Classification of Lifting Techniques for Application of A Robotic Hip Exoskeleton

Abstract

The number of exoskeletons providing load-lifting assistance has significantly increased over the last decade. In this field, to take full advantage of active exoskeletons and provide appropriate assistance to users, it is essential to develop control systems that are able to reliably recognize and classify the users’ movement when performing various lifting tasks. To this end, the movement-decoding algorithm should work robustly with different users and recognize different lifting techniques. Currently, there are no studies presenting methods to classify different lifting techniques in real time for applications with lumbar exoskeletons. We designed a real-time two-step algorithm for a portable hip exoskeleton that can detect the onset of the lifting movement and classify the technique used to accomplish the lift, using only the exoskeleton-embedded sensors. To evaluate the performance of the proposed algorithm, 15 healthy male subjects participated in two experimental sessions in which they were asked to perform lifting tasks using four different techniques (namely, squat lifting, stoop lifting, left-asymmetric lifting, and right-asymmetric lifting) while wearing an active hip exoskeleton. Five classes (the four lifting techniques plus the class “no lift”) were defined for the classification model, which is based on a set of rules (first step) and a pattern recognition algorithm (second step). Leave-one-subject-out cross-validation showed a recognition accuracy of 99.34 ± 0.85%, and the onset of the lift movement was detected within the first 121 to 166 ms of movement.

Gaussian Mixture Models for Control of Quasi-Passive Spinal Exoskeletons

“…Work regarding the control of devices implementing CEAs is sparse as it is usually limited to the low-level control of forces and stiffness [ 15 , 16 , 17 ]. Most papers regarding control of exoskeletons, deal with active devices [ 18 , 19 , 20 ]. Some studies were dealing specifically with controllers for active spinal exoskeletons, where various techniques of lifting were being classified and based on this, appropriate support was given to the user [ 19 , 21 ].…”

“…Most papers regarding control of exoskeletons, deal with active devices [ 18 , 19 , 20 ]. Some studies were dealing specifically with controllers for active spinal exoskeletons, where various techniques of lifting were being classified and based on this, appropriate support was given to the user [ 19 , 21 ]. These studies focused on the detection and classification of the upward lifting motion and neglected the initial part, when the body bends down towards the load.…”

Ergonomic Mechanical Design and Assessment of a Waist Assist Exoskeleton for Reducing Lumbar Loads During Lifting Task

“…Lower back muscle EMG signals of the left and right LES, TES and LD were recorded in symmetrical lifting for six different objects (0, 5, 10, 15, 20, and 25 kg) under two experimental conditions, with and without the waist assist exoskeleton. After filtering with a bandwidth of 10–500 Hz [29] and other processing of EMG signals [30], calculating their integral IEMG values within a lifting cycle, we defined the assistance efficiency of the exoskeleton by the following formula:E=1−IEI where IE is the IEMG when the subjects lift the loads with the exoskeleton, and I is the IEMG when the subjects lift the same loads without the exoskeleton.…”

Towards methodology and metrics for assessing lumbar exoskeletons in industrial applications

“…In state-of-the-art experiments, the lifting trials have been designed to replicate a scenario of repetitive load lifting, similar to the one presented in [13]. In our previous studies, we used the APO, a powered robotic hip exoskeleton, designed to assist the hip flexion-extension movement [13]- [16]. Recruited subjects were asked to repetitively perform lifting and lowering of a 5-kg box between two locations at different heights.…”

“…In this paper, we present an overview of the methodologies used in previous experiments carried out with healthy participants performing repetitive lifting tasks with an active lower-limb exoskeleton [13]- [16]. Moreover, we propose a set of suitable metrics that can be used to evaluate and compare lumbar exoskeletons.…”