The main idea of reinforcement learning is evaluating the chosen action depending on the current reward.According to this concept,many algorithms achieved proper performance on classic Atari 2600 games.The main challe...The main idea of reinforcement learning is evaluating the chosen action depending on the current reward.According to this concept,many algorithms achieved proper performance on classic Atari 2600 games.The main challenge is when the reward is sparse or missing.Such environments are complex exploration environments likeMontezuma’s Revenge,Pitfall,and Private Eye games.Approaches built to deal with such challenges were very demanding.This work introduced a different reward system that enables the simple classical algorithm to learn fast and achieve high performance in hard exploration environments.Moreover,we added some simple enhancements to several hyperparameters,such as the number of actions and the sampling ratio that helped improve performance.We include the extra reward within the human demonstrations.After that,we used Prioritized Double Deep Q-Networks(Prioritized DDQN)to learning from these demonstrations.Our approach enabled the Prioritized DDQNwith a short learning time to finish the first level of Montezuma’s Revenge game and to perform well in both Pitfall and Private Eye.We used the same games to compare our results with several baselines,such as the Rainbow and Deep Q-learning from demonstrations(DQfD)algorithm.The results showed that the new rewards system enabled Prioritized DDQN to out-perform the baselines in the hard exploration games with short learning time.展开更多
This paper is a record of an interview discussion.It explains the demonstration process of the Three Gorges pro-ject in aspects of flood control and navigation,investment,settlement,sediment,ecological environment,geo...This paper is a record of an interview discussion.It explains the demonstration process of the Three Gorges pro-ject in aspects of flood control and navigation,investment,settlement,sediment,ecological environment,geological disasters,science and technology and democratic way of demonstration work.It shows clearly that the demonstra-tional conclusion is fully in conformity with the actual situation.展开更多
In this paper, we propose a new prediction from expert demonstration （PED） methodology to improve reliability and safety in tele-surgery. Data was collected from expert （clinician） demonstrations for the procedure...In this paper, we propose a new prediction from expert demonstration （PED） methodology to improve reliability and safety in tele-surgery. Data was collected from expert （clinician） demonstrations for the procedure of trocar insertion. We encoded a set of force, torque and penetration trajectories by using a Gaussian mixture model （GMM）. A generalization of these profiles and associated parameters were retrieved by Gaussian mixture regression （GMR）. We validated the proposed methodology for tele-robotic placement of the trocar in two stages. First, we tested the efficacy of the proposed PED approach for handling transmission error and latency. Our results showed that for the average case （12% packet error and 1070 loss of packet）, a 58.8~0 improvement in performance was obtained in comparison to using an extended Kalman filter. Next, we validated the methodology for surgical assistance on 15 participants. A haptic assistance mode was devised based on the proposed PED model to assist inexperienced operators to perform the procedure. The PED model was tested for instrument deviation, penetration force and penetration depth. Preliminary study results showed that participants with PED assistance performed the task with more consistency and exerted lesser penetration force than subjects without assistance.展开更多
Autonomous planning is a significant development direction of the space manipulator,and learning from demonstrations(LfD)is a potential strategy for complex tasks in the field.However,separating control from planning ...Autonomous planning is a significant development direction of the space manipulator,and learning from demonstrations(LfD)is a potential strategy for complex tasks in the field.However,separating control from planning may cause large torque fluctuations and energy consumptions,even instability or danger in control of space manipulators,especially for the planning based on the human demonstrations.Therefore,we present an autonomous planning and control strategy for space manipulators based on LfD and focus on the dynamics uncertainty problem,a common problem of actual manipulators.The process can be divided into three stages:firstly,we reproduced the stochastic directed trajectory based on the Gaussian process-based LfD;secondly,we built the model of the stochastic dynamics of the actual manipulator with Gaussian process;thirdly,we designed an optimal controller based on the dynamics model to obtain the improved commanded torques and trajectory,and used the separation theorem to deal with stochastic characteristics during control.We evaluated the strategy with locating pre-screwed bolts experiment by Tiangong-2 manipulator system on the ground.The result showed that,compared with other strategies,the strategy proposed in this paper could significantly reduce torque fluctuations and energy consumptions,and its precision can meet the task requirements.展开更多
In this paper, a detailed theoretical study on the characteristics of cone-shaped inwall capillary-based microsphere resonators is described and demonstrated for sensing applications. The maximum, minimum, slope, cont...In this paper, a detailed theoretical study on the characteristics of cone-shaped inwall capillary-based microsphere resonators is described and demonstrated for sensing applications. The maximum, minimum, slope, contrast, and width of the Fano resonance are analyzed. As the transmission coefficient of the capillary resonator increases, the absolute value of the slope of Fano resonances increases to reach its maximum, which is useful for sensors with an ultra-high sensitivity. There occurs another phenomenon of electromagnetically induced transparency when the reflectivity at the capillary–environment interface is close to 100%. We also experimentally demonstrated its capability for temperature and refractive index sensing, with a sensitivity of 10.9 pm∕°C and 431 d B∕RIU basedon the Fano resonance and the Lorentzian line shape, respectively.展开更多
In actor-critic reinforcement learning(RL)algorithms,function estimation errors are known to cause ineffective random exploration at the beginning of training,and lead to overestimated value estimates and suboptimal p...In actor-critic reinforcement learning(RL)algorithms,function estimation errors are known to cause ineffective random exploration at the beginning of training,and lead to overestimated value estimates and suboptimal policies.In this paper,we address the problem by executing advantage rectification with imperfect demonstrations,thus reducing the function estimation errors.Pretraining with expert demonstrations has been widely adopted to accelerate the learning process of deep reinforcement learning when simulations are expensive to obtain.However,existing methods,such as behavior cloning,often assume the demonstrations contain other information or labels with regard to performances,such as optimal assumption,which is usually incorrect and useless in the real world.In this paper,we explicitly handle imperfect demonstrations within the actor-critic RL frameworks,and propose a new method called learning from imperfect demonstrations with advantage rectification(LIDAR).LIDAR utilizes a rectified loss function to merely learn from selective demonstrations,which is derived from a minimal assumption that the demonstrating policies have better performances than our current policy.LIDAR learns from contradictions caused by estimation errors,and in turn reduces estimation errors.We apply LIDAR to three popular actor-critic algorithms,DDPG,TD3 and SAC,and experiments show that our method can observably reduce the function estimation errors,effectively leverage demonstrations far from the optimal,and outperform state-of-the-art baselines consistently in all the scenarios.展开更多
Hydrogen energy development is transitioning from vision and plan-ning to widespread application.To date,more than 60 countries and regions have announced hydrogen energy development strategies focused on accelerating...Hydrogen energy development is transitioning from vision and plan-ning to widespread application.To date,more than 60 countries and regions have announced hydrogen energy development strategies focused on accelerating demonstration projects and real-world deployment.展开更多
A research arena(WARA-PS)for sensing,data fusion,user interaction,planning and control of collaborative autonomous aerial and surface vehicles in public safety applications is presented.The objective is to demonstrate...A research arena(WARA-PS)for sensing,data fusion,user interaction,planning and control of collaborative autonomous aerial and surface vehicles in public safety applications is presented.The objective is to demonstrate scientific discoveries and to generate new directions for future research on autonomous systems for societal challenges.The enabler is a computational infrastructure with a core system architecture for industrial and academic collaboration.This includes a control and command system together with a framework for planning and executing tasks for unmanned surface vehicles and aerial vehicles.The motivating application for the demonstration is marine search and rescue operations.A state-of-art delegation framework for the mission planning together with three specific applications is also presented.The first one concerns model predictive control for cooperative rendezvous of autonomous unmanned aerial and surface vehicles.The second project is about learning to make safe real-time decisions under uncertainty for autonomous vehicles,and the third one is on robust terrain-aided navigation through sensor fusion and virtual reality tele-operation to support a GPS-free positioning system in marine environments.The research results have been experimentally evaluated and demonstrated to industry and public sector audiences at a marine test facility.It would be most difficult to do experiments on this large scale without the WARA-PS research arena.Furthermore,these demonstrator activities have resulted in effective research dissemination with high public visibility,business impact and new research collaborations between academia and industry.展开更多
CT:As the first ITMA ASIA+CITME exhibition held in Singapore,what are the highlights of this show?Are there any activities planned for the exhibition?Charles Beauduin:The first combined exhibition in Singapore will fe...CT:As the first ITMA ASIA+CITME exhibition held in Singapore,what are the highlights of this show?Are there any activities planned for the exhibition?Charles Beauduin:The first combined exhibition in Singapore will feature the unique selling proposition of an ITMA exhibition,such as live machinery demonstrations,and exhibits clustered in product sectors.As it is only a four-day exhibition,our exhibitors would like to concentrate on business and to present their technologies and solutions to the region’s buyers who don’t visit our Europe or China exhibitions.There is a highlight which will add value to our participants’experience-The ITMA Sustainability Forum which is presented by CEMATEX on the third day of the exhibition.展开更多
The increasing complexity of on-orbit tasks imposes great demands on the flexible operation of space robotic arms, prompting the development of space robots from single-arm manipulation to multi-arm collaboration. In ...The increasing complexity of on-orbit tasks imposes great demands on the flexible operation of space robotic arms, prompting the development of space robots from single-arm manipulation to multi-arm collaboration. In this paper, a combined approach of Learning from Demonstration (LfD) and Reinforcement Learning (RL) is proposed for space multi-arm collaborative skill learning. The combination effectively resolves the trade-off between learning efficiency and feasible solution in LfD, as well as the time-consuming pursuit of the optimal solution in RL. With the prior knowledge of LfD, space robotic arms can achieve efficient guided learning in high-dimensional state-action space. Specifically, an LfD approach with Probabilistic Movement Primitives (ProMP) is firstly utilized to encode and reproduce the demonstration actions, generating a distribution as the initialization of policy. Then in the RL stage, a Relative Entropy Policy Search (REPS) algorithm modified in continuous state-action space is employed for further policy improvement. More importantly, the learned behaviors can maintain and reflect the characteristics of demonstrations. In addition, a series of supplementary policy search mechanisms are designed to accelerate the exploration process. The effectiveness of the proposed method has been verified both theoretically and experimentally. Moreover, comparisons with state-of-the-art methods have confirmed the outperformance of the approach.展开更多
Founded in 1993,Zhejiang Rifa Textile Machinery Co.,Ltd.is a national key high-tech enterprise,a leading enterprise in China’s machinery industry,a CIMS engineering demonstration enterprise under the 863 Program,a na...Founded in 1993,Zhejiang Rifa Textile Machinery Co.,Ltd.is a national key high-tech enterprise,a leading enterprise in China’s machinery industry,a CIMS engineering demonstration enterprise under the 863 Program,a national CAD application engineering demonstration enterprise,a hightech enterprise of the National Torch Plan,and a vice president unit of the China Textile Machinery Association.It currently runs three subsidiaries,namely,Shandong Rifa Textile Machinery Co.,Ltd.,Anhui Rifa Textile Machinery Co.,Ltd.and Zhejiang Rifa Textile Machinery Tech Co.,Ltd.展开更多
The No.1 Central Document of 2024 emphasizes the need to learn from and apply the experience of the"Thousand-Village Demonstration,Ten-Thousand-Village Renovation"project to paint a new picture of livable,wo...The No.1 Central Document of 2024 emphasizes the need to learn from and apply the experience of the"Thousand-Village Demonstration,Ten-Thousand-Village Renovation"project to paint a new picture of livable,workable,harmonious,and beautiful villages,thereby accelerating agricultural and rural modernization and better advancing the construction of Chinese modernization.This paper,based on elucidating the scientific connotations and logical pathways of the"Thousand-Village Demonstration,Ten-Thousand-Village Renovation"project and"harmonious and beautiful villages",analyzes the practices of building"harmonious and beautiful villages"in Gansu Province.It proposes learning from the experience of coordinated advancement in the"Thousand-Village Demonstration,Ten-Thousand-Village Renovation"project to strengthen infrastructure and public service construction;learning from the experience of adapting to local conditions to reinforce rural industrial drive and integrated development;learning from the experience of environmental optimization and shaping to accelerate the improvement of human settlements and ecological civilization construction;and learning from the experience of co-construction,co-governance,and sharing to speed up rural governance and spiritual civilization development,thereby aiding the construction of harmonious and beautiful villages in Gansu.展开更多
[Objectives]To address the weeding challenges within the corn and soybean strip intercropping field and identify appropriate herbicide types and application methods suitable for the corn and soybean strip intercroppin...[Objectives]To address the weeding challenges within the corn and soybean strip intercropping field and identify appropriate herbicide types and application methods suitable for the corn and soybean strip intercropping fields in Siyang County.[Methods]The trial comprised six herbicide treatments and one blank control,with investigations conducted to assess efficacy,safety,and yield.[Results]Each herbicide treatment effectively controlled weeds,demonstrated high safety,and enhanced the yields of both soybeans and corn.The combined application of soil sealing with stem and leaf spray exhibited superior overall weed control compared to soil sealing alone.At 28 d following stem and leaf spray,the plant control effect and fresh weight control effect against weeds in the combined treatment of soil sealing with stem and leaf spray all exceeded 89%.[Conclusions]This study offers technical support for advancing the practice of strip intercropping between corn and soybeans.展开更多
Under the blazing sun of Kamuli District in Uganda’s Eastern Region,a group of young farmers gathered around a patch of freshly turned red soil.Cameras rolled as Uganda’s First Deputy Prime Minister Rebecca Kadaga j...Under the blazing sun of Kamuli District in Uganda’s Eastern Region,a group of young farmers gathered around a patch of freshly turned red soil.Cameras rolled as Uganda’s First Deputy Prime Minister Rebecca Kadaga joined local youth to plant the first chilli seedlings on a 10-acre(4.05 hectares)demonstration farm.The live broadcast,aired on the national agricultural television programme Kungula,marked not only the launch of a digital farming project led by AMPA Media,but also symbolised Africa’s growing ambition to unite tradition with technology.展开更多
The diffusion of industrial robot technology has coincided with increasing divergence in firms’market shares,potentially leading to enhanced market power and shifts in the distribution of factor income.This paper inv...The diffusion of industrial robot technology has coincided with increasing divergence in firms’market shares,potentially leading to enhanced market power and shifts in the distribution of factor income.This paper investigates the impact of industrial robot adoption on firms’labor income share and explores the underlying mechanisms,with particular attention to the rise of superstar firms.The findings suggest that,overall,the use of industrial robots contributes to an increase in labor’s income share,reflecting a generally favorable trend for labor’s position in primary income distribution.This effect,however,is markedly heterogeneous across different types of firms,regions,and industries.A significant concern is that robot adoption strengthens firms’relative market power within industries,fueling the emergence of superstar firms.These firms jointly influence labor income share through both a competition effect and a demonstration effect:the former is the main cause of declining labor shares,while the latter introduces a new channel through which labor’s share is further reduced.Although antitrust policies can help improve labor’s income share,they are not well-suited to curbing the market power expansion driven by industrial robot adoption.Thus,the concern over superstar firms’suppression of labor income remains.Amid the intensifying trend of“machines replacing humans”,this paper offers empirical insights into how to address the distributional implications brought about by the rise of superstar firms.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
Within the context of the"Window of Qingtian"initiative for constructing beautiful countryside in the new era,this study focuses on Malingjiao Village in Zhenbu Town,Qingtian County,exploring innovative appr...Within the context of the"Window of Qingtian"initiative for constructing beautiful countryside in the new era,this study focuses on Malingjiao Village in Zhenbu Town,Qingtian County,exploring innovative approaches and practical models for rural revitalization in mountainous areas.By employing a combination of field research,policy analysis,and case studies,this research deeply analyzes the specific measures implemented in Malingjiao Village,including infrastructure enhancement,integration of primary,secondary,and tertiary industries,revitalization of collective assets,ecological conservation,and cultural heritage preservation.The results indicate that,by pursuing strategies of shared prosperity,agricultural-tourism integration,and integrated development of primary,secondary,and tertiary industries,the village has successfully optimized its industrial structure,expanded the collective economy,increased villager incomes,and improved the ecological environment.This study not only provides a referential demonstration model for beautiful countryside construction throughout Qingtian County but also offers empirical and theoretical support for rural revitalization in mountainous regions across southwestern Zhejiang and even the entire province.展开更多
In recent years,in response to the continuously rising demands of agricultural development,corn,as a key staple crop in China,plays an indispensable role in ensuring national food security.This study comprehensively e...In recent years,in response to the continuously rising demands of agricultural development,corn,as a key staple crop in China,plays an indispensable role in ensuring national food security.This study comprehensively evaluates the growth characteristics of various corn varieties and explores the practical benefits of high-yield cultivation strategies.The results show that a reasonable combination of corn varieties,scientific water and fertilizer management,and efficient pest and disease control measures can significantly increase corn yield.The findings of this study are crucial for accelerating the advancement of the corn industry in Nidang Town and its surrounding areas,while also providing valuable experience and technical support for achieving high-yield corn cultivation in similar regions.展开更多
Exploring the specific environmental impacts and mechanisms of China’s sustainable development pilot policy can enrich and expand China’s institutional and practical experiences,offering valuable insights and refere...Exploring the specific environmental impacts and mechanisms of China’s sustainable development pilot policy can enrich and expand China’s institutional and practical experiences,offering valuable insights and references for advancing global environmental sustainability.This study selects the National Innovation Demonstration Zone for Sustainable Development Agenda(NIDZSDA)as the sample and empirically evaluates the effects of the policy on urban environmental quality,using panel data from 74 prefecture-level cities in China between 2006 and 2020.The findings indicate that the sustainable development policy significantly improves urban environmental quality.Two key mechanisms identified are the aggregation of high-quality talent and the enhancement of technological innovation capabilities.Furthermore,the policy exhibits heterogeneous effects across different types of cities,with more pronounced improvements observed in mega and super cities,as well as in resource-based cities.展开更多
Summer residential tourism is the future trend in China because of tourists’living quality improvement,heat crisis,rising market demand,and optimization of the destinations’residential environment,transport and acce...Summer residential tourism is the future trend in China because of tourists’living quality improvement,heat crisis,rising market demand,and optimization of the destinations’residential environment,transport and accessibility.Compared with summer tourism and vacation tourism,summer residential tourism had got less attention and lacks in prospective and preventive research.Hence,this study focused on potential assessment,pattern recognition and phase segmentation of 32 residential tourism destinations in China selected from 4 lists.An index system of 16 indicators from 5 dimensions was established as Summer Residence Index(SRI),and Range method,Entropy weight method and Composite index method were chosen as the core methods.Three main conclusions were as follows.(1)Only 2 typical districts’SRI value were near to 0.6,and 4 destinations were below 0.1,about 26 destinations were at medium-level,which indicated that China’s summer residential tourism was not so popular and only few destinations have stepped into a higher level.(2)Seven patterns could be recognized based on the contribution of the 5 dimensions to SRI value,including 3 single-factor driven patterns and 4 compound factors driven patterns.(3)Like tourist area life cycle(TALC),Unconscious stage,Initial stage,Developmental stage and Maturity stage could be segmented for summer residential destinations with the value of below 0.1,0.1-0.3,0.3-0.5,and above 0.5.Four destinations were under Unconscious stage.Twenty-two destinations were at initiate stage.Only 4 destinations have stepped into development stage and 2 at maturity stage.China’summer residential tourism has just started and has a better prospect.This study is just an attempt and needs further consideration,for example,a tracking study of SRI calculation for each year will be carried to justify the effectiveness of SRI and to check the rationality of the empirical results.As time goes on,policies in housing,residential estate and other aspects should be included as a factor in the SRI index.Data availability should be optimized because of better data sources and new technologies.Some other districts or cities in 2 batches of national Comprehensive Tourism Demonstration Zones(CTDZs)pilots and provincial CTDZs will be further selections of summer residential tourism destinations.展开更多
文摘The main idea of reinforcement learning is evaluating the chosen action depending on the current reward.According to this concept,many algorithms achieved proper performance on classic Atari 2600 games.The main challenge is when the reward is sparse or missing.Such environments are complex exploration environments likeMontezuma’s Revenge,Pitfall,and Private Eye games.Approaches built to deal with such challenges were very demanding.This work introduced a different reward system that enables the simple classical algorithm to learn fast and achieve high performance in hard exploration environments.Moreover,we added some simple enhancements to several hyperparameters,such as the number of actions and the sampling ratio that helped improve performance.We include the extra reward within the human demonstrations.After that,we used Prioritized Double Deep Q-Networks(Prioritized DDQN)to learning from these demonstrations.Our approach enabled the Prioritized DDQNwith a short learning time to finish the first level of Montezuma’s Revenge game and to perform well in both Pitfall and Private Eye.We used the same games to compare our results with several baselines,such as the Rainbow and Deep Q-learning from demonstrations(DQfD)algorithm.The results showed that the new rewards system enabled Prioritized DDQN to out-perform the baselines in the hard exploration games with short learning time.
文摘This paper is a record of an interview discussion.It explains the demonstration process of the Three Gorges pro-ject in aspects of flood control and navigation,investment,settlement,sediment,ecological environment,geological disasters,science and technology and democratic way of demonstration work.It shows clearly that the demonstra-tional conclusion is fully in conformity with the actual situation.
基金supported in part by the"Juan de la Cierva"Spanish Program
文摘In this paper, we propose a new prediction from expert demonstration （PED） methodology to improve reliability and safety in tele-surgery. Data was collected from expert （clinician） demonstrations for the procedure of trocar insertion. We encoded a set of force, torque and penetration trajectories by using a Gaussian mixture model （GMM）. A generalization of these profiles and associated parameters were retrieved by Gaussian mixture regression （GMR）. We validated the proposed methodology for tele-robotic placement of the trocar in two stages. First, we tested the efficacy of the proposed PED approach for handling transmission error and latency. Our results showed that for the average case （12% packet error and 1070 loss of packet）, a 58.8~0 improvement in performance was obtained in comparison to using an extended Kalman filter. Next, we validated the methodology for surgical assistance on 15 participants. A haptic assistance mode was devised based on the proposed PED model to assist inexperienced operators to perform the procedure. The PED model was tested for instrument deviation, penetration force and penetration depth. Preliminary study results showed that participants with PED assistance performed the task with more consistency and exerted lesser penetration force than subjects without assistance.
基金the Foundation for Innovative Research Groups of the National Natural Science Foundation of China(Grant No.51521003)the National Natural Science Foundation of China(Grant No.61803124)the Post-doctor Research Startup Foundation of Heilongjiang Province。
文摘Autonomous planning is a significant development direction of the space manipulator,and learning from demonstrations(LfD)is a potential strategy for complex tasks in the field.However,separating control from planning may cause large torque fluctuations and energy consumptions,even instability or danger in control of space manipulators,especially for the planning based on the human demonstrations.Therefore,we present an autonomous planning and control strategy for space manipulators based on LfD and focus on the dynamics uncertainty problem,a common problem of actual manipulators.The process can be divided into three stages:firstly,we reproduced the stochastic directed trajectory based on the Gaussian process-based LfD;secondly,we built the model of the stochastic dynamics of the actual manipulator with Gaussian process;thirdly,we designed an optimal controller based on the dynamics model to obtain the improved commanded torques and trajectory,and used the separation theorem to deal with stochastic characteristics during control.We evaluated the strategy with locating pre-screwed bolts experiment by Tiangong-2 manipulator system on the ground.The result showed that,compared with other strategies,the strategy proposed in this paper could significantly reduce torque fluctuations and energy consumptions,and its precision can meet the task requirements.
基金National Natural Science Foundation of China(NSFC)(61377081,61675126)
文摘In this paper, a detailed theoretical study on the characteristics of cone-shaped inwall capillary-based microsphere resonators is described and demonstrated for sensing applications. The maximum, minimum, slope, contrast, and width of the Fano resonance are analyzed. As the transmission coefficient of the capillary resonator increases, the absolute value of the slope of Fano resonances increases to reach its maximum, which is useful for sensors with an ultra-high sensitivity. There occurs another phenomenon of electromagnetically induced transparency when the reflectivity at the capillary–environment interface is close to 100%. We also experimentally demonstrated its capability for temperature and refractive index sensing, with a sensitivity of 10.9 pm∕°C and 431 d B∕RIU basedon the Fano resonance and the Lorentzian line shape, respectively.
基金This work was supported by the National Key R&D Plan(2016YFB0100901)the National Natural Science Foundation of China(Grant Nos.U20B2062&61673237)the Beijing Municipal Science&Technology Project(Z191100007419001).
文摘In actor-critic reinforcement learning(RL)algorithms,function estimation errors are known to cause ineffective random exploration at the beginning of training,and lead to overestimated value estimates and suboptimal policies.In this paper,we address the problem by executing advantage rectification with imperfect demonstrations,thus reducing the function estimation errors.Pretraining with expert demonstrations has been widely adopted to accelerate the learning process of deep reinforcement learning when simulations are expensive to obtain.However,existing methods,such as behavior cloning,often assume the demonstrations contain other information or labels with regard to performances,such as optimal assumption,which is usually incorrect and useless in the real world.In this paper,we explicitly handle imperfect demonstrations within the actor-critic RL frameworks,and propose a new method called learning from imperfect demonstrations with advantage rectification(LIDAR).LIDAR utilizes a rectified loss function to merely learn from selective demonstrations,which is derived from a minimal assumption that the demonstrating policies have better performances than our current policy.LIDAR learns from contradictions caused by estimation errors,and in turn reduces estimation errors.We apply LIDAR to three popular actor-critic algorithms,DDPG,TD3 and SAC,and experiments show that our method can observably reduce the function estimation errors,effectively leverage demonstrations far from the optimal,and outperform state-of-the-art baselines consistently in all the scenarios.
文摘Hydrogen energy development is transitioning from vision and plan-ning to widespread application.To date,more than 60 countries and regions have announced hydrogen energy development strategies focused on accelerating demonstration projects and real-world deployment.
基金All authors are partially supported by the Wallenberg AI,Autonomous Systems and Software Program(WASP)funded by the Knut and Alice Wallenberg Foundation.The first and second authors are additionally supported by the ELLIIT Network Organization for Information and Communication Technology,Swedenthe Swedish Foundation for Strategic Research SSF(Smart Systems Project RIT15-0097)+1 种基金The second author is also supported by a RExperts Program Grant 2020A1313030098 from the Guangdong Department of Science and Technology,ChinaThe fifth and eighth authors are additionally supported by the Swedish Research Council.
文摘A research arena(WARA-PS)for sensing,data fusion,user interaction,planning and control of collaborative autonomous aerial and surface vehicles in public safety applications is presented.The objective is to demonstrate scientific discoveries and to generate new directions for future research on autonomous systems for societal challenges.The enabler is a computational infrastructure with a core system architecture for industrial and academic collaboration.This includes a control and command system together with a framework for planning and executing tasks for unmanned surface vehicles and aerial vehicles.The motivating application for the demonstration is marine search and rescue operations.A state-of-art delegation framework for the mission planning together with three specific applications is also presented.The first one concerns model predictive control for cooperative rendezvous of autonomous unmanned aerial and surface vehicles.The second project is about learning to make safe real-time decisions under uncertainty for autonomous vehicles,and the third one is on robust terrain-aided navigation through sensor fusion and virtual reality tele-operation to support a GPS-free positioning system in marine environments.The research results have been experimentally evaluated and demonstrated to industry and public sector audiences at a marine test facility.It would be most difficult to do experiments on this large scale without the WARA-PS research arena.Furthermore,these demonstrator activities have resulted in effective research dissemination with high public visibility,business impact and new research collaborations between academia and industry.
文摘CT:As the first ITMA ASIA+CITME exhibition held in Singapore,what are the highlights of this show?Are there any activities planned for the exhibition?Charles Beauduin:The first combined exhibition in Singapore will feature the unique selling proposition of an ITMA exhibition,such as live machinery demonstrations,and exhibits clustered in product sectors.As it is only a four-day exhibition,our exhibitors would like to concentrate on business and to present their technologies and solutions to the region’s buyers who don’t visit our Europe or China exhibitions.There is a highlight which will add value to our participants’experience-The ITMA Sustainability Forum which is presented by CEMATEX on the third day of the exhibition.
基金co-supported by the National Natural Science Foundation of China(No.12372045)the Guangdong Basic and Applied Basic Research Foundation,China(No.2023B1515120018)the Shenzhen Science and Technology Program,China(No.JCYJ20220818102207015).
文摘The increasing complexity of on-orbit tasks imposes great demands on the flexible operation of space robotic arms, prompting the development of space robots from single-arm manipulation to multi-arm collaboration. In this paper, a combined approach of Learning from Demonstration (LfD) and Reinforcement Learning (RL) is proposed for space multi-arm collaborative skill learning. The combination effectively resolves the trade-off between learning efficiency and feasible solution in LfD, as well as the time-consuming pursuit of the optimal solution in RL. With the prior knowledge of LfD, space robotic arms can achieve efficient guided learning in high-dimensional state-action space. Specifically, an LfD approach with Probabilistic Movement Primitives (ProMP) is firstly utilized to encode and reproduce the demonstration actions, generating a distribution as the initialization of policy. Then in the RL stage, a Relative Entropy Policy Search (REPS) algorithm modified in continuous state-action space is employed for further policy improvement. More importantly, the learned behaviors can maintain and reflect the characteristics of demonstrations. In addition, a series of supplementary policy search mechanisms are designed to accelerate the exploration process. The effectiveness of the proposed method has been verified both theoretically and experimentally. Moreover, comparisons with state-of-the-art methods have confirmed the outperformance of the approach.
文摘Founded in 1993,Zhejiang Rifa Textile Machinery Co.,Ltd.is a national key high-tech enterprise,a leading enterprise in China’s machinery industry,a CIMS engineering demonstration enterprise under the 863 Program,a national CAD application engineering demonstration enterprise,a hightech enterprise of the National Torch Plan,and a vice president unit of the China Textile Machinery Association.It currently runs three subsidiaries,namely,Shandong Rifa Textile Machinery Co.,Ltd.,Anhui Rifa Textile Machinery Co.,Ltd.and Zhejiang Rifa Textile Machinery Tech Co.,Ltd.
基金Supported by 2025 Gansu Provincial Party School(Institute of Administration)System Social Science Planning Project(QSDXYB2025046).
文摘The No.1 Central Document of 2024 emphasizes the need to learn from and apply the experience of the"Thousand-Village Demonstration,Ten-Thousand-Village Renovation"project to paint a new picture of livable,workable,harmonious,and beautiful villages,thereby accelerating agricultural and rural modernization and better advancing the construction of Chinese modernization.This paper,based on elucidating the scientific connotations and logical pathways of the"Thousand-Village Demonstration,Ten-Thousand-Village Renovation"project and"harmonious and beautiful villages",analyzes the practices of building"harmonious and beautiful villages"in Gansu Province.It proposes learning from the experience of coordinated advancement in the"Thousand-Village Demonstration,Ten-Thousand-Village Renovation"project to strengthen infrastructure and public service construction;learning from the experience of adapting to local conditions to reinforce rural industrial drive and integrated development;learning from the experience of environmental optimization and shaping to accelerate the improvement of human settlements and ecological civilization construction;and learning from the experience of co-construction,co-governance,and sharing to speed up rural governance and spiritual civilization development,thereby aiding the construction of harmonious and beautiful villages in Gansu.
文摘[Objectives]To address the weeding challenges within the corn and soybean strip intercropping field and identify appropriate herbicide types and application methods suitable for the corn and soybean strip intercropping fields in Siyang County.[Methods]The trial comprised six herbicide treatments and one blank control,with investigations conducted to assess efficacy,safety,and yield.[Results]Each herbicide treatment effectively controlled weeds,demonstrated high safety,and enhanced the yields of both soybeans and corn.The combined application of soil sealing with stem and leaf spray exhibited superior overall weed control compared to soil sealing alone.At 28 d following stem and leaf spray,the plant control effect and fresh weight control effect against weeds in the combined treatment of soil sealing with stem and leaf spray all exceeded 89%.[Conclusions]This study offers technical support for advancing the practice of strip intercropping between corn and soybeans.
文摘Under the blazing sun of Kamuli District in Uganda’s Eastern Region,a group of young farmers gathered around a patch of freshly turned red soil.Cameras rolled as Uganda’s First Deputy Prime Minister Rebecca Kadaga joined local youth to plant the first chilli seedlings on a 10-acre(4.05 hectares)demonstration farm.The live broadcast,aired on the national agricultural television programme Kungula,marked not only the launch of a digital farming project led by AMPA Media,but also symbolised Africa’s growing ambition to unite tradition with technology.
基金supported by General Project of the National Social Science Fund of China(NSSFC),“Mechanisms and Strategies of Artificial Intelligence’s Impact on Inter-firm Wage Disparities”(Grant No.21BJY097).
文摘The diffusion of industrial robot technology has coincided with increasing divergence in firms’market shares,potentially leading to enhanced market power and shifts in the distribution of factor income.This paper investigates the impact of industrial robot adoption on firms’labor income share and explores the underlying mechanisms,with particular attention to the rise of superstar firms.The findings suggest that,overall,the use of industrial robots contributes to an increase in labor’s income share,reflecting a generally favorable trend for labor’s position in primary income distribution.This effect,however,is markedly heterogeneous across different types of firms,regions,and industries.A significant concern is that robot adoption strengthens firms’relative market power within industries,fueling the emergence of superstar firms.These firms jointly influence labor income share through both a competition effect and a demonstration effect:the former is the main cause of declining labor shares,while the latter introduces a new channel through which labor’s share is further reduced.Although antitrust policies can help improve labor’s income share,they are not well-suited to curbing the market power expansion driven by industrial robot adoption.Thus,the concern over superstar firms’suppression of labor income remains.Amid the intensifying trend of“machines replacing humans”,this paper offers empirical insights into how to address the distributional implications brought about by the rise of superstar firms.
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Basic Scientific Research Operating Funds Program for Provincial Higher Education Institutions of Zhejiang College of Construction.
文摘Within the context of the"Window of Qingtian"initiative for constructing beautiful countryside in the new era,this study focuses on Malingjiao Village in Zhenbu Town,Qingtian County,exploring innovative approaches and practical models for rural revitalization in mountainous areas.By employing a combination of field research,policy analysis,and case studies,this research deeply analyzes the specific measures implemented in Malingjiao Village,including infrastructure enhancement,integration of primary,secondary,and tertiary industries,revitalization of collective assets,ecological conservation,and cultural heritage preservation.The results indicate that,by pursuing strategies of shared prosperity,agricultural-tourism integration,and integrated development of primary,secondary,and tertiary industries,the village has successfully optimized its industrial structure,expanded the collective economy,increased villager incomes,and improved the ecological environment.This study not only provides a referential demonstration model for beautiful countryside construction throughout Qingtian County but also offers empirical and theoretical support for rural revitalization in mountainous regions across southwestern Zhejiang and even the entire province.
文摘In recent years,in response to the continuously rising demands of agricultural development,corn,as a key staple crop in China,plays an indispensable role in ensuring national food security.This study comprehensively evaluates the growth characteristics of various corn varieties and explores the practical benefits of high-yield cultivation strategies.The results show that a reasonable combination of corn varieties,scientific water and fertilizer management,and efficient pest and disease control measures can significantly increase corn yield.The findings of this study are crucial for accelerating the advancement of the corn industry in Nidang Town and its surrounding areas,while also providing valuable experience and technical support for achieving high-yield corn cultivation in similar regions.
基金fund support was received from National Social Science Fund of China[Grant No.23BJL010].
文摘Exploring the specific environmental impacts and mechanisms of China’s sustainable development pilot policy can enrich and expand China’s institutional and practical experiences,offering valuable insights and references for advancing global environmental sustainability.This study selects the National Innovation Demonstration Zone for Sustainable Development Agenda(NIDZSDA)as the sample and empirically evaluates the effects of the policy on urban environmental quality,using panel data from 74 prefecture-level cities in China between 2006 and 2020.The findings indicate that the sustainable development policy significantly improves urban environmental quality.Two key mechanisms identified are the aggregation of high-quality talent and the enhancement of technological innovation capabilities.Furthermore,the policy exhibits heterogeneous effects across different types of cities,with more pronounced improvements observed in mega and super cities,as well as in resource-based cities.
基金Supported by Ningxia Natural Science Foundation(2024AAC03100).
文摘Summer residential tourism is the future trend in China because of tourists’living quality improvement,heat crisis,rising market demand,and optimization of the destinations’residential environment,transport and accessibility.Compared with summer tourism and vacation tourism,summer residential tourism had got less attention and lacks in prospective and preventive research.Hence,this study focused on potential assessment,pattern recognition and phase segmentation of 32 residential tourism destinations in China selected from 4 lists.An index system of 16 indicators from 5 dimensions was established as Summer Residence Index(SRI),and Range method,Entropy weight method and Composite index method were chosen as the core methods.Three main conclusions were as follows.(1)Only 2 typical districts’SRI value were near to 0.6,and 4 destinations were below 0.1,about 26 destinations were at medium-level,which indicated that China’s summer residential tourism was not so popular and only few destinations have stepped into a higher level.(2)Seven patterns could be recognized based on the contribution of the 5 dimensions to SRI value,including 3 single-factor driven patterns and 4 compound factors driven patterns.(3)Like tourist area life cycle(TALC),Unconscious stage,Initial stage,Developmental stage and Maturity stage could be segmented for summer residential destinations with the value of below 0.1,0.1-0.3,0.3-0.5,and above 0.5.Four destinations were under Unconscious stage.Twenty-two destinations were at initiate stage.Only 4 destinations have stepped into development stage and 2 at maturity stage.China’summer residential tourism has just started and has a better prospect.This study is just an attempt and needs further consideration,for example,a tracking study of SRI calculation for each year will be carried to justify the effectiveness of SRI and to check the rationality of the empirical results.As time goes on,policies in housing,residential estate and other aspects should be included as a factor in the SRI index.Data availability should be optimized because of better data sources and new technologies.Some other districts or cities in 2 batches of national Comprehensive Tourism Demonstration Zones(CTDZs)pilots and provincial CTDZs will be further selections of summer residential tourism destinations.
