Search

Repeatedly occurring droughts in the Czech Republic in previous years have heightened the need to answer questions concerning the provision of drinking water in small municipalities in the context of their development. The goal of the research was to assess what mutual relationships exist between insufficient drinking water supply and the socio-economic level of municipalities with less than 2000 inhabitants. The basis of the study is formed by data collected via a questionnaire survey of the mayors of 2110 municipalities. For the purposes of the analysis, the Drinking Water Supply Threat Index (DWSTI) composite indicator was established. Subsequently, the effect of selected factors on DWSTI was determined via correlation and regression analysis, and results were compared for two size groups of municipalities indicate water supply problems. The digging of new wells for individual needs is seen to be the most significant signal of problems. The absence of water supply infrastructure results in a heightening of the socio-economic deprivation of small municipalities, as it limits new building and becomes a limitation to their development. A solution is possible based on regional or trans-regional financial and managerial support of development together with an active approach on the part of municipalities.

Physical human–robot interaction tasks require robots that can detect and react to external perturbations caused by the human partner. In this contribution, we present a machine learning approach for detecting, estimating, and compensating for such external perturbations using only input from standard sensors. This machine learning approach makes use of Dynamic Mode Decomposition (DMD), a data processing technique developed in the field of fluid dynamics, which is applied to robotics for the first time. DMD is able to isolate the dynamics of a nonlinear system and is therefore well suited for separating noise from regular oscillations in sensor readings during cyclic robot movements. In a training phase, a DMD model for behavior-specific parameter configurations is learned. During task execution, the robot must estimate the external forces exerted by a human interaction partner. We compare the DMD-based approach to other interpolation schemes. A variant, sparsity promoting DMD, is particularly well suited...

We present a data-driven imitation learning system for learning human-robot interactions from human-human demonstrations. During training, the movements of two interaction partners are recorded through motion capture and an interaction model is learned. At runtime, the interaction model is used to continuously adapt the robot's motion, both spatially and temporally, to the movements of the human interaction partner. We show the effectiveness of the approach on complex, sequential tasks by presenting two applications involving collaborative human-robot assembly. Experiments with varied object hand-over positions and task execution speeds confirm the capabilities for spatio-temporal adaption of the demonstrated behavior to the current situation.

Intention inference can be an essential step toward efficient human–robot interaction. For this purpose, we propose the Intention-Driven Dynamics Model (IDDM) to probabilistically model the generative process of movements that are directed by the intention. The IDDM allows the intention to be inferred from observed movements using Bayes’ theorem. The IDDM simultaneously finds a latent state representation of noisy and high-dimensional observations, and models the intention-driven dynamics in the latent states. As most robotics applications are subject to real-time constraints, we develop an efficient online algorithm that allows for real-time intention inference. Two human–robot interaction scenarios, i.e. target prediction for robot table tennis and action recognition for interactive humanoid robots, are used to evaluate the performance of our inference algorithm. In both intention inference tasks, the proposed algorithm achieves substantial improvements over support vector machines and Gaussian processes.

This video demonstrates a novel imitation learning approach for learning human-robot interactions from human-human demonstrations. During training, the movements of two human interaction partners are recorded via motion capture. From this, an interaction model is learned that inherently captures important spatial relationships as well as temporal synchrony of body movements between the two interacting partners. The interaction model is based on interaction meshes that were first adopted by the computer graphics community for the offline animation of interacting virtual characters. We developed a variant of interaction meshes that is suitable for real-time human-robot interaction scenarios. During humanrobot collaboration, the learned interaction model allows for adequate spatio-temporal adaptation of the robots behavior to the movements of the human cooperation partner. Thus, the presented approach is well suited for collaborative tasks requiring continuous body movement coordination of a human and a robot. The feasibility of the approach is demonstrated with the example of a cooperative Lego rocket assembly task.

In order to ensure safe operation, robots must be able to reliably detect behavior perturbations that result from unexpected physical interactions with their environment and human co-workers. While some robots provide firmware force sensors that generate rough force estimates, more accurate force measurements are usually achieved with dedicated force-torque sensors. However, such sensors are often heavy, expensive and require an additional power supply. In the case of lightweight manipulators, the already limited payload capabilities may be reduced in a significant way. This paper presents an experience-based approach for accurately estimating external forces being applied to a robot without the need for a force-torque sensor. Using Information Transfer, a subset of sensors relevant to the executed behavior are identified from a larger set of internal sensors. Models mapping robot sensor data to force-torque measurements are learned using a neural network. These models can be used to predict the magnitude and direction of perturbations from affordable, proprioceptive sensors only. Experiments with a UR5 robot show that our method yields force estimates with accuracy comparable to a dedicated force-torque sensor. Moreover, our method yields a substantial improvement in accuracy over force-torque values provided by the robot firmware.

Robotic manipulation tasks often require the control of forces and torques exerted on external objects. This paper presents a machine learning approach for estimating forces when no force sensors are present on the robot platform. In the training phase, the robot executes the desired manipulation tasks under controlled conditions with systematically varied parameter sets. All internal sensor data, in the presented case from more than 100 sensors, as well as the force exerted by the robot are recorded. Using Transfer Entropy, a statistical model is learned that identifies the subset of sensors relevant for torque estimation in the given task. At runtime, the model is used to accurately estimate the torques exerted during manipulations of the demonstrated kind. The feasibility of the approach is shown in a setting where a robotic manipulator operates a torque wrench to fasten a screw nut. Torque estimates with an accuracy of well below ±1Nm are achieved. A strength of the presented model is that no prior knowledge of the robot's kinematics, mass distribution or sensor instrumentation is required.

Hepatopulmonary syndrome (HPS) and portopulmonary hypertension (PPHTN) are distinct clinical entities that may complicate liver disease. Although HPS and PPHTN are different, several reports describe 6 patients in whom both conditions have occurred, either concurrently or sequentially, sometimes with the onset of PPHTN after liver transplantation. The current report extends this sparse experience by reporting 2 patients who underwent liver transplantation for HPS and who developed pulmonary hypertension after liver transplantation. This experience calls for better understanding of the pathogenesis of HPS and PPHTN and ways to better predict their occurrence.

In physical human-robot interaction, robot behavior must be adjusted to forces applied by the human interaction partner. For measuring such forces, special-purpose sensors may be used, e.g. force-torque sensors, that are however often heavy, expensive and prone to noise. In contrast, we propose a machine learning approach for measuring external perturbations of robot behavior that uses commonly available, low-cost sensors only. During the training phase, behavior-specific statistical models of sensor measurements, so-called perturbation filters, are constructed using Principal Component Analysis, Transfer Entropy and Dynamic Mode Decomposition. During behavior execution, perturbation filters compare measured and predicted sensor values for estimating the amount and direction of forces applied by the human interaction partner. Such perturbation filters can therefore be regarded as virtual force sensors that produce continuous estimates of external forces.

In many settings, e.g. physical human-robot interaction, robotic behavior must be made robust against more or less spontaneous application of external forces. Typically, this problem is tackled by means of special purpose force sensors which are, however, not available on many robotic platforms. In contrast, we propose a machine learning approach suitable for more common, although often noisy sensors. This machine learning approach makes use of Dynamic Mode Decomposition (DMD) which is able to extract the dynamics of a nonlinear system. It is therefore well suited to separate noise from regular oscillations in sensor readings during cyclic robot movements under different behavior configurations. We demonstrate the feasibility of our approach with an example where physical forces are exerted on a humanoid robot during walking. In a training phase, a snapshot based DMD model for behavior specific parameter configurations is learned. During task execution the robot must detect and estimate the external forces exerted by a human interaction partner. We compare the DMD-based approach to other interpolation schemes and show that the former outperforms the latter particularly in the presence of sensor noise. We conclude that DMD which has so far been mostly used in other fields of science, particularly fluid mechanics, is also a highly promising method for robotics.

We address the problem of creating believable animations for virtual humans that need to react to the body movements of a human interaction partner in real-time. Our data-driven approach uses prerecorded motion capture data of two interacting persons and performs motion adaptation during the live human-agent interaction. Extending the interaction mesh approach, our main contribution is a new scheme for efficient identification of motions in the prerecorded animation data that are similar to the live interaction. A global low-dimensional posture space serves to select the most similar interaction example, while local, more detail-rich posture spaces are used to identify poses closely matching the human motion. Using the interaction mesh of the selected motion example, an animation can then be synthesized that takes into account both spatial and temporal similarities between the prerecorded and live interactions.

In this paper we present a new approach for learning responsive robot behavior by imitation of human interaction partners. Extending previous work on robot imitation learning, that has so far mostly concentrated on learning from demonstrations by a single actor, we simultaneously record the movements of two humans engaged in on-going interaction tasks and learn compact models of the interaction. Extracted interaction models can thereafter be used by a robot to engage in a similar interaction with a human partner. We present two algorithms for deriving interaction models from motion capture data as well as experimental results on a humanoid robot.

In many cooperative tasks between a human and a robotic assistant, the human guides the robot by exerting forces, either through direct physical interaction or indirectly via a jointly manipulated object. These physical forces perturb the robot's behavior execution and need to be compensated for in order to successfully complete such tasks. Typically, this problem is tackled by means of special purpose force sensors which are, however, not available on many robotic platforms. In contrast, we propose a machine learning approach based on sensor data, such as accelerometer and pressure sensor information. In the training phase, a statistical model of behavior execution is learned that combines Gaussian Process Regression with a novel periodic kernel. During behavior execution, predictions from the statistical model are continuously compared with stability parameters derived from current sensor readings. Differences between predicted and measured values exceeding the variance of the statistical model are interpreted as guidance information and used to adapt the robot's behavior. Several examples of cooperative tasks between a human and a humanoid NAO robot demonstrate the feasibility of our approach.

Language is an important tool in social communication, but not all communication is channeled through verbal or linguistic expressions. Rock art is an example of visual symbols used in complicated systems of social communication. Rock art became an integrated part of the landscape, and through cognitive symbols, expressions were fixed in a physical, long-lasting medium. In this chapter rock art is seen through social semiotics, a theory about signs and symbols, and how they play an important part in communication between people in public space. Central to social semiotic theory is the principal of “message/reception”, the sender of the message, and the receiver of the message and the symbol convey a message. Social semiotics has uncovered that symbols and structures of symbols often serve as a medium for communication between powerful forces in society and the individual. Rock art was probably a far more diverted, cultural specific, and complex structure in prehistoric societies, therefore it is far more complicated to interpret today than we believe. In this chapter I will present a case study from South Scandinavia, and in this specific context, political control of a certain territory seems important for production of rock art.

How the human brain processes and manages information is a captivating topic within the realm of ‘people in the digital age’, information science and librarianship. One of the most interesting dimensions of this is how we filter information and either instantly or more gradually forget it, when it is deemed unimportant, mostly because we can’t remember and/or usefully apply everything we’ve experienced. This is our neural ‘librarianship’, and different people develop vastly different methods and abilities in this regard. This chapter considers the analogy between the brain and computing science. In the digital age we are about to have an infinitely greater cloud memory at our immediate disposal. Essentially, anything we see or touch digitally – which will be just about everything in our lives from birth forward – will be part of an immensely greater self-referential system, opening to currently unimaginable benefits and opportunities for personal and social growth, all based on individually scaled, primarily unconscious librarianship.

Inference of human intention may be an essential step towards understanding human actions [21] and is hence important for realizing efficient human-robot interaction. In this paper, we propose the Intention-Driven Dynamics Model (IDDM), a latent variable model for inferring unknown human intentions. We train the model based on observed human behaviors/actions and we introduce an approximate inference algorithm to efficiently infer the human’s intention from an ongoing action. We verify the feasibility of the IDDM in two scenarios, i.e., target inference in robot table tennis and action recognition for interactive humanoid robots. In both tasks, the IDDM achieves substantial improvements over state-of-the-art regression and classification.

Programming of complex motor skills for humanoid robots can be a time intensive task, particularly within conventional textual or GUI-driven programming paradigms. Addressing this drawback, we propose a new programming-by-demonstration method called Kinesthetic Bootstrapping for teaching motor skills to humanoid robots by means of intuitive physical interactions. Here, "programming" simply consists of manually moving the robot's joints so as to demonstrate the skill in mind. The bootstrapping algorithm then generates a low-dimensional model of the demonstrated postures.To find a trajectory through this posture space that corresponds to a robust robot motion, a learning phase takes place in a physics-based virtual environment. The virtual robot's motion is optimized via a genetic algorithm and the result is transferred back to the physical robot. The method has been successfully applied to the learning of various complex motor skills such as walking and standing up.

Although there are data in the literature about the safety and efficacy of laparoscopic liver resections, there are not many studies comparing laparoscopic versus open approaches in a case-matched design. The purpose of this study is to compare the perioperative outcome of laparoscopic versus open liver resections from a single institution.Thirty-one patients underwent laparoscopic liver resection between April 1997 and August 2007, with a prospective laparoscopic program started in April 2006 (n=25). This group of patients was compared with 43 consecutive patients undergoing open resection who were matched by size of the lesion (5 cm or less for malignant and 8 cm or less for benign), anatomical location (segments 2, 3, 4b, 5, 6), and type of resection (wedge resection, segmentectomy, partial liver resection). Data were obtained from medical records as well as from a prospective database. Statistical analysis was performed using t-test and chi-square. All data are expressed as mean +/- standard error on the mean (SEM).Mean age in the laparoscopic group was 57.6+/-2.7 years versus 61.9+/-2.3 years in the open group (p=0.2). There were more women in the laparoscopic group [74% females (n=23) and 26% males (n=8)] versus in the open group [40% females (n=17) and 60% males (n=26)] (p=0.003). There were more patients with malignant lesions in the open group (73%) versus in the laparoscopic group (45%) (p=0.01). Eight patients underwent partial and 23 patients segmental/wedge liver resection in the laparoscopic group versus 15 patients who underwent partial and 28 patients segmental/wedge liver resection in the open group (p=0.7). Mean tumor size was 3.9+/-0.4 cm in the laparoscopic group versus 4.2+/-0.3 cm in the open group (p=0.5). Ten (32%) out of 31 cases in the laparoscopic group were hand-assisted. Inflow occlusion was used in 1 case (3%) in the laparoscopic group versus 16 (37.2%) in the open group. Mean operating time was 201+/-15 min for the laparoscopic group and 172+/-12 min for the open group (p=0.1). Mean estimated blood loss during the procedure was 122.5+/-45.4 cc for the laparoscopic group and 299.6+/-33.6 cc for the open group (p=0.002). Surgical margin was similar for malignant cases in both groups. Mean hospital stay was 3.2+/-1.0 days for the laparoscopic group and 6.8+/-0.7 days for the open group (p=0.004). The incidence of postoperative complications was 13% (n=4) in the laparoscopic and 16% (n=7) in the open group (p=0.7).This study shows that, with a longer operative time, the laparoscopic approach, despite the learning curve, offers advantages regarding operative blood loss, postoperative analgesic requirement, time to regular diet, hospital stay, and overall cost compared with the open approach for minor liver resections.

We describe a patient with Budd-Chiari syndrome who developed an right ventricular (RV) thrombus after a mesoatrial shunt procedure for intractable ascites. The patient's hemodynamic performance mimicked RV infarction. The thrombus and its dissolution with urokinase was followed serially by echocardiography. After complete resolution, the patient's hemodynamic picture markedly improved