The generation of synthetic trajectories has become essential in various fields for analyzing complex movement patterns.However,the use of real-world trajectory data poses significant privacy risks,such as location re...The generation of synthetic trajectories has become essential in various fields for analyzing complex movement patterns.However,the use of real-world trajectory data poses significant privacy risks,such as location reidentification and correlation attacks.To address these challenges,privacy-preserving trajectory generation methods are critical for applications relying on sensitive location data.This paper introduces DPIL-Traj,an advanced framework designed to generate synthetic trajectories while achieving a superior balance between data utility and privacy preservation.Firstly,the framework incorporates Differential Privacy Clustering,which anonymizes trajectory data by applying differential privacy techniques that add noise,ensuring the protection of sensitive user information.Secondly,Imitation Learning is used to replicate decision-making behaviors observed in real-world trajectories.By learning from expert trajectories,this component generates synthetic data that closely mimics real-world decision-making processes while optimizing the quality of the generated trajectories.Finally,Markov-based Trajectory Generation is employed to capture and maintain the inherent temporal dynamics of movement patterns.Extensive experiments conducted on the GeoLife trajectory dataset show that DPIL-Traj improves utility performance by an average of 19.85%,and in terms of privacy performance by an average of 12.51%,compared to state-of-the-art approaches.Ablation studies further reveal that DP clustering effectively safeguards privacy,imitation learning enhances utility under noise,and the Markov module strengthens temporal coherence.展开更多
Hydrogen energy is a crucial support for China’s low-carbon energy transition.With the large-scale integration of renewable energy,the combination of hydrogen and integrated energy systems has become one of the most ...Hydrogen energy is a crucial support for China’s low-carbon energy transition.With the large-scale integration of renewable energy,the combination of hydrogen and integrated energy systems has become one of the most promising directions of development.This paper proposes an optimized schedulingmodel for a hydrogen-coupled electro-heat-gas integrated energy system(HCEHG-IES)using generative adversarial imitation learning(GAIL).The model aims to enhance renewable-energy absorption,reduce carbon emissions,and improve grid-regulation flexibility.First,the optimal scheduling problem of HCEHG-IES under uncertainty is modeled as a Markov decision process(MDP).To overcome the limitations of conventional deep reinforcement learning algorithms—including long optimization time,slow convergence,and subjective reward design—this study augments the PPO algorithm by incorporating a discriminator network and expert data.The newly developed algorithm,termed GAIL,enables the agent to perform imitation learning from expert data.Based on this model,dynamic scheduling decisions are made in continuous state and action spaces,generating optimal energy-allocation and management schemes.Simulation results indicate that,compared with traditional reinforcement-learning algorithms,the proposed algorithmoffers better economic performance.Guided by expert data,the agent avoids blind optimization,shortens the offline training time,and improves convergence performance.In the online phase,the algorithm enables flexible energy utilization,thereby promoting renewable-energy absorption and reducing carbon emissions.展开更多
The automatic and rapid generation of excavation trajectories is the foundation for achieving an intelligent excavator.To obtain high-performance trajectories that enhance operational capacity while avoiding the numer...The automatic and rapid generation of excavation trajectories is the foundation for achieving an intelligent excavator.To obtain high-performance trajectories that enhance operational capacity while avoiding the numerous issues present in existing methods for generating effective excavation paths,this paper proposes a trajectory generation method for excavators based on imitation learning,using the mole as a bionic prototype.Given the high excavation efficiency of moles,this paper first analyzes the structural characteristics of the mole’s forelimbs,its digging principles,morphology,and trajectory patterns.Subsequently,a higher-order polynomial is employed to fit and optimize the mole’s excavation trajectory.Next,imitation learning is conducted on sample trajectories based on Dynamic Movement Primitives,followed by the introduction of an obstacle avoidance algorithm.Simulation experiments and comparisons demonstrate that the mole-inspired trajectory method used in this paper performs well and possesses the ability to generate obstacle avoidance trajectories,as well as the convenience of transferring across different machine models.展开更多
The existing research on rescue robots has focused mainly on reconnaissance,detection,and firefighting,and a small number of robots that can achieve human rescue have problems such as poor safety and stability and ins...The existing research on rescue robots has focused mainly on reconnaissance,detection,and firefighting,and a small number of robots that can achieve human rescue have problems such as poor safety and stability and insufficient carrying capacity.This article addresses the above issues and cleverly combines the advantages of soft robotic arms,underactuated robotic arms,and suction cups based on the principles of bionics.A new design for a robotic arm was proposed,and its working principle was explained.Then,the human rescue process was divided into two stages,and the grasping force of the robotic arm in each stage was analyzed separately.Finally,a prototype of the principle was developed,and the feasibility of the design principle of the robotic arm was verified through grasping experiments on a cross-sectional contour model of the human chest.At the same time,grasping experiments were conducted on different objects to demonstrate the potential application of the robotic arm in grasping ground objects.This research proposes a stress envelope adsorption rescue robot arm inspired by the adhesion ability of the Drosera plant and the stress envelope effect,which can apply force to the entire surface of the human body,reduce local force on the human body,ensure load-bearing capacity and adaptability,and improve the safety and stability of rescue grasping.展开更多
IntuiGrasp is a novel three-fingered dexterous hand that pioneers bio-inspired demonstrations with intuitive priors(BDIP)to bridge the gap between human tactile intuition and robotic execution.Unlike conven-tional pro...IntuiGrasp is a novel three-fingered dexterous hand that pioneers bio-inspired demonstrations with intuitive priors(BDIP)to bridge the gap between human tactile intuition and robotic execution.Unlike conven-tional programming,BDIP leverages human's innate priors(e.g.,“A pack of tissues requires gentle grasps,cups demand firm contact”)by enabling real-time transfer of gesture and force policies during physical demon-stration.When a human demonstrator wears IntuiGrasp,driven rings provide real-time haptic feedback on contact stress and slip,while inte-grated tactile sensors translate these human policies into image data,offering valuable data for imitation learning.In this study,human teachers use IntuiGrasp to demonstrate how to grasp three types of objects:a cup,a crumpled tissue pack,and a thin playing card.IntuiGrasp translates the policies for grasping these objects into image information that describes tactile sensations in real time.展开更多
Animals can adapt to their surroundings by modifying their trunk morphology,whereas legged robots currently utilize rigid trunks.This study introduces a single-degree-of-freedom(DoF),six-revolute(6R)morphing trunk mec...Animals can adapt to their surroundings by modifying their trunk morphology,whereas legged robots currently utilize rigid trunks.This study introduces a single-degree-of-freedom(DoF),six-revolute(6R)morphing trunk mechanism designed to equip legged robots with variable-width capabilities.Subsequently,a morphology-aware locomotion learning pipeline,based on reinforcement learning,is proposed for real-time trunk-width deformation and adaptive legged locomotion.The proposed variable-width trunk is integrated into a quadrupedal robot,and the learning pipeline is employed to train the adaptive locomotion controller of this robot.This study has three key contributions:(1)An overconstrained morphing mechanism is designed to achieve single-DoF trunk-width deformation,thereby minimizing power consumption and simplifying motion control.(2)A novel morphology-adaptive learning pipeline is introduced that utilizes adversarial joint-level motion imitation to ensure coordination consistency during morphological adaptation.This method addresses dynamic disturbances and interlimb coordination disruptions caused by width modifications.(3)A historical proprioception-based asymmetric neural network architecture is utilized to attain implicit terrain perception without visual input.Collectively,these developments enable the proposed variable-width legged robot to maintain consistent locomotion across complex terrains and facilitate rapid width deformation in response to environmental changes.Extensive simulation experiments validate the proposed design and control methodology.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
Salamander robots represent an innovative class of crawling robots that combine flexible limbs and spines to achieve exceptional motion stability and adaptability in unstructured environments.These biomimetic systems ...Salamander robots represent an innovative class of crawling robots that combine flexible limbs and spines to achieve exceptional motion stability and adaptability in unstructured environments.These biomimetic systems employ soft actuators that replicate the smooth,organic movements of living organisms,significantly enhancing fluid interaction efficiency and propulsion performance.This research specifically focuses on improving dielectric elastomer actuator(DEA)-based fish-like underwater robots by developing a novel drive mechanism inspired by the salamander musculature.While aquatic organisms such as fish possess complex muscle structures that challenge direct imitation,salamanders offer a more tractable model due to their simpler anatomical organization.Notably,the lateral inferior axonal muscles in salamanders exhibit a nearly flat configuration,with myomangial membranes arranged in a linear distribution from the lateral midline to the abdominal midline—a structural feature that is particularly amenable to DEA replication.Through systematic analysis of salamander morphology,this study develops a DEA driver model that investigates two critical performance parameters:(i)the impact of electrode geometry on the bending angle;and(ii)the relationship between driver quantity and angular displacement.The experimental results confirm that DEAs mimicking salamander muscle architecture can achieve substantially increased bending angles under optimized conditions,thereby demonstrating measurable improvements in robotic propulsion capabilities.展开更多
Robots are key to expanding the scope of space applications.The end-to-end training for robot vision-based detection and precision operations is challenging owing to constraints such as extreme environments and high c...Robots are key to expanding the scope of space applications.The end-to-end training for robot vision-based detection and precision operations is challenging owing to constraints such as extreme environments and high computational overhead.This study proposes a lightweight integrated framework for grasp detection and imitation learning,named GD-IL;it comprises a grasp detection algorithm based on manipulability and Gaussian mixture model(manipulability-GMM),and a grasp trajectory generation algorithm based on a two-stage robot imitation learning algorithm(TS-RIL).In the manipulability-GMM algorithm,we apply GMM clustering and ellipse regression to the object point cloud,propose two judgment criteria to generate multiple candidate grasp bounding boxes for the robot,and use manipulability as a metric for selecting the optimal grasp bounding box.The stages of the TS-RIL algorithm are grasp trajectory learning and robot pose optimization.In the first stage,the robot grasp trajectory is characterized using a second-order dynamic movement primitive model and Gaussian mixture regression(GMM).By adjusting the function form of the forcing term,the robot closely approximates the target-grasping trajectory.In the second stage,a robot pose optimization model is built based on the derived pose error formula and manipulability metric.This model allows the robot to adjust its configuration in real time while grasping,thereby effectively avoiding singularities.Finally,an algorithm verification platform is developed based on a Robot Operating System and a series of comparative experiments are conducted in real-world scenarios.The experimental results demonstrate that GD-IL significantly improves the effectiveness and robustness of grasp detection and trajectory imitation learning,outperforming existing state-of-the-art methods in execution efficiency,manipulability,and success rate.展开更多
To achieve the artificial general intelligence （AGI）, imitate the intelligence？ or imitate the brain？ This is the question! Most artificial intelligence （AI） approaches set the understanding of the intelligence ...To achieve the artificial general intelligence （AGI）, imitate the intelligence？ or imitate the brain？ This is the question! Most artificial intelligence （AI） approaches set the understanding of the intelligence principle as their premise. This may be correct to implement specific intelligence such as computing, symbolic logic, or what the AlphaGo could do. However, this is not correct for AGI, because to understand the principle of the brain intelligence is one of the most difficult challenges for our human beings. It is not wise to set such a question as the premise of the AGI mission. To achieve AGI, a practical approach is to build the so-called neurocomputer, which could be trained to produce autonomous intelligence and AGI. A neurocomputer imitates the biological neural network with neuromorphic devices which emulate the bio-neurons, synapses and other essential neural components. The neurocomputer could perceive the environment via sensors and interact with other entities via a physical body. The philosophy under the ＂new＂ approach, so-called as imitationalism in this paper, is the engineering methodology which has been practiced for thousands of years, and for many cases, such as the invention of the first airplane, succeeded. This paper compares the neurocomputer with the conventional computer. The major progress about neurocomputer is also reviewed.展开更多
Aim The particle texture from diesel engine was imitated by use of computer. Methods The theory of fractal geometry and the diffusion limited aggregation model were used to simulate the micron texture. Results The...Aim The particle texture from diesel engine was imitated by use of computer. Methods The theory of fractal geometry and the diffusion limited aggregation model were used to simulate the micron texture. Results The fractal dimensions of granule distribution and corpuscle superficial area are quite conformed with those of measurement. Conclusion The texture parameters of engine particle cluster can be obtained precisely by use of fractal theory.展开更多
UG and imitation are two parallel hypotheses trying to answer how childrens language acquisition is realized. Imitation fails to explain how children acquire language; however, it helps a lot in childrens language acq...UG and imitation are two parallel hypotheses trying to answer how childrens language acquisition is realized. Imitation fails to explain how children acquire language; however, it helps a lot in childrens language acquisition.展开更多
In this study,a 3D virtual reality and visualization engine for rendering the ocean,named VV-Ocean,is designed for marine applications.The design goals of VV-Ocean aim at high fidelity simulation of ocean environment,...In this study,a 3D virtual reality and visualization engine for rendering the ocean,named VV-Ocean,is designed for marine applications.The design goals of VV-Ocean aim at high fidelity simulation of ocean environment,visualization of massive and multidimensional marine data,and imitation of marine lives.VV-Ocean is composed of five modules,i.e.memory management module,resources management module,scene management module,rendering process management module and interaction management module.There are three core functions in VV-Ocean:reconstructing vivid virtual ocean scenes,visualizing real data dynamically in real time,imitating and simulating marine lives intuitively.Based on VV-Ocean,we establish a sea-land integration platform which can reproduce drifting and diffusion processes of oil spilling from sea bottom to surface.Environment factors such as ocean current and wind field have been considered in this simulation.On this platform oil spilling process can be abstracted as movements of abundant oil particles.The result shows that oil particles blend with water well and the platform meets the requirement for real-time and interactive rendering.VV-Ocean can be widely used in ocean applications such as demonstrating marine operations,facilitating maritime communications,developing ocean games,reducing marine hazards,forecasting the weather over oceans,serving marine tourism,and so on.Finally,further technological improvements of VV-Ocean are discussed.展开更多
One of the assumptions of previous research in evolutionary game dynamics is that individuals use only one rule to update their strategy. In reality, an individual's strategy update rules may change with the envir...One of the assumptions of previous research in evolutionary game dynamics is that individuals use only one rule to update their strategy. In reality, an individual's strategy update rules may change with the environment, and it is possible for an individual to use two or more rules to update their strategy. We consider the case where an individual updates strategies based on the Moran and imitation processes, and establish mixed stochastic evolutionary game dynamics by combining both processes. Our aim is to study how individuals change strategies based on two update rules and how this affects evolutionary game dynamics. We obtain an analytic expression and properties of the fixation probability and fixation times(the unconditional fixation time or conditional average fixation time) associated with our proposed process. We find unexpected results. The fixation probability within the proposed model is independent of the probabilities that the individual adopts the imitation rule update strategy. This implies that the fixation probability within the proposed model is equal to that from the Moran and imitation processes. The one-third rule holds in the proposed mixed model. However, under weak selection, the fixation times are different from those of the Moran and imitation processes because it is connected with the probability that individuals adopt an imitation update rule. Numerical examples are presented to illustrate the relationships between fixation times and the probability that an individual adopts the imitation update rule, as well as between fixation times and selection intensity. From the simulated analysis, we find that the fixation time for a mixed process is greater than that of the Moran process, but is less than that of the imitation process. Moreover, the fixation times for a cooperator in the proposed process increase as the probability of adopting an imitation update increases; however, the relationship becomes more complex than a linear relationship.展开更多
Here,the challenges of sample efficiency and navigation performance in deep rein-forcement learning for visual navigation are focused and a deep imitation reinforcement learning approach is proposed.Our contributions ...Here,the challenges of sample efficiency and navigation performance in deep rein-forcement learning for visual navigation are focused and a deep imitation reinforcement learning approach is proposed.Our contributions are mainly three folds:first,a frame-work combining imitation learning with deep reinforcement learning is presented,which enables a robot to learn a stable navigation policy faster in the target-driven navigation task.Second,the surrounding images is taken as the observation instead of sequential images,which can improve the navigation performance for more information.Moreover,a simple yet efficient template matching method is adopted to determine the stop action,making the system more practical.Simulation experiments in the AI-THOR environment show that the proposed approach outperforms previous end-to-end deep reinforcement learning approaches,which demonstrate the effectiveness and efficiency of our approach.展开更多
The zone of proximal development(ZPD) and the scaffolding theory are very different,both in terms of their theoretical origins and connotations,and can even be said to be very different.However,during the development ...The zone of proximal development(ZPD) and the scaffolding theory are very different,both in terms of their theoretical origins and connotations,and can even be said to be very different.However,during the development of the two concepts,some scholars have misunderstood them,resulting in the two being mistaken for similar concepts and therefore often confused.Professor James Lantolf from Pennsylvania State University(State College,USA) was interviewed by Professor Lili Qin from Dalian University of Foreign Studies(Dalian,China) and provides an indepth analysis of these issues.The interview begins with the theoretical roots,connotations and definitions of the ZPD and scaffolding concepts,and then unravels the story of how they have been“mistakenly loved for life”,and ultimately it is made clear that the two concepts are completely different in their practical application to language teaching and should not continue to be used interchangeably.展开更多
Mobile Edge Computing(MEC)is promising to alleviate the computation and storage burdens for terminals in wireless networks.The huge energy consumption of MEC servers challenges the establishment of smart cities and th...Mobile Edge Computing(MEC)is promising to alleviate the computation and storage burdens for terminals in wireless networks.The huge energy consumption of MEC servers challenges the establishment of smart cities and their service time powered by rechargeable batteries.In addition,Orthogonal Multiple Access(OMA)technique cannot utilize limited spectrum resources fully and efficiently.Therefore,Non-Orthogonal Multiple Access(NOMA)-based energy-efficient task scheduling among MEC servers for delay-constraint mobile applications is important,especially in highly-dynamic vehicular edge computing networks.The various movement patterns of vehicles lead to unbalanced offloading requirements and different load pressure for MEC servers.Self-Imitation Learning(SIL)-based Deep Reinforcement Learning(DRL)has emerged as a promising machine learning technique to break through obstacles in various research fields,especially in time-varying networks.In this paper,we first introduce related MEC technologies in vehicular networks.Then,we propose an energy-efficient approach for task scheduling in vehicular edge computing networks based on DRL,with the purpose of both guaranteeing the task latency requirement for multiple users and minimizing total energy consumption of MEC servers.Numerical results demonstrate that the proposed algorithm outperforms other methods.展开更多
Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly acc...Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly accomplish driving functions. Speaking of machine vision, deep learning techniques, and specifically convolutional neural networks, have been proven to be the state of the art technology in the field. As these networks typically involve millions of parameters and elements, designing an optimal architecture for deep learning structures is a difficult task which is globally under investigation by researchers. This study experimentally evaluates the impact of three major architectural properties of convolutional networks, including the number of layers, filters, and filter size on their performance. In this study, several models with different properties are developed,equally trained, and then applied to an autonomous car in a realistic simulation environment. A new ensemble approach is also proposed to calculate and update weights for the models regarding their mean squared error values. Based on design properties,performance results are reported and compared for further investigations. Surprisingly, the number of filters itself does not largely affect the performance efficiency. As a result, proper allocation of filters with different kernel sizes through the layers introduces a considerable improvement in the performance.Achievements of this study will provide the researchers with a clear clue and direction in designing optimal network architectures for deep learning purposes.展开更多
基金supported by the Natural Science Foundation of Fujian Province of China(2025J01380)National Natural Science Foundation of China(No.62471139)+3 种基金the Major Health Research Project of Fujian Province(2021ZD01001)Fujian Provincial Units Special Funds for Education and Research(2022639)Fujian University of Technology Research Start-up Fund(GY-S24002)Fujian Research and Training Grants for Young and Middle-aged Leaders in Healthcare(GY-H-24179).
文摘The generation of synthetic trajectories has become essential in various fields for analyzing complex movement patterns.However,the use of real-world trajectory data poses significant privacy risks,such as location reidentification and correlation attacks.To address these challenges,privacy-preserving trajectory generation methods are critical for applications relying on sensitive location data.This paper introduces DPIL-Traj,an advanced framework designed to generate synthetic trajectories while achieving a superior balance between data utility and privacy preservation.Firstly,the framework incorporates Differential Privacy Clustering,which anonymizes trajectory data by applying differential privacy techniques that add noise,ensuring the protection of sensitive user information.Secondly,Imitation Learning is used to replicate decision-making behaviors observed in real-world trajectories.By learning from expert trajectories,this component generates synthetic data that closely mimics real-world decision-making processes while optimizing the quality of the generated trajectories.Finally,Markov-based Trajectory Generation is employed to capture and maintain the inherent temporal dynamics of movement patterns.Extensive experiments conducted on the GeoLife trajectory dataset show that DPIL-Traj improves utility performance by an average of 19.85%,and in terms of privacy performance by an average of 12.51%,compared to state-of-the-art approaches.Ablation studies further reveal that DP clustering effectively safeguards privacy,imitation learning enhances utility under noise,and the Markov module strengthens temporal coherence.
基金supported by State Grid Corporation Technology Project(No.522437250003).
文摘Hydrogen energy is a crucial support for China’s low-carbon energy transition.With the large-scale integration of renewable energy,the combination of hydrogen and integrated energy systems has become one of the most promising directions of development.This paper proposes an optimized schedulingmodel for a hydrogen-coupled electro-heat-gas integrated energy system(HCEHG-IES)using generative adversarial imitation learning(GAIL).The model aims to enhance renewable-energy absorption,reduce carbon emissions,and improve grid-regulation flexibility.First,the optimal scheduling problem of HCEHG-IES under uncertainty is modeled as a Markov decision process(MDP).To overcome the limitations of conventional deep reinforcement learning algorithms—including long optimization time,slow convergence,and subjective reward design—this study augments the PPO algorithm by incorporating a discriminator network and expert data.The newly developed algorithm,termed GAIL,enables the agent to perform imitation learning from expert data.Based on this model,dynamic scheduling decisions are made in continuous state and action spaces,generating optimal energy-allocation and management schemes.Simulation results indicate that,compared with traditional reinforcement-learning algorithms,the proposed algorithmoffers better economic performance.Guided by expert data,the agent avoids blind optimization,shortens the offline training time,and improves convergence performance.In the online phase,the algorithm enables flexible energy utilization,thereby promoting renewable-energy absorption and reducing carbon emissions.
基金supported by the National Science Foundation of China(Grant No.52375246,No.52372428,No.52105100)Guangxi Science and Technology Program(Grant No.2023AB09014)Jilin Province Science and Technology Development Program,(Grant No.20230201094GX,No.20230201069GX).
文摘The automatic and rapid generation of excavation trajectories is the foundation for achieving an intelligent excavator.To obtain high-performance trajectories that enhance operational capacity while avoiding the numerous issues present in existing methods for generating effective excavation paths,this paper proposes a trajectory generation method for excavators based on imitation learning,using the mole as a bionic prototype.Given the high excavation efficiency of moles,this paper first analyzes the structural characteristics of the mole’s forelimbs,its digging principles,morphology,and trajectory patterns.Subsequently,a higher-order polynomial is employed to fit and optimize the mole’s excavation trajectory.Next,imitation learning is conducted on sample trajectories based on Dynamic Movement Primitives,followed by the introduction of an obstacle avoidance algorithm.Simulation experiments and comparisons demonstrate that the mole-inspired trajectory method used in this paper performs well and possesses the ability to generate obstacle avoidance trajectories,as well as the convenience of transferring across different machine models.
基金Supported by National Natural Science Foundation of China(Grant No.52475032)Central Government Guides Local Science and Technology Development Fund Projects(Grant No.246Z2001G)Hebei Provincial Natural Science Foundation Key Projects(Grant No.E2021203125).
文摘The existing research on rescue robots has focused mainly on reconnaissance,detection,and firefighting,and a small number of robots that can achieve human rescue have problems such as poor safety and stability and insufficient carrying capacity.This article addresses the above issues and cleverly combines the advantages of soft robotic arms,underactuated robotic arms,and suction cups based on the principles of bionics.A new design for a robotic arm was proposed,and its working principle was explained.Then,the human rescue process was divided into two stages,and the grasping force of the robotic arm in each stage was analyzed separately.Finally,a prototype of the principle was developed,and the feasibility of the design principle of the robotic arm was verified through grasping experiments on a cross-sectional contour model of the human chest.At the same time,grasping experiments were conducted on different objects to demonstrate the potential application of the robotic arm in grasping ground objects.This research proposes a stress envelope adsorption rescue robot arm inspired by the adhesion ability of the Drosera plant and the stress envelope effect,which can apply force to the entire surface of the human body,reduce local force on the human body,ensure load-bearing capacity and adaptability,and improve the safety and stability of rescue grasping.
文摘IntuiGrasp is a novel three-fingered dexterous hand that pioneers bio-inspired demonstrations with intuitive priors(BDIP)to bridge the gap between human tactile intuition and robotic execution.Unlike conven-tional programming,BDIP leverages human's innate priors(e.g.,“A pack of tissues requires gentle grasps,cups demand firm contact”)by enabling real-time transfer of gesture and force policies during physical demon-stration.When a human demonstrator wears IntuiGrasp,driven rings provide real-time haptic feedback on contact stress and slip,while inte-grated tactile sensors translate these human policies into image data,offering valuable data for imitation learning.In this study,human teachers use IntuiGrasp to demonstrate how to grasp three types of objects:a cup,a crumpled tissue pack,and a thin playing card.IntuiGrasp translates the policies for grasping these objects into image information that describes tactile sensations in real time.
基金Supported by State Key Lab of Mechanical System and Vibration Project of China(Grant No.MSVZD202008).
文摘Animals can adapt to their surroundings by modifying their trunk morphology,whereas legged robots currently utilize rigid trunks.This study introduces a single-degree-of-freedom(DoF),six-revolute(6R)morphing trunk mechanism designed to equip legged robots with variable-width capabilities.Subsequently,a morphology-aware locomotion learning pipeline,based on reinforcement learning,is proposed for real-time trunk-width deformation and adaptive legged locomotion.The proposed variable-width trunk is integrated into a quadrupedal robot,and the learning pipeline is employed to train the adaptive locomotion controller of this robot.This study has three key contributions:(1)An overconstrained morphing mechanism is designed to achieve single-DoF trunk-width deformation,thereby minimizing power consumption and simplifying motion control.(2)A novel morphology-adaptive learning pipeline is introduced that utilizes adversarial joint-level motion imitation to ensure coordination consistency during morphological adaptation.This method addresses dynamic disturbances and interlimb coordination disruptions caused by width modifications.(3)A historical proprioception-based asymmetric neural network architecture is utilized to attain implicit terrain perception without visual input.Collectively,these developments enable the proposed variable-width legged robot to maintain consistent locomotion across complex terrains and facilitate rapid width deformation in response to environmental changes.Extensive simulation experiments validate the proposed design and control methodology.
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.
基金supported by the Joint Open Fund of Guizhou Provincial Department of Education(Grant No.[2022]439)the Doctoral Research Foundation of Guiyang University,China(Grant No.GYUKY-2025)。
文摘Salamander robots represent an innovative class of crawling robots that combine flexible limbs and spines to achieve exceptional motion stability and adaptability in unstructured environments.These biomimetic systems employ soft actuators that replicate the smooth,organic movements of living organisms,significantly enhancing fluid interaction efficiency and propulsion performance.This research specifically focuses on improving dielectric elastomer actuator(DEA)-based fish-like underwater robots by developing a novel drive mechanism inspired by the salamander musculature.While aquatic organisms such as fish possess complex muscle structures that challenge direct imitation,salamanders offer a more tractable model due to their simpler anatomical organization.Notably,the lateral inferior axonal muscles in salamanders exhibit a nearly flat configuration,with myomangial membranes arranged in a linear distribution from the lateral midline to the abdominal midline—a structural feature that is particularly amenable to DEA replication.Through systematic analysis of salamander morphology,this study develops a DEA driver model that investigates two critical performance parameters:(i)the impact of electrode geometry on the bending angle;and(ii)the relationship between driver quantity and angular displacement.The experimental results confirm that DEAs mimicking salamander muscle architecture can achieve substantially increased bending angles under optimized conditions,thereby demonstrating measurable improvements in robotic propulsion capabilities.
基金Supported by National Natural Science Foundation of China(Grant No.52475280)Shaanxi Provincial Natural Science Basic Research Program(Grant No.2025SYSSYSZD-105).
文摘Robots are key to expanding the scope of space applications.The end-to-end training for robot vision-based detection and precision operations is challenging owing to constraints such as extreme environments and high computational overhead.This study proposes a lightweight integrated framework for grasp detection and imitation learning,named GD-IL;it comprises a grasp detection algorithm based on manipulability and Gaussian mixture model(manipulability-GMM),and a grasp trajectory generation algorithm based on a two-stage robot imitation learning algorithm(TS-RIL).In the manipulability-GMM algorithm,we apply GMM clustering and ellipse regression to the object point cloud,propose two judgment criteria to generate multiple candidate grasp bounding boxes for the robot,and use manipulability as a metric for selecting the optimal grasp bounding box.The stages of the TS-RIL algorithm are grasp trajectory learning and robot pose optimization.In the first stage,the robot grasp trajectory is characterized using a second-order dynamic movement primitive model and Gaussian mixture regression(GMM).By adjusting the function form of the forcing term,the robot closely approximates the target-grasping trajectory.In the second stage,a robot pose optimization model is built based on the derived pose error formula and manipulability metric.This model allows the robot to adjust its configuration in real time while grasping,thereby effectively avoiding singularities.Finally,an algorithm verification platform is developed based on a Robot Operating System and a series of comparative experiments are conducted in real-world scenarios.The experimental results demonstrate that GD-IL significantly improves the effectiveness and robustness of grasp detection and trajectory imitation learning,outperforming existing state-of-the-art methods in execution efficiency,manipulability,and success rate.
基金supported by the Natural Science Foundation of China(Nos.61425025 and 61390515)
文摘To achieve the artificial general intelligence （AGI）, imitate the intelligence？ or imitate the brain？ This is the question! Most artificial intelligence （AI） approaches set the understanding of the intelligence principle as their premise. This may be correct to implement specific intelligence such as computing, symbolic logic, or what the AlphaGo could do. However, this is not correct for AGI, because to understand the principle of the brain intelligence is one of the most difficult challenges for our human beings. It is not wise to set such a question as the premise of the AGI mission. To achieve AGI, a practical approach is to build the so-called neurocomputer, which could be trained to produce autonomous intelligence and AGI. A neurocomputer imitates the biological neural network with neuromorphic devices which emulate the bio-neurons, synapses and other essential neural components. The neurocomputer could perceive the environment via sensors and interact with other entities via a physical body. The philosophy under the ＂new＂ approach, so-called as imitationalism in this paper, is the engineering methodology which has been practiced for thousands of years, and for many cases, such as the invention of the first airplane, succeeded. This paper compares the neurocomputer with the conventional computer. The major progress about neurocomputer is also reviewed.
文摘Aim The particle texture from diesel engine was imitated by use of computer. Methods The theory of fractal geometry and the diffusion limited aggregation model were used to simulate the micron texture. Results The fractal dimensions of granule distribution and corpuscle superficial area are quite conformed with those of measurement. Conclusion The texture parameters of engine particle cluster can be obtained precisely by use of fractal theory.
文摘UG and imitation are two parallel hypotheses trying to answer how childrens language acquisition is realized. Imitation fails to explain how children acquire language; however, it helps a lot in childrens language acquisition.
基金supported by the Global Change Research Program of China under Project 2012CB955603the Natural Science Foundation of China under Project 41076115+2 种基金the National Basic Research Program of China under Project 2009CB723903the Public Science and Technology Research Funds of the Ocean under Project 201005019the National High-Tech Research and Development Program of China under Project 2008AA121701
文摘In this study,a 3D virtual reality and visualization engine for rendering the ocean,named VV-Ocean,is designed for marine applications.The design goals of VV-Ocean aim at high fidelity simulation of ocean environment,visualization of massive and multidimensional marine data,and imitation of marine lives.VV-Ocean is composed of five modules,i.e.memory management module,resources management module,scene management module,rendering process management module and interaction management module.There are three core functions in VV-Ocean:reconstructing vivid virtual ocean scenes,visualizing real data dynamically in real time,imitating and simulating marine lives intuitively.Based on VV-Ocean,we establish a sea-land integration platform which can reproduce drifting and diffusion processes of oil spilling from sea bottom to surface.Environment factors such as ocean current and wind field have been considered in this simulation.On this platform oil spilling process can be abstracted as movements of abundant oil particles.The result shows that oil particles blend with water well and the platform meets the requirement for real-time and interactive rendering.VV-Ocean can be widely used in ocean applications such as demonstrating marine operations,facilitating maritime communications,developing ocean games,reducing marine hazards,forecasting the weather over oceans,serving marine tourism,and so on.Finally,further technological improvements of VV-Ocean are discussed.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.71871171,71871173,and 71832010)
文摘One of the assumptions of previous research in evolutionary game dynamics is that individuals use only one rule to update their strategy. In reality, an individual's strategy update rules may change with the environment, and it is possible for an individual to use two or more rules to update their strategy. We consider the case where an individual updates strategies based on the Moran and imitation processes, and establish mixed stochastic evolutionary game dynamics by combining both processes. Our aim is to study how individuals change strategies based on two update rules and how this affects evolutionary game dynamics. We obtain an analytic expression and properties of the fixation probability and fixation times(the unconditional fixation time or conditional average fixation time) associated with our proposed process. We find unexpected results. The fixation probability within the proposed model is independent of the probabilities that the individual adopts the imitation rule update strategy. This implies that the fixation probability within the proposed model is equal to that from the Moran and imitation processes. The one-third rule holds in the proposed mixed model. However, under weak selection, the fixation times are different from those of the Moran and imitation processes because it is connected with the probability that individuals adopt an imitation update rule. Numerical examples are presented to illustrate the relationships between fixation times and the probability that an individual adopts the imitation update rule, as well as between fixation times and selection intensity. From the simulated analysis, we find that the fixation time for a mixed process is greater than that of the Moran process, but is less than that of the imitation process. Moreover, the fixation times for a cooperator in the proposed process increase as the probability of adopting an imitation update increases; however, the relationship becomes more complex than a linear relationship.
基金National Natural Science Foundation of China,Grant/Award Numbers:61703418,61825305。
文摘Here,the challenges of sample efficiency and navigation performance in deep rein-forcement learning for visual navigation are focused and a deep imitation reinforcement learning approach is proposed.Our contributions are mainly three folds:first,a frame-work combining imitation learning with deep reinforcement learning is presented,which enables a robot to learn a stable navigation policy faster in the target-driven navigation task.Second,the surrounding images is taken as the observation instead of sequential images,which can improve the navigation performance for more information.Moreover,a simple yet efficient template matching method is adopted to determine the stop action,making the system more practical.Simulation experiments in the AI-THOR environment show that the proposed approach outperforms previous end-to-end deep reinforcement learning approaches,which demonstrate the effectiveness and efficiency of our approach.
文摘The zone of proximal development(ZPD) and the scaffolding theory are very different,both in terms of their theoretical origins and connotations,and can even be said to be very different.However,during the development of the two concepts,some scholars have misunderstood them,resulting in the two being mistaken for similar concepts and therefore often confused.Professor James Lantolf from Pennsylvania State University(State College,USA) was interviewed by Professor Lili Qin from Dalian University of Foreign Studies(Dalian,China) and provides an indepth analysis of these issues.The interview begins with the theoretical roots,connotations and definitions of the ZPD and scaffolding concepts,and then unravels the story of how they have been“mistakenly loved for life”,and ultimately it is made clear that the two concepts are completely different in their practical application to language teaching and should not continue to be used interchangeably.
基金supported in part by the National Natural Science Foundation of China under Grant 61971084 and Grant 62001073in part by the National Natural Science Foundation of Chongqing under Grant cstc2019jcyj-msxmX0208in part by the open research fund of National Mobile Communications Research Laboratory,Southeast University,under Grant 2020D05.
文摘Mobile Edge Computing(MEC)is promising to alleviate the computation and storage burdens for terminals in wireless networks.The huge energy consumption of MEC servers challenges the establishment of smart cities and their service time powered by rechargeable batteries.In addition,Orthogonal Multiple Access(OMA)technique cannot utilize limited spectrum resources fully and efficiently.Therefore,Non-Orthogonal Multiple Access(NOMA)-based energy-efficient task scheduling among MEC servers for delay-constraint mobile applications is important,especially in highly-dynamic vehicular edge computing networks.The various movement patterns of vehicles lead to unbalanced offloading requirements and different load pressure for MEC servers.Self-Imitation Learning(SIL)-based Deep Reinforcement Learning(DRL)has emerged as a promising machine learning technique to break through obstacles in various research fields,especially in time-varying networks.In this paper,we first introduce related MEC technologies in vehicular networks.Then,we propose an energy-efficient approach for task scheduling in vehicular edge computing networks based on DRL,with the purpose of both guaranteeing the task latency requirement for multiple users and minimizing total energy consumption of MEC servers.Numerical results demonstrate that the proposed algorithm outperforms other methods.
文摘Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly accomplish driving functions. Speaking of machine vision, deep learning techniques, and specifically convolutional neural networks, have been proven to be the state of the art technology in the field. As these networks typically involve millions of parameters and elements, designing an optimal architecture for deep learning structures is a difficult task which is globally under investigation by researchers. This study experimentally evaluates the impact of three major architectural properties of convolutional networks, including the number of layers, filters, and filter size on their performance. In this study, several models with different properties are developed,equally trained, and then applied to an autonomous car in a realistic simulation environment. A new ensemble approach is also proposed to calculate and update weights for the models regarding their mean squared error values. Based on design properties,performance results are reported and compared for further investigations. Surprisingly, the number of filters itself does not largely affect the performance efficiency. As a result, proper allocation of filters with different kernel sizes through the layers introduces a considerable improvement in the performance.Achievements of this study will provide the researchers with a clear clue and direction in designing optimal network architectures for deep learning purposes.
