Development of a wearable modular IMU sensor network suit with a distributed vibrotactile feedback for on-line movement guidance

Nassour, John; Tacca, Nicholas; Erjiage, Guan; Cheng, Gordon

doi:10.1109/aim46487.2021.9517473

Cited by 3 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work will be also devoted to perform a more exhaustive characterization of the system and identify the relationship between the stimulus and the motor actuation as done in [21] as well as the JND of the device. Furthermore, we will also test the system in conjunction with continuous error measurement (CoP trajectory measured over time) during the task execution as in [26], and in integration with wireless and completely wearable devices for kinematic measurements as in [17].…”

Section: Discussionmentioning

confidence: 99%

“…However, also in this case, the majority of solutions are not designed to deliver guidance feedback regarding the correct direction of motion [12] and/or provide only vibrational stimuli [16], as in [17], where the authors presented a modular wireless sensor network suit for body postural measurements with distributed vibrotactile ON/OFF feedback (without any modulation of the duration of the OFF periods) to convey warning information and limb guidance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Cue Haptic Guidance Through Wearables for Enhancing Human Ergonomics

Fani¹,

Ciotti²,

Bianchi³

2022

IEEE Trans. Haptics

View full text Add to dashboard Cite

Wearable haptic systems can be easily integrated with the human body and represent an effective solution for a natural and unobtrusive stimulus delivery. These characteristics can open interesting perspectives for different applications, such as haptic guidance for human ergonomics enhancement, e.g. during human-robot collaborative tasks in industrial scenarios, where the usage of the visual communication channel can be problematic. In this work, we propose a wearable multi-cue system that can be worn at the arm level on both the two upper limbs, which conveys both squeezing stimuli (provided by an armband haptic device) and vibration, to provide corrective feedback for posture balancing along the user's frontal and sagittal plane, respectively. We evaluated the effectiveness of our system in delivering directional information to control the user's center of pressure position on a balancing board. We compared the here proposed haptic guidance with visual guidance cues. Results show no statistically significant differences in terms of success rate and time for task completion for the two conditions. Furthermore, participants underwent through a Subjective Quantitative Evaluation and a NASA-TLX test, evaluating the wearable haptic system as intuitive and effective.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi-Cue Haptic Guidance Through Wearables for Enhancing Human Ergonomics

Fani¹,

Ciotti²,

Bianchi³

2022

IEEE Trans. Haptics

View full text Add to dashboard Cite

show abstract

Wearable high-density EMG sleeve for complex hand gesture classification and continuous joint angle estimation

Tacca,

Dunlap,

Donegan

et al. 2024

Sci Rep

View full text Add to dashboard Cite

High-density electromyography (HD-EMG) can provide a natural interface to enhance human–computer interaction (HCI). This study aims to demonstrate the capability of a novel HD-EMG forearm sleeve equipped with up to 150 electrodes to capture high-resolution muscle activity, decode complex hand gestures, and estimate continuous hand position via joint angle predictions. Ten able-bodied participants performed 37 hand movements and grasps while EMG was recorded using the HD-EMG sleeve. Simultaneously, an 18-sensor motion capture glove calculated 23 joint angles from the hand and fingers across all movements for training regression models. For classifying across the 37 gestures, our decoding algorithm was able to differentiate between sequential movements with $$97.3 \pm 0.3\%$$ 97.3 ± 0.3 % accuracy calculated on a 100 ms bin-by-bin basis. In a separate mixed dataset consisting of 19 movements randomly interspersed, decoding performance achieved an average bin-wise accuracy of $$92.8 \pm 0.8\%$$ 92.8 ± 0.8 % . When evaluating decoders for use in real-time scenarios, we found that decoders can reliably decode both movements and movement transitions, achieving an average accuracy of $$93.3 \pm 0.9\%$$ 93.3 ± 0.9 % on the sequential set and $$88.5 \pm 0.9\%$$ 88.5 ± 0.9 % on the mixed set. Furthermore, we estimated continuous joint angles from the EMG sleeve data, achieving a $$R^2$$ R 2 of $$0.884 \pm 0.003$$ 0.884 ± 0.003 in the sequential set and $$0.750 \pm 0.008$$ 0.750 ± 0.008 in the mixed set. Median absolute error (MAE) was kept below 10° across all joints, with a grand average MAE of $$1.8 \pm 0.04^\circ$$ 1.8 ± 0 . 04 ∘ and $$3.4 \pm 0.07^\circ$$ 3.4 ± 0 . 07 ∘ for the sequential and mixed datasets, respectively. We also assessed two algorithm modifications to address specific challenges for EMG-driven HCI applications. To minimize decoder latency, we used a method that accounts for reaction time by dynamically shifting cue labels in time. To reduce training requirements, we show that pretraining models with historical data provided an increase in decoding performance compared with models that were not pretrained when reducing the in-session training data to only one attempt of each movement. The HD-EMG sleeve, combined with sophisticated machine learning algorithms, can be a powerful tool for hand gesture recognition and joint angle estimation. This technology holds significant promise for applications in HCI, such as prosthetics, assistive technology, rehabilitation, and human–robot collaboration.

show abstract