Insufficient interfacial activity and poor wettability between fibers and matrix are the two main factors limiting the improvement of mechanical properties of Carbon Fiber Reinforced Plastics(CFRP).Owl feathers are kn...Insufficient interfacial activity and poor wettability between fibers and matrix are the two main factors limiting the improvement of mechanical properties of Carbon Fiber Reinforced Plastics(CFRP).Owl feathers are known for their unique compact structure;they are not only lightweight but also strong.In this study,an in-depth look at owl feathers was made and it found that owl feathers not only have the macro branches structure between feather shafts and branches but also have fine feather structures on the branches.The presence of these fine feather structures increases the specific surface area of the plume branches and allows neighboring plume branches to hook up with each other,forming an effective mechanical interlocking structure.These structures bring owl feathers excellent mechanical properties.Inspired by the natural structure of owl feathers,a weaving technique and a sizing process were combined to prepare bionic Carbon Fiber(CF)fabrics and then to fabricate the bionic CFRP with structural characteristics similar to owl feathers.To evaluate the effect of the fine feather structure on the mechanical properties of CFRP,a mechanical property study on CFRP with and without the fine feather imitation structure were conducted.The experimental results show that the introduction of the fine feather branch structure enhance the mechanical properties of CFRP significantly.Specifically,the tensile strength of the composites increased by 6.42%and 13.06%and the flexural strength increased by 8.02%and 16.87%in the 0°and 90°sample directions,respectively.These results provide a new design idea for the improvement of the mechanical properties of the CFRP,promoting the application of CFRP in engineering fields,such as automotive transportation,rail transit,aerospace,and construction.展开更多
This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization balanc...This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization balance.By integrating surrogate models to approximate the objective functions,SMOGWO significantly improves the efficiency and accuracy of the optimization process.The effectiveness of this approach is evaluated using the CEC2009 multi-objective test function suite,where SMOGWO achieves a superiority rate of 76.67%compared to other leading multi-objective algorithms.Furthermore,the practical applicability of SMOGWO is demonstrated through a case study on empty and heavy train allocation,which validates its ability to balance line capacity,minimize transportation costs,and optimize the technical combination of heavy trains.The research highlights SMOGWO's potential as a robust solution for optimization challenges in railway transportation,offering valuable contributions toward enhancing operational efficiency and promoting sustainable development in the sector.展开更多
Biomimetics has recently emerged as an interesting approach to enhance renewable energy technologies.In this work,bioinspired Trailing Edge Serrations(TES)were evaluated on a typical Vertical Axis Wind Turbine(VAWT)ai...Biomimetics has recently emerged as an interesting approach to enhance renewable energy technologies.In this work,bioinspired Trailing Edge Serrations(TES)were evaluated on a typical Vertical Axis Wind Turbine(VAWT)airfoil,the DU06-W200.As noise reduction benefits of these mechanisms are already well-established,this study focuses on their impact on airfoil and VAWT performance.A saw-tooth geometry was chosen based on VAWT specifications and existing research,followed by a detailed assessment through wind tunnel tests using a newly developed aerodynamic balance.For a broad spectrum of attack angles and Reynolds numbers,lift,drag,and pitching moments were carefully measured.The results show that TES enhance the lift-to-drag ratio,especially in stalled conditions,and postpone stall at negative angles,expanding the effective performance range.A notable increase in pitching moment also is also observed,relevant for blade-strut joint design.Additionally,the impact on turbine performance was estimated using an analytical model,demonstrating excellent accuracy when compared against previous experimental results.TES offer a modest 2%improve-ment in peak performance,though they slightly narrow the optimal tip-speed ratio zone.Despite this,the potential noise reduction and performance gains make TES a valuable addition to VAWT designs,especially in urban settings.展开更多
In the visual‘teach-and-repeat’task,a mobile robot is expected to perform path following based on visual memory acquired along a route that it has traversed.Following a visually familiar route is also a critical nav...In the visual‘teach-and-repeat’task,a mobile robot is expected to perform path following based on visual memory acquired along a route that it has traversed.Following a visually familiar route is also a critical navigation skill for foraging insects,which they accomplish robustly despite tiny brains.Inspired by the mushroom body structure in the insect brain and its well-understood associative learning ability,we develop an embodied model that can accomplish visual teach-and-repeat efficiently.Critical to the performance is steering the robot body reflexively based on the relative familiarity of left and right visual fields,eliminating the need for stopping and scanning regularly for optimal directions.The model is robust against noise in visual processing and motor control and can produce performance comparable to pure pursuit or visual localisation methods that rely heavily on the estimation of positions.The model is tested on a real robot and also shown to be able to correct for significant intrinsic steering bias.展开更多
Piezoelectric actuators are widely utilized in positioning systems to realize nano-scale resolution. However, the backward motion always generates for some piezoelectric actuators, which reduces the working efficiency...Piezoelectric actuators are widely utilized in positioning systems to realize nano-scale resolution. However, the backward motion always generates for some piezoelectric actuators, which reduces the working efficiency. Bionic motions have already been employed in the field of piezoelectric actuators to realize better performance. By imitating the movement form of seals, seal type piezoelectric actuator is capable to realize large operating strokes easily. Nevertheless, the conventional seal type piezoelectric actuator has a complicated structure and control system, which limits further applications. Hence, an improved bionic piezoelectric actuator is proposed to realize a long motion stroke and eliminate backward movement with a simplified structure and control method in this study. The composition and motion principle of the designed actuator are discussed, and the performance is investigated with simulations and experiments. Results confirm that the presented actuator effectively realizes the linear movement that has a large working stroke stably without backward motion. The smallest stepping displacement ΔL is 0.2 μm under 1 Hz and 50 V. The largest motion speed is 900 μm/s with 900 Hz and 120 V. The largest vertical and horizontal load are 250 g and 12 g, respectively. This work shows that the improved bionic piezoelectric actuator is feasible for eliminating backward motion and has a great working ability.展开更多
The lower limb assisted exoskeleton is a prominent area of research within the field of exoskeleton technology.However,several challenges remain,including the development of flexible actuators,high battery consumption...The lower limb assisted exoskeleton is a prominent area of research within the field of exoskeleton technology.However,several challenges remain,including the development of flexible actuators,high battery consumption,the risk of joint misalignment,and limited assistive capabilities.This paper proposes a compact flexible actuator incorporating two elastic elements named Adjustable Energy Storage Series Elastic Actuator(AES-SEA),which combining an adjustable energy storage device with a series elastic actuator for application in exoskeleton hip joints.This design aims to enhance energy efficiency and improve assistive effects.Subsequently,we introduce a novel knee joint bionic structure based on a pulley-groove configuration and a four-link mechanism,designed to replicate human knee joint motion and prevent joint misalignment.Additionally,we propose an innovative controller that integrates concepts from Linear Quadratic Regulator(LQR)control and virtual tunnel for level walking assistance.This controller modulates the assisted reference trajectory using the virtual tunnel concept,enabling different levels of assistance both inside and outside the tunnel by adjusting the parameters Q and R.This approach enhances the assisting force while ensuring the safety of human-computer interaction.Finally,metabolic experiments were conducted to evaluate the effectiveness of the exoskeleton assistance.展开更多
Flexible sensors,a class of devices that can convert external mechanical or physical signals into changes in resistance,capacitance,or current,have developed rapidly since the concept was first proposed.Due to the spe...Flexible sensors,a class of devices that can convert external mechanical or physical signals into changes in resistance,capacitance,or current,have developed rapidly since the concept was first proposed.Due to the special properties and naturally occurring excellent microstructures of biomaterials,it can provide more desirable properties to flexible devices.This paper systematically discusses the commonly used biomaterials for bio-based flexible devices in current research applications and their deployment in preparing flexible sensors with different mechanisms.According to the characteristics of other properties and application requirements of biomaterials,the mechanisms of their functional group properties,special microstructures,and bonding interactions in the context of various sensing applications are presented in detail.The practical application scenarios of biomaterial-based flexible devices are highlighted,including human-computer interactions,energy harvesting,wound healing,and related biomedical applications.Finally,this paper also reviews in detail the limitations of biobased materials in the construction of flexible devices and presents challenges and trends in the development of biobased flexible sensors,as well as to better explore the properties of biomaterials to ensure functional synergy within the composite materials.展开更多
Gecko-inspired robots have significant potential applications;however,deviations in the yaw direction during locomotion are inevitable for legged robots that lack external sensing.These deviations cause the robot to s...Gecko-inspired robots have significant potential applications;however,deviations in the yaw direction during locomotion are inevitable for legged robots that lack external sensing.These deviations cause the robot to stray from its intended path.Therefore,a cost-effective and straightforward solution is essential for reducing this deviation.In nature,the tail is often used to maintain balance and stability.Similarly,it has been used in robots to improve manoeuvrability and stability.Our aim is to reduce this deviation using a morphological computation approach,specifically by adding a tail.To test this hypothesis,we investigated four different tails(rigid plate,rigid gecko-shaped,soft plate,and soft gecko-shaped)and assessed the deviation of the robot with these tails on different slopes.Additionally,to evaluate the influence of different tail parameters,such as material,shape,and linkage,we investigated the locomotion performance in terms of the robot's climbing speed on slopes,its ability to turn at narrow corners,and the resistance of the tails to external disturbances.A new auto-reset joint was designed to ensure that a disturbed tail could be quickly reset.Our results demonstrate that the yaw deviation of the robot can be reduced by applying a tail.Among the four tails,the soft gecko-shaped tail was the most effective for most tasks.In summary,our findings demonstrate the functional role of the tail in reducing yaw deviation,improving climbing ability and stability and provide a reference for selecting the most suitable tail for geckoinspired robots.展开更多
The unidirectional flow of lymphatic fluid depends significantly on the valve structure within the lymphatic system,thus impacting tumor cell metastasis via the lymphatic system.However,existing microdevices for study...The unidirectional flow of lymphatic fluid depends significantly on the valve structure within the lymphatic system,thus impacting tumor cell metastasis via the lymphatic system.However,existing microdevices for studying tumor lymphatic metastasis have overlooked the impact of open-close valve structures on the lymphatic flow field.This paper presents a novel biomimetic lymphatic valve structure,which innovatively incorporates the thin-shell theory into the modeling of lymphatic-mimicking structures.Through finite element simulations,we have systematically analyzed the influence of valve thickness and elasticity on its deformation characteristics.Materials closely matching the actual properties of biological tissues are synthesized.And the soft-etching technique was used to fabricate lymphomimetic microchannels,which were then tested to evaluate their capability in intercepting unidirectional flow.The results showed that the lymphomimetic valve structure had no observable leaks and effectively intercepted unidirectional flow.Our study not only elucidates the mechanism of lymphatic circulation but also presents a dependable biomimetic model that could facilitate additional biological investigations and phenotypic drug screening.展开更多
Developing innovative capabilities in university students is essential for individual career success and broader societal advancement.This study introduces a predictive Feature Selection(FS)model named bWRBA-SVM-FS,wh...Developing innovative capabilities in university students is essential for individual career success and broader societal advancement.This study introduces a predictive Feature Selection(FS)model named bWRBA-SVM-FS,which combines an enhanced Bat Algorithm(BA)and Support Vector Machine(SVM).To enhance the optimization capability of BA,water follow search and random follow search are introduced to optimize the efficiency and accuracy of the feature subset search.Experimental validation conducted on the IEEE CEC 2017 benchmark functions and the talented innovative capacity dataset demonstrates the efficacy of the proposed method relative to peer and prominent machine learning models.The experimental results reveal that the predictive accuracy of the bWRBA-SVM-FS model is 97.503%,with a sensitivity of 98.391%.Our findings indicate significant predictors of innovation capacity,including project application goals,educational background,and interdisciplinary thinking abilities.The bWRBA-SVM-FS model offers effective strategies for talent selection in higher education,fostering the development of future research leaders.展开更多
Pacinian Corpuscle(PC)is the largest tactile vibration receptor in mammalian skin,with a layered structure that enables signal amplification and high-pass filtering functions.Modern robots feature vibro-tactile sensor...Pacinian Corpuscle(PC)is the largest tactile vibration receptor in mammalian skin,with a layered structure that enables signal amplification and high-pass filtering functions.Modern robots feature vibro-tactile sensors with excellent mechanical properties and fine resolution,but these sensors are prone to low-frequency noise interference when detecting high-frequency vibrations.In this study,a bionic PC with a longitudinally decreasing dynamic fractal structure is proposed.By creating a lumped parameter model of the PC’s layered structure,the bionic PC made of gelatin-chitosan based hydrogel can achieve high-pass filtering and specific frequency band signal amplification without requiring back-end circuits.The experimental results demonstrate that the bionic PC retains the structural characteristics of a natural PC,and the influence of structural factors,such as the number of layers in its shell,on filtration characteristics is explored.Additionally,a vibration source positioning experiment was conducted to simulate the earthquake sensing abilities of elephants.This natural structural design simplifies the filter circuit,is low-cost,cost-effective,stable in performance,and reduces redundancy in the robot’s signal circuit.Integrating this technology with robots can enhance their environmental perception,thereby improving the safety of interactions.展开更多
Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely us...Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely used in pulmonary disease diagnosis,such as pneumonia and tuberculosis.However,traditional feature fusion methods often suffer from feature disparity,information loss,redundancy,and increased complexity,hindering the further extension of DL algorithms.To solve this problem,we propose a Graph-Convolution Fusion Network with Self-Supervised Feature Alignment(Self-FAGCFN)to address the limitations of traditional feature fusion methods in deep learning-based medical image classification for respiratory diseases such as pneumonia and tuberculosis.The network integrates Convolutional Neural Networks(CNNs)for robust feature extraction from two-dimensional grid structures and Graph Convolutional Networks(GCNs)within a Graph Neural Network branch to capture features based on graph structure,focusing on significant node representations.Additionally,an Attention-Embedding Ensemble Block is included to capture critical features from GCN outputs.To ensure effective feature alignment between pre-and post-fusion stages,we introduce a feature alignment loss that minimizes disparities.Moreover,to address the limitations of proposed methods,such as inappropriate centroid discrepancies during feature alignment and class imbalance in the dataset,we develop a Feature-Centroid Fusion(FCF)strategy and a Multi-Level Feature-Centroid Update(MLFCU)algorithm,respectively.Extensive experiments on public datasets LungVision and Chest-Xray demonstrate that the Self-FAGCFN model significantly outperforms existing methods in diagnosing pneumonia and tuberculosis,highlighting its potential for practical medical applications.展开更多
In complex water environments,search tasks often involve multiple Autonomous Underwater Vehicles(AUVs),and a single centralized control cannot handle the complexity and computational burden of large-scale systems.Targ...In complex water environments,search tasks often involve multiple Autonomous Underwater Vehicles(AUVs),and a single centralized control cannot handle the complexity and computational burden of large-scale systems.Target search in complex water environments has always been a major challenge in the field of underwater robots.To address this problem,this paper proposes a multi-biomimetic robot fish collaborative target search method based on Distributed Model Predictive Control(DMPC).First,we established a bionic robot fish kinematic model and a multi-biomimetic robot fish communication model;second,this paper proposed a distributed model predictive control algorithm based on the distributed search theory framework,so that the bionic robot fish can dynamically adjust their search path according to each other’s position information and search status,avoid repeated coverage or missing areas,and thus improve the search efficiency;third,we conducted simulation experiments based on DMPC,and the results showed that the proposed method has a target search success rate of more than 90%in static targets,dynamic targets,and obstacle environments.Finally,we compared this method with Centralized Model Predictive Control(CMPC)and Random Walk(RW)algorithms.The DMPC approach demonstrates significant advantages,achieving a remarkable target search success rate of 94.17%.These findings comprehensively validate the effectiveness and superiority of the proposed methodology.It can be seen that DMPC can effectively dispatch multiple bionic robot fish to work together to achieve efficient search of vast waters.It can significantly improve the flexibility,scalability,robustness and cooperation efficiency of the system and has broad application prospects.展开更多
The radula is a crucial adaptation for food-processing in molluscs.A deeper understanding of the interaction between the radula and the preferred food is lacking,complicating the inference of the precise ecological ro...The radula is a crucial adaptation for food-processing in molluscs.A deeper understanding of the interaction between the radula and the preferred food is lacking,complicating the inference of the precise ecological roles of radular structures.This study presents the first experimental set-up that allows to study the influence of the radular morphology,specifically the degree of tooth-tooth interlocking(so-called collective effect),on the feeding efficiency.For this purpose,physical 3D models of the teeth were designed using CAD software and 3D printing technique.The feeding efficiencies with models of different degree of interlocking were determined by tensile tests,pulling the models trough agar gels with different viscosities.The forces generated by the models and the masses of the removed gel fragments were determined.We found,that radular models with a high degree of tooth–tooth interlocking performed best as they were able to remove most agar.We additionally broke the teeth and determined,that the teeth with the highest degree of interlocking could resist to highest force.Overall,the study highlights the complex interplay between radular morphology and its ecological function,suggesting that even minor morphological alterations can significantly impact the efficiency and effectiveness of food gathering.Understanding these interactions cannot only shed light on the ecological adaptations of molluscs,but provide further insights into development of more effective grinding,scraping,and cleaning technical devices.展开更多
The global incidence of Alzheimer's Disease(AD)is on a swift rise.The Electroencephalogram(EEG)signals is an effective tool for the identification of AD and its initial Mild Cognitive Impairment(MCI)stage using ma...The global incidence of Alzheimer's Disease(AD)is on a swift rise.The Electroencephalogram(EEG)signals is an effective tool for the identification of AD and its initial Mild Cognitive Impairment(MCI)stage using machine learning models.Analysis of AD using EEG involves multi-channel analysis.However,the use of multiple channels may impact the classification performance due to data redundancy and complexity.In this work,a hybrid EEG channel selection is proposed using a combination of Reptile Search Algorithm and Snake Optimizer(RSO)for AD and MCI detection based on decomposition methods.Empirical Mode Decomposition(EMD),Low-Complexity Orthogonal Wavelet Filter Banks(LCOWFB),Variational Mode Decomposition,and discrete-wavelet transform decomposition techniques have been employed for subbands-based EEG analysis.We extracted thirty-four features from each subband of EEG signals.Finally,a hybrid RSO optimizer is compared with five individual metaheuristic algorithms for effective channel selection.The effectiveness of this model is assessed by two publicly accessible AD EEG datasets.An accuracy of 99.22% was achieved for binary classification from RSO with EMD using 4(out of 16)EEG channels.Moreover,the RSO with LCOWFBs obtained 89.68%the average accuracy for three-class classification using 7(out of 19)channels.The performance reveals that RSO performs better than individual Metaheuristic algorithms with 60%fewer channels and improved accuracy of 4%than existing AD detection techniques.展开更多
Muscle Shortening Maneuver(MSM)is a rehabilitation technique successfully applied to several pathological conditions.The concept is to passively elongate and shorten the target muscle group of the affected limb.As a r...Muscle Shortening Maneuver(MSM)is a rehabilitation technique successfully applied to several pathological conditions.The concept is to passively elongate and shorten the target muscle group of the affected limb.As a result,the functionality(muscle strength and range of motion)of that limb is improved.The existing system induces these oscillations manually or without any feedback control,which can compromise the effectiveness and standardization of MSM.In this paper,we present a mechatronic system that can precisely deliver motion oscillations to the upper limb for a controllable execution of MSM.First,we collected the parameters(frequency and amplitude of the oscillations)from a system where a motor was heuristically used by a well-experienced therapist to induce the oscillations(without any feedback control).Based on these specifications,we chose the motor and rebuilt the experimental setup,implementing a sliding mode control with a sliding perturbation observer.With our system,the operator can choose a given frequency and amplitude of the oscillations within the range we experimentally observed.We tested our system with ten participants of different anthropometry.We found that our system can accurately reproduce oscillations in the frequency range 0.8 to 1.2 Hz and amplitude range 2 to 6 cm,with a maximum percentage normalized root mean square error around 7%.展开更多
Laser-Induced Graphene (LIG) is regarded as a promising sensor carrier due to its inherent three-dimensional porous structure. However, as two mutually exclusive properties of the pressure sensor, sensitivity and work...Laser-Induced Graphene (LIG) is regarded as a promising sensor carrier due to its inherent three-dimensional porous structure. However, as two mutually exclusive properties of the pressure sensor, sensitivity and working range are difficult to be further improved by the single porous structure. Inspired by the unique geometry of Oxalis corniculata L. leaves, we here propose a novel method consist of laser pre-etching and inducing steps to fabricate LIG-based electrodes with a two-stage architecture featuring microjigsaw and microporous structures. The following injection of liquid-silicone significantly improves the friction resistance and bending reliability of LIG materials. The interface contact between external microjigsaw structures induces substantial resistance changes, and the internal microporous structure exhibits reversibility during dynamic deformation. Consequently, the jigsaw-like pressure sensor achieves a balanced performance with sensitivities of 3.64, 1.20 and 0.03 kPa^(- 1) in pressure range of 0 -20, 20 - 40 and 40 - 150 kPa, respectively. The bionic LIG-based pressure sensor serves as the core component and further integrated with an all-in-one wireless transmission system capable of monitoring various health parameters such as subtle pulse rates, heartbeat rhythms, sounds, etc., indicating broad prospects in future wearable electronics.展开更多
Achieving robust walking for different stairs is one of the most challenging tasks for quadruped robots in real world.Traditional model-based methods heavily rely on environmental factors,are burdened by intricate mod...Achieving robust walking for different stairs is one of the most challenging tasks for quadruped robots in real world.Traditional model-based methods heavily rely on environmental factors,are burdened by intricate modelling complexities,and lack generalizability.The potential for advancements in adaptive locomotion control,often impeded by complex modelling processes,can be substantially enhanced through the application of Reinforcement Learning(RL).In this paper,a learning-based method is proposed to directionally enhance the stair-climbing skill of quadruped robots under different stair conditions.First,the general policy model based on proprioceptive perception is trained as a pre-training model.Then,the pre-training model was initialized,and different terrain information from the stairs was introduced for customized training to enhance the stair-climbing skill without affecting the existing locomotion performance.Finally,the customized control policy is deployed to the real robot to realize motion control in real environments.The experimental results demonstrate that the customized control policy can significantly improve the motion performance of quadruped robots when facing complex stair terrains and has certain generalizability in other complex terrains.The proposed algorithm can be extended to various terrestrial environments.展开更多
Metaheuristic algorithms are pivotal in cloud task scheduling. However, the complexity and uncertainty of the scheduling problem severely limit algorithms. To bypass this circumvent, numerous algorithms have been prop...Metaheuristic algorithms are pivotal in cloud task scheduling. However, the complexity and uncertainty of the scheduling problem severely limit algorithms. To bypass this circumvent, numerous algorithms have been proposed. The Hiking Optimization Algorithm (HOA) have been used in multiple fields. However, HOA suffers from local optimization, slow convergence, and low efficiency of late iteration search when solving cloud task scheduling problems. Thus, this paper proposes an improved HOA called CMOHOA. It collaborates with multi-strategy to improve HOA. Specifically, Chebyshev chaos is introduced to increase population diversity. Then, a hybrid speed update strategy is designed to enhance convergence speed. Meanwhile, an adversarial learning strategy is introduced to enhance the search capability in the late iteration. Different scenarios of scheduling problems are used to test the CMOHOA’s performance. First, CMOHOA was used to solve basic cloud computing task scheduling problems, and the results showed that it reduced the average total cost by 10% or more. Secondly, CMOHOA has been applied to edge fog cloud scheduling problems, and the results show that it reduces the average total scheduling cost by 2% or more. Finally, CMOHOA reduced the average total cost by 7% or more in scheduling problems for information transmission.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
基金supported by the Science and Technology Development Program of Jilin Province(No.20240101122JC)and(No.20240101143JC)the Key Scientific and Technological Research and Development Projects of Jilin Provincial Science and Technology Department(Grant Number 20230201108GX)。
文摘Insufficient interfacial activity and poor wettability between fibers and matrix are the two main factors limiting the improvement of mechanical properties of Carbon Fiber Reinforced Plastics(CFRP).Owl feathers are known for their unique compact structure;they are not only lightweight but also strong.In this study,an in-depth look at owl feathers was made and it found that owl feathers not only have the macro branches structure between feather shafts and branches but also have fine feather structures on the branches.The presence of these fine feather structures increases the specific surface area of the plume branches and allows neighboring plume branches to hook up with each other,forming an effective mechanical interlocking structure.These structures bring owl feathers excellent mechanical properties.Inspired by the natural structure of owl feathers,a weaving technique and a sizing process were combined to prepare bionic Carbon Fiber(CF)fabrics and then to fabricate the bionic CFRP with structural characteristics similar to owl feathers.To evaluate the effect of the fine feather structure on the mechanical properties of CFRP,a mechanical property study on CFRP with and without the fine feather imitation structure were conducted.The experimental results show that the introduction of the fine feather branch structure enhance the mechanical properties of CFRP significantly.Specifically,the tensile strength of the composites increased by 6.42%and 13.06%and the flexural strength increased by 8.02%and 16.87%in the 0°and 90°sample directions,respectively.These results provide a new design idea for the improvement of the mechanical properties of the CFRP,promoting the application of CFRP in engineering fields,such as automotive transportation,rail transit,aerospace,and construction.
基金supported by the National Natural Science Foundation of China(Project No.5217232152102391)+2 种基金Sichuan Province Science and Technology Innovation Talent Project(2024JDRC0020)China Shenhua Energy Company Limited Technology Project(GJNY-22-7/2300-K1220053)Key science and technology projects in the transportation industry of the Ministry of Transport(2022-ZD7-132).
文摘This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization balance.By integrating surrogate models to approximate the objective functions,SMOGWO significantly improves the efficiency and accuracy of the optimization process.The effectiveness of this approach is evaluated using the CEC2009 multi-objective test function suite,where SMOGWO achieves a superiority rate of 76.67%compared to other leading multi-objective algorithms.Furthermore,the practical applicability of SMOGWO is demonstrated through a case study on empty and heavy train allocation,which validates its ability to balance line capacity,minimize transportation costs,and optimize the technical combination of heavy trains.The research highlights SMOGWO's potential as a robust solution for optimization challenges in railway transportation,offering valuable contributions toward enhancing operational efficiency and promoting sustainable development in the sector.
基金The authors wish to thank the financial support of the Spanish Ministry of Science,Innovation and Universities in reference to the Project:Efficiency improvement and noise reduction of a vertical axis wind turbine for urban environments(MERTURB)-Ref.MCINN-22-TED2021-131307B-100.
文摘Biomimetics has recently emerged as an interesting approach to enhance renewable energy technologies.In this work,bioinspired Trailing Edge Serrations(TES)were evaluated on a typical Vertical Axis Wind Turbine(VAWT)airfoil,the DU06-W200.As noise reduction benefits of these mechanisms are already well-established,this study focuses on their impact on airfoil and VAWT performance.A saw-tooth geometry was chosen based on VAWT specifications and existing research,followed by a detailed assessment through wind tunnel tests using a newly developed aerodynamic balance.For a broad spectrum of attack angles and Reynolds numbers,lift,drag,and pitching moments were carefully measured.The results show that TES enhance the lift-to-drag ratio,especially in stalled conditions,and postpone stall at negative angles,expanding the effective performance range.A notable increase in pitching moment also is also observed,relevant for blade-strut joint design.Additionally,the impact on turbine performance was estimated using an analytical model,demonstrating excellent accuracy when compared against previous experimental results.TES offer a modest 2%improve-ment in peak performance,though they slightly narrow the optimal tip-speed ratio zone.Despite this,the potential noise reduction and performance gains make TES a valuable addition to VAWT designs,especially in urban settings.
基金support from the Huawei Technologies Co.,Ltd.[grant number YBN2020045132].
文摘In the visual‘teach-and-repeat’task,a mobile robot is expected to perform path following based on visual memory acquired along a route that it has traversed.Following a visually familiar route is also a critical navigation skill for foraging insects,which they accomplish robustly despite tiny brains.Inspired by the mushroom body structure in the insect brain and its well-understood associative learning ability,we develop an embodied model that can accomplish visual teach-and-repeat efficiently.Critical to the performance is steering the robot body reflexively based on the relative familiarity of left and right visual fields,eliminating the need for stopping and scanning regularly for optimal directions.The model is robust against noise in visual processing and motor control and can produce performance comparable to pure pursuit or visual localisation methods that rely heavily on the estimation of positions.The model is tested on a real robot and also shown to be able to correct for significant intrinsic steering bias.
基金supported by The Key Science and Technology Plan Project of Jinhua City,China:2023-3-084,2023-2-011Zhejiang Provincial"Revealing the list and taking command"Project of China KYH06Y22349Open Fund Project of Key Laboratory of CNC Equipment reliability,Ministry of Education JLU-cncr-202407.
文摘Piezoelectric actuators are widely utilized in positioning systems to realize nano-scale resolution. However, the backward motion always generates for some piezoelectric actuators, which reduces the working efficiency. Bionic motions have already been employed in the field of piezoelectric actuators to realize better performance. By imitating the movement form of seals, seal type piezoelectric actuator is capable to realize large operating strokes easily. Nevertheless, the conventional seal type piezoelectric actuator has a complicated structure and control system, which limits further applications. Hence, an improved bionic piezoelectric actuator is proposed to realize a long motion stroke and eliminate backward movement with a simplified structure and control method in this study. The composition and motion principle of the designed actuator are discussed, and the performance is investigated with simulations and experiments. Results confirm that the presented actuator effectively realizes the linear movement that has a large working stroke stably without backward motion. The smallest stepping displacement ΔL is 0.2 μm under 1 Hz and 50 V. The largest motion speed is 900 μm/s with 900 Hz and 120 V. The largest vertical and horizontal load are 250 g and 12 g, respectively. This work shows that the improved bionic piezoelectric actuator is feasible for eliminating backward motion and has a great working ability.
基金supported by Guangdong Provincial Key Laboratory of Minimally Invasive Surgical Instruments and Manufacturing Technology(MISIMT-2021-4)the Fundamental Research Funds for the Central Universities(N2329001).
文摘The lower limb assisted exoskeleton is a prominent area of research within the field of exoskeleton technology.However,several challenges remain,including the development of flexible actuators,high battery consumption,the risk of joint misalignment,and limited assistive capabilities.This paper proposes a compact flexible actuator incorporating two elastic elements named Adjustable Energy Storage Series Elastic Actuator(AES-SEA),which combining an adjustable energy storage device with a series elastic actuator for application in exoskeleton hip joints.This design aims to enhance energy efficiency and improve assistive effects.Subsequently,we introduce a novel knee joint bionic structure based on a pulley-groove configuration and a four-link mechanism,designed to replicate human knee joint motion and prevent joint misalignment.Additionally,we propose an innovative controller that integrates concepts from Linear Quadratic Regulator(LQR)control and virtual tunnel for level walking assistance.This controller modulates the assisted reference trajectory using the virtual tunnel concept,enabling different levels of assistance both inside and outside the tunnel by adjusting the parameters Q and R.This approach enhances the assisting force while ensuring the safety of human-computer interaction.Finally,metabolic experiments were conducted to evaluate the effectiveness of the exoskeleton assistance.
基金supported financially by the National Natural Science Foundation of China(52205308,22208120)the China Postdoctoral Science Foundation(2022M711300).
文摘Flexible sensors,a class of devices that can convert external mechanical or physical signals into changes in resistance,capacitance,or current,have developed rapidly since the concept was first proposed.Due to the special properties and naturally occurring excellent microstructures of biomaterials,it can provide more desirable properties to flexible devices.This paper systematically discusses the commonly used biomaterials for bio-based flexible devices in current research applications and their deployment in preparing flexible sensors with different mechanisms.According to the characteristics of other properties and application requirements of biomaterials,the mechanisms of their functional group properties,special microstructures,and bonding interactions in the context of various sensing applications are presented in detail.The practical application scenarios of biomaterial-based flexible devices are highlighted,including human-computer interactions,energy harvesting,wound healing,and related biomedical applications.Finally,this paper also reviews in detail the limitations of biobased materials in the construction of flexible devices and presents challenges and trends in the development of biobased flexible sensors,as well as to better explore the properties of biomaterials to ensure functional synergy within the composite materials.
基金supported by the National Key Research&Development Program of China(Grant No.2020YFB1313504)the State Key Laboratory of Mechanics and Control for Aerospace Structures of Nanjing University of Aeronautics and Astronautics.
文摘Gecko-inspired robots have significant potential applications;however,deviations in the yaw direction during locomotion are inevitable for legged robots that lack external sensing.These deviations cause the robot to stray from its intended path.Therefore,a cost-effective and straightforward solution is essential for reducing this deviation.In nature,the tail is often used to maintain balance and stability.Similarly,it has been used in robots to improve manoeuvrability and stability.Our aim is to reduce this deviation using a morphological computation approach,specifically by adding a tail.To test this hypothesis,we investigated four different tails(rigid plate,rigid gecko-shaped,soft plate,and soft gecko-shaped)and assessed the deviation of the robot with these tails on different slopes.Additionally,to evaluate the influence of different tail parameters,such as material,shape,and linkage,we investigated the locomotion performance in terms of the robot's climbing speed on slopes,its ability to turn at narrow corners,and the resistance of the tails to external disturbances.A new auto-reset joint was designed to ensure that a disturbed tail could be quickly reset.Our results demonstrate that the yaw deviation of the robot can be reduced by applying a tail.Among the four tails,the soft gecko-shaped tail was the most effective for most tasks.In summary,our findings demonstrate the functional role of the tail in reducing yaw deviation,improving climbing ability and stability and provide a reference for selecting the most suitable tail for geckoinspired robots.
基金supported by National Natural Science Foundation of National Key Research and Development Program of China(2020YFB2009002).
文摘The unidirectional flow of lymphatic fluid depends significantly on the valve structure within the lymphatic system,thus impacting tumor cell metastasis via the lymphatic system.However,existing microdevices for studying tumor lymphatic metastasis have overlooked the impact of open-close valve structures on the lymphatic flow field.This paper presents a novel biomimetic lymphatic valve structure,which innovatively incorporates the thin-shell theory into the modeling of lymphatic-mimicking structures.Through finite element simulations,we have systematically analyzed the influence of valve thickness and elasticity on its deformation characteristics.Materials closely matching the actual properties of biological tissues are synthesized.And the soft-etching technique was used to fabricate lymphomimetic microchannels,which were then tested to evaluate their capability in intercepting unidirectional flow.The results showed that the lymphomimetic valve structure had no observable leaks and effectively intercepted unidirectional flow.Our study not only elucidates the mechanism of lymphatic circulation but also presents a dependable biomimetic model that could facilitate additional biological investigations and phenotypic drug screening.
基金supported by the Zhejiang Province 14th Five Year Plan Teaching Reform Project(jg20220514).
文摘Developing innovative capabilities in university students is essential for individual career success and broader societal advancement.This study introduces a predictive Feature Selection(FS)model named bWRBA-SVM-FS,which combines an enhanced Bat Algorithm(BA)and Support Vector Machine(SVM).To enhance the optimization capability of BA,water follow search and random follow search are introduced to optimize the efficiency and accuracy of the feature subset search.Experimental validation conducted on the IEEE CEC 2017 benchmark functions and the talented innovative capacity dataset demonstrates the efficacy of the proposed method relative to peer and prominent machine learning models.The experimental results reveal that the predictive accuracy of the bWRBA-SVM-FS model is 97.503%,with a sensitivity of 98.391%.Our findings indicate significant predictors of innovation capacity,including project application goals,educational background,and interdisciplinary thinking abilities.The bWRBA-SVM-FS model offers effective strategies for talent selection in higher education,fostering the development of future research leaders.
基金funded by the National Natural Science Foundation of China(No.52475190 and 52275191)China Postdoctoral Science Foundation Funded Project(No.2024M751165)the Tribology Science Fund of State Key Laboratory of Tribology in Advanced Equipment(No.SKLTKF24B17).
文摘Pacinian Corpuscle(PC)is the largest tactile vibration receptor in mammalian skin,with a layered structure that enables signal amplification and high-pass filtering functions.Modern robots feature vibro-tactile sensors with excellent mechanical properties and fine resolution,but these sensors are prone to low-frequency noise interference when detecting high-frequency vibrations.In this study,a bionic PC with a longitudinally decreasing dynamic fractal structure is proposed.By creating a lumped parameter model of the PC’s layered structure,the bionic PC made of gelatin-chitosan based hydrogel can achieve high-pass filtering and specific frequency band signal amplification without requiring back-end circuits.The experimental results demonstrate that the bionic PC retains the structural characteristics of a natural PC,and the influence of structural factors,such as the number of layers in its shell,on filtration characteristics is explored.Additionally,a vibration source positioning experiment was conducted to simulate the earthquake sensing abilities of elephants.This natural structural design simplifies the filter circuit,is low-cost,cost-effective,stable in performance,and reduces redundancy in the robot’s signal circuit.Integrating this technology with robots can enhance their environmental perception,thereby improving the safety of interactions.
基金supported by the National Natural Science Foundation of China(62276092,62303167)the Postdoctoral Fellowship Program(Grade C)of China Postdoctoral Science Foundation(GZC20230707)+3 种基金the Key Science and Technology Program of Henan Province,China(242102211051,242102211042,212102310084)Key Scientiffc Research Projects of Colleges and Universities in Henan Province,China(25A520009)the China Postdoctoral Science Foundation(2024M760808)the Henan Province medical science and technology research plan joint construction project(LHGJ2024069).
文摘Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely used in pulmonary disease diagnosis,such as pneumonia and tuberculosis.However,traditional feature fusion methods often suffer from feature disparity,information loss,redundancy,and increased complexity,hindering the further extension of DL algorithms.To solve this problem,we propose a Graph-Convolution Fusion Network with Self-Supervised Feature Alignment(Self-FAGCFN)to address the limitations of traditional feature fusion methods in deep learning-based medical image classification for respiratory diseases such as pneumonia and tuberculosis.The network integrates Convolutional Neural Networks(CNNs)for robust feature extraction from two-dimensional grid structures and Graph Convolutional Networks(GCNs)within a Graph Neural Network branch to capture features based on graph structure,focusing on significant node representations.Additionally,an Attention-Embedding Ensemble Block is included to capture critical features from GCN outputs.To ensure effective feature alignment between pre-and post-fusion stages,we introduce a feature alignment loss that minimizes disparities.Moreover,to address the limitations of proposed methods,such as inappropriate centroid discrepancies during feature alignment and class imbalance in the dataset,we develop a Feature-Centroid Fusion(FCF)strategy and a Multi-Level Feature-Centroid Update(MLFCU)algorithm,respectively.Extensive experiments on public datasets LungVision and Chest-Xray demonstrate that the Self-FAGCFN model significantly outperforms existing methods in diagnosing pneumonia and tuberculosis,highlighting its potential for practical medical applications.
基金funded by National Natural Science Foundation of China(Nos.62473236,62073196).
文摘In complex water environments,search tasks often involve multiple Autonomous Underwater Vehicles(AUVs),and a single centralized control cannot handle the complexity and computational burden of large-scale systems.Target search in complex water environments has always been a major challenge in the field of underwater robots.To address this problem,this paper proposes a multi-biomimetic robot fish collaborative target search method based on Distributed Model Predictive Control(DMPC).First,we established a bionic robot fish kinematic model and a multi-biomimetic robot fish communication model;second,this paper proposed a distributed model predictive control algorithm based on the distributed search theory framework,so that the bionic robot fish can dynamically adjust their search path according to each other’s position information and search status,avoid repeated coverage or missing areas,and thus improve the search efficiency;third,we conducted simulation experiments based on DMPC,and the results showed that the proposed method has a target search success rate of more than 90%in static targets,dynamic targets,and obstacle environments.Finally,we compared this method with Centralized Model Predictive Control(CMPC)and Random Walk(RW)algorithms.The DMPC approach demonstrates significant advantages,achieving a remarkable target search success rate of 94.17%.These findings comprehensively validate the effectiveness and superiority of the proposed methodology.It can be seen that DMPC can effectively dispatch multiple bionic robot fish to work together to achieve efficient search of vast waters.It can significantly improve the flexibility,scalability,robustness and cooperation efficiency of the system and has broad application prospects.
基金Open Access funding enabled and organized by Projekt DEALfinanced by the Deutsche Forschungsgemeinschaft(DFG)grant 470833544 to WK.
文摘The radula is a crucial adaptation for food-processing in molluscs.A deeper understanding of the interaction between the radula and the preferred food is lacking,complicating the inference of the precise ecological roles of radular structures.This study presents the first experimental set-up that allows to study the influence of the radular morphology,specifically the degree of tooth-tooth interlocking(so-called collective effect),on the feeding efficiency.For this purpose,physical 3D models of the teeth were designed using CAD software and 3D printing technique.The feeding efficiencies with models of different degree of interlocking were determined by tensile tests,pulling the models trough agar gels with different viscosities.The forces generated by the models and the masses of the removed gel fragments were determined.We found,that radular models with a high degree of tooth–tooth interlocking performed best as they were able to remove most agar.We additionally broke the teeth and determined,that the teeth with the highest degree of interlocking could resist to highest force.Overall,the study highlights the complex interplay between radular morphology and its ecological function,suggesting that even minor morphological alterations can significantly impact the efficiency and effectiveness of food gathering.Understanding these interactions cannot only shed light on the ecological adaptations of molluscs,but provide further insights into development of more effective grinding,scraping,and cleaning technical devices.
文摘The global incidence of Alzheimer's Disease(AD)is on a swift rise.The Electroencephalogram(EEG)signals is an effective tool for the identification of AD and its initial Mild Cognitive Impairment(MCI)stage using machine learning models.Analysis of AD using EEG involves multi-channel analysis.However,the use of multiple channels may impact the classification performance due to data redundancy and complexity.In this work,a hybrid EEG channel selection is proposed using a combination of Reptile Search Algorithm and Snake Optimizer(RSO)for AD and MCI detection based on decomposition methods.Empirical Mode Decomposition(EMD),Low-Complexity Orthogonal Wavelet Filter Banks(LCOWFB),Variational Mode Decomposition,and discrete-wavelet transform decomposition techniques have been employed for subbands-based EEG analysis.We extracted thirty-four features from each subband of EEG signals.Finally,a hybrid RSO optimizer is compared with five individual metaheuristic algorithms for effective channel selection.The effectiveness of this model is assessed by two publicly accessible AD EEG datasets.An accuracy of 99.22% was achieved for binary classification from RSO with EMD using 4(out of 16)EEG channels.Moreover,the RSO with LCOWFBs obtained 89.68%the average accuracy for three-class classification using 7(out of 19)channels.The performance reveals that RSO performs better than individual Metaheuristic algorithms with 60%fewer channels and improved accuracy of 4%than existing AD detection techniques.
基金supported by the European Union by the Next Generation EU Project ECS00000017‘Ecosistema dell’Innovazione’Tuscany Health Ecosystem(THE,PNRR,Spoke 9:Robotics and Automation for Health)by the Italian Ministry of Education and Research(MUR)in the framework of the FoReLab project(Departments of Excellence).
文摘Muscle Shortening Maneuver(MSM)is a rehabilitation technique successfully applied to several pathological conditions.The concept is to passively elongate and shorten the target muscle group of the affected limb.As a result,the functionality(muscle strength and range of motion)of that limb is improved.The existing system induces these oscillations manually or without any feedback control,which can compromise the effectiveness and standardization of MSM.In this paper,we present a mechatronic system that can precisely deliver motion oscillations to the upper limb for a controllable execution of MSM.First,we collected the parameters(frequency and amplitude of the oscillations)from a system where a motor was heuristically used by a well-experienced therapist to induce the oscillations(without any feedback control).Based on these specifications,we chose the motor and rebuilt the experimental setup,implementing a sliding mode control with a sliding perturbation observer.With our system,the operator can choose a given frequency and amplitude of the oscillations within the range we experimentally observed.We tested our system with ten participants of different anthropometry.We found that our system can accurately reproduce oscillations in the frequency range 0.8 to 1.2 Hz and amplitude range 2 to 6 cm,with a maximum percentage normalized root mean square error around 7%.
基金supported by the Natural Science Foundation of Hunan Province,China(No.2024JJ6039).
文摘Laser-Induced Graphene (LIG) is regarded as a promising sensor carrier due to its inherent three-dimensional porous structure. However, as two mutually exclusive properties of the pressure sensor, sensitivity and working range are difficult to be further improved by the single porous structure. Inspired by the unique geometry of Oxalis corniculata L. leaves, we here propose a novel method consist of laser pre-etching and inducing steps to fabricate LIG-based electrodes with a two-stage architecture featuring microjigsaw and microporous structures. The following injection of liquid-silicone significantly improves the friction resistance and bending reliability of LIG materials. The interface contact between external microjigsaw structures induces substantial resistance changes, and the internal microporous structure exhibits reversibility during dynamic deformation. Consequently, the jigsaw-like pressure sensor achieves a balanced performance with sensitivities of 3.64, 1.20 and 0.03 kPa^(- 1) in pressure range of 0 -20, 20 - 40 and 40 - 150 kPa, respectively. The bionic LIG-based pressure sensor serves as the core component and further integrated with an all-in-one wireless transmission system capable of monitoring various health parameters such as subtle pulse rates, heartbeat rhythms, sounds, etc., indicating broad prospects in future wearable electronics.
文摘Achieving robust walking for different stairs is one of the most challenging tasks for quadruped robots in real world.Traditional model-based methods heavily rely on environmental factors,are burdened by intricate modelling complexities,and lack generalizability.The potential for advancements in adaptive locomotion control,often impeded by complex modelling processes,can be substantially enhanced through the application of Reinforcement Learning(RL).In this paper,a learning-based method is proposed to directionally enhance the stair-climbing skill of quadruped robots under different stair conditions.First,the general policy model based on proprioceptive perception is trained as a pre-training model.Then,the pre-training model was initialized,and different terrain information from the stairs was introduced for customized training to enhance the stair-climbing skill without affecting the existing locomotion performance.Finally,the customized control policy is deployed to the real robot to realize motion control in real environments.The experimental results demonstrate that the customized control policy can significantly improve the motion performance of quadruped robots when facing complex stair terrains and has certain generalizability in other complex terrains.The proposed algorithm can be extended to various terrestrial environments.
基金supported by the National Natural Science Foundation of China (52275480)the Guizhou Provincial Science and Technology Program of Qiankehe Zhongdi Guiding ([2023]02)+1 种基金the Guizhou Provincial Science and Technology Program of Qiankehe Platform Talent Project (GCC[2023]001)the Guizhou Provincial Science and Technology Project of Qiankehe Platform Project (KXJZ[2024]002).
文摘Metaheuristic algorithms are pivotal in cloud task scheduling. However, the complexity and uncertainty of the scheduling problem severely limit algorithms. To bypass this circumvent, numerous algorithms have been proposed. The Hiking Optimization Algorithm (HOA) have been used in multiple fields. However, HOA suffers from local optimization, slow convergence, and low efficiency of late iteration search when solving cloud task scheduling problems. Thus, this paper proposes an improved HOA called CMOHOA. It collaborates with multi-strategy to improve HOA. Specifically, Chebyshev chaos is introduced to increase population diversity. Then, a hybrid speed update strategy is designed to enhance convergence speed. Meanwhile, an adversarial learning strategy is introduced to enhance the search capability in the late iteration. Different scenarios of scheduling problems are used to test the CMOHOA’s performance. First, CMOHOA was used to solve basic cloud computing task scheduling problems, and the results showed that it reduced the average total cost by 10% or more. Secondly, CMOHOA has been applied to edge fog cloud scheduling problems, and the results show that it reduces the average total scheduling cost by 2% or more. Finally, CMOHOA reduced the average total cost by 7% or more in scheduling problems for information transmission.
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.
