Simulation-Aided Handover Prediction From Video Using Recurrent Image-to-Motion Networks.

Recent advances in deep neural networks have opened up new possibilities for visuomotor robot learning. In the context of human-robot or robot-robot collaboration, such networks can be trained to predict future poses and this information can be used to improve the dynamics of cooperative tasks. This is important, both in terms of realizing various cooperative behaviors, and for ensuring safety. In this article, we propose a recurrent neural architecture, capable of transforming variable-length input motion videos into a set of parameters describing a robot trajectory, where predictions can be made after receiving only a few frames. A simulation environment is utilized to expand the training database and to improve generalization capability of the network. The resulting architecture demonstrates good accuracy when predicting handover trajectories, with models trained on synthetic and real data showing better performance than when trained on real or simulated data only. The computed trajectories enable the execution of handover tasks with uncalibrated robots, which was verified in an experiment with two real robots.

Training of deep neural networks for the generation of dynamic movement primitives.

Dynamic movement primitives (DMPs) have proven to be an effective movement representation for motor skill learning. In this paper, we propose a new approach for training deep neural networks to synthesize dynamic movement primitives. The distinguishing property of our approach is that it can utilize a novel loss function that measures the physical distance between movement trajectories as opposed to measuring the distance between the parameters of DMPs that have no physical meaning. This was made possible by deriving differential equations that can be applied to compute the gradients of the proposed loss function, thus enabling an effective application of backpropagation to optimize the parameters of the underlying deep neural network. While the developed approach is applicable to any neural network architecture, it was evaluated on two different architectures based on encoder-decoder networks and convolutional neural networks. Our results show that the minimization of the proposed loss function leads to better results than when more conventional loss functions are used.

Exercise training in patients with stable chronic heart failure: effects on thoracic impedance cardiography and B-type natriuretic peptide.

PURPOSE: Recent evidence has suggested that patients with stable chronic heart failure (CHF) may respond favorably to a progressive exercise program. The use of noninvasive hemodynamic monitoring and B-type natriuretic peptide (BNP) measurement in these patients is not well reported. This study investigated the utility of noninvasive hemodynamic monitoring and point-of-care BNP in a cardiac rehabilitation outpatient setting. METHODS: Patients with stable CHF were assigned to a supervised 12-week exercise program (n = 13) or control (n = 6). At baseline and at the end of the study period, patients were assessed for functional and quality-of-life status. Point-of-care BNP and noninvasive hemodynamic parameters were also obtained. RESULTS: As expected, patients assigned to the exercise group showed significant improvement in quality of life and distance covered by the 6-minute walk test, but control subjects showed no such changes. There was a trend toward improved BNP in the exercise group, with 73% of these patients showing a decrease in comparison with 67% of controls showing an increase. There was a significant improvement in stroke volume in the exercise group but not in the control group. CONCLUSIONS: Both BNP and noninvasive hemodynamic monitoring can be utilized in the cardiac rehabilitation outpatient setting and seem to mirror the favorable response to exercise of other functional tests.