scholarly journals The Wearable Robotic Forearm: Design and Predictive Control of a Collaborative Supernumerary Robot

Robotics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 91
Author(s):  
Vighnesh Vatsal ◽  
Guy Hoffman

This article presents the design process of a supernumerary wearable robotic forearm (WRF), along with methods for stabilizing the robot’s end-effector using human motion prediction. The device acts as a lightweight “third arm” for the user, extending their reach during handovers and manipulation in close-range collaborative activities. It was developed iteratively, following a user-centered design process that included an online survey, contextual inquiry, and an in-person usability study. Simulations show that the WRF significantly enhances a wearer’s reachable workspace volume, while remaining within biomechanical ergonomic load limits during typical usage scenarios. While operating the device in such scenarios, the user introduces disturbances in its pose due to their body movements. We present two methods to overcome these disturbances: autoregressive (AR) time series and a recurrent neural network (RNN). These models were used for forecasting the wearer’s body movements to compensate for disturbances, with prediction horizons determined through linear system identification. The models were trained offline on a subset of the KIT Human Motion Database, and tested in five usage scenarios to keep the 3D pose of the WRF’s end-effector static. The addition of the predictive models reduced the end-effector position errors by up to 26% compared to direct feedback control.

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2804
Author(s):  
Silvia Imbesi ◽  
Sofia Scataglini

Smart clothing plays a big role to foster innovation and to. boost health and well-being, improving the quality of the life of people, especially when addressed to niche users with particular needs related to their health. Designing smart apparel, in order to monitor physical and physiological functions in older users, is a crucial asset that user centered design is exploring, balancing needs expressed by the users with technological requirements related to the design process. In this paper, the authors describe a user centered methodology for the design of smart garments based on the evaluation of users’ acceptance of smart clothing. This comparison method can be considered as similar to a simplified version of the quality function deployment tool, and is used to evaluate the general response of each garment typology to different categories of requirements, determining the propensity of the older user to the utilization of the developed product. The suggested methodology aims at introducing in the design process a tool to evaluate and compare developed solutions, reducing complexity in design processes by providing a tool for the comparison of significant solutions, correlating quantitative and qualitative factors.


Author(s):  
DU Hui ◽  
GAO Feng ◽  
PAN Yang

A novel 3-UP3R parallel mechanism with six degree of freedoms is proposed in this paper. One most important advantage of this mechanism is that the three translational and three rotational motions are partially decoupled: the end-effector position is only determined by three inputs, while the rotational angles are relative to all six inputs. The design methodology via GF set theory is brought out, using which the limb type can be determined. The mobility of the end-effector is analyzed. After that, the kinematic and velocity models are formulated. Then, workspace is studied, and since the robot is partially decoupled, the reachable workspace is also the dexterous workspace. In the end, both local and global performances are discussed using conditioning indexes. The experiment of real prototype shows that this mechanism works well and may be applied in many fields.


2021 ◽  
Author(s):  
Jeonghwan Hwang ◽  
Taeheon Lee ◽  
Honggu Lee ◽  
Seonjeong Byun

BACKGROUND Despite the unprecedented performances of deep learning algorithms in clinical domains, full reviews of algorithmic predictions by human experts remain mandatory. Under these circumstances, artificial intelligence (AI) models are primarily designed as clinical decision support systems (CDSSs). However, from the perspective of clinical practitioners, the lack of clinical interpretability and user-centered interfaces block the adoption of these AI systems in practice. OBJECTIVE The aim of this study was to develop an AI-based CDSS for assisting polysomnographic technicians in reviewing AI-predicted sleep staging results. This study proposed and evaluated a CDSS that provides clinically sound explanations for AI predictions in a user-centered fashion. METHODS User needs for the system were identified during interviews with polysomnographic technicians. User observation sessions were conducted to understand the workflow of the practitioners during sleep scoring. Iterative design process was performed to ensure easy integration of the tool into clinical workflows. Then, we evaluated the system with polysomnographic technicians. We measured the improvements in sleep staging accuracies after adopting our tool and assessed qualitatively how the participants perceived and used the tool. RESULTS The user study revealed that technicians desire explanations relevant to key electroencephalogram (EEG) patterns for sleep staging when assessing the correctness of the AI predictions. Here, technicians could evaluate whether AI models properly locate and use those patterns during prediction. Based on this, information in AI models that is closely related to sleep EEG patterns was formulated and visualized during the iterative design process. Furthermore, we developed a different visualization strategy for each pattern based on the way the technicians interpreted the EEG recordings with these patterns during their workflows. Generally, the tool evaluation results from the nine polysomnographic technicians were positive. Quantitatively, technicians achieved better classification performances after reviewing the AI-generated predictions with the proposed system; classification accuracies measured with Macro-F1 scores improved from 60.20 to 62.71. Qualitatively, participants reported that the provided information from the tool effectively supported them, and they were able to develop notable adoption strategies for the tool. CONCLUSIONS Our findings indicate that formulating clinical explanations for automated predictions using the information in the AI with a user-centered design process is an effective strategy for developing a CDSS for sleep staging.


2017 ◽  
Vol 3 (1) ◽  
pp. 39-43 ◽  
Author(s):  
Ekaterina Ivanova ◽  
Michael Minge ◽  
Henning Schmidt ◽  
Manfred Thüring ◽  
Jörg Krüger

Abstract:Robotic therapy devices have been an important part of clinical neurological rehabilitation for several years. Until now such devices are only available for patients receiving therapy inside rehabilitation hospitals. Since patients should continue rehabilitation training after hospital discharge at home, intelligent robotic rehab devices could help to achieve this goal. This paper presents therapeutic requirements and early phases of the user-centered design process of the patient’s work station as part of a novel robot-based system for motor telerehabilitation.


DYNA ◽  
2015 ◽  
Vol 82 (193) ◽  
pp. 223-232 ◽  
Author(s):  
Natalia Padilla-Zea ◽  
Nuria Medina-Medina ◽  
Francisco L. Gutiérrez-Vela ◽  
José R. López-Arcos ◽  
Patricia Paderewski ◽  
...  

2018 ◽  
Vol 15 ◽  
pp. 99-106 ◽  
Author(s):  
Tiina Ervasti ◽  
Hilppa Gregow ◽  
Andrea Vajda ◽  
Terhi K. Laurila ◽  
Antti Mäkelä

Abstract. An online survey was used to map the needs and preferences of the Finnish general public concerning extended-range forecasts and their presentation. First analyses of the survey were used to guide the co-design process of novel extended-range forecasts to be developed and tested during the project. In addition, the survey was used to engage the respondents from the general public to participate in a one year piloting phase that started in June 2017. The respondents considered that the tailored extended-range forecasts would be beneficial in planning activities, preparing for the weather risks and scheduling the everyday life. The respondents also perceived the information about the impacts of weather conditions more important than advice on how to prepare for the impacts.


2021 ◽  
Author(s):  
Jan Thomas Meyer ◽  
Selina Weber ◽  
Lukas Jäger ◽  
Roland Sigrist ◽  
Roger Gassert ◽  
...  

Abstract Background: Advanced assistive technologies (AAT) aim to exploit the vast potential of technological developments made in the past decades to improve the quality of life of people with disabilities. Combining complex robotic technologies with the unique needs of people with disabilities requires a strong focus on user-centered design to ensure that the AAT appropriately addresses the daily life struggles of target users. The CYBATHLON aims to promote this mindset by empowering the AAT target users (“pilots”) to compete on race tracks that represent daily life obstacles. The objective of this work was to investigate the influence of the CYABTHALON on AAT technology development, acceptance, and user involvement (i.e., application of user-centered design).Methods: With an online survey targetting the pilots and technical leads of teams preparing for the CYBATHLON 2020 Global Edition, we investigated to what extent the pilots were involved in device development and how this influences the perceived daily life usability of the showcased AAT. Furthermore, the effects of user-centered design variables on the individual race performances were analyzed.Results: A total of 81 responses from 35 pilots and 46 technical leads were collected in the two weeks prior to the event. Of all teams partaking in the included disciplines of the CYBATHLON 2020 Global Edition, 81.8% (36 of 44) were included in the study. User-centered design appeared to be a prevalent practice among the teams, as 85.7% of all pilots reported a certain level of involvement. However, only 25.5% of the pilots reported daily life usage, despite QUEST usability scores of both respondent groups showing moderate to high satisfaction with the respected AAT across all investigated disciplines. An explorative linear mixed model indicated that daily life usage (p < 0.05) and prolonged user involvement (e.g. more than 2 years, p < 0.001) have a significant positive effect on the race performance at the competition.Conclusions: We conclude that the CYBATHLON positively fullfills its conceptual goals of promoting active participation and inclusion of people with disabilities in the design and evaluation of AAT, thereby stimulating the development of promising novel technological solutions. Also, our data could underline the value of the competition as a benchmark, highlighting remaining usability limitations or technology adoption hurdles.


Author(s):  
Horia D. Pitariu ◽  
Daniela M. Andrei ◽  
Adriana M. Guran

The present chapter focuses on the idea of rethinking the concept of usability moving from the traditional view of usability expressed in the internal characteristics of the product towards usability understood as deriving from the quality of interactions between humans, their work and the web design product. Usability is not only an add-on or a final result in the design process but it is embedded as a main concern within the design process itself. Related to this perspective on usability, the authors discussed the design models which can support it and argued on the importance of using social research tools for a better understanding of the people and their needs starting with the very first stage of design. Further on the authors have provided a brief description of the most frequently used research methods in user needs analysis (interviews, focus groups and surveys) together with short guidelines in preparing and using these methods. The last part is dedicated to the illustration of user needs analysis taken from two of their research projects.


Author(s):  
Loris Barbieri ◽  
Agostino Angilica ◽  
Fabio Bruno ◽  
Maurizio Muzzupappa

The importance of participatory design (PD) is progressively increasing thanks to its capacity to explore a wide variety of concepts, thus increasing the opportunity to create a successful product. In fact the design process should not be a solo activity, as designers often need inputs and other points of view, especially from end-users. According to the ultimate idea of PD, end-users are actively involved in the various activities of the product development to ensure that their needs and desires are satisfied. This paper presents a novel approach to the participatory design of product interfaces in a user-centered design (UCD) process. The approach is based on an interactive tool that allows end-users to design custom user interfaces of household appliances taking advantage of their own needs and experiences. The tool incorporates the analytical and more abstract knowledge of the designers codified in the form of aesthetical, technological and manufacturing constraints (i.e., limitations in the number and geometry of interface components, a limited number of colors, a discretization of the area where interface widgets are placed). This solution allows the end-users to directly design their favorite interface without the interference of any other subject. Through an accurate analysis of the choices done by the users, the designers are able to access to the deepest level of the users’ expression in order to catch their latent needs and tacit knowledge. The tool has been designed in order to make possible to immediately perform usability tests on the designed interface by using a Mixed Reality prototype. The paper describes the development of the tool and proposes a methodology that has been specifically addressed to include this tool in a design process based on UCD principles. Both the tool and the methodology are presented through the description of a case-study related to the redesign of a washing machine dashboard. Experimental results show that the proposed tool can be an effective support to design product interfaces during PD sessions.


Sign in / Sign up

Export Citation Format

Share Document