AMiCUS 2.0-System Presentation and Demonstration of Adaptability to Personal Needs by the Example of an Individual with Progressed Multiple Sclerosis.

AMiCUS is a human-robot interface that enables tetraplegics to control an assistive roboticarm in real-time using only head motion, allowing them to perform simple manipulation tasksindependently. The interface may be used as a standalone system or to provide direct control aspart of a semi-autonomous system. Within this work, we present our new gesture-free prototypeAMiCUS 2.0, which has been designed with special attention to accessibility and ergonomics. As such,AMiCUS 2.0 addresses the needs of tetraplegics with additional impairments that may come alongwith multiple sclerosis. In an experimental setup, both AMiCUS 1.0 and 2.0 are compared with eachother, showing higher accessibility and usability for AMiCUS 2.0. Moreover, in an activity of dailyliving, a proof-of-concept is provided that an individual with progressed multiple sclerosis is able tooperate the robotic arm in a temporal and functional scope, as would be necessary to perform directcontrol tasks for use in a commercial semi-autonomous system. The results indicate that AMiCUS 2.0makes an important step towards closing the gaps of assistive technology, being accessible to thosewho rely on such technology the most.

Time Coherent Full-Body Poses Estimated Using Only Five Inertial Sensors: Deep versus Shallow Learning.

Full-body motion capture typically requires sensors/markers to be placed on each rigid body segment, which results in long setup times and is obtrusive. The number of sensors/markers can be reduced using deep learning or offline methods. However, this requires large training datasets and/or sufficient computational resources. Therefore, we investigate the following research question: "What is the performance of a shallow approach, compared to a deep learning one, for estimating time coherent full-body poses using only five inertial sensors?". We propose to incorporate past/future inertial sensor information into a stacked input vector, which is fed to a shallow neural network for estimating full-body poses. Shallow and deep learning approaches are compared using the same input vector configurations. Additionally, the inclusion of acceleration input is evaluated. The results show that a shallow learning approach can estimate full-body poses with a similar accuracy (~6 cm) to that of a deep learning approach (~7 cm). However, the jerk errors are smaller using the deep learning approach, which can be the effect of explicit recurrent modelling. Furthermore, it is shown that the delay using a shallow learning approach (72 ms) is smaller than that of a deep learning approach (117 ms).

AMiCUS-A Head Motion-Based Interface for Control of an Assistive Robot.

Within this work we present AMiCUS, a Human-Robot Interface that enables tetraplegics to control a multi-degree of freedom robot arm in real-time using solely head motion, empowering them to perform simple manipulation tasks independently. The article describes the hardware, software and signal processing of AMiCUS and presents the results of a volunteer study with 13 able-bodied subjects and 6 tetraplegics with severe head motion limitations. As part of the study, the subjects performed two different pick-and-place tasks. The usability was assessed with a questionnaire. The overall performance and the main control elements were evaluated with objective measures such as completion rate and interaction time. The results show that the mapping of head motion onto robot motion is intuitive and the given feedback is useful, enabling smooth, precise and efficient robot control and resulting in high user-acceptance. Furthermore, it could be demonstrated that the robot did not move unintendedly, giving a positive prognosis for safety requirements in the framework of a certification of a product prototype. On top of that, AMiCUS enabled every subject to control the robot arm, independent of prior experience and degree of head motion limitation, making the system available for a wide range of motion impaired users.

Long term stability of surface EMG pattern classification for prosthetic control.

Long-term functioning of a hand prosthesis is crucial for its acceptance by patients with upper limb deficit. In this study the reliability over days of the performance of pattern classification approaches based on surface electromyography (sEMG) signal for the control of upper limb prostheses was investigated. Recordings of sEMG from the forearm muscles were obtained across five consecutive days from five healthy subjects. It was demonstrated that the classification performance decreased monotonically on average by 4.1% per day. It was also found that the accumulated error was confined to three of the eight movement classes investigated. This contribution gives insight on the long term behavior of pattern classification, which is crucial for commercial viability.