A visual-based shared control architecture for remote telemanipulation

Abi-Farraj, Firas; Pedemonte, Nicolò; Giordano, Paolo Robuffo

doi:10.1109/iros.2016.7759628

Cited by 46 publications

(92 citation statements)

References 23 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is interesting to address the problem for more complicated tasks consisting, for example, of a sequence of primitive motions. Another potential extension of the shared control algorithm is the incorporation of visual information, as in [3], to improve the robustness of the system towards loose joints and miscalibrations. The stability of the teloperation loop is to be analyzed as well.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

A learning-based shared control architecture for interactive task execution

Abi-Farraj

Osa

Peters

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Abstract-Shared control is a key technology for various robotic applications in which a robotic system and a human operator are meant to collaborate efficiently. In order to achieve efficient task execution in shared control, it is essential to predict the desired behavior for a given situation or context to simplify the control task for the human operator. To do this prediction, we use Learning from Demonstration (LfD), which is a popular approach for transferring human skills to robots. We encode the demonstrated behavior as trajectory distributions and generalize the learned distributions to new situations. The goal of this paper is to present a shared control framework that uses learned expert distributions to gain more autonomy. Our approach controls the balance between the controller's autonomy and the human preference based on the distributions of the demonstrated trajectories. Moreover, the learned distributions are autonomously refined from collaborative task executions, resulting in a master-slave system with increasing autonomy that requires less user input with an increasing number of task executions. We experimentally validated that our shared control approach enables efficient task executions. Moreover, the conducted experiments demonstrated that the developed system improves its performances through interactive task executions with our shared control.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

A learning-based shared control architecture for interactive task execution

Abi-Farraj

Osa

Peters

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Experiment #1: shared-control of a robotic telemanipulator 1) Experimental setup: this first evaluation considers a shared-control teleoperation experiment in a virtual environment. It is inspired by [18], that describes the algorithmic design of a shared-control architecture for visual-based teleoperation. In [18], a grounded kinesthetic interface has been used for providing force cues, but no -even minor -evaluation was presented.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…It is inspired by [18], that describes the algorithmic design of a shared-control architecture for visual-based teleoperation. In [18], a grounded kinesthetic interface has been used for providing force cues, but no -even minor -evaluation was presented. The experimental setup is shown in Fig.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…The slave side consists of a 6-DoF Viper S850 robotic arm carrying a gripper, simulated using the popular V-REP environment, and two objects to grasp. The autonomous algorithm proposed in [18] is in charge of always keeping the manipulator gripper pointed towards the object to be grasped (2 DoF) with the aim of assisting the human operator in the grasping task. At the same time, the human operator is given the possibility to steer the slave end-effector along the remaining 4 null-space directions (w.r.t.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…5). The haptic cues introduced in [18] are meant to inform the operator about how close the slave manipulator is to given constraints (singularities and joint limits in the considered scenario). These constraints are encoded in a global cost function H(q), with q ∈ R 6 being the manipulator joint configuration vector.…”

Section: Experimental Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Design and Evaluation of a Wearable Haptic Device for Skin Stretch, Pressure, and Vibrotactile Stimuli

Aggravi

Pausé

Giordano

et al. 2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Abstract-This paper presents a wearable haptic device for the forearm and its application in robotic teleoperation. The device is able to provide skin stretch, pressure, and vibrotactile stimuli. Two servo motors, housed in a 3D printed lightweight platform, actuate an elastic fabric belt, wrapped around the arm. When the two servo motors rotate in opposite directions, the belt is tightened (or loosened), thereby compressing (or decompressing) the arm. On the other hand, when the two motors rotate in the same direction, the belt applies a shear force to the arm skin. Moreover, the belt houses four vibrotactile motors, positioned evenly around the arm at 90 degrees from each other. The device weights 220 g for 115×122×50 mm of dimensions, making it wearable and unobtrusive. We carried out a perceptual characterization of the device as well as two human-subjects teleoperation experiments in a virtual environment, employing a total of 34 subjects. In the first experiment, participants were asked to control the motion of a robotic manipulator for grasping an object; in the second experiment, participants were asked to teleoperate the motion of a quadrotor fleet along a given path. In both scenarios, the wearable haptic device provided feedback information about the status of the slave robot(s) and of the given task. Results showed the effectiveness of the proposed device. Performance on completion time, length trajectory, and perceived effectiveness when using the wearable device improved of 19.8%, 25.1%, and 149.1% than when wearing no device, respectively. Finally, all subjects but three preferred the conditions including wearable haptics.

show abstract

A General Framework for Shared Control in Robot Teleoperation with Force and Visual Feedback

Nicolis

2019

Special Topics in Information Technology

View full text Add to dashboard Cite

In the last decade, the topic of human robot interaction has received increasing interest from research and industry, as robots must now interface with human users to accomplish complex tasks. In this scenario, robotics engineers are required to take the human component into account in the robot design and control. This is especially true in telerobotics, where interaction with the user plays an important role in the controlled system stability. By means of a thorough analysis and practical experiments, this contribution aims at giving a concrete idea of the aspects that need to be considered in the design of a complete control framework for teleoperated systems, that are able to seamlessly integrate with a human operator through shared control.

show abstract

A visual-based shared control architecture for remote telemanipulation

Cited by 46 publications

References 23 publications

A learning-based shared control architecture for interactive task execution

A learning-based shared control architecture for interactive task execution

Design and Evaluation of a Wearable Haptic Device for Skin Stretch, Pressure, and Vibrotactile Stimuli

A General Framework for Shared Control in Robot Teleoperation with Force and Visual Feedback

Contact Info

Product

Resources

About