The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We propose a self-supervised approach for learning representations of relationships between humans and their environment, including object interactions, attributes, and body pose, entirely from unlabeled videos recorded from multiple viewpoints (Fig. 2). We train an embedding with a triplet loss that contrasts a pair of simultaneous frames from different viewpoints with temporally adjacent and visually...
We present an anomaly detection system based on an autonomous robot performing a patrol task. Using a generative adversarial network (GAN), we compare the robot's current view with a learned model of normality. Our preliminary experimental results show that the approach is well suited for anomaly detection, providing efficient results with a low false positive rate.
The main goal of this study is to analyse the effects of combined transcranial direct current stimulation (tDCS) and wrist robot-assisted therapy in subacute stroke patients. Twenty-four patients were included in this study and randomly assigned to the experimental (EG) or control group (CG). All participants performed wrist robot-assisted training a) in conjunction with tDCS (real stimulation for...
Robot-assisted therapy is regarded as an effective and reliable method for the delivery of highly repetitive rehabilitation training in restoring motor skills after a stroke. This study focuses on the rehabilitation of fine hand motion skills due to their vital role in performing delicate activities of daily living (ADL) tasks. The proposed rehabilitation system combines an adaptive assist-as-needed...
Recent technological developments regarding wearable soft-robotic devices extend beyond the current application of rehabilitation robotics and enable unobtrusive support of the arms and hands during daily activities. In this light, the HandinMind (HiM) system was developed, comprising a soft-robotic, grip supporting glove with an added computer gaming environment. The present study aims to gain first...
This paper deals with some research outcomes in the field of FES&BCI based rehabilitation equipment, specifically, hybrid exoskeleton&FES&BCI systems. The novelty of the proposed FES&exoskeleton systems is the balanced control between FES, voluntary motion induced by the user and the exoskeleton trajectory guidance. The upper limb exoskeleton&FES hybrid EXOSLIM system has been...
Daily life activities, such as eating and sleeping, are deeply influenced by a person's culture, hence generating differences in the way a same activity is performed by individuals belonging to different cultures. We argue that taking cultural information into account can improve the performance of systems for the automated recognition of human activities. We propose four different solutions to the...
The purpose of this study was to investigate the effect of RAGT on the static balance ability of sitting posture in SCI. Changes in COP in the open eyes showed significant differences between groups in the anterior sway category. In both groups, there was a tendency for the front and back sway to decrease, suggesting that RAGT and upper body balance training may have an effect of reducing anterior...
Object detection and pose estimation is a fundamental functionality among robotic perception for manipulation. Applying robots to diverse tasks requires a robust perception skill. In this manuscript, we introduce an overview of our object recognition and pose estimation process and its our initial results. Our approach follows the previous approaches using local feature extraction and match. As a...
Epiduroscopy is one of the widely implemented procedures in effective diagnosing and curing lumbago patients. Such endoscopic surgery requires much skill to control the surgical instruments well. Therefore, this paper proposes an epiduroscopy training simulator using a haptic master device. The proposed training simulator calculates forces using virtual fixture implemented in a catheter insertion...
Generating emotional body expressions for socially assistive robots has been gaining increased attention to enhance the engagement and empathy in human-robot interaction. In this paper, we propose a new model of emotional body expression for the robot inspired by social and emotional development of infant from their parents. An infant is often influenced by social referencing, meaning that they perceive...
Over time, surgical trainees learn to compensate for the lack of haptic feedback in commercial robotic minimally invasive surgical systems. Incorporating touch cues into robotic surgery training could potentially shorten this learning process if the benefits of haptic feedback were sustained after it is removed. In this paper, we develop a wrist-squeezing haptic feedback system and evaluate whether...
Path planning for robots with obstacles is an important problem and have not been resolved well yet. An extended Support Vector Machine(SVM)-based path planning method(which is named the multi-constraints SVM method in this paper) was proposed in previous work. However, no analysis was provided for the planned paths. So, an detailed analysis of the paths based on the method above will be given in...
Programming by Demonstration allows to transfer skills from human demonstrators to robotic systems by observation and reproduction. One aspect that is often overlooked is that humans show different trajectories over multiple demonstrations for the same task. Observed movements may be more precise in some phases and more diverse in others. It is well-known that the variability of the execution carries...
Weed scouting is an important part of modern integrated weed management but can be time consuming and sparse when performed manually. Automated weed scouting and weed destruction has typically been performed using classification systems able to classify a set group of species known a priori. This greatly limits deployability as classification systems must be retrained for any field with a different...
Many interesting natural phenomena are sparsely distributed and discrete. Locating the hotspots of such sparsely distributed phenomena is often difficult because their density gradient is likely to be very noisy. We present a novel approach to this search problem, where we model the co-occurrence relations between a robot's observations with a Bayesian nonparametric topic model. This approach makes...
Two less addressed issues of deep reinforcement learning are (1) lack of generalization capability to new goals, and (2) data inefficiency, i.e., the model requires several (and often costly) episodes of trial and error to converge, which makes it impractical to be applied to real-world scenarios. In this paper, we address these two issues and apply our model to target-driven visual navigation. To...
Policy search can in principle acquire complex strategies for control of robots and other autonomous systems. When the policy is trained to process raw sensory inputs, such as images and depth maps, it can also acquire a strategy that combines perception and control. However, effectively processing such complex inputs requires an expressive policy class, such as a large neural network. These high-dimensional...
Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without extensive manual engineering. However, robotic skill learning must typically make trade-offs to enable practical real-world learning, such as requiring manually designed policy or value function representations, initialization from human demonstrations, instrumentation of the training...
3Sergey Levine is with Google Brain, Mountain View, CA 94043, USA. We present a policy search method for learning complex feedback control policies that map from high-dimensional sensory inputs to motor torques, for manipulation tasks with discontinuous contact dynamics. We build on a prior technique called guided policy search (GPS), which iteratively optimizes a set of local policies for specific...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.