EMPress

McIntosh, Jess; McNeill, Charlie; Fraser, Mike; Kerber, Frederic; Löchtefeld, Markus; Krüger, Antonio

doi:10.1145/2858036.2858093

Cited by 114 publications

(18 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most common approaches rely on optical technology [61,68] and electromyography (EMG) [38,50]. However more recent devices offer higher resolution of gesturesensing based on radar [31] and sonar [49] technologies.…”

Section: Touchless Systemsmentioning

confidence: 99%

Agency in Mid-air Interfaces

Cornelio

Pirro

Thanh

et al. 2017

Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Touchless interfaces allow users to view, control and manipulate digital content without physically touching an interface. They are being explored in a wide range of application scenarios from medical surgery to car dashboard controllers. One aspect of touchless interaction that has not been explored to date is the Sense of Agency (SoA). The SoA refers to the subjective experience of voluntary control over actions in the external world. In this paper, we investigated the SoA in touchless systems using the intentional binding paradigm. We first compare touchless systems with physical interactions and then augmented different types of haptic feedback to explore how different outcome modalities influence users' SoA.From our experiments, we demonstrated that an intentional binding effect is observed in both physical and touchless interactions with no statistical difference. Additionally, we found that haptic and auditory feedback help to increase SoA compared with visual feedback in touchless interfaces. We discuss these findings and identify design opportunities that take agency into consideration.

show abstract

Section: Touchless Systemsmentioning

confidence: 99%

Agency in Mid-air Interfaces

Cornelio

Pirro

Thanh

et al. 2017

Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Past work has explored gesture detection via muscle activity [16,29,34,41,48,50,51,61]. Classification techniques include machine learning pipelines often with manually defined features [12,13,29,34,41,51], Hidden Markov Models (HMMs) [31,50,61,62], and dynamic time warping [26]. The current work focuses on detecting gestures designed for robot control from a minimal number of wearable sensors, without requiring per-user training or calibration sessions.…”

Section: Gesture Detectionmentioning

confidence: 99%

Plug-and-Play Gesture Control Using Muscle and Motion Sensors

DelPreto

Rus

2020

Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction

View full text Add to dashboard Cite

As the capacity for machines to extend human capabilities continues to grow, the communication channels used must also expand. Allowing machines to interpret nonverbal commands such as gestures can help make interactions more similar to interactions with another person. Yet to be pervasive and effective in realistic scenarios, such interfaces should not require significant sensing infrastructure or per-user setup time. The presented work takes a step towards these goals by using wearable muscle and motion sensors to detect gestures without dedicated calibration or training procedures. An algorithm is presented for clustering unlabeled streaming data in real time, and it is applied to adaptively thresholding muscle and motion signals acquired via electromyography (EMG) and an inertial measurement unit (IMU). This enables plug-and-play online detection of arm stiffening, fist clenching, rotation gestures, and forearm activation. It also augments a neural network pipeline, trained only on strategically chosen training data from previous users, to detect left, right, up, and down gestures. Together, these pipelines offer a plug-and-play gesture vocabulary suitable for remotely controlling a robot. Experiments with 6 subjects evaluate classifier performance and interface efficacy. Classifiers correctly identified 97.6% of 1,200 cued gestures, and a drone correctly responded to 81.6% of 1,535 unstructured gestures as subjects remotely controlled it through target hoops during 119 minutes of total flight time. CCS CONCEPTS • Human-centered computing → Human computer interaction (HCI); Gestural input; • Computer systems organization → Robotics; • Computing methodologies → Machine learning.

show abstract

“…It is worth noting that more complex and computationally expensive algorithms such as a recurrent neural network (LSTM) were also implemented with similar accuracy to SVM. SVMs are commonly used in this type of application, with examples like NASA's Biosleeve project (Wolf et al, 2013) and McIntosh's SVM implementation in a multimodal sensing (sEMG and FSR) system (McIntosh et al, 2016). Myo EMG data classification accuracy is highly dependent on the gripping force which is not the case with the TAB data classification.…”

Section: Performance: Tab Vs Myomentioning

confidence: 99%

“…More recent works report results of the integration of EMG sensors with other means of sensing such as force sensing (Guo et al, 2015;McIntosh et al, 2016). Motion intent recognition studies have observed the mechanical signals produced as a result of the contraction of the muscles (Yap et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Tactile Signatures and Hand Motion Intent Recognition for Wearable Assistive Devices

et al. 2019

View full text Add to dashboard Cite

Within the field of robotics and autonomous systems where there is a human in the loop, intent recognition plays an important role. This is especially true for wearable assistive devices used for rehabilitation, particularly post-stroke recovery. This paper reports results on the use of tactile patterns to detect weak muscle contractions in the forearm while at the same time associating these patterns with the muscle synergies during different grips. To investigate this concept, a series of experiments with healthy participants were carried out using a tactile arm brace (TAB) on the forearm while performing four different types of grip. The expected force patterns were established by analysing the muscle synergies of the four grip types and the forearm physiology. The results showed that the tactile signatures of the forearm recorded on the TAB align with the anticipated force patterns. Furthermore, a linear separability of the data across all four grip types was identified. Using the TAB data, machine learning algorithms achieved a 99% classification accuracy. The TAB results were highly comparable to a similar commercial intent recognition system based on a surface electromyography (sEMG) sensing.

show abstract

EMPress

Cited by 114 publications

References 15 publications

Agency in Mid-air Interfaces

Agency in Mid-air Interfaces

Plug-and-Play Gesture Control Using Muscle and Motion Sensors

Tactile Signatures and Hand Motion Intent Recognition for Wearable Assistive Devices

Contact Info

Product

Resources

About