用于重建物理和虚拟抓取的可重构数据手套

In this work,we present a reconfigurable data glove design to capture different modes of human hand-object interactions,which are critical in training embodied artificial intelligence(AI)agents for fine manipulation tasks.To achieve various downstream tasks with distinct features,our reconfigurable data glove operates in three modes sharing a unified backbone design that reconstructs hand gestures in real time.In the tactile-sensing mode,the glove system aggregates manipulation force via customized force sensors made from a soft and thin piezoresistive material;this design minimizes interference during complex hand movements.The virtual reality(VR)mode enables real-time interaction in a physically plausible fashion:A caging-based approach is devised to determine stable grasps by detecting collision events.Leveraging a state-of-the-art finite element method,the simulation mode collects data on fine-grained four-dimensionalmanipulation events comprising hand and object motions in three-dimensional space and how the object's physical properties(e.g.,stress and energy)change in accordance with manipulation over time.Notably,the glove system presented here is the first to use high-fidelity simulation to investigate the unobservable physical and causal factors behind manipulation actions.In a series of experiments,we characterize our data glove in terms of individual sensors and the overall system.More specifically,we evaluate the system's three modes by①recording hand gestures and associated forces,②improving manipulation fluency in VR,and③producing realistic simulation effects of various tool uses,respectively.Based on these three modes,our reconfigurable data glove collects and reconstructs fine-grained human grasp data in both physical and virtual environments,thereby opening up new avenues for the learning of manipulation skills for embodied AI agents.

Recent advances in multimodal sensing integration and decoupling strategies for tactile perception

Human skin perceives external environmental stimulus by the synergies between the subcutaneous tactile corpuscles.Soft electronics with multiple sensing capabilities by mimicking the function of human skin are of significance in health monitoring and artificial sensation.The last decade has witnessed unprecedented development and convergence between multimodal tactile sensing devices and soft bioelectronics.Despite these advances,traditional flexible electronics achieve multimodal tactile sensing for pressure,strain,temperature,and humidity by integrating monomodal sensing devices together.This strategy results in high energy consumption,limited integration,and complex manufacturing process.Various multimodal sensors and crosstalk-free sensing mechanisms have been proposed to bridge the gap between natural sensory system and artificial perceptual system.In this review,we provide a comprehensive summary of tactile sensing mechanism,integration design principles,signal-decoupling strategies,and current applications for multimodal tactile perception.Finally,we highlight the current challenges and present the future perspectives to promote the development of multimodal tactile perception.

Artificial Tactile Sense Technique for Predicting Beef Tenderness Based on FS Pressure Sensor

We present a rapid system for predicting beef tenderness by mimicking the human tactile sense. The detection system includes a FS pressure sensor, a power supply conversion circuit, a signal amplifier and a box in which the sample is mounted. A sample of raw Longissimus dorsi (LD) muscle is placed in the measuring box; then a rod connected to the pressure sensor is pressed into the beef sample to a given depth; the reaction force of the beef sample is measured and used to predict the tenderness. Sensory evaluation and Warner-Bratzler Shear Force (WBSF) evaluation of samples from the same LD muscle are used for comparison. The new detection system agrees with established procedure 95% of the time, and the time to test a sample is less than 5 minutes.

Research on control technology of elderly-assistant & walking-assistant robot based on tactile-slip sensation

In this paper,according to the old people's physical characteristics and their technical requirements for comfort and mastery when operating the robot,a control approach driven by tactile and slip senses is investigated to control the elderly-assistant & walking-assistant robot. First,on the basis of the proposed driving control system program of tactile and slip,a detection system of tactile and slip senses are designed. Based on the tactile and slip feature representation and extraction,an improved classification and recognition method is proposed which combines K-nearest neighbor (KNN) algorithm and K-means algorithm. And then,a robot control system based on TMS320F2812 is designed in this paper,including its hardware and software design. Then,a moving control method including the fuzzy adaptive control algorithm is presented for the walking-assistant robot to realize some different moving properties. At last,by the experimental verification in the walking-assistant robot,the research results show that the tactile and slip senses detection and recognition method is effective,and the whole control system has good feasibility and adaptability.

Interactive Display under the Influence of Tactile Sense

Humans have a variety of sense in dynamic environment,and tactile sensation is an important way apperceiving the world.It enhances the process of experience and the interaction between humans and environment.However,vision as a dominant sense impairs the variety of sense.In the display design,current designers often put more emphasis on structure,form,color,and such other visual elements,consequently neglect the importance of the tactile sensation,which weakens real experience of humans.

Advanced polymer materials-based electronic skins for tactile and non-contact sensing applications

Recently,polymer materials have been at the forefront of other materials in building high-performance flexible electronic skin(e-skin)devices due to con-spicuous advantages including excellent mechanical flexibility,good compatibil-ity,and high plasticity.However,most research works just paid considerable attention and effort to the design,construction,and possible application of e-skins that reproduce the tactile perception of the human skin sensory system.Compared with tactile sensing devices,e-skins that aim to imitate the non-contact sensing features in the sensory system of human skin tend to avoid undesired issues such as bacteria spreading and mechanical wear.To further promote the development of e-skins to the human skin sensory system where tactile perception and non-contact sensing complement each other,significant progress and advances have been achieved in the field of polymer materials enabled e-skins for both tactile perception and non-contact sensing applications.In this review,the latest progress in polymer material-based e-skins with regard to tactile,non-contact sensing capabilities and their practical applications are introduced.The fabrication strategies of polymer materials and their role in building high-performance e-skins for tactile and non-contact sensing are highlighted.Furthermore,we also review the research works that integrated the polymer-based tactile and non-contact e-skins into robots and prostheses,smart gloves,and VR/AR devices and addressed some representative problems to dem-onstrate their suitability in practical applications in human–machine interac-tions.Finally,the current challenges in the construction of high-performance tactile and non-contact e-skins are highlighted and promising properties in this direction,by taking advantage of the polymer materials,are outlined.

Emerging flexible and wearable physical sensing platforms for healthcare and biomedical applications

There are now numerous emerging flexible and wearable sensing technologies that can perform a myriad of physical and physiological measurements.Rapid advances in developing and implementing such sensors in the last several years have demonstrated the growing significance and potential utility of this unique class of sensing platforms.Applications include wearable consumer electronics,soft robotics,medical prosthetics,electronic skin,and health monitoring.In this review,we provide a state-ofthe-art overview of the emerging flexible and wearable sensing platforms for healthcare and biomedical applications.We first introduce the selection of flexible and stretchable materials and the fabrication of sensors based on these materials.We then compare the different solid-state and liquid-state physical sensing platforms and examine the mechanical deformation-based working mechanisms of these sensors.We also highlight some of the exciting applications of flexible and wearable physical sensors in emerging healthcare and biomedical applications,in particular for artificial electronic skins,physiological health monitoring and assessment,and therapeutic and drug delivery.Finally,we conclude this review by offering some insight into the challenges and opportunities facing this field.

The Merits of Passive Compliant Joints in Legged Locomotion： Fast Learning, Superior Energy Efficiency and Versatile Sensing in a Quadruped Robot

A quadruped robot with four actuated hip joints and four passive highly compliant knee joints is used to demonstrate the potential of underactuation from two standpoints： learning locomotion and perception. First, we show that： （i） forward locomotion on flat ground can be learned rapidly （minutes of optimization time）; （ii） a simulation study reveals that a passive knee configuration leads to faster, more stable, and more efficient locomotion than a variant of the robot with active knees; （iii） the robot is capable of learning turning gaits as well. The merits of underactuation （reduced controller complexity, weight, and energy consumption） are thus preserved without compromising the versatility of behavior. Direct optimization on the reduced space of active joints leads to effective learning of model-free controllers. Second, we find passive compliant joints with po- tentiometers to effectively complement inertial sensors in a velocity estimation task and to outperform inertial and pressure sensors in a terrain detection task. Encoders on passive compliant joints thus constitute a cheap and compact but powerful sensing device that gauges joint position and force/torque, and -- if mounted more distally than the last actuated joints in a legged robot -- it delivers valuable information about the interaction of the robot with the ground.

1D-2D nanohybrid-based textile strain sensor to boost multiscale deformative motion sensing performance

The development of strain sensors with both superior sensitivity(gauge factor(GF)>100)and broad strain-sensing range(>50%strain)is still a grand challenge.Materials,which demonstrate significant structural deformation under microscale motion,are required to offer high sensitivity.Structural connection of materials upon large-scale motion is demanded to widen strainsensing range.However,it is hard to achieve both features simultaneously.Herein,we design a crepe roll structure-inspired textile yarn-based strain sensor with one-dimensional(1D)-two-dimensional(2D)nanohybrid strain-sensing sheath,which possesses superior stretchability.This ultrastretchable strain sensor exhibits a wide and stable strain-sensing range from microscale to large-scale(0.01%–125%),and superior sensitivity(GF of 139.6 and 198.8 at 0.01%and 125%,respectively)simultaneously.The strain sensor is structurally constructed by a superelastic 1D-structured core elastomer polyurethane yarn(PUY),a novel high conductive crepe roll-structured(CRS)1D-2D nanohybrid multilayer sheath which assembled by 1D nanomaterials silver nanowires(AgNWs)working as bridges to connect adjacent layers and 2D nanomaterials graphene nanoplates(GNPs)offering brittle lamellar structure,and a thin polydopamine(PDA)wrapping layer providing protection in exterior environment.During the stretching/deformation process,microcracks originate and propagate in the GNPs lamellar structure enable resistance to change significantly,while AgNWs bridge adjacent GNPs to accommodate applied stress partially and boost strain.The 1D crepe roll structure-inspired strain sensor demonstrates multifunctionality in multiscale deformative motion detection,such as respiratory motions of Sprague–Dawleyw rat,flexible digital display,and proprioception of multi-joint finger bending and antagonistic flexion/extension motions of its flexible continuum body.

Embodied tactile perception and learning

Various living creatures exhibit embodiment intelligence,which is reflected by a collaborative interaction of the brain,body,and environment.The actual behavior of embodiment intelligence is generated by a continuous and dynamic interaction between a subject and the environment through information perception and physical manipulation.The physical interaction between a robot and the environment is the basis for realizing embodied perception and learning.Tactile information plays a critical role in this physical interaction process.It can be used to ensure safety,stability,and compliance,and can provide unique information that is difficult to capture using other perception modalities.However,due to the limitations of existing sensors and perception and learning methods,the development of robotic tactile research lags significantly behind other sensing modalities,such as vision and hearing,thereby seriously restricting the development of robotic embodiment intelligence.This paper presents the current challenges related to robotic tactile embodiment intelligence and reviews the theory and methods of robotic embodied tactile intelligence.Tactile perception and learning methods for embodiment intelligence can be designed based on the development of new large-scale tactile array sensing devices,with the aim to make breakthroughs in the neuromorphic computing technology of tactile intelligence.

Additive manufacturing of flexible 3D surface electrodes for electrostatic adhesion control and smart robotic gripping

Mechanically flexible surface structures with embedded conductive electrodes are attractive in contact-based devices,such as those used in reversible dry/adhesion and tactile sensing.Geometrical shapes of the surface structures strongly determine the contact behavior and therefore the resulting adhesion and sensing functionalities;however,available features are often restricted by fabrication techniques.Here,we additively manufacture elastomeric structure arrays with diverse angles,shapes,and sizes;this is followed by integration of conductive nanowire electrodes.The fabricated flexible three-dimensional(3D)surface electrodes are mechanically compliant and electrically conductive,providing multifunctional ability to sense touch and to switch adhesion via a combined effect of shear-and electro adhesives.We designed soft,anisotropic flexible structures to mimic the gecko’s reversible adhesion,which is governed by van der Waals forces;we integrated nanowires to further manipulate the localized electric field among the adjacent flexible 3D surface electrodes to provide additional means to digitally tune the electrostatic attraction at the contact interface.In addition,the composite surface can sense the contact force via capacitive sensing.Using our flexible 3D surface electrodes,we demonstrate a complete soft gripper that can grasp diverse convex objects,including metal,ceramic,and plastic products,as well as fresh fruits,and that exhibits 72%greater electroadhesive gripping force when voltage is applied.

Active shape reconstruction using a novel visuotactile palm sensor

Tactile sensing enables high-precision 3D shape perception when vision is limited.However,tactilebased shape reconstruction remains a challenging problem.In this paper,a novel visuotactile sensor,GelStereo Palm 2.0,is proposed to better capture 3D contact geometry.Leveraging the dense tactile point cloud captured by GelStereo Palm 2.0,an active shape reconstruction pipeline is presented to achieve accurate and efficient 3D shape reconstruction on irregular surfaces.GelStereo Palm 2.0 achieves a spatial resolution of 1.5 mm and a reconstruction accuracy of 0.3 mm.The accuracy of the proposed active shape reconstruction pipeline reaches 2.3 mm within 18 explorations.The proposed method has potential applications in the shape reconstruction of transparent or underwater objects.