Recognizing human interactions in RGB videos is a critical task in computer vision,with applications in video surveillance.Existing deep learning-based architectures have achieved strong results,but are computationall...Recognizing human interactions in RGB videos is a critical task in computer vision,with applications in video surveillance.Existing deep learning-based architectures have achieved strong results,but are computationally intensive,sensitive to video resolution changes and often fail in crowded scenes.We propose a novel hybrid system that is computationally efficient,robust to degraded video quality and able to filter out irrelevant individuals,making it suitable for real-life use.The system leverages multi-modal handcrafted features for interaction representation and a deep learning classifier for capturing complex dependencies.Using Mask R-CNN and YOLO11-Pose,we extract grayscale silhouettes and keypoint coordinates of interacting individuals,while filtering out irrelevant individuals using a proposed algorithm.From these,we extract silhouette-based features(local ternary pattern and histogram of optical flow)and keypoint-based features(distances,angles and velocities)that capture distinct spatial and temporal information.A Bidirectional Long Short-Term Memory network(BiLSTM)then classifies the interactions.Extensive experiments on the UT Interaction,SBU Kinect Interaction and the ISR-UOL 3D social activity datasets demonstrate that our system achieves competitive accuracy.They also validate the effectiveness of the chosen features and classifier,along with the proposed system’s computational efficiency and robustness to occlusion.展开更多
Accurate fingertip detection is critical for translating hand gestures into actionable commands in vision-based human‒computer interaction(HCI)systems.However,challenges such as complex backgrounds,dynamic hand postur...Accurate fingertip detection is critical for translating hand gestures into actionable commands in vision-based human‒computer interaction(HCI)systems.However,challenges such as complex backgrounds,dynamic hand postures,and real-time processing constraints hinder reliable detection.This paper introduces a robust framework integrating three key innovations:(1)an adaptive Gaussian mixture model(GMM)enhanced with neighborhood pixel connectivity for precise motion extraction;(2)a weighted YCbCr color-space shadow removal algorithm to eliminate false positives;and(3)a centroid distance method refined with circularity constraints for accurate fingertip localization.Extensive experiments demonstrate a recognition accuracy of 97.26%across diverse scenarios,including varying illuminations,occlusions,and hand rotations.The algorithm processes each frame in 23.43 ms on average,satisfying real-time requirements.Comparative evaluations against state-of-the-art methods reveal significant improvements in precision(8.3%),recall(6.1%),and F-measure(7.8%).This work advances HCI applications such as virtual keyboards,gesture-controlled interfaces,and augmented reality systems.展开更多
Video action recognition(VAR)aims to analyze dynamic behaviors in videos and achieve semantic understanding.VAR faces challenges such as temporal dynamics,action-scene coupling,and the complexity of human interactions...Video action recognition(VAR)aims to analyze dynamic behaviors in videos and achieve semantic understanding.VAR faces challenges such as temporal dynamics,action-scene coupling,and the complexity of human interactions.Existing methods can be categorized into motion-level,event-level,and story-level ones based on spatiotemporal granularity.However,single-modal approaches struggle to capture complex behavioral semantics and human factors.Therefore,in recent years,vision-language models(VLMs)have been introduced into this field,providing new research perspectives for VAR.In this paper,we systematically review spatiotemporal hierarchical methods in VAR and explore how the introduction of large models has advanced the field.Additionally,we propose the concept of“Factor”to identify and integrate key information from both visual and textual modalities,enhancing multimodal alignment.We also summarize various multimodal alignment methods and provide in-depth analysis and insights into future research directions.展开更多
Background Regular physical training induces adaptive effects across multiple organ systems,highlighting the existence of inter-organ communication networks.However,the molecular mechanisms underlying both exercise-in...Background Regular physical training induces adaptive effects across multiple organ systems,highlighting the existence of inter-organ communication networks.However,the molecular mechanisms underlying both exercise-induced adaptations and organ-to-organ signaling are not fully characterized.Circulating extracellular vesicles(EVs),including exosomes,carry molecules like microRNAs(miRNAs)that may mediate tissue crosstalk.This study aimed to identify specific exercise training-responsive miRNAs that affect skeletal muscle function.Methods miRNA expression profiles of serum-derived EVs were analyzed in healthy young individuals before and after 3 weeks endurance exercise training.Exercise training-responsive miRNAs were then validated for a functional role in cellular metabolic processes in human myotubes.Results We identified several exercise training-responsive miRNAs within exosome-rich EVs in serum,including miR-136-3p.In human myotubes,miR-136-3p enhanced glucose uptake and targeted the nardilysin convertase(NRDC)gene.Transfection of miR-136-3p or silencing of NRDC induced a shift towards glycolytic metabolism in mitochondria and modulated gene expressions related to myogenesis.Pancreatic islets were identified as a potential source of miR-136-3p based on in silico analysis of gene expression and a molecular analysis of conditioned media from isolated pancreatic islets.Conclusion MiR-136-3p is an endurance training-responsive molecular transducer that modulates glucose metabolism and cellular proliferation in myocytes.Associated with EVs,extracellular miR-136-3p may serve as a molecular messenger to communicate islet–skeletal muscle crosstalk after exercise.Extracellular miR-136-3p may serve as a molecular messenger to communicate islet–skeletal muscle crosstalk.Our results highlight a miRNA-mediated mechanism that participates in inter-organ communication to fine tune the metabolic adaptations to exercise.展开更多
A complete characterization of the behavior in human-robot interactions(HRI) includes both: the behavioral dynamics and the control laws that characterize how the behavior is regulated with the perception data. In thi...A complete characterization of the behavior in human-robot interactions(HRI) includes both: the behavioral dynamics and the control laws that characterize how the behavior is regulated with the perception data. In this way, this work proposes a leader-follower coordinate control based on an impedance control that allows to establish a dynamic relation between social forces and motion error. For this, a scheme is presented to identify the impedance based on fictitious social forces, which are described by distance-based potential fields.As part of the validation procedure, we present an experimental comparison to select the better of two different fictitious force structures. The criteria are determined by two qualities: least impedance errors during the validation procedure and least parameter variance during the recursive estimation procedure.Finally, with the best fictitious force and its identified impedance,an impedance control is designed for a mobile robot Pioneer 3AT,which is programmed to follow a human in a structured scenario.According to results, and under the hypothesis that moving like humans will be acceptable by humans, it is believed that the proposed control improves the social acceptance of the robot for this kind of interaction.展开更多
AIM: To investigate the biological function of 14-3-3σ protein and to look for proteins that interact with 14-3-3σ protein in colon cancer stem cells. METHODS: Reverse transcription polymerase chain reaction was per...AIM: To investigate the biological function of 14-3-3σ protein and to look for proteins that interact with 14-3-3σ protein in colon cancer stem cells. METHODS: Reverse transcription polymerase chain reaction was performed to amplify the 14-3-3σ gene from the mRNA of colon cancer stem cells. The gene was then cloned into the pGEM-T vector. After being sequenced, the target gene 14-3-3σ was cut from the pGEM-T vector and cloned into the pGBKT7 yeast expression plasmid. Then, the bait plasmid pGBKT7-14-3-3σ was transformed into the yeast strain AH109. After the expression of the pGBKT7-14-3-3σ fusion protein in the AH109 yeast strain was accomplished, a yeast two-hybrid screening assay was performed by mating AH109 with Y187 that contained a HeLa cDNA library plasmid. The interaction between the 14-3-3σ protein and the proteins obtained from positive colonies was further confirmed by repeating the yeast two-hybridscreen. After extracting and sequencing the plasmids from the positive colonies, we performed a bioinformatics analysis. A coimmunoprecipitation assay was performed to confirm the interaction between 14-3-3σ and the proteins obtained from the positive colonies. Finally, we constructed 14-3-3σ and potassium channel modulatory factor 1 (KCMF1) siRNA expression plasmids and transfected them into colon cancer stem cells. RESULTS: The bait plasmid pGBKT7-14-3-3σ was constructed successfully, and the 14-3-3σ protein had no toxic or autonomous activation effect on the yeast. Nineteen true-positive colonies were selected and sequenced, and their full-length sequences were obtained. We searched for homologous DNA sequences for these sequences from GenBank. Among the positive colonies, four coding genes with known functions were obtained, including KCMF1 , quinone oxidore-ductase (NQO2 ), hydroxyisobutyrate dehydrogenase (HIBADH ) and 14-3-3σ . For the subsequent coimmu-noprecipitation assay, the plasmids PCDEF-Flag-14-3-3σ, PCDEF-Myc-KCMF1, PCDEF-Myc-NQO2 and PCDEF-Myc-HIBADH were successfully constructed, and the sequences were further confirmed by DNA sequencing. The Fugene 6 reagent was used to transfect the plasmids, and fluorescence-activated cell sorting analysis showed the transfection efficiency was 97.8% after 48 h. The HEK 293FT cells showed the stable expression of the PCDEF-Flag-14-3-3σ, PCDEF-Myc-KCMF1, PCDEF-Myc-NQO2 and PCDEF-Myc-HIBADH plasmids. After anti-Myc antibody immunoprecipitation with Myc-KCMF1, Myc-NQO2 and Myc-HIBADH from cell lysates, the presence of Flag-14-3-3σ protein in the immuno-precipitated complex was determined by western blot analysis. The knock-down expression of the 14-3-3σ and KCMF1 proteins significantly inhibited cell proliferation and colony formation of SW1116csc. CONCLUSION: Genes of the proteins that interactedwith 14-3-3σ were successfully screened from a HeLa cDNA library. KCMF1 and 14-3-3σ protein may affect the proliferation and colony formation of human colon cancer stem cells.展开更多
A series of“half-sandwich”bis(imino)pyridyl iron complexes with a substituted 8-(p-Xphenyl)naphthylamine(X=OMe,Me,CF3)was designed and synthesized by combining weakπ-πinteraction with steric and electronic tunings...A series of“half-sandwich”bis(imino)pyridyl iron complexes with a substituted 8-(p-Xphenyl)naphthylamine(X=OMe,Me,CF3)was designed and synthesized by combining weakπ-πinteraction with steric and electronic tunings.The weak noncovalentπ-πinteraction as well as the steric and electronic effects of bis(imino)pyridyl iron complexes were identified by experimental analyses and calculations.The roles of weakπ-πinteraction,steric bulk,and electronic tuning on the ethylene polymerization performance of bis(imino)pyridyl iron catalysts were studied in detail.The combination ofπ-πinteraction with steric and electronic tunings can access to thermally stable bis(imino)pyridyl iron at 130°C.展开更多
Photocatalysis is one of the most capable green energy techniques for sustainable solar-to-chemical energy conversion.However,the speedy recombination of photocarriers remains a critical bottleneck in achieving high p...Photocatalysis is one of the most capable green energy techniques for sustainable solar-to-chemical energy conversion.However,the speedy recombination of photocarriers remains a critical bottleneck in achieving high photocatalytic efficiency.Recent advancements have underscored the pivotal role of internal and external electrostatic fields in regulating charge dynamics within semiconductor systems.This review highlights the emerging strategy of employing non-covalent electrostatic interactions to modulate photocatalytic behavior.Internally,spontaneous polarization within polar or ferroelectric semiconductors facilitates efficient charge separation through built-in electric fields.Externally applied mechanical stress and magnetic fields further augment these effects via piezoelectric and magnetoelectric phenomena,offering dynamic control over carrier transport.Beyond macroscopic fields,subtle non-covalent electrostatic forces,such as hydrogen bonds,van der Waals forces,andπ-πstacking,significantly influence surface adsorption,electronic structure modulation,and interfacial charge transfer processes.Combining these external influences with semiconductor properties,we can develop innovative strategies to stabilize the reactive intermediates and reduce the recombination pathways,improving the practical implications of these synergistic effects in energy conversion and environmental remediation.This review systematically elucidates the mechanistic contributions of internal polarization and external fields to the modulation of non-covalent electrostatic forces in photocatalytic systems.Emphasis is placed on material design strategies that integrate structural polarity,field-responsive behavior,and interfacial engineering to achieve superior photocatalytic performance.Finally,the prospects of non-covalent electrostatic interactions in photocatalysis are discussed,providing insights to guide the rational development of more efficient and sustainable photocatalytic systems.展开更多
This article describes a pilot study aiming at generating social interactions between a humanoid robot and adolescents with autism spectrum disorder (ASD), through the practice of a gesture imitation game. The partici...This article describes a pilot study aiming at generating social interactions between a humanoid robot and adolescents with autism spectrum disorder (ASD), through the practice of a gesture imitation game. The participants were a 17-year-old young lady with ASD and intellectual deficit, and a control participant: a preadolescent with ASD but no intellectual deficit (Asperger syndrome). The game is comprised of four phases: greetings, pairing, imitation, and closing. Field educators were involved, playing specific roles: visual or physical inciter. The use of a robot allows for catching the participants’ attention, playing the imitation game for a longer period of time than with a human partner, and preventing the game partner’s negative facial expressions resulting from tiredness, impatience, or boredom. The participants’ behavior was observed in terms of initial approach towards the robot, positioning relative to the robot in terms of distance and orientation, reactions to the robot’s voice or moves, signs of happiness, and imitation attempts. Results suggest a more and more natural approach towards the robot during the sessions, as well as a higher level of social interaction, based on the variations of the parameters listed above. We use these preliminary results to draw the next steps of our research work as well as identify further perspectives, with this aim in mind: improving social interactions with adolescents with ASD and intellectual deficit, allowing for better integration of these people into our societies.展开更多
In this paper,we present an RFID based human and Unmanned Aerial Vehicle(UAV)Interaction system,termed RFHUI,to provide an intuitive and easy-to-operate method to navigate a UAV in an indoor environment.It relies on t...In this paper,we present an RFID based human and Unmanned Aerial Vehicle(UAV)Interaction system,termed RFHUI,to provide an intuitive and easy-to-operate method to navigate a UAV in an indoor environment.It relies on the passive Radio-Frequency IDentification(RFID)technology to precisely track the pose of a handheld controller,and then transfer the pose information to navigate the UAV.A prototype of the handheld controller is created by attaching three or more Ultra High Frequency(UHF)RFID tags to a board.A Commercial Off-The-Shelf(COTS)RFID reader with multiple antennas is deployed to collect the observations of the tags.First,the precise positions of all the tags can be obtained by our proposed method,which leverages a Bayesian filter and Channel State Information(CSI)phase measurements collected from the RFID reader.Second,we introduce a Singular Value Decomposition(SVD)based approach to obtain a 6-DoF(Degrees of Freedom)pose of the controller from estimated positions of the tags.Furthermore,the pose of the controller can be precisely tracked in a real-time manner,while the user moves the controller.Finally,control commands will be generated from the controller's pose and sent to the UAV for navigation.The performance of the RFHUI is evaluated by several experiments.The results show that it provides precise poses with 0.045m mean error in position and 2.5∘mean error in orientation for the controller,and enables the controller to precisely and intuitively navigate the UAV in an indoor environment.展开更多
Recent advancements in the Internet of Things IoT and cloud computing have paved the way for mobile Healthcare(mHealthcare)services.A patient within the hospital is monitored by several devices.Moreover,upon leaving t...Recent advancements in the Internet of Things IoT and cloud computing have paved the way for mobile Healthcare(mHealthcare)services.A patient within the hospital is monitored by several devices.Moreover,upon leaving the hospital,the patient can be remotely monitored whether directly using body wearable sensors or using a smartphone equipped with sensors to monitor different user-health parameters.This raises potential challenges for intelligent monitoring of patient's health.In this paper,an improved architecture for smart mHealthcare is proposed that is supported by HCI design principles.The HCI also provides the support for the User-Centric Design(UCD)for smart mHealthcare models.Furthermore,the HCI along with IoT's(Internet of Things)5-layered architecture has the potential of improving User Experience(UX)in mHealthcare design and help saving lives.The intelligent mHealthcare system is supported by the IoT sensing and communication layers and health care providers are supported by the application layer for the medical,behavioral,and health-related information.Health care providers and users are further supported by an intelligent layer performing critical situation assessment and performing a multi-modal communication using an intelligent assistant.The HCI design focuses on the ease-of-use,including user experience and safety,alarms,and error-resistant displays of the end-user,and improves user's experience and user satisfaction.展开更多
To solve the problem of risk identification and quantitative assessment for human-computer interaction(HCI)in complex avionics systems,an HCI safety analysis framework based on system-theoretical process analysis(STPA...To solve the problem of risk identification and quantitative assessment for human-computer interaction(HCI)in complex avionics systems,an HCI safety analysis framework based on system-theoretical process analysis(STPA)and cognitive reliability and error analysis method(CREAM)is proposed.STPACREAM can identify unsafe control actions and find the causal path during the interaction of avionics systems and pilot with the help of formal verification tools automatically.The common performance conditions(CPC)of avionics systems in the aviation environment is established and a quantitative analysis of human failure is carried out.Taking the head-up display(HUD)system interaction process as an example,a case analysis is carried out,the layered safety control structure and formal model of the HUD interaction process are established.For the interactive behavior“Pilots approaching with HUD”,four unsafe control actions and35 causal scenarios are identified and the impact of common performance conditions at different levels on the pilot decision model are analyzed.The results show that HUD's HCI level gradually improves as the scores of CPC increase,and the quality of crew member cooperation and time sufficiency of the task is the key to its HCI.Through case analysis,it is shown that STPACREAM can quantitatively assess the hazards in HCI and identify the key factors that impact safety.展开更多
Humans and animals are in regular and at times close contact in modern intensive farming systems.The quality of human-animal interactions can have a profound impact on the productivity and welfare of farm animals.Inte...Humans and animals are in regular and at times close contact in modern intensive farming systems.The quality of human-animal interactions can have a profound impact on the productivity and welfare of farm animals.Interactions by humans may be neutral,positive or negative in nature.Regular pleasant contact with humans may result in desirable alterations in the physiology,behaviour,health and productivity of farm animals.On the contrary,animals that were subjected to aversive human contact were highly fearful of humans and their growth and reproductive performance could be compromised.Farm animals are particularly sensitive to human stimulation that occurs early in life,while many systems of the animals are still developing.This may have long-lasting impact and could possibly modify their genetic potential.The question as to how human contact can have a positive impact on responses to stressors,and productivity is not well understood.Recent work in our laboratory suggested that pleasant human contact may alter ability to tolerate various stressors through enhanced heat shock protein（hsp） 70 expression.The induction of hsp is often associated with increased tolerance to environmental stressors and disease resistance in animals.The attitude and consequent behaviour of stockpeople affect the animals＇ fear of human which eventually influence animals＇ productivity and welfare.Other than attitude and behaviour,technical skills,knowledge,job motivation,commitment and job satisfaction are prerequisites for high job performance.展开更多
G-quadruplex ligands have been accepted as potential therapeutic agents for anticancer treatment. Thioflavin T （ThT）, a highly selective G-quadruplex ligand, can bind G-quadruplex with a fluorescent light-up signal ...G-quadruplex ligands have been accepted as potential therapeutic agents for anticancer treatment. Thioflavin T （ThT）, a highly selective G-quadruplex ligand, can bind G-quadruplex with a fluorescent light-up signal change and high specificity against DNA duplex. However, there are still different opinions that ThT induces/stabilizes G-quadruplex foldings/topologies in human telomere sequence. Here, a sensitive single-molecule nanopore technology was utilized to analyze the interactions between human telomeric DNA （Tel DNA） and ThT. Both translocation time and current blockade were measured to investigate the translocation behaviors. Furthermore, the effects of metal ion （K~ and Na~） and pH on the translocation behaviors were studied. Based on the single-molecule level analysis, there are some conclusions： （1） In the electrolyte solution containing 50 mmol/L I（Cl and 450 mmol/L NaCl, ThT can bind strongly with Tel DNA but nearly does not change the G-quadruplex form; （2） in the presence of high concentration K~, the ThT binding induces the structural change of hybrid G-quadruplex into antiparallel topology with an enhanced structural stability; （3） In either alkaline or acidic buffer, G-quadruplex form will change in certain degree. All above conclusions are helpful to deeply understand the interaction behaviors between Tel DNA and ThT. This nanopore platform, investigating G-quadruplex ligands at the single-molecule level, has great potential for the design of new drugs and sensors.展开更多
A facial expression emotion recognition based human-robot interaction(FEER-HRI) system is proposed, for which a four-layer system framework is designed. The FEERHRI system enables the robots not only to recognize huma...A facial expression emotion recognition based human-robot interaction(FEER-HRI) system is proposed, for which a four-layer system framework is designed. The FEERHRI system enables the robots not only to recognize human emotions, but also to generate facial expression for adapting to human emotions. A facial emotion recognition method based on2D-Gabor, uniform local binary pattern(LBP) operator, and multiclass extreme learning machine(ELM) classifier is presented,which is applied to real-time facial expression recognition for robots. Facial expressions of robots are represented by simple cartoon symbols and displayed by a LED screen equipped in the robots, which can be easily understood by human. Four scenarios,i.e., guiding, entertainment, home service and scene simulation are performed in the human-robot interaction experiment, in which smooth communication is realized by facial expression recognition of humans and facial expression generation of robots within 2 seconds. As a few prospective applications, the FEERHRI system can be applied in home service, smart home, safe driving, and so on.展开更多
With the increasing of the elderly population and the growing hearth care cost, the role of service robots in aiding the disabled and the elderly is becoming important. Many researchers in the world have paid much att...With the increasing of the elderly population and the growing hearth care cost, the role of service robots in aiding the disabled and the elderly is becoming important. Many researchers in the world have paid much attention to heaRthcare robots and rehabilitation robots. To get natural and harmonious communication between the user and a service robot, the information perception/feedback ability, and interaction ability for service robots become more important in many key issues.展开更多
This paper presents a novel enhanced human-robot interaction system based on model reference adaptive control. The presented method delivers guaranteed stability and task performance and has two control loops. A robot...This paper presents a novel enhanced human-robot interaction system based on model reference adaptive control. The presented method delivers guaranteed stability and task performance and has two control loops. A robot-specific inner loop, which is a neuroadaptive controller, learns the robot dynamics online and makes the robot respond like a prescribed impedance model. This loop uses no task information, including no prescribed trajectory. A task-specific outer loop takes into account the human operator dynamics and adapts the prescribed robot impedance model so that the combined human-robot system has desirable characteristics for task performance. This design is based on model reference adaptive control, but of a nonstandard form. The net result is a controller with both adaptive impedance characteristics and assistive inputs that augment the human operator to provide improved task performance of the human-robot team. Simulations verify the performance of the proposed controller in a repetitive point-to-point motion task. Actual experimental implementations on a PR2 robot further corroborate the effectiveness of the approach.展开更多
This paper proposes a method to recognize human-object interactions by modeling context between human actions and interacted objects.Human-object interaction recognition is a challenging task due to severe occlusion b...This paper proposes a method to recognize human-object interactions by modeling context between human actions and interacted objects.Human-object interaction recognition is a challenging task due to severe occlusion between human and objects during the interacting process.Since that human actions and interacted objects provide strong context information,i.e.some actions are usually related to some specific objects,the accuracy of recognition is significantly improved for both of them.Through the proposed method,both global and local temporal features from skeleton sequences are extracted to model human actions.In the meantime,kernel features are utilized to describe interacted objects.Finally,all possible solutions from actions and objects are optimized by modeling the context between them.The results of experiments demonstrate the effectiveness of our method.展开更多
A more natural way for non-expert users to express their tasks in an open-ended set is to use natural language. In this case,a human-centered intelligent agent/robot is required to be able to understand and generate p...A more natural way for non-expert users to express their tasks in an open-ended set is to use natural language. In this case,a human-centered intelligent agent/robot is required to be able to understand and generate plans for these naturally expressed tasks. For this purpose, it is a good way to enhance intelligent robot's abilities by utilizing open knowledge extracted from the web, instead of hand-coded knowledge. A key challenge of utilizing open knowledge lies in the semantic interpretation of the open knowledge organized in multiple modes, which can be unstructured or semi-structured, before one can use it.Previous approaches used a limited lexicon to employ combinatory categorial grammar(CCG) as the underlying formalism for semantic parsing over sentences. Here, we propose a more effective learning method to interpret semi-structured user instructions. Moreover, we present a new heuristic method to recover missing semantic information from the context of an instruction. Experiments showed that the proposed approach renders significant performance improvement compared to the baseline methods and the recovering method is promising.展开更多
Human-robot interaction(HRI) is fundamental for human-centered robotics, and has been attracting intensive research for more than a decade. The series elastic actuator(SEA) provides inherent compliance, safety and fur...Human-robot interaction(HRI) is fundamental for human-centered robotics, and has been attracting intensive research for more than a decade. The series elastic actuator(SEA) provides inherent compliance, safety and further benefits for HRI, but the introduced elastic element also brings control difficulties. In this paper, we address the stiffness rendering problem for a cable-driven SEA system, to achieve either low stiffness for good transparency or high stiffness bigger than the physical spring constant, and to assess the rendering accuracy with quantified metrics. By taking a velocity-sourced model of the motor, a cascaded velocity-torque-impedance control structure is established. To achieve high fidelity torque control, the 2-DOF(degree of freedom) stabilizing control method together with a compensator has been used to handle the competing requirements on tracking performance, noise and disturbance rejection,and energy optimization in the cable-driven SEA system. The conventional passivity requirement for HRI usually leads to a conservative design of the impedance controller, and the rendered stiffness cannot go higher than the physical spring constant. By adding a phase-lead compensator into the impedance controller,the stiffness rendering capability was augmented with guaranteed relaxed passivity. Extensive simulations and experiments have been performed, and the virtual stiffness has been rendered in the extended range of 0.1 to 2.0 times of the physical spring constant with guaranteed relaxed passivity for physical humanrobot interaction below 5 Hz. Quantified metrics also verified good rendering accuracy.展开更多
基金supported and funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R410),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Recognizing human interactions in RGB videos is a critical task in computer vision,with applications in video surveillance.Existing deep learning-based architectures have achieved strong results,but are computationally intensive,sensitive to video resolution changes and often fail in crowded scenes.We propose a novel hybrid system that is computationally efficient,robust to degraded video quality and able to filter out irrelevant individuals,making it suitable for real-life use.The system leverages multi-modal handcrafted features for interaction representation and a deep learning classifier for capturing complex dependencies.Using Mask R-CNN and YOLO11-Pose,we extract grayscale silhouettes and keypoint coordinates of interacting individuals,while filtering out irrelevant individuals using a proposed algorithm.From these,we extract silhouette-based features(local ternary pattern and histogram of optical flow)and keypoint-based features(distances,angles and velocities)that capture distinct spatial and temporal information.A Bidirectional Long Short-Term Memory network(BiLSTM)then classifies the interactions.Extensive experiments on the UT Interaction,SBU Kinect Interaction and the ISR-UOL 3D social activity datasets demonstrate that our system achieves competitive accuracy.They also validate the effectiveness of the chosen features and classifier,along with the proposed system’s computational efficiency and robustness to occlusion.
基金funded by the Jiaying University Research Start-Up Fund(grant number 323E0431).
文摘Accurate fingertip detection is critical for translating hand gestures into actionable commands in vision-based human‒computer interaction(HCI)systems.However,challenges such as complex backgrounds,dynamic hand postures,and real-time processing constraints hinder reliable detection.This paper introduces a robust framework integrating three key innovations:(1)an adaptive Gaussian mixture model(GMM)enhanced with neighborhood pixel connectivity for precise motion extraction;(2)a weighted YCbCr color-space shadow removal algorithm to eliminate false positives;and(3)a centroid distance method refined with circularity constraints for accurate fingertip localization.Extensive experiments demonstrate a recognition accuracy of 97.26%across diverse scenarios,including varying illuminations,occlusions,and hand rotations.The algorithm processes each frame in 23.43 ms on average,satisfying real-time requirements.Comparative evaluations against state-of-the-art methods reveal significant improvements in precision(8.3%),recall(6.1%),and F-measure(7.8%).This work advances HCI applications such as virtual keyboards,gesture-controlled interfaces,and augmented reality systems.
基金supported by the Zhejiang Provincial Natural Science Foundation of China(No.LQ23F030001)the National Natural Science Foundation of China(No.62406280)+5 种基金the Autism Research Special Fund of Zhejiang Foundation for Disabled Persons(No.2023008)the Liaoning Province Higher Education Innovative Talents Program Support Project(No.LR2019058)the Liaoning Province Joint Open Fund for Key Scientific and Technological Innovation Bases(No.2021-KF-12-05)the Central Guidance on Local Science and Technology Development Fund of Liaoning Province(No.2023JH6/100100066)the Key Laboratory for Biomedical Engineering of Ministry of Education,Zhejiang University,Chinain part by the Open Research Fund of the State Key Laboratory of Cognitive Neuroscience and Learning.
文摘Video action recognition(VAR)aims to analyze dynamic behaviors in videos and achieve semantic understanding.VAR faces challenges such as temporal dynamics,action-scene coupling,and the complexity of human interactions.Existing methods can be categorized into motion-level,event-level,and story-level ones based on spatiotemporal granularity.However,single-modal approaches struggle to capture complex behavioral semantics and human factors.Therefore,in recent years,vision-language models(VLMs)have been introduced into this field,providing new research perspectives for VAR.In this paper,we systematically review spatiotemporal hierarchical methods in VAR and explore how the introduction of large models has advanced the field.Additionally,we propose the concept of“Factor”to identify and integrate key information from both visual and textual modalities,enhancing multimodal alignment.We also summarize various multimodal alignment methods and provide in-depth analysis and insights into future research directions.
基金supported by grants from the Knut and Alice Wallenberg foundation(P-OB,JRZ,and AK)the Swedish Research Council(JRZ and AK),Centrum för idrottsforskning(AK and JRZ)+7 种基金the NovoNordisk Foundation Metabolic Stress Associated Molecules(MSAM)consortium NNF15SA0018346 and Metabolite-related Inflammation and Disease(MeRIAD)consortium Grant number 0064142(AK)the Swedish Diabetes Foundation(AK and JRZ)the European Foundation for the Study of Diabetes(JRZ and AK)the Region Stockholm(ALF project)(JRZ and KC)the Strategic Research Program in Diabetes at Karolinska Institutet(JRZ and AK)supported by the Strategic Research Programme in Diabetes(SRP Diabetes)for use of the Seahorse flux analyzer.Human islets were made possible through the Juvenile Diabetes Research Foundation(JDRF)award 31-2008-416(European Coordinating Infrastructure for Islet Transplantation(ECIT),Islet for Basic Research program)AK holds a Distinguished Investigator Grant within Endocrinology and Metabolism from the Novo Nordisk Foundation(NNF24OC0088739)JRZ received the 2024 European Association for the Study of Diabetes(ESAD)-Novo Nordisk Foundation Diabetes Prize for Excellence(NNF24SA0092609).
文摘Background Regular physical training induces adaptive effects across multiple organ systems,highlighting the existence of inter-organ communication networks.However,the molecular mechanisms underlying both exercise-induced adaptations and organ-to-organ signaling are not fully characterized.Circulating extracellular vesicles(EVs),including exosomes,carry molecules like microRNAs(miRNAs)that may mediate tissue crosstalk.This study aimed to identify specific exercise training-responsive miRNAs that affect skeletal muscle function.Methods miRNA expression profiles of serum-derived EVs were analyzed in healthy young individuals before and after 3 weeks endurance exercise training.Exercise training-responsive miRNAs were then validated for a functional role in cellular metabolic processes in human myotubes.Results We identified several exercise training-responsive miRNAs within exosome-rich EVs in serum,including miR-136-3p.In human myotubes,miR-136-3p enhanced glucose uptake and targeted the nardilysin convertase(NRDC)gene.Transfection of miR-136-3p or silencing of NRDC induced a shift towards glycolytic metabolism in mitochondria and modulated gene expressions related to myogenesis.Pancreatic islets were identified as a potential source of miR-136-3p based on in silico analysis of gene expression and a molecular analysis of conditioned media from isolated pancreatic islets.Conclusion MiR-136-3p is an endurance training-responsive molecular transducer that modulates glucose metabolism and cellular proliferation in myocytes.Associated with EVs,extracellular miR-136-3p may serve as a molecular messenger to communicate islet–skeletal muscle crosstalk after exercise.Extracellular miR-136-3p may serve as a molecular messenger to communicate islet–skeletal muscle crosstalk.Our results highlight a miRNA-mediated mechanism that participates in inter-organ communication to fine tune the metabolic adaptations to exercise.
文摘A complete characterization of the behavior in human-robot interactions(HRI) includes both: the behavioral dynamics and the control laws that characterize how the behavior is regulated with the perception data. In this way, this work proposes a leader-follower coordinate control based on an impedance control that allows to establish a dynamic relation between social forces and motion error. For this, a scheme is presented to identify the impedance based on fictitious social forces, which are described by distance-based potential fields.As part of the validation procedure, we present an experimental comparison to select the better of two different fictitious force structures. The criteria are determined by two qualities: least impedance errors during the validation procedure and least parameter variance during the recursive estimation procedure.Finally, with the best fictitious force and its identified impedance,an impedance control is designed for a mobile robot Pioneer 3AT,which is programmed to follow a human in a structured scenario.According to results, and under the hypothesis that moving like humans will be acceptable by humans, it is believed that the proposed control improves the social acceptance of the robot for this kind of interaction.
基金Supported by The Medical Guidance Projects of Shanghai Science Committee,No.10411961800National Natural Science Foundation of China,No.81101617
文摘AIM: To investigate the biological function of 14-3-3σ protein and to look for proteins that interact with 14-3-3σ protein in colon cancer stem cells. METHODS: Reverse transcription polymerase chain reaction was performed to amplify the 14-3-3σ gene from the mRNA of colon cancer stem cells. The gene was then cloned into the pGEM-T vector. After being sequenced, the target gene 14-3-3σ was cut from the pGEM-T vector and cloned into the pGBKT7 yeast expression plasmid. Then, the bait plasmid pGBKT7-14-3-3σ was transformed into the yeast strain AH109. After the expression of the pGBKT7-14-3-3σ fusion protein in the AH109 yeast strain was accomplished, a yeast two-hybrid screening assay was performed by mating AH109 with Y187 that contained a HeLa cDNA library plasmid. The interaction between the 14-3-3σ protein and the proteins obtained from positive colonies was further confirmed by repeating the yeast two-hybridscreen. After extracting and sequencing the plasmids from the positive colonies, we performed a bioinformatics analysis. A coimmunoprecipitation assay was performed to confirm the interaction between 14-3-3σ and the proteins obtained from the positive colonies. Finally, we constructed 14-3-3σ and potassium channel modulatory factor 1 (KCMF1) siRNA expression plasmids and transfected them into colon cancer stem cells. RESULTS: The bait plasmid pGBKT7-14-3-3σ was constructed successfully, and the 14-3-3σ protein had no toxic or autonomous activation effect on the yeast. Nineteen true-positive colonies were selected and sequenced, and their full-length sequences were obtained. We searched for homologous DNA sequences for these sequences from GenBank. Among the positive colonies, four coding genes with known functions were obtained, including KCMF1 , quinone oxidore-ductase (NQO2 ), hydroxyisobutyrate dehydrogenase (HIBADH ) and 14-3-3σ . For the subsequent coimmu-noprecipitation assay, the plasmids PCDEF-Flag-14-3-3σ, PCDEF-Myc-KCMF1, PCDEF-Myc-NQO2 and PCDEF-Myc-HIBADH were successfully constructed, and the sequences were further confirmed by DNA sequencing. The Fugene 6 reagent was used to transfect the plasmids, and fluorescence-activated cell sorting analysis showed the transfection efficiency was 97.8% after 48 h. The HEK 293FT cells showed the stable expression of the PCDEF-Flag-14-3-3σ, PCDEF-Myc-KCMF1, PCDEF-Myc-NQO2 and PCDEF-Myc-HIBADH plasmids. After anti-Myc antibody immunoprecipitation with Myc-KCMF1, Myc-NQO2 and Myc-HIBADH from cell lysates, the presence of Flag-14-3-3σ protein in the immuno-precipitated complex was determined by western blot analysis. The knock-down expression of the 14-3-3σ and KCMF1 proteins significantly inhibited cell proliferation and colony formation of SW1116csc. CONCLUSION: Genes of the proteins that interactedwith 14-3-3σ were successfully screened from a HeLa cDNA library. KCMF1 and 14-3-3σ protein may affect the proliferation and colony formation of human colon cancer stem cells.
基金supported by the State Key Research Development Program of China(No.2021YFB3800701)National Natural Science Foundation of China(NSFC,No.52173016)+2 种基金Guangdong Basic and Applied Basic Research Foundation(Nos.2024A1515012784,2024A1515011102,and 2023A1515110549)Fundamental Research Funds for the Central Universities,Sun Yat-sen University(No.24qnpy047)PetroChina Scientific and Technological Projects(No.2022DJ6308).
文摘A series of“half-sandwich”bis(imino)pyridyl iron complexes with a substituted 8-(p-Xphenyl)naphthylamine(X=OMe,Me,CF3)was designed and synthesized by combining weakπ-πinteraction with steric and electronic tunings.The weak noncovalentπ-πinteraction as well as the steric and electronic effects of bis(imino)pyridyl iron complexes were identified by experimental analyses and calculations.The roles of weakπ-πinteraction,steric bulk,and electronic tuning on the ethylene polymerization performance of bis(imino)pyridyl iron catalysts were studied in detail.The combination ofπ-πinteraction with steric and electronic tunings can access to thermally stable bis(imino)pyridyl iron at 130°C.
基金the Deputyship for Research and Innovation,“Ministry of Education”in Saudi Arabia for funding this research(IFKSU-HCRA-12-3).
文摘Photocatalysis is one of the most capable green energy techniques for sustainable solar-to-chemical energy conversion.However,the speedy recombination of photocarriers remains a critical bottleneck in achieving high photocatalytic efficiency.Recent advancements have underscored the pivotal role of internal and external electrostatic fields in regulating charge dynamics within semiconductor systems.This review highlights the emerging strategy of employing non-covalent electrostatic interactions to modulate photocatalytic behavior.Internally,spontaneous polarization within polar or ferroelectric semiconductors facilitates efficient charge separation through built-in electric fields.Externally applied mechanical stress and magnetic fields further augment these effects via piezoelectric and magnetoelectric phenomena,offering dynamic control over carrier transport.Beyond macroscopic fields,subtle non-covalent electrostatic forces,such as hydrogen bonds,van der Waals forces,andπ-πstacking,significantly influence surface adsorption,electronic structure modulation,and interfacial charge transfer processes.Combining these external influences with semiconductor properties,we can develop innovative strategies to stabilize the reactive intermediates and reduce the recombination pathways,improving the practical implications of these synergistic effects in energy conversion and environmental remediation.This review systematically elucidates the mechanistic contributions of internal polarization and external fields to the modulation of non-covalent electrostatic forces in photocatalytic systems.Emphasis is placed on material design strategies that integrate structural polarity,field-responsive behavior,and interfacial engineering to achieve superior photocatalytic performance.Finally,the prospects of non-covalent electrostatic interactions in photocatalysis are discussed,providing insights to guide the rational development of more efficient and sustainable photocatalytic systems.
文摘This article describes a pilot study aiming at generating social interactions between a humanoid robot and adolescents with autism spectrum disorder (ASD), through the practice of a gesture imitation game. The participants were a 17-year-old young lady with ASD and intellectual deficit, and a control participant: a preadolescent with ASD but no intellectual deficit (Asperger syndrome). The game is comprised of four phases: greetings, pairing, imitation, and closing. Field educators were involved, playing specific roles: visual or physical inciter. The use of a robot allows for catching the participants’ attention, playing the imitation game for a longer period of time than with a human partner, and preventing the game partner’s negative facial expressions resulting from tiredness, impatience, or boredom. The participants’ behavior was observed in terms of initial approach towards the robot, positioning relative to the robot in terms of distance and orientation, reactions to the robot’s voice or moves, signs of happiness, and imitation attempts. Results suggest a more and more natural approach towards the robot during the sessions, as well as a higher level of social interaction, based on the variations of the parameters listed above. We use these preliminary results to draw the next steps of our research work as well as identify further perspectives, with this aim in mind: improving social interactions with adolescents with ASD and intellectual deficit, allowing for better integration of these people into our societies.
文摘In this paper,we present an RFID based human and Unmanned Aerial Vehicle(UAV)Interaction system,termed RFHUI,to provide an intuitive and easy-to-operate method to navigate a UAV in an indoor environment.It relies on the passive Radio-Frequency IDentification(RFID)technology to precisely track the pose of a handheld controller,and then transfer the pose information to navigate the UAV.A prototype of the handheld controller is created by attaching three or more Ultra High Frequency(UHF)RFID tags to a board.A Commercial Off-The-Shelf(COTS)RFID reader with multiple antennas is deployed to collect the observations of the tags.First,the precise positions of all the tags can be obtained by our proposed method,which leverages a Bayesian filter and Channel State Information(CSI)phase measurements collected from the RFID reader.Second,we introduce a Singular Value Decomposition(SVD)based approach to obtain a 6-DoF(Degrees of Freedom)pose of the controller from estimated positions of the tags.Furthermore,the pose of the controller can be precisely tracked in a real-time manner,while the user moves the controller.Finally,control commands will be generated from the controller's pose and sent to the UAV for navigation.The performance of the RFHUI is evaluated by several experiments.The results show that it provides precise poses with 0.045m mean error in position and 2.5∘mean error in orientation for the controller,and enables the controller to precisely and intuitively navigate the UAV in an indoor environment.
文摘Recent advancements in the Internet of Things IoT and cloud computing have paved the way for mobile Healthcare(mHealthcare)services.A patient within the hospital is monitored by several devices.Moreover,upon leaving the hospital,the patient can be remotely monitored whether directly using body wearable sensors or using a smartphone equipped with sensors to monitor different user-health parameters.This raises potential challenges for intelligent monitoring of patient's health.In this paper,an improved architecture for smart mHealthcare is proposed that is supported by HCI design principles.The HCI also provides the support for the User-Centric Design(UCD)for smart mHealthcare models.Furthermore,the HCI along with IoT's(Internet of Things)5-layered architecture has the potential of improving User Experience(UX)in mHealthcare design and help saving lives.The intelligent mHealthcare system is supported by the IoT sensing and communication layers and health care providers are supported by the application layer for the medical,behavioral,and health-related information.Health care providers and users are further supported by an intelligent layer performing critical situation assessment and performing a multi-modal communication using an intelligent assistant.The HCI design focuses on the ease-of-use,including user experience and safety,alarms,and error-resistant displays of the end-user,and improves user's experience and user satisfaction.
基金supported by the National Key Research and Development Program of China(2021YFB1600601)the Joint Funds of the National Natural Science Foundation of China and the Civil Aviation Administration of China(U1933106)+2 种基金the Scientific Research Project of Tianjin Educational Committee(2019KJ134)the Natural Science Foundation of TianjinIntelligent Civil Aviation Program(21JCQNJ C00900)。
文摘To solve the problem of risk identification and quantitative assessment for human-computer interaction(HCI)in complex avionics systems,an HCI safety analysis framework based on system-theoretical process analysis(STPA)and cognitive reliability and error analysis method(CREAM)is proposed.STPACREAM can identify unsafe control actions and find the causal path during the interaction of avionics systems and pilot with the help of formal verification tools automatically.The common performance conditions(CPC)of avionics systems in the aviation environment is established and a quantitative analysis of human failure is carried out.Taking the head-up display(HUD)system interaction process as an example,a case analysis is carried out,the layered safety control structure and formal model of the HUD interaction process are established.For the interactive behavior“Pilots approaching with HUD”,four unsafe control actions and35 causal scenarios are identified and the impact of common performance conditions at different levels on the pilot decision model are analyzed.The results show that HUD's HCI level gradually improves as the scores of CPC increase,and the quality of crew member cooperation and time sufficiency of the task is the key to its HCI.Through case analysis,it is shown that STPACREAM can quantitatively assess the hazards in HCI and identify the key factors that impact safety.
文摘Humans and animals are in regular and at times close contact in modern intensive farming systems.The quality of human-animal interactions can have a profound impact on the productivity and welfare of farm animals.Interactions by humans may be neutral,positive or negative in nature.Regular pleasant contact with humans may result in desirable alterations in the physiology,behaviour,health and productivity of farm animals.On the contrary,animals that were subjected to aversive human contact were highly fearful of humans and their growth and reproductive performance could be compromised.Farm animals are particularly sensitive to human stimulation that occurs early in life,while many systems of the animals are still developing.This may have long-lasting impact and could possibly modify their genetic potential.The question as to how human contact can have a positive impact on responses to stressors,and productivity is not well understood.Recent work in our laboratory suggested that pleasant human contact may alter ability to tolerate various stressors through enhanced heat shock protein（hsp） 70 expression.The induction of hsp is often associated with increased tolerance to environmental stressors and disease resistance in animals.The attitude and consequent behaviour of stockpeople affect the animals＇ fear of human which eventually influence animals＇ productivity and welfare.Other than attitude and behaviour,technical skills,knowledge,job motivation,commitment and job satisfaction are prerequisites for high job performance.
基金financially supported by the National Natural Science Foundation of China(No. 21475091)the Science andTechnology Department of Sichuan Province(No. 2015GZ0301)
文摘G-quadruplex ligands have been accepted as potential therapeutic agents for anticancer treatment. Thioflavin T （ThT）, a highly selective G-quadruplex ligand, can bind G-quadruplex with a fluorescent light-up signal change and high specificity against DNA duplex. However, there are still different opinions that ThT induces/stabilizes G-quadruplex foldings/topologies in human telomere sequence. Here, a sensitive single-molecule nanopore technology was utilized to analyze the interactions between human telomeric DNA （Tel DNA） and ThT. Both translocation time and current blockade were measured to investigate the translocation behaviors. Furthermore, the effects of metal ion （K~ and Na~） and pH on the translocation behaviors were studied. Based on the single-molecule level analysis, there are some conclusions： （1） In the electrolyte solution containing 50 mmol/L I（Cl and 450 mmol/L NaCl, ThT can bind strongly with Tel DNA but nearly does not change the G-quadruplex form; （2） in the presence of high concentration K~, the ThT binding induces the structural change of hybrid G-quadruplex into antiparallel topology with an enhanced structural stability; （3） In either alkaline or acidic buffer, G-quadruplex form will change in certain degree. All above conclusions are helpful to deeply understand the interaction behaviors between Tel DNA and ThT. This nanopore platform, investigating G-quadruplex ligands at the single-molecule level, has great potential for the design of new drugs and sensors.
基金supported by the National Natural Science Foundation of China(61403422,61273102)the Hubei Provincial Natural Science Foundation of China(2015CFA010)+1 种基金the Ⅲ Project(B17040)the Fundamental Research Funds for National University,China University of Geosciences(Wuhan)
文摘A facial expression emotion recognition based human-robot interaction(FEER-HRI) system is proposed, for which a four-layer system framework is designed. The FEERHRI system enables the robots not only to recognize human emotions, but also to generate facial expression for adapting to human emotions. A facial emotion recognition method based on2D-Gabor, uniform local binary pattern(LBP) operator, and multiclass extreme learning machine(ELM) classifier is presented,which is applied to real-time facial expression recognition for robots. Facial expressions of robots are represented by simple cartoon symbols and displayed by a LED screen equipped in the robots, which can be easily understood by human. Four scenarios,i.e., guiding, entertainment, home service and scene simulation are performed in the human-robot interaction experiment, in which smooth communication is realized by facial expression recognition of humans and facial expression generation of robots within 2 seconds. As a few prospective applications, the FEERHRI system can be applied in home service, smart home, safe driving, and so on.
文摘With the increasing of the elderly population and the growing hearth care cost, the role of service robots in aiding the disabled and the elderly is becoming important. Many researchers in the world have paid much attention to heaRthcare robots and rehabilitation robots. To get natural and harmonious communication between the user and a service robot, the information perception/feedback ability, and interaction ability for service robots become more important in many key issues.
基金The work was supported by the National Science Foundation，the Office of Naval Research grant，the AFOSR (Air Force Office of Scientific Research) EOARD (European Office of Aerospace Research and Development) grant，the U.S. Army Research Office grant
文摘This paper presents a novel enhanced human-robot interaction system based on model reference adaptive control. The presented method delivers guaranteed stability and task performance and has two control loops. A robot-specific inner loop, which is a neuroadaptive controller, learns the robot dynamics online and makes the robot respond like a prescribed impedance model. This loop uses no task information, including no prescribed trajectory. A task-specific outer loop takes into account the human operator dynamics and adapts the prescribed robot impedance model so that the combined human-robot system has desirable characteristics for task performance. This design is based on model reference adaptive control, but of a nonstandard form. The net result is a controller with both adaptive impedance characteristics and assistive inputs that augment the human operator to provide improved task performance of the human-robot team. Simulations verify the performance of the proposed controller in a repetitive point-to-point motion task. Actual experimental implementations on a PR2 robot further corroborate the effectiveness of the approach.
文摘This paper proposes a method to recognize human-object interactions by modeling context between human actions and interacted objects.Human-object interaction recognition is a challenging task due to severe occlusion between human and objects during the interacting process.Since that human actions and interacted objects provide strong context information,i.e.some actions are usually related to some specific objects,the accuracy of recognition is significantly improved for both of them.Through the proposed method,both global and local temporal features from skeleton sequences are extracted to model human actions.In the meantime,kernel features are utilized to describe interacted objects.Finally,all possible solutions from actions and objects are optimized by modeling the context between them.The results of experiments demonstrate the effectiveness of our method.
基金supported by the National Natural Science Foundation of China(61175057)the USTC Key-Direction Research Fund(WK0110000028)
文摘A more natural way for non-expert users to express their tasks in an open-ended set is to use natural language. In this case,a human-centered intelligent agent/robot is required to be able to understand and generate plans for these naturally expressed tasks. For this purpose, it is a good way to enhance intelligent robot's abilities by utilizing open knowledge extracted from the web, instead of hand-coded knowledge. A key challenge of utilizing open knowledge lies in the semantic interpretation of the open knowledge organized in multiple modes, which can be unstructured or semi-structured, before one can use it.Previous approaches used a limited lexicon to employ combinatory categorial grammar(CCG) as the underlying formalism for semantic parsing over sentences. Here, we propose a more effective learning method to interpret semi-structured user instructions. Moreover, we present a new heuristic method to recover missing semantic information from the context of an instruction. Experiments showed that the proposed approach renders significant performance improvement compared to the baseline methods and the recovering method is promising.
基金supported by the National Natural Science Foundation of China(61403215)the National Natural Science Foundation of Tianjin(13JCYBJC36600)the Fundamental Research Funds for the Central Universities
文摘Human-robot interaction(HRI) is fundamental for human-centered robotics, and has been attracting intensive research for more than a decade. The series elastic actuator(SEA) provides inherent compliance, safety and further benefits for HRI, but the introduced elastic element also brings control difficulties. In this paper, we address the stiffness rendering problem for a cable-driven SEA system, to achieve either low stiffness for good transparency or high stiffness bigger than the physical spring constant, and to assess the rendering accuracy with quantified metrics. By taking a velocity-sourced model of the motor, a cascaded velocity-torque-impedance control structure is established. To achieve high fidelity torque control, the 2-DOF(degree of freedom) stabilizing control method together with a compensator has been used to handle the competing requirements on tracking performance, noise and disturbance rejection,and energy optimization in the cable-driven SEA system. The conventional passivity requirement for HRI usually leads to a conservative design of the impedance controller, and the rendered stiffness cannot go higher than the physical spring constant. By adding a phase-lead compensator into the impedance controller,the stiffness rendering capability was augmented with guaranteed relaxed passivity. Extensive simulations and experiments have been performed, and the virtual stiffness has been rendered in the extended range of 0.1 to 2.0 times of the physical spring constant with guaranteed relaxed passivity for physical humanrobot interaction below 5 Hz. Quantified metrics also verified good rendering accuracy.
