Abstract
In rehabilitation, assistive and space robotics, the capability to track the body posture of a user in real time is highly desirable. In more specific cases, such as teleoperated extra-vehicular activity, prosthetics and home service robotics, the ideal posture-tracking device must also be wearable, light and low-power, while still enforcing the best possible accuracy. Additionally, the device must be targeted at effective human-machine interaction. In this paper, we present and test such a device based upon commercial inertial measurement units: it weighs 575 g in total, lasts up to 10.5 h of continual operation, can be donned and doffed in under a minute and costs less than 290 EUR. We assess the attainable performance in terms of error in an online trajectory-tracking task in Virtual Reality using the device through an experiment involving 10 subjects, showing that an average user can attain a precision of 0.66 cm during a static precision task and 6.33 cm while tracking a moving trajectory, when tested in the full peri-personal space of a user.
Highlights
Multi-modal intent detection is the problem of detecting a person’s intention to move or to activate one’s muscles using sensors pertaining to different modalities, for example, going beyond the traditional usage of surface electromyography [1,2]
No clear substitute for surface electromyography (sEMG) is in sight, this technique suffers from a number of drawbacks and alternative means are being studied [2,6] to detect muscle activation in a different way, for example, force myography through muscle bulging [7,8] and ultrasound scanning through musculoskeletal internal movement detection
The absolute precision of the Vive tracking system has been assessed as sub-millimetric in a static configuration [21,22] and, reasonably, the positioning accuracy of the target in Virtual Reality (VR) was in the same range
Summary
Multi-modal intent detection is the problem of detecting a person’s intention to move or to activate one’s muscles using sensors pertaining to different modalities, for example, going beyond the traditional usage of surface electromyography (sEMG) [1,2]. For example, that the user is drawing their arms close to each other might be useful to enforce a coordinated two-handed prosthetic grasping of a heavy basket—this idea already appears in Reference [1]. As well, such information could be extremely valuable in solving the limb-position effect [9,10], which refers to the change in muscular recruitment and activity (and, by extension, measurable muscular signals) for the same hand movement due to a change in body pose
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
