Research Projects
Fabric-based robotic skin using multimodal sensing modules
Jul. 2022 - Jan. 2024
A robotic skin deploying two types of transducers (electrodes and encapsulated microphones) for complementary sensibilities on tactile stimuli.
Two transducers assembled into a multimodal sensing module (MSM) using a vented screw.
Multilayered fabric consisting tranducing layer features piezoresistivity and transmits elicited vibrations.
MSMs distributed across sensory domain to perform electrical resistance tomography (ERT) and acoustic super-resolution (ASR) to each localise low and high temporal tactile stimuli.
Applied on a robotic arm and perceives wide range of touches from pressing (dominantly low temporal stimulus in a static force) to tickling (dominantly high temporal stimulus in dynamic vibrations).
Biomimetic elastomeric robot skin using electrical impedance and acoustic tomography for tactile sensing
Mar. 2021 - Jun. 2022
Skin-inspired multi-layer structure is fabricated using silicone elastomer and ionic hydrogel.
The ionic hydrogel layer is used as a medium for tactile sensing.
The tomographic imaging methods are utilised to reconstruct a multi-modal tactile image from measurement data.
The developed robotic skin ca be repaired using chitosan topohesive and silicone adhesive, even after severe damage (incision)
Related publication : [Sci. Ro. 7.67]
Robotic skin using microphones for dynamic touch perception and touch classification
Jan. 2019 - Nov. 2022
A robotic skin using sparsely distributed microphones is developed to perceive dynamic touch by collecting vibrations induced by a touch.
Vibrations collected by distributed microphones are processed to localise a touch on a large surface with a few transducers.
Spatiotemporal properties of microphone signals are analysed with CNN to classify touches (pat, rub, etc.).
The developed skin enriches tactile communication between humans and robotic systems by simultaneously interpreting a touch in real-time.
Related publications : [ICRA 2021] [TMech 29.4]
Intention recognition using surface electromyography
Mar. 2018 - Dec. 2021
sEMG is widely used for intention recognition due to its early detection.
Various sensing modules and signal processing methods are implemented depending on the subject and a target application.
For force enhancement in a healthy subject, single-channel electrodes are attached on various muscles to recognise multiple complex states.
For hand motion rehabilitation in a stroke patient, high-density electrodes are used to detect an intention in binary classes from a poor signal quality.
Related publications : [FITEE 2019] [ICORR 2022] [EMBC 2023]