The generation of synthetic trajectories has become essential in various fields for analyzing complex movement patterns.However,the use of real-world trajectory data poses significant privacy risks,such as location re...The generation of synthetic trajectories has become essential in various fields for analyzing complex movement patterns.However,the use of real-world trajectory data poses significant privacy risks,such as location reidentification and correlation attacks.To address these challenges,privacy-preserving trajectory generation methods are critical for applications relying on sensitive location data.This paper introduces DPIL-Traj,an advanced framework designed to generate synthetic trajectories while achieving a superior balance between data utility and privacy preservation.Firstly,the framework incorporates Differential Privacy Clustering,which anonymizes trajectory data by applying differential privacy techniques that add noise,ensuring the protection of sensitive user information.Secondly,Imitation Learning is used to replicate decision-making behaviors observed in real-world trajectories.By learning from expert trajectories,this component generates synthetic data that closely mimics real-world decision-making processes while optimizing the quality of the generated trajectories.Finally,Markov-based Trajectory Generation is employed to capture and maintain the inherent temporal dynamics of movement patterns.Extensive experiments conducted on the GeoLife trajectory dataset show that DPIL-Traj improves utility performance by an average of 19.85%,and in terms of privacy performance by an average of 12.51%,compared to state-of-the-art approaches.Ablation studies further reveal that DP clustering effectively safeguards privacy,imitation learning enhances utility under noise,and the Markov module strengthens temporal coherence.展开更多
A trajectory generation method which is based on NURBS interpolation is studied to improve the fitting accuracy and smoothness of non-circular cross section and obtain higher accuracy of the final non-circular profile...A trajectory generation method which is based on NURBS interpolation is studied to improve the fitting accuracy and smoothness of non-circular cross section and obtain higher accuracy of the final non-circular profile control. After using the NURBS, the most optimized and smooth trajectory for the linear actuator can be obtained. For the purpose of machining the non-circular cross section by CNC turning, the fast response linear actuator has been used. The control algorithm which is compound control of proportional-integral-differential （PID） and iterative learning control has been developed for non-circular profile generation. By using the NURBS interpolation and the compound control of PID and iterative learning control, the final motion accuracy of linear actuator has been improved, therefore, the machining accuracy of the non-circular turning can be improved.展开更多
The cooperative interception trajectories generation of multiple interceptors to hypersonic targets is studied.First,to solve the problem of on-line trajectory generation of the single interceptor,a generation method ...The cooperative interception trajectories generation of multiple interceptors to hypersonic targets is studied.First,to solve the problem of on-line trajectory generation of the single interceptor,a generation method based on neighborhood optimal control is adopted.Then,when intercepting the strong maneuvering targets,the single interceptor is insufficient in maneuverability,therefore,an on-line multiple trajectories generation algorithm is proposed,which uses the multiple interceptors intercept area(IIA)to cover the target's predicted intercept area(PIA)cooperatively.Through optimizing the interceptors'zero control terminal location,the trajectories are generated on-line by using the neighborhood optimal control method,these trajectories could make the IIA maximally cover the PIA.The simulation results show that the proposed method can greatly improve the interception probability,which provides a reference for the collaborative interception of multiple interceptors.展开更多
This paper proposes a trajectory generation method utilizing the Bézier curve for mobile robots and employs it in the cooperative transportation task.In contrast to the approach of predefining spatial features an...This paper proposes a trajectory generation method utilizing the Bézier curve for mobile robots and employs it in the cooperative transportation task.In contrast to the approach of predefining spatial features and then allocating time accordingly,the proposed method expresses the spatial characteristics through duration on the basis of ensuring the continuity of dynamics,and then concurrent planning of spatial and temporal characteristics,thereby leading to a trade-off between time efficiency and optimizing spatial features.Furthermore,the proposed method is combined with formation control and applied to a cooperative transportation task.The effectiveness and practicability of the proposed trajectory generation method are verified through both simulation and experiment.展开更多
A new trajectory generation for heat load test is proposed based on gauss pseudospectral method within limit range. Firstly,with multiple path constraints and flight task requirements taken into consideration, heat lo...A new trajectory generation for heat load test is proposed based on gauss pseudospectral method within limit range. Firstly,with multiple path constraints and flight task requirements taken into consideration, heat load parameters are introduced into the dynamics equations. In order to solve the problem of generating such a trajectory within limit range rapidly, the dynamics equations have been normalized by Earth related parameters. Secondly, since the gauss pseudospectral method is just employed to solve the discrete nonlinear programming problem, transformations are developed, which can relate the Lagrange multipliers of the discrete nonlinear programming problem to the costates of the continuous optimal control problem. In addtion, another approach of trajectory generation by tracking the given heat rate is also presented. Finally, simulation results with common aero vehicle(CAV-H) show that the trajectories obtained by both methods can well perform the heat load test with high stagnation heating rate and the large total aeroheating amount; meanwhile, gauss pseudospectral method is better than the compared one in the given range. Furthermore, the 3-D trajectory states and control variables, angle of attack and bank, which are generated by gauss pseudospectral method, can change smoothly.展开更多
Humanoid walking planning is a complicated task because of the high number of degrees of freedom （DOFs） and the variable mechanical structure during walking. In this paper, a planning method for 3- dimensional （3-D...Humanoid walking planning is a complicated task because of the high number of degrees of freedom （DOFs） and the variable mechanical structure during walking. In this paper, a planning method for 3- dimensional （3-D） walking movements was developed based on a model of a typical humanoid robot with 12 DOFs on the lower body. The planning process includes trajectory generation for the hip, ankle, and knee joints in the Cartesian space. The balance of the robot was ensured by adjusting the hip motion. The angles for each DOF were obtained from 3-D kinematics calculation. The calculation gave reference trajectories of all the DOFs on the humanoid robot which were used to control the real robot. The simulation results show that the method is effective.展开更多
The hypersonic interception in near space is a great challenge because of the target’s unpredictable trajectory, which demands the interceptors of trajectory cluster coverage of the predicted area and optimal traject...The hypersonic interception in near space is a great challenge because of the target’s unpredictable trajectory, which demands the interceptors of trajectory cluster coverage of the predicted area and optimal trajectory modification capability aiming at the consistently updating predicted impact point(PIP) in the midcourse phase. A novel midcourse optimal trajectory cluster generation and trajectory modification algorithm is proposed based on the neighboring optimal control theory. Firstly, the midcourse trajectory optimization problem is introduced; the necessary conditions for the optimal control and the transversality constraints are given.Secondly, with the description of the neighboring optimal trajectory existence theory(NOTET), the neighboring optimal control(NOC)algorithm is derived by taking the second order partial derivations with the necessary conditions and transversality conditions. The revised terminal constraints are reversely integrated to the initial time and the perturbations of the co-states are further expressed with the states deviations and terminal constraints modifications.Thirdly, the simulations of two different scenarios are carried out and the results prove the effectiveness and optimality of the proposed method.展开更多
High-Altitude Long-Endurance(HALE)solar-powered Unmanned Aircraft Vehicles(UAVs)can utilize solar energy as power source and maintain extremely long cruise endurance,which has attracted extensive attentions from resea...High-Altitude Long-Endurance(HALE)solar-powered Unmanned Aircraft Vehicles(UAVs)can utilize solar energy as power source and maintain extremely long cruise endurance,which has attracted extensive attentions from researchers.Trajectory optimization is a promising way to achieve superior flight time because of the finite solar energy absorbed in a day.In this work,a method of trajectory optimization and guidance for HALE solar-powered aircraft based on a Reinforcement Learning(RL)framework is introduced.According to flight and environment information,a neural network controller outputs commands of thrust,attack angle,and bank angle to realize an autonomous flight based on energy maximization.The validity of the proposed method was evaluated in a 5-km radius area in simulation,and results have shown that after one day-night cycle,the battery energy of the RL-controller was improved by 31%and 17%compared with those of a Steady-State(SS)strategy with a constant speed and a constant altitude and a kind of statemachine strategy,respectively.In addition,results of an uninterrupted flight test have shown that the endurance of the RL controller was longer than those of the control cases.展开更多
Numerical control electrical discharge machining(NC EDM) is one of the most widely used machining technologies for manufacturing a closed blisk flow path, particularly for three-dimensional(3D) curved and twisted flow...Numerical control electrical discharge machining(NC EDM) is one of the most widely used machining technologies for manufacturing a closed blisk flow path, particularly for three-dimensional(3D) curved and twisted flow channels. In this process, tool electrode design and machining trajectory planning are the key factors affecting machining accessibility and efficiency. Herein, to reduce the difficulty in designing the electrode and its motion path in the closed curved and twisted channels, a heuristic search hybrid optimisation strategy based on channel grids is adopted to realise the initial electrode trajectory design search and optimised size reduction. By transferring the trajectory optimisation constraints from the complex free-form surface to numbered grids, the search is found to be more orderly and accurate. The two trajectory indicators, namely argument angle and minimum distance, are analysed separately for the optimised results of the adaptive learning particle swarm optimisation algorithm, demonstrating that they can meet the actual processing requirements.Experimental results of NC EDM indicate that the motion path generated by this design method can meet the machining requirements of 3D curved and twisted flow channels.展开更多
This study is dedicated to the development of a direct optimal control-based algorithm for trajectory optimization problems that accounts for the closed-loop stability of the trajectory tracking error dynamics already...This study is dedicated to the development of a direct optimal control-based algorithm for trajectory optimization problems that accounts for the closed-loop stability of the trajectory tracking error dynamics already during the optimization.Consequently,the trajectory is designed such that the Linear Time-Varying(LTV)dynamic system,describing the controller’s error dynamics,is stable,while additionally the desired optimality criterion is optimized and all enforced constraints on the trajectory are fulfilled.This is achieved by means of a Lyapunov stability analysis of the LTV dynamics within the optimization problem using a time-dependent,quadratic Lyapunov function candidate.Special care is taken with regard to ensuring the correct definiteness of the ensuing matrices within the Lyapunov stability analysis,specifically considering a numerically stable formulation of these in the numerical optimization.The developed algorithm is applied to a trajectory design problem for which the LTV system is part of the path-following error dynamics,which is required to be stable.The main benefit of the proposed scheme in this context is that the designed trajectory trades-off the required stability and robustness properties of the LTV dynamics with the optimality of the trajectory already at the design phase and thus,does not produce unstable optimal trajectories the system must follow in the real application.展开更多
User location trajectory refers to the sequence of geographic location information that records the user’s movement or stay within a period of time and is usually used in mobile crowd sensing networks,in which the us...User location trajectory refers to the sequence of geographic location information that records the user’s movement or stay within a period of time and is usually used in mobile crowd sensing networks,in which the user participates in the sensing task,the process of sensing data collection faces the problem of privacy leakage.To address the privacy leakage issue of trajectory data during uploading,publishing,and sharing when users use location services on mobile smart group sensing terminal devices,this paper proposes a privacy protection method based on generative adversarial networks and attention mechanisms(BiLS-A-GAN).The method designs a generator attention model,GAttention,and a discriminator attention model,DAttention.In the generator,GAttention,combined with a bidirectional long short-term memory network,more effectively senses contextual information and captures dependencies within sequences.The discriminator uses DAttention and the long short-term memory network to distinguish the authenticity of data.Through continuous interaction between these two models,trajectory data with the statistical characteristics of the original data is generated.This non-original trajectory data can effectively reduce the probability of an attacker’s identification,thereby enhancing the privacy protection of user information.Reliability assessment of the Trajectory-User Linking(TUL)task performed on the real-world semantic trajectory dataset Foursquare NYC,compared with traditional privacy-preserving algorithms that focus only on the privacy enhancement of the data,this approach,while achieving a high level of privacy protection,retains more temporal,spatial,and thematic features from the original trajectory data,to not only guarantee the user’s personal privacy,but also retain the reliability of the information itself in the direction of geographic analysis and other directions,and to achieve the win-win purpose of both data utilization and privacy preservation.展开更多
With the swift advancement of industrial automation,robots have emerged as an essential component in emerging industries and high-end equipment,thereby propelling industrial production towards greater intelligence and...With the swift advancement of industrial automation,robots have emerged as an essential component in emerging industries and high-end equipment,thereby propelling industrial production towards greater intelligence and efficiency.This paper reviews the pivotal technologies for motion planning of robots engaged in contact tasks within industrial automation contexts,encompassing environmental recognition,trajectory generation strategies,and sim-to-real transfer.Environmental recognition technology empowers robots to accurately discern objects and obstacles in their operational environment.Trajectory generation strategies formulate optimal motion paths based on environmental data and task specifications.Sim-to-real transfer is committed to effectively translating strategies from simulated environments to actual production,thereby diminishing the discrepancies between simulation and reality.The article also delves into the application of artificial intelligence in robot motion planning and how embodied intelligence models catalyze the evolution of robotics technology towards enhanced intelligence and automation.The paper concludes with a synthesis of the methodologies addressing this challenge and a perspective on the myriad challenges that warrant attention.展开更多
This paper presents a novel three-dimensional autonomous entry guidance for relatively high lift-to-drag ratio vehicles satisfying geographic constraints and other path constraints. The guidance is composed of onboard...This paper presents a novel three-dimensional autonomous entry guidance for relatively high lift-to-drag ratio vehicles satisfying geographic constraints and other path constraints. The guidance is composed of onboard trajectory planning and robust trajectory tracking. For trajectory planning, a longitudinal sub-planner is introduced to generate a feasible drag-versus-energy profile by using the interpolation between upper boundary and lower boundary of entry corridor to get the desired trajectory length. The associated magnitude of the bank angle can be specified by drag profile, while the sign of bank angle is determined by lateral sub-planner. Two-reverse mode is utilized to satisfy waypoint constraints and dynamic heading error corridor is utilized to satisfy no-fly zone constraints. The longitudinal and lateral sub-planners are iteratively employed until all of the path constraints are satisfied. For trajectory tracking, a novel tracking law based on the active disturbance rejection control is introduced. Finally, adaptability tests and Monte Carlo simulations of the entry guidance approach are performed. Results show that the proposed entry guidance approach can adapt to different entry missions and is able to make the vehicle reach the prescribed target point precisely in spite of geographic constraints.展开更多
A method for the implementation of integrated three-degree-of-freedom constrained entry guidance for reusable launch vehicle is presented.Given any feasible entry conditions,terminal area energy management interface c...A method for the implementation of integrated three-degree-of-freedom constrained entry guidance for reusable launch vehicle is presented.Given any feasible entry conditions,terminal area energy management interface conditions,and the reference trajectory generated onboard then,the method can generate a longitudinal guidance profile rapidly,featuring linear quadratic regular method and a proportional-integral-derivative tracking law with time-varying gains,which satisfies all the entry corridor constraints and meets the requirements with high precision.Afterwards,by utilizing special features of crossrange parameter,establishing bank-reversal corridor,and determining bank-reversals according to dynamically adjusted method,the algorithm enables the lateral entry guidance system to fly a wide range of missions and provides reliable and good performance in the presence of significant aerodynamic modeling uncertainty.Fast trajectory guidance profiles and simulations with a reusable launch vehicle model for various missions and aerodynamic uncertainties are presented to demonstrate the capacity and reliability of this method.展开更多
Harvesting wind energy is promising for extending long-endurance flights,which can be greatly facilitated by a flight technique called dynamic soaring.The presented study is concerned with generating model-based traje...Harvesting wind energy is promising for extending long-endurance flights,which can be greatly facilitated by a flight technique called dynamic soaring.The presented study is concerned with generating model-based trajectories with smooth control histories for dynamic soaring maneuvers exploiting wind gradients.The desired smoothness is achieved by introducing a trigonometric series parameterization for the controls,which are formulated with respect to the normalized time.Specifically,the periodicity of the trigonometric functions is leveraged to facilitate the connection of cycles and streamline the problem formulation.Without relying on a specified wind profile,a freefinal-time quadratic programming-based control strategy is developed for the online correction of the flight trajectory,which requires only the instant wind information.Offline and online numerical studies show the trade-off to achieve the smoothness and demonstrate the effectiveness of the proposed method in a varying wind field.展开更多
We present in this paper a robust online path planning method, which allows a micro rotorcraff drone to fly safely in GPS-denied and obstacle-strewn environments with limited onboard computational power. The approach ...We present in this paper a robust online path planning method, which allows a micro rotorcraff drone to fly safely in GPS-denied and obstacle-strewn environments with limited onboard computational power. The approach is based on an effi- ciently managed grid map and a closed-form solution to the two point boundary value problem （TPBVP）. The grid map assists trajectory evaluation whereas the solution to the TPBVP generates smooth trajectories. Finally, a top-level trajectory switching algorithm is utilized to minimize the computational cost. Advantages of the proposed approach include its conservation of com- putational resource, robustness of trajectory generation and agility of reaction to unknown environment. The result has been realized on actual drones platforms and successfully demonstrated in real flight tests. The video of flight tests can be found at： http：//uav.ece.nus.edu.sg/robust-online-path-planning-Lai2015.html.展开更多
Mobile robot local motion planning is responsible for the fast and smooth obstacle avoidance,which is one of the main indicators for evaluating mobile robots'navigation capabilities.Current methods formulate local...Mobile robot local motion planning is responsible for the fast and smooth obstacle avoidance,which is one of the main indicators for evaluating mobile robots'navigation capabilities.Current methods formulate local motion planning as a unified problem;therefore it cannot satisfy the real-time requirement on the platform with limited computing ability.In order to solve this problem,this paper proposes a fast local motion planning method that can reach a planning frequency of 500 Hz on a low-cost CPU.The proposed method decouples the local motion planning as the front-end path searching and the back-end optimization.The front-end is composed of the environment topology analysis and graph searching.The back-end includes dynamically feasible trajectory generation and optimal trajectory selection.Different from the popular methods,the proposed method decomposes the local motion planning into four sub-modules,each of which aims to solve one problem.Combining four sub-modules,the proposed method can obtain the complete local motion planning algorithm which can fast generate a smooth and collision-free trajectory.The experimental results demonstrate that the proposed method has the ability to obtain the smooth,dynamically feasible and collision-free trajectory and the speed of the planning is fast.展开更多
基金supported by the Natural Science Foundation of Fujian Province of China(2025J01380)National Natural Science Foundation of China(No.62471139)+3 种基金the Major Health Research Project of Fujian Province(2021ZD01001)Fujian Provincial Units Special Funds for Education and Research(2022639)Fujian University of Technology Research Start-up Fund(GY-S24002)Fujian Research and Training Grants for Young and Middle-aged Leaders in Healthcare(GY-H-24179).
文摘The generation of synthetic trajectories has become essential in various fields for analyzing complex movement patterns.However,the use of real-world trajectory data poses significant privacy risks,such as location reidentification and correlation attacks.To address these challenges,privacy-preserving trajectory generation methods are critical for applications relying on sensitive location data.This paper introduces DPIL-Traj,an advanced framework designed to generate synthetic trajectories while achieving a superior balance between data utility and privacy preservation.Firstly,the framework incorporates Differential Privacy Clustering,which anonymizes trajectory data by applying differential privacy techniques that add noise,ensuring the protection of sensitive user information.Secondly,Imitation Learning is used to replicate decision-making behaviors observed in real-world trajectories.By learning from expert trajectories,this component generates synthetic data that closely mimics real-world decision-making processes while optimizing the quality of the generated trajectories.Finally,Markov-based Trajectory Generation is employed to capture and maintain the inherent temporal dynamics of movement patterns.Extensive experiments conducted on the GeoLife trajectory dataset show that DPIL-Traj improves utility performance by an average of 19.85%,and in terms of privacy performance by an average of 12.51%,compared to state-of-the-art approaches.Ablation studies further reveal that DP clustering effectively safeguards privacy,imitation learning enhances utility under noise,and the Markov module strengthens temporal coherence.
基金the Tenth Five-Year National Science and Technology Key Project of China(No.BA203B04).
文摘A trajectory generation method which is based on NURBS interpolation is studied to improve the fitting accuracy and smoothness of non-circular cross section and obtain higher accuracy of the final non-circular profile control. After using the NURBS, the most optimized and smooth trajectory for the linear actuator can be obtained. For the purpose of machining the non-circular cross section by CNC turning, the fast response linear actuator has been used. The control algorithm which is compound control of proportional-integral-differential （PID） and iterative learning control has been developed for non-circular profile generation. By using the NURBS interpolation and the compound control of PID and iterative learning control, the final motion accuracy of linear actuator has been improved, therefore, the machining accuracy of the non-circular turning can be improved.
基金supported by the National Natural Science Foundation of China(61873278)。
文摘The cooperative interception trajectories generation of multiple interceptors to hypersonic targets is studied.First,to solve the problem of on-line trajectory generation of the single interceptor,a generation method based on neighborhood optimal control is adopted.Then,when intercepting the strong maneuvering targets,the single interceptor is insufficient in maneuverability,therefore,an on-line multiple trajectories generation algorithm is proposed,which uses the multiple interceptors intercept area(IIA)to cover the target's predicted intercept area(PIA)cooperatively.Through optimizing the interceptors'zero control terminal location,the trajectories are generated on-line by using the neighborhood optimal control method,these trajectories could make the IIA maximally cover the PIA.The simulation results show that the proposed method can greatly improve the interception probability,which provides a reference for the collaborative interception of multiple interceptors.
基金supported in part by Shanghai Rising-Star Program under Grant No.22QA1409400in part by National Natural Science Foundation of China under Grant Nos.62473287 and 62088101in part by Shanghai Municipal Science and Technology Major Project under Grant No.2021SHZDZX0100。
文摘This paper proposes a trajectory generation method utilizing the Bézier curve for mobile robots and employs it in the cooperative transportation task.In contrast to the approach of predefining spatial features and then allocating time accordingly,the proposed method expresses the spatial characteristics through duration on the basis of ensuring the continuity of dynamics,and then concurrent planning of spatial and temporal characteristics,thereby leading to a trade-off between time efficiency and optimizing spatial features.Furthermore,the proposed method is combined with formation control and applied to a cooperative transportation task.The effectiveness and practicability of the proposed trajectory generation method are verified through both simulation and experiment.
文摘A new trajectory generation for heat load test is proposed based on gauss pseudospectral method within limit range. Firstly,with multiple path constraints and flight task requirements taken into consideration, heat load parameters are introduced into the dynamics equations. In order to solve the problem of generating such a trajectory within limit range rapidly, the dynamics equations have been normalized by Earth related parameters. Secondly, since the gauss pseudospectral method is just employed to solve the discrete nonlinear programming problem, transformations are developed, which can relate the Lagrange multipliers of the discrete nonlinear programming problem to the costates of the continuous optimal control problem. In addtion, another approach of trajectory generation by tracking the given heat rate is also presented. Finally, simulation results with common aero vehicle(CAV-H) show that the trajectories obtained by both methods can well perform the heat load test with high stagnation heating rate and the large total aeroheating amount; meanwhile, gauss pseudospectral method is better than the compared one in the given range. Furthermore, the 3-D trajectory states and control variables, angle of attack and bank, which are generated by gauss pseudospectral method, can change smoothly.
基金the National Natural Science Foundation of China (Nos. 90405017 and 60604010)
文摘Humanoid walking planning is a complicated task because of the high number of degrees of freedom （DOFs） and the variable mechanical structure during walking. In this paper, a planning method for 3- dimensional （3-D） walking movements was developed based on a model of a typical humanoid robot with 12 DOFs on the lower body. The planning process includes trajectory generation for the hip, ankle, and knee joints in the Cartesian space. The balance of the robot was ensured by adjusting the hip motion. The angles for each DOF were obtained from 3-D kinematics calculation. The calculation gave reference trajectories of all the DOFs on the humanoid robot which were used to control the real robot. The simulation results show that the method is effective.
基金supported by the National Natural Science Foundation of China(6150340861573374)
文摘The hypersonic interception in near space is a great challenge because of the target’s unpredictable trajectory, which demands the interceptors of trajectory cluster coverage of the predicted area and optimal trajectory modification capability aiming at the consistently updating predicted impact point(PIP) in the midcourse phase. A novel midcourse optimal trajectory cluster generation and trajectory modification algorithm is proposed based on the neighboring optimal control theory. Firstly, the midcourse trajectory optimization problem is introduced; the necessary conditions for the optimal control and the transversality constraints are given.Secondly, with the description of the neighboring optimal trajectory existence theory(NOTET), the neighboring optimal control(NOC)algorithm is derived by taking the second order partial derivations with the necessary conditions and transversality conditions. The revised terminal constraints are reversely integrated to the initial time and the perturbations of the co-states are further expressed with the states deviations and terminal constraints modifications.Thirdly, the simulations of two different scenarios are carried out and the results prove the effectiveness and optimality of the proposed method.
基金Foundation of the Special Research Assistant of Chinese Academy of Sciences(No.E0290A0301)。
文摘High-Altitude Long-Endurance(HALE)solar-powered Unmanned Aircraft Vehicles(UAVs)can utilize solar energy as power source and maintain extremely long cruise endurance,which has attracted extensive attentions from researchers.Trajectory optimization is a promising way to achieve superior flight time because of the finite solar energy absorbed in a day.In this work,a method of trajectory optimization and guidance for HALE solar-powered aircraft based on a Reinforcement Learning(RL)framework is introduced.According to flight and environment information,a neural network controller outputs commands of thrust,attack angle,and bank angle to realize an autonomous flight based on energy maximization.The validity of the proposed method was evaluated in a 5-km radius area in simulation,and results have shown that after one day-night cycle,the battery energy of the RL-controller was improved by 31%and 17%compared with those of a Steady-State(SS)strategy with a constant speed and a constant altitude and a kind of statemachine strategy,respectively.In addition,results of an uninterrupted flight test have shown that the endurance of the RL controller was longer than those of the control cases.
基金financially supported by Aeronautical Science Foundation of China(No.2011ZE52055)Fundamental Research Funds for the Central Universities(No.3082018NF2018006)。
文摘Numerical control electrical discharge machining(NC EDM) is one of the most widely used machining technologies for manufacturing a closed blisk flow path, particularly for three-dimensional(3D) curved and twisted flow channels. In this process, tool electrode design and machining trajectory planning are the key factors affecting machining accessibility and efficiency. Herein, to reduce the difficulty in designing the electrode and its motion path in the closed curved and twisted channels, a heuristic search hybrid optimisation strategy based on channel grids is adopted to realise the initial electrode trajectory design search and optimised size reduction. By transferring the trajectory optimisation constraints from the complex free-form surface to numbered grids, the search is found to be more orderly and accurate. The two trajectory indicators, namely argument angle and minimum distance, are analysed separately for the optimised results of the adaptive learning particle swarm optimisation algorithm, demonstrating that they can meet the actual processing requirements.Experimental results of NC EDM indicate that the motion path generated by this design method can meet the machining requirements of 3D curved and twisted flow channels.
基金supported in part by the TUM University Foundation Fellowshipin part by the German Federal Ministry for Economic Affairs and Energy(BMWi)within the Federal Aeronautical Research Program LuFo V-3 through Project“HOTRUN”(No.20E1720A)。
文摘This study is dedicated to the development of a direct optimal control-based algorithm for trajectory optimization problems that accounts for the closed-loop stability of the trajectory tracking error dynamics already during the optimization.Consequently,the trajectory is designed such that the Linear Time-Varying(LTV)dynamic system,describing the controller’s error dynamics,is stable,while additionally the desired optimality criterion is optimized and all enforced constraints on the trajectory are fulfilled.This is achieved by means of a Lyapunov stability analysis of the LTV dynamics within the optimization problem using a time-dependent,quadratic Lyapunov function candidate.Special care is taken with regard to ensuring the correct definiteness of the ensuing matrices within the Lyapunov stability analysis,specifically considering a numerically stable formulation of these in the numerical optimization.The developed algorithm is applied to a trajectory design problem for which the LTV system is part of the path-following error dynamics,which is required to be stable.The main benefit of the proposed scheme in this context is that the designed trajectory trades-off the required stability and robustness properties of the LTV dynamics with the optimality of the trajectory already at the design phase and thus,does not produce unstable optimal trajectories the system must follow in the real application.
基金supported by the Key Projects of Gansu University of Political Science and Law(GZF2023XZD18)Gansu Province 2020 Provincial Virtual Simulation First-Class Course(GZYL2020-18)+6 种基金2020 School Level Education Reform Project of Gansu University of Political Science and Law(GZJG2020-B06)the 2022 Provincial Industrial Support Project(2022CYZC-57)Soft Science Special Project of Gansu Basic Research Plan under Grant(22JR11RA106)Gansu Soft Science Project(20CX4ZA074)ScientificResearch Project of Colleges andUniversities of Gansu Provincial Department of Education(2015A-114)Key Research Project of Gansu University of Political Science and Law under Grant(GZF2022XZD08)Provincial Program of Innovation and Entrepreneurship Training for College Students in Gansu Province(S202311406024).
文摘User location trajectory refers to the sequence of geographic location information that records the user’s movement or stay within a period of time and is usually used in mobile crowd sensing networks,in which the user participates in the sensing task,the process of sensing data collection faces the problem of privacy leakage.To address the privacy leakage issue of trajectory data during uploading,publishing,and sharing when users use location services on mobile smart group sensing terminal devices,this paper proposes a privacy protection method based on generative adversarial networks and attention mechanisms(BiLS-A-GAN).The method designs a generator attention model,GAttention,and a discriminator attention model,DAttention.In the generator,GAttention,combined with a bidirectional long short-term memory network,more effectively senses contextual information and captures dependencies within sequences.The discriminator uses DAttention and the long short-term memory network to distinguish the authenticity of data.Through continuous interaction between these two models,trajectory data with the statistical characteristics of the original data is generated.This non-original trajectory data can effectively reduce the probability of an attacker’s identification,thereby enhancing the privacy protection of user information.Reliability assessment of the Trajectory-User Linking(TUL)task performed on the real-world semantic trajectory dataset Foursquare NYC,compared with traditional privacy-preserving algorithms that focus only on the privacy enhancement of the data,this approach,while achieving a high level of privacy protection,retains more temporal,spatial,and thematic features from the original trajectory data,to not only guarantee the user’s personal privacy,but also retain the reliability of the information itself in the direction of geographic analysis and other directions,and to achieve the win-win purpose of both data utilization and privacy preservation.
基金Supported by National Natural Science Foundation of China(Grant Nos.52575091,U2341231)。
文摘With the swift advancement of industrial automation,robots have emerged as an essential component in emerging industries and high-end equipment,thereby propelling industrial production towards greater intelligence and efficiency.This paper reviews the pivotal technologies for motion planning of robots engaged in contact tasks within industrial automation contexts,encompassing environmental recognition,trajectory generation strategies,and sim-to-real transfer.Environmental recognition technology empowers robots to accurately discern objects and obstacles in their operational environment.Trajectory generation strategies formulate optimal motion paths based on environmental data and task specifications.Sim-to-real transfer is committed to effectively translating strategies from simulated environments to actual production,thereby diminishing the discrepancies between simulation and reality.The article also delves into the application of artificial intelligence in robot motion planning and how embodied intelligence models catalyze the evolution of robotics technology towards enhanced intelligence and automation.The paper concludes with a synthesis of the methodologies addressing this challenge and a perspective on the myriad challenges that warrant attention.
基金supported by National Natural Science Foundation of China (No. 11202024)
文摘This paper presents a novel three-dimensional autonomous entry guidance for relatively high lift-to-drag ratio vehicles satisfying geographic constraints and other path constraints. The guidance is composed of onboard trajectory planning and robust trajectory tracking. For trajectory planning, a longitudinal sub-planner is introduced to generate a feasible drag-versus-energy profile by using the interpolation between upper boundary and lower boundary of entry corridor to get the desired trajectory length. The associated magnitude of the bank angle can be specified by drag profile, while the sign of bank angle is determined by lateral sub-planner. Two-reverse mode is utilized to satisfy waypoint constraints and dynamic heading error corridor is utilized to satisfy no-fly zone constraints. The longitudinal and lateral sub-planners are iteratively employed until all of the path constraints are satisfied. For trajectory tracking, a novel tracking law based on the active disturbance rejection control is introduced. Finally, adaptability tests and Monte Carlo simulations of the entry guidance approach are performed. Results show that the proposed entry guidance approach can adapt to different entry missions and is able to make the vehicle reach the prescribed target point precisely in spite of geographic constraints.
文摘A method for the implementation of integrated three-degree-of-freedom constrained entry guidance for reusable launch vehicle is presented.Given any feasible entry conditions,terminal area energy management interface conditions,and the reference trajectory generated onboard then,the method can generate a longitudinal guidance profile rapidly,featuring linear quadratic regular method and a proportional-integral-derivative tracking law with time-varying gains,which satisfies all the entry corridor constraints and meets the requirements with high precision.Afterwards,by utilizing special features of crossrange parameter,establishing bank-reversal corridor,and determining bank-reversals according to dynamically adjusted method,the algorithm enables the lateral entry guidance system to fly a wide range of missions and provides reliable and good performance in the presence of significant aerodynamic modeling uncertainty.Fast trajectory guidance profiles and simulations with a reusable launch vehicle model for various missions and aerodynamic uncertainties are presented to demonstrate the capacity and reliability of this method.
基金supported in part by the TUM University Foundation Fellowshipin part by the German Federal Ministry for Economic Affairs and Energy(BMWi)within the Federal Aeronautical Research Program LuFo VI-1through Project“RAUDY”(No.20E1910B)。
文摘Harvesting wind energy is promising for extending long-endurance flights,which can be greatly facilitated by a flight technique called dynamic soaring.The presented study is concerned with generating model-based trajectories with smooth control histories for dynamic soaring maneuvers exploiting wind gradients.The desired smoothness is achieved by introducing a trigonometric series parameterization for the controls,which are formulated with respect to the normalized time.Specifically,the periodicity of the trigonometric functions is leveraged to facilitate the connection of cycles and streamline the problem formulation.Without relying on a specified wind profile,a freefinal-time quadratic programming-based control strategy is developed for the online correction of the flight trajectory,which requires only the instant wind information.Offline and online numerical studies show the trade-off to achieve the smoothness and demonstrate the effectiveness of the proposed method in a varying wind field.
文摘We present in this paper a robust online path planning method, which allows a micro rotorcraff drone to fly safely in GPS-denied and obstacle-strewn environments with limited onboard computational power. The approach is based on an effi- ciently managed grid map and a closed-form solution to the two point boundary value problem （TPBVP）. The grid map assists trajectory evaluation whereas the solution to the TPBVP generates smooth trajectories. Finally, a top-level trajectory switching algorithm is utilized to minimize the computational cost. Advantages of the proposed approach include its conservation of com- putational resource, robustness of trajectory generation and agility of reaction to unknown environment. The result has been realized on actual drones platforms and successfully demonstrated in real flight tests. The video of flight tests can be found at： http：//uav.ece.nus.edu.sg/robust-online-path-planning-Lai2015.html.
基金the National Key R&D Program of China (No.2017YFB1301300)。
文摘Mobile robot local motion planning is responsible for the fast and smooth obstacle avoidance,which is one of the main indicators for evaluating mobile robots'navigation capabilities.Current methods formulate local motion planning as a unified problem;therefore it cannot satisfy the real-time requirement on the platform with limited computing ability.In order to solve this problem,this paper proposes a fast local motion planning method that can reach a planning frequency of 500 Hz on a low-cost CPU.The proposed method decouples the local motion planning as the front-end path searching and the back-end optimization.The front-end is composed of the environment topology analysis and graph searching.The back-end includes dynamically feasible trajectory generation and optimal trajectory selection.Different from the popular methods,the proposed method decomposes the local motion planning into four sub-modules,each of which aims to solve one problem.Combining four sub-modules,the proposed method can obtain the complete local motion planning algorithm which can fast generate a smooth and collision-free trajectory.The experimental results demonstrate that the proposed method has the ability to obtain the smooth,dynamically feasible and collision-free trajectory and the speed of the planning is fast.
