A Dedicated Tool Frame Based Tongue Interface Layout Improves 2D Visual Guided Control of an Assistive Robotic Manipulator: A Design Parameter for Tele-Applications

Abstract

It is crucial to increase the independence of severely disabled individuals. Assistive robotics can aid in the desired activities of daily living, including tasks requiring remote performance e.g. grasping remote objects, turning switches on/off, and opening/closing doors. The robot control is compromised by the lack of efficient interfaces for individuals with disabilities and the lack of depth perception. This paper addresses these challenges by presenting the development and evaluation of efficient tongue-based robot interfaces and low-level robot control schemes targeting telerobotic control through a 2D display. Ten able-bodied participants were successful in completing ten rounds of controlling a JACO robot to perform a pouring water task, using five different control methods, under 2D or 3D visual feedback. The tool-frame based tongue interface layout, L2_TF (with emulated joystick, mode switch button and a "GO" button) improved the 2D visual guided control of the JACO robot compared with the other tongue control methods. The mean trajectory length of completing the task using L2_TF was 3% longer compared with the standard joystick when controlling through 2D. The trajectory length for reaching and grabbing a bottle was shortest for L2_TF compared with all other control methods, including the joystick. The iTongue control layouts performed well in gripping time, showing no significant difference between 2D and 3D. The transition from 2D to 3D resulted in a mean decrease of 27.7% for task completion time across all interfaces. L2_TF and the joystick had the strongest and most similar robustness to the transition between 3D and 2D.

Adapting to progressive paralysis: A tongue-brain hybrid robot interface for individuals with amyotrophic lateral sclerosis

“…We utilized a TCI based on iTongue as this system has previously proved capable of directly and continuously controlling a robotic arm using this system [10], [11], [13]. In this study, the adapted iTongue generally outperformed the BCI and the hybrids, as expected.…”

“…with no motor functionality below the neck). It should be noted that most interfaces have only been evaluated with healthy participants (see "evaluation" column in Table I), despite ÷ 0 1 1 [11] ÷ 0 0 12 [12] ÷ ÷ 0 0 1 [13] ÷ 0 0 10 [14] ÷ ÷ ÷ ?…”

“…Possibly, tongue control provides the best performance of full control of an ARM [10], [11], [13] as it has provided control much faster than other tetraplegia accessible modalities. In a prior tongue control study, healthy individuals performed pick-up tasks of an object placed more than 40 cm away from the initial position within 40s [11].…”

“…For this study, we replaced the standard mounting braces with dental two-component A-silicone soft putty (TopDent ImpressA) by embedding the iTongue mouth-piece unit (MPU) in the putty and forming it against the palate of the participant until it solidified (after approximately 2 minutes). In addition, the tongue piercing, used as an activation unit in the commercial version, was replaced with a non-invasive activation unit glued to the tongue as has been done in previous studies [11], [13]. The raw signals (the electrical potential measured over the individual coils and filtered by an LC bandpass filter [71]) recorded from the MPU were wirelessly sent to a central unit from which the signal was transmitted to a laptop via a COM-port for processing.…”

Frame-Based Slip Detection for an Underactuated Robotic Gripper for Assistance of Users with Disabilities

“…For individuals with severe sensory-motor disabilities, grasping tasks can be achieved with the help of assistive robot arms, which can be controlled via remaining bodily functions, such as tongue movements [3]. Developing such an interface for these robot manipulators is a complex task [4], and therefore, supporting the control with autonomy of the robot to reduce the complexity is of great importance. While grasping points for grasping tasks of robotic arms can be synthesized well with modern computer vision methods [5], the grasp might still be unstable, causing objects to slip out of the gripper during the pickup or midair during an executed task.…”