Application of immersive technologies and natural language to hyper-redundant robot teleoperation
- PDF / 2,671,883 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 60 Downloads / 192 Views
ORIGINAL ARTICLE
Application of immersive technologies and natural language to hyper‑redundant robot teleoperation Andrés Martín‑Barrio1 · Juan Jesús Roldán1 · Silvia Terrile1 · Jaime del Cerro1 · Antonio Barrientos1 Received: 23 April 2019 / Accepted: 25 November 2019 © Springer-Verlag London Ltd., part of Springer Nature 2019
Abstract This work presents an analysis of immersive realities and natural language applied to the teleoperation of hyper-redundant robots. Such devices have a large number of degrees of freedom, so they often exhibit complex configurations frustrating their spatial understanding. This work aims to contrast two hypotheses; first, if immersive interfaces enhance the telepresence and efficiency against conventional ones; and second, if natural language reduces workload and improves performance against other conventional tools. A total of 2 interfaces and 6 interaction tools have been tested by 50 people. As a result, immersive interfaces were more efficient, improved situational awareness and visual feedback, and were chosen by 94% of participants against conventional ones. On the other hand, participants performed better using natural language than conventional tools despite having less previous experience with the first ones. Additionally, according to 52% of the population, the preferred interaction tool was a mixed strategy that combined voice recognition and hand gestures. Therefore, it is concluded that immersive realities and natural language should play a very important role in the near future of hyper-redundant robots and their teleoperation. Keywords Virtual reality · Augmented reality · Mixed reality · Natural language · Hyper-redundant robot · Soft robot · Teleoperation
1 Introduction In every robotic device, the concept of Degree of Freedom (DoF) is very important. It can be defined as the number of movements or independent parameters that define the configuration of a robot (Barrientos et al. 2007). Traditionally, manipulator robots have been designed to have up to 6 DoF because it is the minimum number for which a robot can properly position and orient its end-effector in a threedimensional (3D) space. However, robots with a higher number of DoF have some advantages against traditional ones: they have higher kinematic skills, and they can recover from a failure in some of their joints and have better abilities Electronic supplementary material The online version of this article (https://doi.org/10.1007/s10055-019-00414-9) contains supplementary material, which is available to authorized users. * Andrés Martín‑Barrio [email protected] 1
Centre for Automation and Robotics (CAR), CSIC‑UPM, Universidad Politécnica de Madrid, c/ José Gutiérrez Abascal, No. 2, 28006 Madrid, Spain
to actuate in complex environments with obstacles. Those robots with more than 6 DoF are called redundant, while those with more than 12 DoF can be named as hyper-redundant (Martín-Barrio et al. 2018b). Traditionally, hyper-redundant robots have been conceived to be discrete, with a high number
Data Loading...
