Generating diverse motor behaviors critical for survival is a challenge that confronts the central nervous system(CNS)of all animals.During movement execution,the CNS performs complex calculations to control a large n...Generating diverse motor behaviors critical for survival is a challenge that confronts the central nervous system(CNS)of all animals.During movement execution,the CNS performs complex calculations to control a large number of neuromusculoskeletal elements.The theory of modular motor control proposes that spinal interneurons are organized in discrete modules that can be linearly combined to generate a variety of behavioral patterns.These modules have been previously represented as stimulus-evoked force fields(FFs)comprising isometric limb-endpoint forces across workspace locations.Here,we ask whether FFs elicited by different stimulations indeed represent the most elementary units of motor control or are themselves the combination of a limited number of even more fundamental motor modules.To probe for potentially more elementary modules,we optogenetically stimulated the lumbosacral spinal cord of intact and spinalized Thy1-ChR2 transgenic mice(n=21),eliciting FFs from as many single stimulation loci as possible(20-70 loci per mouse)at minimally necessary power.We found that the resulting varieties of FFs defied simple categorization with just a few clusters.We used gradient descent to further decompose the FFs into their underlying basic force fields(BFFs),whose linear combination explained FF variability.Across mice,we identified 4-5 BFFs with partially localizable but overlapping representations along the spinal cord.The BFFs were structured and topographically distributed in such a way that a rostral-to-caudal traveling wave of activity across the lumbosacral spinal cord may generate a swing-to-stance gait cycle.These BFFs may represent more rudimentary submodules that can be flexibly merged to produce a library of motor modules for building different motor behaviors.展开更多
To integrate driver experience and heterogeneous vehicle platform characteristics in a motion-planning algorithm,based on the driver-behavior-based transferable motion primitives(MPs), a general motion-planning framew...To integrate driver experience and heterogeneous vehicle platform characteristics in a motion-planning algorithm,based on the driver-behavior-based transferable motion primitives(MPs), a general motion-planning framework for offline generation and online selection of MPs is proposed. Optimal control theory is applied to solve the boundary value problems in the process of generating MPs, where the driver behaviors and the vehicle motion characteristics are integrated into the optimization in the form of constraints. Moreover, a layered, unequal-weighted MP selection framework is proposed that utilizes a combination of environmental constraints, nonholonomic vehicle constraints,trajectory smoothness, and collision risk as the single-step extension evaluation index. The library of MPs generated offline demonstrates that the proposed generation method realizes the effective expansion of MP types and achieves diverse generation of MPs with various velocity attributes and platform types. We also present how the MP selection algorithm utilizes a unique MP library to achieve online extension of MP sequences. The results show that the proposed motion-planning framework can not only improve the efficiency and rationality of the algorithm based on driving experience but can also transfer between heterogeneous vehicle platforms and highlight the unique motion characteristics of the platform.展开更多
Articulated movements are fundamental in many human and robotic tasks.While humans can learn and generalise arbitrarily long sequences of movements,and particularly can optimise them to ft the constraints and features...Articulated movements are fundamental in many human and robotic tasks.While humans can learn and generalise arbitrarily long sequences of movements,and particularly can optimise them to ft the constraints and features of their body,robots are often programmed to execute point-to-point precise but fxed patterns.This study proposes a new approach to interpreting and reproducing articulated and complex trajectories as a set of known robot-based primitives.Instead of achieving accurate reproductions,the proposed approach aims at interpreting data in an agent-centred fashion,according to an agent s primitive movements.The method improves the accuracy of a reproduction with an incremental process that seeks frst a rough approximation by capturing the most essential features of a demonstrated trajectory.Observing the discrepancy between the demonstrated and reproduced trajectories,the process then proceeds with incremental decompositions and new searches in sub-optimal parts of the trajectory.The aim is to achieve an agent-centred interpretation and progressive learning that fts in the frst place the robots capability,as opposed to a data-centred decomposition analysis.Tests on both geometric and human generated trajectories reveal that the use of own primitives results in remarkable robustness and generalisation properties of the method.In particular,because trajectories are understood and abstracted by means of agent-optimised primitives,the method has two main features： 1） Reproduced trajectories are general and represent an abstraction of the data.2） The algorithm is capable of reconstructing highly noisy or corrupted data without pre-processing thanks to an implicit and emergent noise suppression and feature detection.This study suggests a novel bio-inspired approach to interpreting,learning and reproducing articulated movements and trajectories.Possible applications include drawing,writing,movement generation,object manipulation,and other tasks where the performance requires human-like interpretation and generalisation capabilities.展开更多
Let { W(t);t≥0 } be a standard Brownian motion.For a positive integer m ,define a Gaussian processX m(t)=1m!∫ t 0(t-s) m d W(s).In this paper the liminf behavior of the increments of this process is discu...Let { W(t);t≥0 } be a standard Brownian motion.For a positive integer m ,define a Gaussian processX m(t)=1m!∫ t 0(t-s) m d W(s).In this paper the liminf behavior of the increments of this process is discussed by establishing some probability inequalities.Some previous results are extended and improved.展开更多
This paper studies the problem of coordinated motion generation for a group of rigid bodies. Two classes of coordinated motion primitives, relative equilibria and ma- neuvers, are given as building blocks for generati...This paper studies the problem of coordinated motion generation for a group of rigid bodies. Two classes of coordinated motion primitives, relative equilibria and ma- neuvers, are given as building blocks for generating coordi- nated motions. In a motion-primitive based planning frame- work, a control method is proposed for the robust execution of a coordinated motion plan in the presence of perturba- tions. The control method combines the relative equilibria stabilization with maneuver design, and results in a close- loop motion planning framework. The performance of the control method has been illustrated through a numerical sim- ulation.展开更多
A three-loop control strategy is developed for exoskeleton to reduce interaction torque and improve compliance control performance in human-exoskeleton collaborative movement.In the outer loop,dynamic movement primiti...A three-loop control strategy is developed for exoskeleton to reduce interaction torque and improve compliance control performance in human-exoskeleton collaborative movement.In the outer loop,dynamic movement primitives is employed to learn one demonstration trajectories of individual walking gaits and to generate the reference trajectory,which serves as the input for the admittance middle layer.In the middle layer,the admittance scheme is designed to determine the desired joint trajectory,which is then input to the inner position control loop of the exoskeleton.Due to model uncertainties in the position control loop,an adaptive fuzzy fxed-time controller is incorporated to approximate uncertain dynamics,and ensures that the exoskeleton's state errors converge into a small neighborhood around zero within a fnite period,regardless of original conditions.This three-loop control strategy has two key advantages:(1)the exoskeleton can identify individual gaits with varying physical features such as motion frequency and amplitude;(2)the operator wearable comfort is signifcantly improved based on humanexoskeleton impedance and synchronous motion indicators.Finally,both comparative simulations and experimental validations confrm the efcacy of the proposed control framework in achieving smooth and coordinated human-exoskeleton interactions.展开更多
Human-robot collaboration fully leverages the strengths of both humans and robots,which is crucial for handling large,heavy objects at construction sites.To address the challenges of human-machine cooperation in handl...Human-robot collaboration fully leverages the strengths of both humans and robots,which is crucial for handling large,heavy objects at construction sites.To address the challenges of human-machine cooperation in handling large-scale,heavy objects-specifically building curtain walls-a human-robot collaboration system was designed based on the concept of"human-centered with machine support".This system allows the handling of curtain walls according to different human intentions.First,a robot trajectory learning and generalization model based on dynamic motion primitives was developed.The operator's motion intent was then characterized by their speed,force,and torque,with the force impulse introduced to define the operator's intentions for acceleration and deceleration.Finally,a collaborative experiment was conducted on an experimental platform to validate the robot's understanding of human handling intentions and to verify its ability to handle curtain wall.Collaboration between humans and robots ensured a smooth and labor-saving handling process.展开更多
Segmentation of demonstration trajectories and learning the contained motion primitives can effectively enhance the assistive robot's intelligence to flexibly reproduce learnt tasks in an unstructured environment....Segmentation of demonstration trajectories and learning the contained motion primitives can effectively enhance the assistive robot's intelligence to flexibly reproduce learnt tasks in an unstructured environment.With the aim to conveniently and accurately segment demonstration trajectories,a novel demonstration trajectory segmentation approach is proposed based on the beta process autoregressive hidden Markov model(BP-ARHMM)algorithm and generalised time warping(GTW)algorithm aiming to enhance the segmentation accuracy utilising acquired demonstration data.This approach first adopts the GTW algorithm to align the multiple demonstration trajectories for the same task.Then,it adopts the BP-AR-HMM algorithm to segment the demonstration trajectories,acquire the contained motion primitives,and establish the related task library.This segmentation approach is validated on the 6-degree-of-freedom JACO robotic arm by assisting users to accomplish a holding water glass task and an eating task.The experimental results show that the motion primitives within the trajectories can be correctly segmented with a high segmentation accuracy.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
In this article,a robot skills learning framework is developed,which considers both motion modeling and execution.In order to enable the robot to learn skills from demonstrations,a learning method called dynamic movem...In this article,a robot skills learning framework is developed,which considers both motion modeling and execution.In order to enable the robot to learn skills from demonstrations,a learning method called dynamic movement primitives(DMPs)is introduced to model motion.A staged teaching strategy is integrated into DMPs frameworks to enhance the generality such that the complicated tasks can be also performed for multi-joint manipulators.The DMP connection method is used to make an accurate and smooth transition in position and velocity space to connect complex motion sequences.In addition,motions are categorized into different goals and durations.It is worth mentioning that an adaptive neural networks(NNs)control method is proposed to achieve highly accurate trajectory tracking and to ensure the performance of action execution,which is beneficial to the improvement of reliability of the skills learning system.The experiment test on the Baxter robot verifies the effectiveness of the proposed method.展开更多
BACKGROUND Data on clinical characteristics,treatment outcomes,and prognosis of pancreatic primitive neuroectodermal tumors(PNETs)are limited.AIM To analyze the clinical data of 30 patients with pancreatic PNETs to id...BACKGROUND Data on clinical characteristics,treatment outcomes,and prognosis of pancreatic primitive neuroectodermal tumors(PNETs)are limited.AIM To analyze the clinical data of 30 patients with pancreatic PNETs to identify their clinical characteristics and factors associated with prognosis.METHODS We used the keywords"primary neuroectodermal tumor,""digestive tract,""pancreas,""pancreatic,"and"gastrointestinal,"individually or in combination,to collect data from a global database for all patients with pancreatic PNET to date.Univariate and Cox regression analyses were performed to identify prognostic factors for patient survival.RESULTS A total of 30 cases of pancreatic PNET were included in this study:15 males and 15 females with a mean age of 24 years.The main symptom was abdominal pain(73.3%),and the median tumor size was 7.85 cm.Twenty-four patients(80.0%)underwent surgery and nineteen patients received adjuvant therapy.Local metastasis was observed in 13 patients(43.3%),lymph node metastasis in 10 patients(33.3%),and distant metastasis in 6 patients(20.0%).Local recurrence was observed in 13 patients(43.3%).The median survival time of all patients was 29.4 months,and the overall estimated 1-year and 3-year survival rates were approximately 66.0%and 36.4%,respectively.Univariate analysis showed that chemotherapy(P=0.036),local metastasis(P=0.041),lymph node metastasis(P=0.003),distant metastasis(P=0.049),and surgical margins(P=0.048)were the prognostic factors affecting survival.Multivariate analysis revealed only lymph node metastasis(P=0.012)as a prognostic factor.CONCLUSION Pancreatic PNET is extremely rare,occurs in young adults,has no apparent sex predisposition,has a high rate of metastasis and early recurrence,and has a very poor prognosis.The diagnosis of pancreatic PNET requires a combination of clinical symptoms,pathologic features,immunohistochemistry,and cytogenetic analysis.Univariate analysis suggested that chemotherapy,metastasis,and surgical margins were prognostic factors affecting survival,and multivariate analysis suggested that lymph node metastasis is an important prognostic factor.Therefore,early diagnosis,early and extensive resection,and adjuvant chemoradiotherapy may help improve prognosis.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
Walking is the basic locomotion pattern for bipedal robots.The walking pattern is widely generated using the linear inverted pendulum model.The linear inverted pendulum motion of each support period can be designed as...Walking is the basic locomotion pattern for bipedal robots.The walking pattern is widely generated using the linear inverted pendulum model.The linear inverted pendulum motion of each support period can be designed as a walk primitive to be connected to form a walking trajectory.A novel method of integrating double support phase into the walk primitive was proposed in this article.The method describes the generation of walking patterns using walk primitives with double support,specifically for lateral plane including walking in place,walking for lateral,and walking initiation,and for sagittal plane including fixed step length walking,variable step length walking,and walking initiation.Compared to walk primitives without double support phase,those with double support phase reduce the maximum speed required by the robot and eliminate the need to adjust foothold for achieving continuous speed.The performance of the proposed method is validated by simulations and experiments on Neubot,a position-controlled biped robot.展开更多
The distribution of 0 and 1 is studied in the highest level a e-1of primitive sequences over Z/(2\+e). It is proved that the proportion of 0 (or 1) in one period of a e-1is between 40% and 60% for e≥8.
Origami,a traditional Japanese art,is an example of superior handwork produced by human hands.Achieving such extreme dexterity is one of the goals of robotic technology.In the work described in this paper,we developed...Origami,a traditional Japanese art,is an example of superior handwork produced by human hands.Achieving such extreme dexterity is one of the goals of robotic technology.In the work described in this paper,we developed a new general-purpose robot system with sufficient capabilities for performing Origami.We decomposed the complex folding motions into simple primitives and generated the overall motion as a combination of these primitives.Also,to measure the paper deformation in real-time,we built an estimator using a physical simulator and a depth camera.As a result,our experimental system achieved consecutive valley folds and a squash fold.展开更多
Personalized gait curves are generated to enhance patient adaptability to gait trajectories used for passive training in the early stage of rehabilitation for hemiplegic patients.The article utilizes the random forest...Personalized gait curves are generated to enhance patient adaptability to gait trajectories used for passive training in the early stage of rehabilitation for hemiplegic patients.The article utilizes the random forest algorithm to construct a gait parameter model,which maps the relationship between parameters such as height,weight,age,gender,and gait speed,achieving prediction of key points on the gait curve.To enhance prediction accuracy,an attention mechanism is introduced into the algorithm to focus more on the main features.Meanwhile,to ensure high similarity between the reconstructed gait curve and the normal one,probabilistic motion primitives(ProMP)are used to learn the probability distribution of normal gait data and construct a gait trajectorymodel.Finally,using the specified step speed as input,select a reference gait trajectory from the learned trajectory,and reconstruct the curve of the reference trajectoryusing the gait keypoints predictedby the parametermodel toobtain the final curve.Simulation results demonstrate that the method proposed in this paper achieves 98%and 96%curve correlations when generating personalized lower limb gait curves for different patients,respectively,indicating its suitability for such tasks.展开更多
In this paper,we exhibit a free monoid containing all prefix codes in connection with the sets of i-th powers of primitive words for all i≥2.This extends two results given by Shyr and Tsai in 1998 at the same time.
Space-Time Block Coded(STBC)Orthogonal Frequency Division Multiplexing(OFDM)satisfies higher data-rate requirements while maintaining signal quality in a multipath fading channel.However,conventional STBCs,including O...Space-Time Block Coded(STBC)Orthogonal Frequency Division Multiplexing(OFDM)satisfies higher data-rate requirements while maintaining signal quality in a multipath fading channel.However,conventional STBCs,including Orthogonal STBCs(OSTBCs),Non-Orthogonal(NOSTBCs),and Quasi-Orthogonal STBCs(QOSTBCs),do not provide both maximal diversity order and unity code rate simultaneously for more than two transmit antennas.This paper targets this problem and applies Maximum Rank Distance(MRD)codes in designing STBCOFDM systems.By following the direct-matrix construction method,we can construct binary extended finite field MRD-STBCs for any number of transmitting antennas.Work uses MRD-STBCs built over Phase-Shift Keying(PSK)modulation to develop an MRD-based STBC-OFDM system.The MRD-based STBC-OFDM system sacrifices minor error performance compared to traditional OSTBC-OFDM but shows improved results against NOSTBC and QOSTBC-OFDM.It also provides 25%higher data-rates than OSTBC-OFDM in configurations that use more than two transmit antennas.The tradeoffs are minor increases in computational complexity and processing delays.展开更多
基金supported by the CUHK Faculty of Medicine Faculty Innovation Award FIA2016/A/04(to V.C.K.C.)Group Research Scheme NL/JW/rc/grs1819/0426/19hc(to V.C.K.C.)The Hong Kong Research Grants Council 24115318,CUHK-R4022-18,14114721,and 14119022(to V.C.K.C)。
文摘Generating diverse motor behaviors critical for survival is a challenge that confronts the central nervous system(CNS)of all animals.During movement execution,the CNS performs complex calculations to control a large number of neuromusculoskeletal elements.The theory of modular motor control proposes that spinal interneurons are organized in discrete modules that can be linearly combined to generate a variety of behavioral patterns.These modules have been previously represented as stimulus-evoked force fields(FFs)comprising isometric limb-endpoint forces across workspace locations.Here,we ask whether FFs elicited by different stimulations indeed represent the most elementary units of motor control or are themselves the combination of a limited number of even more fundamental motor modules.To probe for potentially more elementary modules,we optogenetically stimulated the lumbosacral spinal cord of intact and spinalized Thy1-ChR2 transgenic mice(n=21),eliciting FFs from as many single stimulation loci as possible(20-70 loci per mouse)at minimally necessary power.We found that the resulting varieties of FFs defied simple categorization with just a few clusters.We used gradient descent to further decompose the FFs into their underlying basic force fields(BFFs),whose linear combination explained FF variability.Across mice,we identified 4-5 BFFs with partially localizable but overlapping representations along the spinal cord.The BFFs were structured and topographically distributed in such a way that a rostral-to-caudal traveling wave of activity across the lumbosacral spinal cord may generate a swing-to-stance gait cycle.These BFFs may represent more rudimentary submodules that can be flexibly merged to produce a library of motor modules for building different motor behaviors.
基金Supported by National Natural Science Foundation of China (Grant Nos. 91420203 and 61703041)。
文摘To integrate driver experience and heterogeneous vehicle platform characteristics in a motion-planning algorithm,based on the driver-behavior-based transferable motion primitives(MPs), a general motion-planning framework for offline generation and online selection of MPs is proposed. Optimal control theory is applied to solve the boundary value problems in the process of generating MPs, where the driver behaviors and the vehicle motion characteristics are integrated into the optimization in the form of constraints. Moreover, a layered, unequal-weighted MP selection framework is proposed that utilizes a combination of environmental constraints, nonholonomic vehicle constraints,trajectory smoothness, and collision risk as the single-step extension evaluation index. The library of MPs generated offline demonstrates that the proposed generation method realizes the effective expansion of MP types and achieves diverse generation of MPs with various velocity attributes and platform types. We also present how the MP selection algorithm utilizes a unique MP library to achieve online extension of MP sequences. The results show that the proposed motion-planning framework can not only improve the efficiency and rationality of the algorithm based on driving experience but can also transfer between heterogeneous vehicle platforms and highlight the unique motion characteristics of the platform.
基金supported by European Community s Seventh Framework Programme FP7/2007-2013,Challenge 2,Cognitive Systems,Interaction,Robotics(No.248311AMARSi)
文摘Articulated movements are fundamental in many human and robotic tasks.While humans can learn and generalise arbitrarily long sequences of movements,and particularly can optimise them to ft the constraints and features of their body,robots are often programmed to execute point-to-point precise but fxed patterns.This study proposes a new approach to interpreting and reproducing articulated and complex trajectories as a set of known robot-based primitives.Instead of achieving accurate reproductions,the proposed approach aims at interpreting data in an agent-centred fashion,according to an agent s primitive movements.The method improves the accuracy of a reproduction with an incremental process that seeks frst a rough approximation by capturing the most essential features of a demonstrated trajectory.Observing the discrepancy between the demonstrated and reproduced trajectories,the process then proceeds with incremental decompositions and new searches in sub-optimal parts of the trajectory.The aim is to achieve an agent-centred interpretation and progressive learning that fts in the frst place the robots capability,as opposed to a data-centred decomposition analysis.Tests on both geometric and human generated trajectories reveal that the use of own primitives results in remarkable robustness and generalisation properties of the method.In particular,because trajectories are understood and abstracted by means of agent-optimised primitives,the method has two main features： 1） Reproduced trajectories are general and represent an abstraction of the data.2） The algorithm is capable of reconstructing highly noisy or corrupted data without pre-processing thanks to an implicit and emergent noise suppression and feature detection.This study suggests a novel bio-inspired approach to interpreting,learning and reproducing articulated movements and trajectories.Possible applications include drawing,writing,movement generation,object manipulation,and other tasks where the performance requires human-like interpretation and generalisation capabilities.
基金Project Supported by National Science Fundation of China(1 9571 0 2 1 ) and Zhejiang Province
文摘Let { W(t);t≥0 } be a standard Brownian motion.For a positive integer m ,define a Gaussian processX m(t)=1m!∫ t 0(t-s) m d W(s).In this paper the liminf behavior of the increments of this process is discussed by establishing some probability inequalities.Some previous results are extended and improved.
基金supported by the National Natural Science Foundation of China (11072002,10832006)
文摘This paper studies the problem of coordinated motion generation for a group of rigid bodies. Two classes of coordinated motion primitives, relative equilibria and ma- neuvers, are given as building blocks for generating coordi- nated motions. In a motion-primitive based planning frame- work, a control method is proposed for the robust execution of a coordinated motion plan in the presence of perturba- tions. The control method combines the relative equilibria stabilization with maneuver design, and results in a close- loop motion planning framework. The performance of the control method has been illustrated through a numerical sim- ulation.
基金supported by the National Natural Science Foundation of China(Grant No.52175046)the Sichuan Science and Technology Program(Grant Nos.2024YFFK0037,2024ZYD0165)。
文摘A three-loop control strategy is developed for exoskeleton to reduce interaction torque and improve compliance control performance in human-exoskeleton collaborative movement.In the outer loop,dynamic movement primitives is employed to learn one demonstration trajectories of individual walking gaits and to generate the reference trajectory,which serves as the input for the admittance middle layer.In the middle layer,the admittance scheme is designed to determine the desired joint trajectory,which is then input to the inner position control loop of the exoskeleton.Due to model uncertainties in the position control loop,an adaptive fuzzy fxed-time controller is incorporated to approximate uncertain dynamics,and ensures that the exoskeleton's state errors converge into a small neighborhood around zero within a fnite period,regardless of original conditions.This three-loop control strategy has two key advantages:(1)the exoskeleton can identify individual gaits with varying physical features such as motion frequency and amplitude;(2)the operator wearable comfort is signifcantly improved based on humanexoskeleton impedance and synchronous motion indicators.Finally,both comparative simulations and experimental validations confrm the efcacy of the proposed control framework in achieving smooth and coordinated human-exoskeleton interactions.
基金supported by 2022 Doctoral Fund Project of Shandong Jianzhu University(X22012Z)the National Natural Science Foundation of China(U20A20283).
文摘Human-robot collaboration fully leverages the strengths of both humans and robots,which is crucial for handling large,heavy objects at construction sites.To address the challenges of human-machine cooperation in handling large-scale,heavy objects-specifically building curtain walls-a human-robot collaboration system was designed based on the concept of"human-centered with machine support".This system allows the handling of curtain walls according to different human intentions.First,a robot trajectory learning and generalization model based on dynamic motion primitives was developed.The operator's motion intent was then characterized by their speed,force,and torque,with the force impulse introduced to define the operator's intentions for acceleration and deceleration.Finally,a collaborative experiment was conducted on an experimental platform to validate the robot's understanding of human handling intentions and to verify its ability to handle curtain wall.Collaboration between humans and robots ensured a smooth and labor-saving handling process.
基金Doctoral Research Start-up Fund of Shandong Jiaotong University,Grant/Award Number:BS2024009Natural Science Foundation of Shandong Province of China,Grant/Award Number:ZR2022ME087+1 种基金State Key Laboratory of Robotics and Systems(HIT),Grant/Award Number:SKLRS-2024-KF-09Open Access Publication Fund of Universität Hamburg。
文摘Segmentation of demonstration trajectories and learning the contained motion primitives can effectively enhance the assistive robot's intelligence to flexibly reproduce learnt tasks in an unstructured environment.With the aim to conveniently and accurately segment demonstration trajectories,a novel demonstration trajectory segmentation approach is proposed based on the beta process autoregressive hidden Markov model(BP-ARHMM)algorithm and generalised time warping(GTW)algorithm aiming to enhance the segmentation accuracy utilising acquired demonstration data.This approach first adopts the GTW algorithm to align the multiple demonstration trajectories for the same task.Then,it adopts the BP-AR-HMM algorithm to segment the demonstration trajectories,acquire the contained motion primitives,and establish the related task library.This segmentation approach is validated on the 6-degree-of-freedom JACO robotic arm by assisting users to accomplish a holding water glass task and an eating task.The experimental results show that the motion primitives within the trajectories can be correctly segmented with a high segmentation accuracy.
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.
基金National Natural Science Foundation of China(Nos.62225304,92148204 and 62061160371)National Key Research and Development Program of China(Nos.2021ZD0114503 and 2019YFB1703600)Beijing Top Discipline for Artificial Intelligence Science and Engineering,University of Science and Technology Beijing,and the Beijing Natural Science Foundation(No.JQ20026).
文摘In this article,a robot skills learning framework is developed,which considers both motion modeling and execution.In order to enable the robot to learn skills from demonstrations,a learning method called dynamic movement primitives(DMPs)is introduced to model motion.A staged teaching strategy is integrated into DMPs frameworks to enhance the generality such that the complicated tasks can be also performed for multi-joint manipulators.The DMP connection method is used to make an accurate and smooth transition in position and velocity space to connect complex motion sequences.In addition,motions are categorized into different goals and durations.It is worth mentioning that an adaptive neural networks(NNs)control method is proposed to achieve highly accurate trajectory tracking and to ensure the performance of action execution,which is beneficial to the improvement of reliability of the skills learning system.The experiment test on the Baxter robot verifies the effectiveness of the proposed method.
文摘BACKGROUND Data on clinical characteristics,treatment outcomes,and prognosis of pancreatic primitive neuroectodermal tumors(PNETs)are limited.AIM To analyze the clinical data of 30 patients with pancreatic PNETs to identify their clinical characteristics and factors associated with prognosis.METHODS We used the keywords"primary neuroectodermal tumor,""digestive tract,""pancreas,""pancreatic,"and"gastrointestinal,"individually or in combination,to collect data from a global database for all patients with pancreatic PNET to date.Univariate and Cox regression analyses were performed to identify prognostic factors for patient survival.RESULTS A total of 30 cases of pancreatic PNET were included in this study:15 males and 15 females with a mean age of 24 years.The main symptom was abdominal pain(73.3%),and the median tumor size was 7.85 cm.Twenty-four patients(80.0%)underwent surgery and nineteen patients received adjuvant therapy.Local metastasis was observed in 13 patients(43.3%),lymph node metastasis in 10 patients(33.3%),and distant metastasis in 6 patients(20.0%).Local recurrence was observed in 13 patients(43.3%).The median survival time of all patients was 29.4 months,and the overall estimated 1-year and 3-year survival rates were approximately 66.0%and 36.4%,respectively.Univariate analysis showed that chemotherapy(P=0.036),local metastasis(P=0.041),lymph node metastasis(P=0.003),distant metastasis(P=0.049),and surgical margins(P=0.048)were the prognostic factors affecting survival.Multivariate analysis revealed only lymph node metastasis(P=0.012)as a prognostic factor.CONCLUSION Pancreatic PNET is extremely rare,occurs in young adults,has no apparent sex predisposition,has a high rate of metastasis and early recurrence,and has a very poor prognosis.The diagnosis of pancreatic PNET requires a combination of clinical symptoms,pathologic features,immunohistochemistry,and cytogenetic analysis.Univariate analysis suggested that chemotherapy,metastasis,and surgical margins were prognostic factors affecting survival,and multivariate analysis suggested that lymph node metastasis is an important prognostic factor.Therefore,early diagnosis,early and extensive resection,and adjuvant chemoradiotherapy may help improve prognosis.
基金supported by the National Science Foundation of China(Grant No.52375246,No.52372428,No.52105100)Guangxi Science and Technology Program(Grant No.2023AB09014)Jilin Province Science and Technology Development Program,(Grant No.20230201094GX,No.20230201069GX).
文摘The automatic and rapid generation of excavation trajectories is the foundation for achieving an intelligent excavator.To obtain high-performance trajectories that enhance operational capacity while avoiding the numerous issues present in existing methods for generating effective excavation paths,this paper proposes a trajectory generation method for excavators based on imitation learning,using the mole as a bionic prototype.Given the high excavation efficiency of moles,this paper first analyzes the structural characteristics of the mole’s forelimbs,its digging principles,morphology,and trajectory patterns.Subsequently,a higher-order polynomial is employed to fit and optimize the mole’s excavation trajectory.Next,imitation learning is conducted on sample trajectories based on Dynamic Movement Primitives,followed by the introduction of an obstacle avoidance algorithm.Simulation experiments and comparisons demonstrate that the mole-inspired trajectory method used in this paper performs well and possesses the ability to generate obstacle avoidance trajectories,as well as the convenience of transferring across different machine models.
基金supported in part by the National Key R&D Program under Grant 2018YFB1304504.
文摘Walking is the basic locomotion pattern for bipedal robots.The walking pattern is widely generated using the linear inverted pendulum model.The linear inverted pendulum motion of each support period can be designed as a walk primitive to be connected to form a walking trajectory.A novel method of integrating double support phase into the walk primitive was proposed in this article.The method describes the generation of walking patterns using walk primitives with double support,specifically for lateral plane including walking in place,walking for lateral,and walking initiation,and for sagittal plane including fixed step length walking,variable step length walking,and walking initiation.Compared to walk primitives without double support phase,those with double support phase reduce the maximum speed required by the robot and eliminate the need to adjust foothold for achieving continuous speed.The performance of the proposed method is validated by simulations and experiments on Neubot,a position-controlled biped robot.
文摘The distribution of 0 and 1 is studied in the highest level a e-1of primitive sequences over Z/(2\+e). It is proved that the proportion of 0 (or 1) in one period of a e-1is between 40% and 60% for e≥8.
基金supported by JSPS KAKENHI Grant Number JP731131,JP1069176.
文摘Origami,a traditional Japanese art,is an example of superior handwork produced by human hands.Achieving such extreme dexterity is one of the goals of robotic technology.In the work described in this paper,we developed a new general-purpose robot system with sufficient capabilities for performing Origami.We decomposed the complex folding motions into simple primitives and generated the overall motion as a combination of these primitives.Also,to measure the paper deformation in real-time,we built an estimator using a physical simulator and a depth camera.As a result,our experimental system achieved consecutive valley folds and a squash fold.
基金supported by Guizhou Provincial Department of Science and Technology(Guizhou Science and Technology Cooperation Support[2021]General 442)Guizhou Provincial Department of Science and Technology(Guizhou Science and Technology Cooperation Support[2023]General 179)Guizhou Provincial Department of Science and Technology(Guizhou Science and Technology Cooperation Support[2023]General 096).
文摘Personalized gait curves are generated to enhance patient adaptability to gait trajectories used for passive training in the early stage of rehabilitation for hemiplegic patients.The article utilizes the random forest algorithm to construct a gait parameter model,which maps the relationship between parameters such as height,weight,age,gender,and gait speed,achieving prediction of key points on the gait curve.To enhance prediction accuracy,an attention mechanism is introduced into the algorithm to focus more on the main features.Meanwhile,to ensure high similarity between the reconstructed gait curve and the normal one,probabilistic motion primitives(ProMP)are used to learn the probability distribution of normal gait data and construct a gait trajectorymodel.Finally,using the specified step speed as input,select a reference gait trajectory from the learned trajectory,and reconstruct the curve of the reference trajectoryusing the gait keypoints predictedby the parametermodel toobtain the final curve.Simulation results demonstrate that the method proposed in this paper achieves 98%and 96%curve correlations when generating personalized lower limb gait curves for different patients,respectively,indicating its suitability for such tasks.
基金Supported by the National Natural Science Foundation of China(11861071).
文摘In this paper,we exhibit a free monoid containing all prefix codes in connection with the sets of i-th powers of primitive words for all i≥2.This extends two results given by Shyr and Tsai in 1998 at the same time.
基金supported by the Excellent Foreign Student scholarship program,Sirindhorn International Institute of Technology.
文摘Space-Time Block Coded(STBC)Orthogonal Frequency Division Multiplexing(OFDM)satisfies higher data-rate requirements while maintaining signal quality in a multipath fading channel.However,conventional STBCs,including Orthogonal STBCs(OSTBCs),Non-Orthogonal(NOSTBCs),and Quasi-Orthogonal STBCs(QOSTBCs),do not provide both maximal diversity order and unity code rate simultaneously for more than two transmit antennas.This paper targets this problem and applies Maximum Rank Distance(MRD)codes in designing STBCOFDM systems.By following the direct-matrix construction method,we can construct binary extended finite field MRD-STBCs for any number of transmitting antennas.Work uses MRD-STBCs built over Phase-Shift Keying(PSK)modulation to develop an MRD-based STBC-OFDM system.The MRD-based STBC-OFDM system sacrifices minor error performance compared to traditional OSTBC-OFDM but shows improved results against NOSTBC and QOSTBC-OFDM.It also provides 25%higher data-rates than OSTBC-OFDM in configurations that use more than two transmit antennas.The tradeoffs are minor increases in computational complexity and processing delays.
