior optimization are becoming more and more popular in the field of robotics because algorithms are mature enough to tackle real problems in this domain. Robust implementations of state-of-the-art algorithms are often not publicly available though, and experiments are hardly reproducible because open-source implementations are often not available or are still in a stage of research code. Consequently, often it is infeasible to deploy these algorithms on robotic systems. BOLeRo closes this gap for policy search and evolutionary algorithms by delivering open-source implementations of behavior learning algorithms for robots. It is easy to integrate in robotic middlewares and it can be used to compare methods and develop prototypes in simulation.

Effects of Colloidal Oatmeal Topical Atopic Dermatitis Cream on Skin Microbiome and Skin Barrier Properties

Atopic dermatitis is characterized by dry, itchy, inflamed skin with a dysbiotic microbiome. In this clinical study (NCT03673059), we compared the effects of an eczema cream containing 1% colloidal oat and a standard moisturizer on the skin microbiome and skin barrier function of patients with mild to moderate eczema. Patients were randomly assigned to treatment with 1% colloidal oat eczema cream or a standard, non-fragranced daily moisturizer. Treatment lasted 14 days, followed by a 7-day regression period. Of 61 patients who completed the study, 30 received the 1% colloidal oat eczema cream and 31 received the standard moisturizer. At 14 days, the 1% colloidal oat eczema cream reduced mean Eczema Area Severity Index and Atopic Dermatitis Severity Index scores by 51% and 54%, respectively. Unlike treatment with the standard moisturizer, treatment with the 1% colloidal oat eczema cream was associated with trends towards lower prevalence of Staphylococcus species and higher microbiome diversity at lesion sites. The 1% colloidal oat eczema cream significantly improved skin pH, skin barrier function, and skin hydration from baseline to day 14, whereas the standard moisturizer improved hydration. Overall, the results demonstrate that topical products can have differing effects on the skin barrier properties and the microbiome. Importantly, we show that the use of a 1% colloidal oat eczema cream improves microbiome composition and significantly repairs skin barrier defects. J Drugs Dermatol. 2020;19(5):   doi:10.36849/JDD.2020.4924.

Application of convolutional neural networks for classification of adult mosquitoes in the field

Dengue, chikungunya and Zika are arboviruses transmitted by mosquitos of the genus Aedes and have caused several outbreaks in world over the past ten years. Morphological identification of mosquitos is currently restricted due to the small number of adequately trained professionals. We implemented a computational model based on a convolutional neural network (CNN) to extract features from mosquito images to identify adult mosquitoes from the species Aedes aegypti, Aedes albopictus and Culex quinquefasciatus. To train the CNN to perform automatic morphological classification of mosquitoes, we used a dataset that included 4,056 mosquito images. Three neural networks, including LeNet, AlexNet and GoogleNet, were used. During the validation phase, the accuracy of the mosquito classification was 57.5% using LeNet, 74.7% using AlexNet and 83.9% using GoogleNet. During the testing phase, the best result (76.2%) was obtained using GoogleNet; results of 52.4% and 51.2% were obtained using LeNet and AlexNet, respectively. Significantly, accuracies of 100% and 90% were achieved for the classification of Aedes and Culex, respectively. A classification accuracy of 82% was achieved for Aedes females. Our results provide information that is fundamental for the automatic morphological classification of adult mosquito species in field. The use of CNN's is an important method for autonomous identification and is a valuable and accessible resource for health workers and taxonomists for the identification of some insects that can transmit infectious agents to humans.

Multimodal grasp data set: A novel visual–tactile data set for robotic manipulation

This article introduces a visual–tactile multimodal grasp data set, aiming to further the research on robotic manipulation. The data set was built by the novel designed dexterous robot hand, the Intel’s Eagle Shoal robot hand (Intel Labs China, Beijing, China). The data set contains 2550 sets data, including tactile, joint, time label, image, and RGB and depth video. With the integration of visual and tactile data, researchers could be able to better understand the grasping process and analyze the deeper grasping issues. In this article, the building process of the data set was introduced, as well as the data set composition. In order to evaluate the quality of data set, the tactile data were analyzed by short-time Fourier transform. The tactile data–based slip detection was realized by long short-term memory and contrasted with visual data. The experiments compared the long short-term memory with the traditional classifiers, and generalization ability on different grasp directions and different objects is implemented. The results have proved that the data set’s value in promoting research on robotic manipulation area showed the effective slip detection and generalization ability of long short-term memory. Further work on visual and tactile data will be devoted to in the future.

Expression of cutaneous immunity markers during infant skin maturation

BACKGROUND/OBJECTIVES

Infant skin undergoes a maturation process during the early years of life. Little is known about the skin's innate immunity. We investigated the dynamics of innate immunity markers collected from the surface of infant skin during the first 36 months of life.

METHODS

A total of 117 healthy infants aged 3-36 months participated in the study. We extracted human beta defensin-1 and interleukin 1 alpha and its receptor antagonist using transdermal analysis patches from the skin surface of the posterior lower leg area. The extracts were analyzed using a spot enzyme-linked immunosorbent assay.

RESULTS

Skin surface human beta defensin-1 levels were higher early in life and decreased with infant age. The ratio of interleukin 1 alpha receptor antagonist to interleukin 1 alpha did not change significantly with age but showed a distinct difference between sexes, with female infants having higher values than male infants.

CONCLUSION

As is the case with skin structure and functional properties, cutaneous innate immunity also appears to undergo a maturation period during infancy, with innate immunity slowly declining as adaptive immunity takes over. Sex differences in immune markers may explain sex-dependent susceptibilities to infection.

Integrated Mechanical, Thermal, Data, and Power Transfer Interfaces for Future Space Robotics

In-situ connectability among modules of a space system can provide significantly enhanced flexibility, adaptability, and robustness for space exploration and servicing missions. Connection of modules in extra-terrestrial environment is hence a topic of rising importance in modern orbital or planetary missions. As an example, the increasing number of satellites sent to space have introduced a large set of connections of various type, for transferring mechanical loads, data, electrical power and heat from one module to another. This paper provides a comprehensive review of published work in space robotic connections and presents the different transfer types developed and used to date in robotic applications for orbital and extra-terrestrial planetary missions. The aims of this paper are to present a detailed analysis of the state of the art available technologies, to make an analysis of and comparison among different solutions to common problems, to synthesize and identify future connectability research, and to lay the foundation for future European space robotic connectability effort and work for a complex and growing important future space missions. All types are described in their base characteristics and evaluated for orbital and planetary environments. This analysis shows that despite the large number of connectors developed for each of the four functionalities (mechanical, thermal, data, and electrical power) here considered, the trend is that researchers are integrating more than one functionalizes into a single equipment or device, to reduce costs and improve standardization. The outcomes of this literature review have contributed toward the design of a future multifunctional, standard and scalable interface at the early stage of the Standard Interface for Robotic Manipulation of Payloads in Future Space Missions (SIROM) project, a European Commission funded Horizon 2020 project. SIROM interfaces will be employed by European prime contractors in future extra-terrestrial missions.

The BesMan Learning Platform for Automated Robot Skill Learning

We describe the BesMan learning platform which allows learning robotic manipulation behavior. It is a stand-alone solution which can be combined with different robotic systems and applications. Behavior that is adaptive to task changes and different target platforms can be learned to solve unforeseen challenges and tasks, which can occur during deployment of a robot. The learning platform is composed of components that deal with preprocessing of human demonstrations, segmenting the demonstrated behavior into basic building blocks, imitation, refinement by means of reinforcement learning, and generalization to related tasks. The core components are evaluated in an empirical study with 10 participants with respect to automation level and time requirements. We show that most of the required steps for transferring skills from humans to robots can be automated and all steps can be performed in reasonable time allowing to apply the learning platform on demand.

A Hybrid FPGA-Based System for EEG- and EMG-Based Online Movement Prediction

A current trend in the development of assistive devices for rehabilitation, for example exoskeletons or active orthoses, is to utilize physiological data to enhance their functionality and usability, for example by predicting the patient's upcoming movements using electroencephalography (EEG) or electromyography (EMG). However, these modalities have different temporal properties and classification accuracies, which results in specific advantages and disadvantages. To use physiological data analysis in rehabilitation devices, the processing should be performed in real-time, guarantee close to natural movement onset support, provide high mobility, and should be performed by miniaturized systems that can be embedded into the rehabilitation device. We present a novel Field Programmable Gate Array (FPGA) -based system for real-time movement prediction using physiological data. Its parallel processing capabilities allows the combination of movement predictions based on EEG and EMG and additionally a P300 detection, which is likely evoked by instructions of the therapist. The system is evaluated in an offline and an online study with twelve healthy subjects in total. We show that it provides a high computational performance and significantly lower power consumption in comparison to a standard PC. Furthermore, despite the usage of fixed-point computations, the proposed system achieves a classification accuracy similar to systems with double precision floating-point precision.

An Intelligent Man-Machine Interface-Multi-Robot Control Adapted for Task Engagement Based on Single-Trial Detectability of P300

Advanced man-machine interfaces (MMIs) are being developed for teleoperating robots at remote and hardly accessible places. Such MMIs make use of a virtual environment and can therefore make the operator immerse him-/herself into the environment of the robot. In this paper, we present our developed MMI for multi-robot control. Our MMI can adapt to changes in task load and task engagement online. Applying our approach of embedded Brain Reading we improve user support and efficiency of interaction. The level of task engagement was inferred from the single-trial detectability of P300-related brain activity that was naturally evoked during interaction. With our approach no secondary task is needed to measure task load. It is based on research results on the single-stimulus paradigm, distribution of brain resources and its effect on the P300 event-related component. It further considers effects of the modulation caused by a delayed reaction time on the P300 component evoked by complex responses to task-relevant messages. We prove our concept using single-trial based machine learning analysis, analysis of averaged event-related potentials and behavioral analysis. As main results we show (1) a significant improvement of runtime needed to perform the interaction tasks compared to a setting in which all subjects could easily perform the tasks. We show that (2) the single-trial detectability of the event-related potential P300 can be used to measure the changes in task load and task engagement during complex interaction while also being sensitive to the level of experience of the operator and (3) can be used to adapt the MMI individually to the different needs of users without increasing total workload. Our online adaptation of the proposed MMI is based on a continuous supervision of the operator's cognitive resources by means of embedded Brain Reading. Operators with different qualifications or capabilities receive only as many tasks as they can perform to avoid mental overload as well as mental underload.

An Adaptive Spatial Filter for User-Independent Single Trial Detection of Event-Related Potentials

GOAL

Current brain-computer interfaces (BCIs) are usually based on various, often supervised, signal processing methods. The disadvantage of supervised methods is the requirement to calibrate them with recently acquired subject-specific training data. Here, we present a novel algorithm for dimensionality reduction (spatial filter), that is ideally suited for single-trial detection of event-related potentials (ERPs) and can be adapted online to a new subject to minimize or avoid calibration time.

METHODS

The algorithm is based on the well-known xDAWN filter, but uses generalized eigendecomposition to allow an incremental training by recursive least squares (RLS) updates of the filter coefficients. We analyze the effectiveness of the spatial filter in different transfer scenarios and combinations with adaptive classifiers.

RESULTS

The results show that it can compensate changes due to switching between different users, and therefore allows to reuse training data that has been previously recorded from other subjects.

CONCLUSIONS

The presented approach allows to reduce or completely avoid a calibration phase and to instantly use the BCI system with only a minor decrease of performance.

SIGNIFICANCE

The novel filter can adapt a precomputed spatial filter to a new subject and make a BCI system user independent.

Current Capabilities and Development Potential in Surgical Robotics

Commercial surgical robots have been in clinical use since the mid-1990s, supporting surgeons in various tasks. In the past decades, many systems emerged as research platforms, and a few entered the global market. This paper summarizes the currently available surgical systems and research directions in the broader field of surgical robotics. The widely deployed teleoperated manipulators aim to enhance human cognitive and physical skills and provide smart tools for surgeons, while image-guided robotics focus on surpassing human limitations by introducing automated targeting and treatment delivery methods. Both concepts are discussed based on prototypes and commercial systems. Through concrete examples the possible future development paths of surgical robots are illustrated. While research efforts are taking different approaches to improve the capacity of such systems, the aim of this survey is to assess their maturity from the commercialization point of view.

Über die Desorption von positiven und negativen Ionen durch starke elektrische Felder

An Hand von Beobachtungen über die Feldelektronenemission wird gezeigt, daß sich aus dünnen, auf Wolframeinkristallspitzen aufgedampften Kaliumchloridschichten, deren Schichtdicke größer ist, als dem Minimum der Elektronenaustrittsarbeit entspricht, durch positive Felder positive Kaliumionen, durch negative Felder negative Chlorionen „abreißen“ lassen; im ersten Fall erscheint die effektive Austrittsarbeit der Elektronen nach dem Abreißvorgang vergrößert, im zweiten Fall vermindert. Aus den dünnsten, vermutlich monomolekularen Kaliumchloridschichten, gelingt es dagegen mit den hier verwendeten Feldstärken nur, positive Ionen, aber keine negativen Ionen abzureißen; dies wird verständlich, wenn man beachtet, daß aus energetischen Gründen das Chlor in unmittelbarer Berührung mit der Wolframoberfläche nicht als Ion, sondern nur als neutrales Atom gebunden sein kann, weil seine Elektronenaffinität (3,79 eV) kleiner als die Austrittsarbeit des Wolframs (4,5 eV) ist.

Zur Deutung von früher untersuchten Abreißerscheinungen an gasbeladenen Wolframspitzen, die einer thermischen Nachbehandlung unterworfen waren, wird die Annahme vorgeschlagen, daß es sich bei den „Zentren“, die für die starken Intensitätsunterschiede im Feldelektronenemissionsbild solcher Schichten und für die Abreißerscheinungen verantwortlich sind, um überschüssige Metallatome handelt, die an bestimmten Stellen der Oberfläche der dünnen Oxyd- bzw. Carbidschicht eingebaut sind, mit der die gasbeladene Wolframoberfläche nach ihrer thermischen Nachbehandlung bedeckt ist.

Integration of fiber-optic sensor arrays into a multi-modal tactile sensor processing system for robotic end-effectors

With the increasing complexity of robotic missions and the development towards long-term autonomous systems, the need for multi-modal sensing of the environment increases. Until now, the use of tactile sensor systems has been mostly based on sensing one modality of forces in the robotic end-effector. The use of a multi-modal tactile sensory system is motivated, which combines static and dynamic force sensor arrays together with an absolute force measurement system. This publication is focused on the development of a compact sensor interface for a fiber-optic sensor array, as optic measurement principles tend to have a bulky interface. Mechanical, electrical and software approaches are combined to realize an integrated structure that provides decentralized data pre-processing of the tactile measurements. Local behaviors are implemented using this setup to show the effectiveness of this approach.

A Validation Process for Underwater Localization Algorithms

This paper describes the validation process of a localization algorithm for underwater vehicles. In order to develop new localization algorithms, it is essential to characterize them with regard to their accuracy, long-term stability and robustness to external sources of noise. This is only possible if a gold-standard reference localization (GSRL) is available against which any new localization algorithm (NLA) can be tested. This process requires a vehicle which carries all the required sensor and processing systems for both the GSRL and the NLA. This paper will show the necessity of such a validation process, briefly sketch the test vehicle and its capabilities, describe the challenges in computing the localizations of both the GSRL and the NLA simultaneously for comparison, and conclude with experimental data of real-world trials.

Distributed Computation in a Quadrupedal Robotic System

Today's and future space missions (will) have to deal with increasing requirements regarding autonomy and flexibility in the locomotor system. To cope with these requirements, a higher bandwidth for sensor information is needed. In this paper, a robotic system is presented that is equipped with artificial feet and a spine incorporating increased sensing capabilities for walking robots. In the proposed quadrupedal robotic system, the front and rear parts are connected via an actuated spinal structure with six degrees of freedom. In order to increase the robustness of the system's locomotion in terms of traction and stability, a foot-like structure equipped with various sensors has been developed. In terms of distributed local control, both structures are as self-contained as possible with regard to sensing, sensor preprocessing, control and communication. This allows the robot to respond rapidly to occurring events with only minor latency.

pySPACE-a signal processing and classification environment in Python

In neuroscience large amounts of data are recorded to provide insights into cerebral information processing and function. The successful extraction of the relevant signals becomes more and more challenging due to increasing complexities in acquisition techniques and questions addressed. Here, automated signal processing and machine learning tools can help to process the data, e.g., to separate signal and noise. With the presented software pySPACE (http://pyspace.github.io/pyspace), signal processing algorithms can be compared and applied automatically on time series data, either with the aim of finding a suitable preprocessing, or of training supervised algorithms to classify the data. pySPACE originally has been built to process multi-sensor windowed time series data, like event-related potentials from the electroencephalogram (EEG). The software provides automated data handling, distributed processing, modular build-up of signal processing chains and tools for visualization and performance evaluation. Included in the software are various algorithms like temporal and spatial filters, feature generation and selection, classification algorithms, and evaluation schemes. Further, interfaces to other signal processing tools are provided and, since pySPACE is a modular framework, it can be extended with new algorithms according to individual needs. In the presented work, the structural hierarchies are described. It is illustrated how users and developers can interface the software and execute offline and online modes. Configuration of pySPACE is realized with the YAML format, so that programming skills are not mandatory for usage. The concept of pySPACE is to have one comprehensive tool that can be used to perform complete signal processing and classification tasks. It further allows to define own algorithms, or to integrate and use already existing libraries.

Incremental learning of skill collections based on intrinsic motivation

Life-long learning of reusable, versatile skills is a key prerequisite for embodied agents that act in a complex, dynamic environment and are faced with different tasks over their lifetime. We address the question of how an agent can learn useful skills efficiently during a developmental period, i.e., when no task is imposed on him and no external reward signal is provided. Learning of skills in a developmental period needs to be incremental and self-motivated. We propose a new incremental, task-independent skill discovery approach that is suited for continuous domains. Furthermore, the agent learns specific skills based on intrinsic motivation mechanisms that determine on which skills learning is focused at a given point in time. We evaluate the approach in a reinforcement learning setup in two continuous domains with complex dynamics. We show that an intrinsically motivated, skill learning agent outperforms an agent which learns task solutions from scratch. Furthermore, we compare different intrinsic motivation mechanisms and how efficiently they make use of the agent's developmental period.