Human machine interface (HMI) has recently received more and more attentions as it would provide a media for human to interact with outside environments to promote people's lifestyles. Flexible and stretchable electronics have been widely laminated onto the surface of human skin, gloves, or other soft objects for collecting the deformation signal. The paper proposes an HMI based on stretchable smart glove embedded with soft piezoresistive strain sensors for signal classification and controlling the motion of robot fingers. The stretchable polydimethylsiloxane-carbon black (PDMS-CB) strain sensors satisfy larger deformation (>30%) which is validated by FEM simulation and experiments. The morphology of the soft and complex objects is detected by the smart glove when fingers touch the objects. Feature signals are extracted with the different finger gestures by the soft strain sensors laminated onto different fingers. Human robot interaction (HRI) algorithm is proposed to analyze and recognize the finger gestures for controlling the motion of the robot fingers. Experiments demonstrate that the motion of robot finger is successfully controlled remotely by the smart glove embedded with PDMS-CB strain sensors. Exploring HRI capabilities into the stretchable smart glove represents promising research directions in the future.
Soft electronics have been widely applied to wearable electronics, hand gesture detection and human robot interaction (HRI). Soft wrist-worn sensor system (SWSS) with electromyography (EMG), strain/pressure sensing abilities has been created for continuous hand gesture recognition, which includes multi-source data sensing, data collection and process, and wireless communication. SWSS is conformal contact with skin surface as the softness of SWSS, and it would improve the wearability with the wrist during long-term hand gesture monitoring. Linear discriminant analysis (LDA) and support vector machines (SVM) algorithms are applied to hand gesture recognition with average accuracy 83.67%, 86.8% for Group #1 (wrist flexion (WF), wrist extension (WE), finger flexion (FF), finger extension (FE), radial deviation (RD), and ulnar deviation (UD)) and 84.71%, 88.53% for Group #2 (sign language 0–9 digits), respectively. It is found that the recognition accuracy has just a little decreased during the long-term hand gesture detection at different sessions (at initial time, one day after, three days after and seven days after). This paper demonstrated the feasibility of gesture recognition via SWSS on wrist, and it could be integrated into wrist-worn electronic system for human robot interaction.
11 September 2017 in IEEE Internet of Things Journal
Exposure to air pollution poses a significant risk to human health, particularly to urban dwellers. When correlated with individual health outcomes, high resolution information on human mobility, and the spatial and temporal distribution of the pollutants can lead to a better understanding of the effects of pollution exposure. People-centric sensing is normally carried out by data sharing through a central cloud server. This system architecture is not designed to serve the ever-growing number of high fidelity connected devices, particularly when crowdsourcing urban data on location and environmental conditions. Here, we outline an architecture for a people-centric and cognitive Internet of Things (PIoT) environmental sensing platform, which involves closed loops of interactions among people nodes and physical devices as well as servers and recommendations on device connections by cognitive computing. Taking advantage of smart objects and virtual node technology in PIoT, an algorithm to aggregate on-demand user data from smart devices is proposed. A PIoT prototype sensing system is designed and deployed to measure the space-time distribution of particulate matter in air (PM 2.5 ), and mobility counts, for quantifying personal exposure to air pollution. A case study of particulate matter PM 2.5 exposure in New York City is presented to illustrate the potential application of people-centric measurement system and data analysis.
As flexible and wearable electronics play more and more important role in smart watches, smart glass and virtual reality, and the power supply to the wearable electronics have been revealed more attentions for long-term usage and continuous healthy monitoring. To overcome the challenge, flexible self-powered BTO-PVDF/PDMS piezoelectric-triboelectric electric hybrid generators (BPP-HNG) are developed to human gesture monitoring and human machine interaction (HMI) application without external power supply. BPP-HNG based on BTO-PVDF and PDMS films are prepared by sol–gel and spin-coating method. When the BTO content is 20 wt.%, BPP-HNG exhibits better electrical performance with an output voltage of 20.51 V. A real-time gesture monitoring system is designed and developed to human machine interaction, which is able to control the motion of robot finger through BPP-HNG. BPP-HNG could monitor and recognize various gestures in real time, enabling synchronization between the human hand and the robot’s hand. With the convergence of AI technology and big data, BPP-HNG based HMI technology is expected to realize the potential of smarter and more intuitive interactions.
15 November 2021 in IEEE Transactions on Industrial Electronics
This article develops a gait planning method for underactuated bipedal robot on uneven and compliant terrain. First, we employ a linear spring-damper model to describe foot-ground compliant contact, and establish a decoupled robot–ground three-dimensional dynamic mode. Second, based on a velocity-based bipedal stability definition and human walking characteristics, we propose a gait planning method to realize underactuated bipedal walking on uneven and compliant terrain. We decouple bipedal gait planning into sagittal and lateral master-slave ones. By planning the motion state of Center-of-Mass (CoM) of a robot, we make the movement of lateral and sagittal coincident such that bipedal walking is realized. Finally, underactuated bipedal walking with an average walking speed of 0.216 m/s and a step length of 183.9 mm is realized on uneven terrain where the maximum height of unevenness is 32 mm. The experimental results show that underactuated bipedal walking can be realized on uneven and compliant terrain by using the proposed method to control robot CoM and track its desired velocity.