Unmanned Aerial Vehicles(UAVs)are useful in dangerous and dynamic tasks such as search-and-rescue,forest surveillance,and anti-terrorist operations.These tasks can be solved better through the collaboration of multipl...Unmanned Aerial Vehicles(UAVs)are useful in dangerous and dynamic tasks such as search-and-rescue,forest surveillance,and anti-terrorist operations.These tasks can be solved better through the collaboration of multiple UAVs under human supervision.However,it is still difficult for human to monitor,understand,predict and control the behaviors of the UAVs due to the task complexity as well as the black-box machine learning and planning algorithms being used.In this paper,the coactive design method is adopted to analyze the cognitive capabilities required for the tasks and design the interdependencies among the heterogeneous teammates of UAVs or human for coherent collaboration.Then,an agent-based task planner is proposed to automatically decompose a complex task into a sequence of explainable subtasks under constrains of resources,execution time,social rules and costs.Besides,a deep reinforcement learning approach is designed for the UAVs to learn optimal policies of a flocking behavior and a path planner that are easy for the human operator to understand and control.Finally,a mixed-initiative action selection mechanism is used to evaluate the learned policies as well as the human’s decisions.Experimental results demonstrate the effectiveness of the proposed methods.展开更多
Traditionally, heuristic re-planning algorithms are used to tackle the problem of dynamic task planning for multiple satellites. However, the traditional heuristic strategies depend on the concrete tasks, which often ...Traditionally, heuristic re-planning algorithms are used to tackle the problem of dynamic task planning for multiple satellites. However, the traditional heuristic strategies depend on the concrete tasks, which often affect the result’s optimality. Noticing that the historical information of cooperative task planning will impact the latter planning results, we propose a hybrid learning algorithm for dynamic multi-satellite task planning, which is based on the multi-agent reinforcement learning of policy iteration and the transfer learning. The reinforcement learning strategy of each satellite is described with neural networks. The policy neural network individuals with the best topological structure and weights are found by applying co-evolutionary search iteratively. To avoid the failure of the historical learning caused by the randomly occurring observation requests, a novel approach is proposed to balance the quality and efficiency of the task planning, which converts the historical learning strategy to the current initial learning strategy by applying the transfer learning algorithm. The simulations and analysis show the feasibility and adaptability of the proposed approach especially for the situation with randomly occurring observation requests.展开更多
Task planning and collaboration of multiple robots have broad application prospects and value in the field of robotics.To improve the performance and working efficiency of our Spherical Underwater Robot(SUR),we propos...Task planning and collaboration of multiple robots have broad application prospects and value in the field of robotics.To improve the performance and working efficiency of our Spherical Underwater Robot(SUR),we propose a multi-robot control strategy that can realize the task planning and collaboration of multiple robots.To complete real-time information sharing of multiple robots,we first build an acoustic communication system with excellent communication performance under low noise ratio conditions.Then,the task planning and collaboration control strategy adjust the SURs so that they maintain their positions in the desired formation when the formation moves.Multiple SURs can move along desired trajectories in the expected formation.The control strategy of each SUR uses only its information and limited information of its neighboring SURs.Finally,based on theoretical analysis and experiments,we evaluate the validity and reliability of the proposed strategy.In comparison to the traditional leader–follower method,it is not necessary to designate a leader and its followers explicitly in our system;thus,important advantages,such as fault tolerance,are achieved.展开更多
With the new development trend of multi-resource coordinated Earth observation and the new goal of Earth observation application of“short response time,high observation accuracy,and wide coverage”,space-aeronautics ...With the new development trend of multi-resource coordinated Earth observation and the new goal of Earth observation application of“short response time,high observation accuracy,and wide coverage”,space-aeronautics cooperative complex task planning problem has become an urgent problem to be solved.The focus of this problem is to use multiple resources to perform collaborative observations on complex tasks.By analyzing the process from task assignment to receiving task observation results,we propose a multi-layer interactive task planning framework which is composed of a preprocessing method for complex tasks,a task allocation layer,a task planning layer,and a task coordination layer.According to the characteristics of the framework,a hybrid genetic parallel tabu(HGPT)algorithm is proposed on this basis.The algorithm uses genetic annealing algorithm(GAA),parallel tabu(PT)algorithm,and heuristic rules to achieve task allocation,task planning,and task coordination.At the same time,coding improvements,operator design,annealing operations,and parallel calculations are added to the algorithm.In order to verify the effectiveness of the algorithm,simulation experiments under complex task scenarios of different scales are carried out.Experimental results show that this method can effectively solve the problems of observing complex tasks.Meanwhile,the optimization effect and convergence speed of the HGPT is better than that of the related algorithms.展开更多
The unreasonable observation arrangements in the satellite operation control center(SOCC)may result in the observation data cannot be downloaded as scheduled.Meanwhile,if the operation instructions released by the sat...The unreasonable observation arrangements in the satellite operation control center(SOCC)may result in the observation data cannot be downloaded as scheduled.Meanwhile,if the operation instructions released by the satellite telemetry tracking center(STTC)for the on-board payloads are not injected on the specific satellites in time,the corresponding satellites cannot perform the observation operations as planned.Therefore,there is an urgent need to design an integrated instruction release,and observation task planning(I-IRO-TP)scheme by efficiently collaborating the SOCC and STTC.Motivated by this fact,we design an interaction mechanism between the SOCC and the STTC,where we first formulate the I-IRO-TP problem as a constraint satisfaction problem aiming at maximizing the number of completed tasks.Furthermore,we propose an interactive imaging task planning algorithm based on the analysis of resource distribution in the STTC during the previous planning periods to preferentially select the observation arcs that not only satisfy the requirements in the observation resource allocation phase but also facilitate the arrangement of measurement and control instruction release.We conduct extensive simulations to demonstrate the effectiveness of the proposed algorithm in terms of the number of completed tasks.展开更多
Multiple earth observing satellites need to communicate with each other to observe plenty of targets on the Earth together. The factors, such as external interference, result in satellite information interaction delay...Multiple earth observing satellites need to communicate with each other to observe plenty of targets on the Earth together. The factors, such as external interference, result in satellite information interaction delays, which is unable to ensure the integrity and timeliness of the information on decision making for satellites. And the optimization of the planning result is affected. Therefore, the effect of communication delay is considered during the multi-satel ite coordinating process. For this problem, firstly, a distributed cooperative optimization problem for multiple satellites in the delayed communication environment is formulized. Secondly, based on both the analysis of the temporal sequence of tasks in a single satellite and the dynamically decoupled characteristics of the multi-satellite system, the environment information of multi-satellite distributed cooperative optimization is constructed on the basis of the directed acyclic graph（DAG）. Then, both a cooperative optimization decision making framework and a model are built according to the decentralized partial observable Markov decision process（DEC-POMDP）. After that, a satellite coordinating strategy aimed at different conditions of communication delay is mainly analyzed, and a unified processing strategy on communication delay is designed. An approximate cooperative optimization algorithm based on simulated annealing is proposed. Finally, the effectiveness and robustness of the method presented in this paper are verified via the simulation.展开更多
In an Internet based multi-operator and multi-robot system (IMOMR), operators have to work collaboratively to overcome the constraints of space and time. Inherently, the activities among them can be defined as a compu...In an Internet based multi-operator and multi-robot system (IMOMR), operators have to work collaboratively to overcome the constraints of space and time. Inherently, the activities among them can be defined as a computer-supported cooperative work (CSCW). As a practical application of CSCW, a collaborative task planning system (CTPS) for IMOMR is proposed in this paper on the basis of Petri nets. Its definition, components design, and concrete implementation are given in detail, respectively. As a result, a clear collaboration mechanism of multiple operators in an IMOMR is obtained to guarantee their task planning.展开更多
The results of analyzing the managerial characteristics and complexity of product cooperative development suggest that task planning is an important aspect for process management of product cooperative development and...The results of analyzing the managerial characteristics and complexity of product cooperative development suggest that task planning is an important aspect for process management of product cooperative development and the method for planning tasks should be able to model the dependency between tasks and iterations during the development process. In this paper, a DSM-based method and its corresponding optimization algorithms are developed. At first the coupled task sets and uncoupled task sets are identified, and the tasks are then optimized by the corresponding algorithms. The optimal tasks plan will reduce the development time and cost. Considering the practical requirements in real world, a Multilayer DSM is proposed, and its information communication techniques between DSM and traversing principle are described in details.展开更多
In response to the uncertainty of information of the injured in post disaster situations,considering constraints such as random chance and the quantity of rescue resource,the split deliv-ery vehicle routing problem wi...In response to the uncertainty of information of the injured in post disaster situations,considering constraints such as random chance and the quantity of rescue resource,the split deliv-ery vehicle routing problem with stochastic demands(SDVRPSD)model and the multi-depot split delivery heterogeneous vehicle routing problem with stochastic demands(MDSDHVRPSD)model are established.A two-stage hybrid variable neighborhood tabu search algorithm is designed for unmanned vehicle task planning to minimize the path cost of rescue plans.Simulation experiments show that the solution obtained by the algorithm can effectively reduce the rescue vehicle path cost and the rescue task completion time,with high optimization quality and certain portability.展开更多
In dynamic and uncertain reconnaissance missions,effective task assignment and path planning for multiple unmanned aerial vehicles(UAVs)present significant challenges.A stochastic multi-UAV reconnaissance scheduling p...In dynamic and uncertain reconnaissance missions,effective task assignment and path planning for multiple unmanned aerial vehicles(UAVs)present significant challenges.A stochastic multi-UAV reconnaissance scheduling problem is formulated as a combinatorial optimization task with nonlinear objectives and coupled constraints.To solve the non-deterministic polynomial(NP)-hard problem efficiently,a novel learning-enhanced pigeon-inspired optimization(L-PIO)algorithm is proposed.The algorithm integrates a Q-learning mechanism to dynamically regulate control parameters,enabling adaptive exploration–exploitation trade-offs across different optimization phases.Additionally,geometric abstraction techniques are employed to approximate complex reconnaissance regions using maximum inscribed rectangles and spiral path models,allowing for precise cost modeling of UAV paths.The formal objective function is developed to minimize global flight distance and completion time while maximizing reconnaissance priority and task coverage.A series of simulation experiments are conducted under three scenarios:static task allocation,dynamic task emergence,and UAV failure recovery.Comparative analysis with several updated algorithms demonstrates that L-PIO exhibits superior robustness,adaptability,and computational efficiency.The results verify the algorithm's effectiveness in addressing dynamic reconnaissance task planning in real-time multi-UAV applications.展开更多
Although large language models(LLMs)have succeeded in natural language understanding,there are still many challenges in converting natural language instructions into understandable and executable action plans for UAVs...Although large language models(LLMs)have succeeded in natural language understanding,there are still many challenges in converting natural language instructions into understandable and executable action plans for UAVs while generalizing across different missions.This paper introduces MUTP-LLM,a novel hybrid framework that addresses this gap by integrating the semantic flexibility of LLMs with the formal rigor of traditional planners through a structured,multi-stage architecture.Specifically,our framework first employs an large language model(LLM)to translate ambiguous human commands into a structured symbolic task sequence.A hierarchical planner then generates a high-level plan by allocating and sequencing these tasks.Subsequently,another LLM instance grounds the abstract plan into concrete navigational waypoints.Crucially,a two-stage validation mechanism verifies the plan's logical coherence and physical safety before it is dispatched for execution.Simulation experiments demonstrate that MUTP-LLM achieves superior performance in task success,planning robustness,and safety compared to end-to-end LLM or purely traditional approaches.展开更多
The complexity and uncertainty in power systems cause great challenges to controlling power grids.As a popular data-driven technique,deep reinforcement learning(DRL)attracts attention in the control of power grids.How...The complexity and uncertainty in power systems cause great challenges to controlling power grids.As a popular data-driven technique,deep reinforcement learning(DRL)attracts attention in the control of power grids.However,DRL has some inherent drawbacks in terms of data efficiency and explainability.This paper presents a novel hierarchical task planning(HTP)approach,bridging planning and DRL,to the task of power line flow regulation.First,we introduce a threelevel task hierarchy to model the task and model the sequence of task units on each level as a task planning-Markov decision processes(TP-MDPs).Second,we model the task as a sequential decision-making problem and introduce a higher planner and a lower planner in HTP to handle different levels of task units.In addition,we introduce a two-layer knowledge graph that can update dynamically during the planning procedure to assist HTP.Experimental results conducted on the IEEE 118-bus and IEEE 300-bus systems demonstrate our HTP approach outperforms proximal policy optimization,a state-of-the-art deep reinforcement learning(DRL)approach,improving efficiency by 26.16%and 6.86%on both systems.展开更多
This paper studies the coordinated planning of transmission tasks in the heterogeneous space networks to enable efficient sharing of ground stations cross satellite systems.Specifically,we first formulate the coordina...This paper studies the coordinated planning of transmission tasks in the heterogeneous space networks to enable efficient sharing of ground stations cross satellite systems.Specifically,we first formulate the coordinated planning problem into a mixed integer liner programming(MILP)problem based on time expanded graph.Then,the problem is transferred and reformulated into a consensus optimization framework which can be solved by satellite systems parallelly.With alternating direction method of multipliers(ADMM),a semi-distributed coordinated transmission task planning algorithm is proposed,in which each satellite system plans its own tasks based on local information and limited communication with the coordination center.Simulation results demonstrate that compared with the centralized and fully-distributed methods,the proposed semi-distributed coordinated method can strike a better balance among task complete rate,complexity,and the amount of information required to be exchanged.展开更多
Many heat transfer tubes are distributed on the tube plates of a steam generator that requires periodic inspection by robots.Existing inspection robots are usually involved in issues:Robots with manipulators need comp...Many heat transfer tubes are distributed on the tube plates of a steam generator that requires periodic inspection by robots.Existing inspection robots are usually involved in issues:Robots with manipulators need complicated installation due to their fixed base;tube mobile robots suffer from low running efficiency because of their structural restricts.Since there are thousands of tubes to be checked,task planning is essential to guarantee the precise,orderly,and efficient inspection process.Most in-service robots check the task tubes using row-by-row and column-bycolumn planning.This leads to unnecessary inspections,resulting in a long shutdown and affecting the regular operation of a nuclear power plant.Therefore,this paper introduces the structure and control system of a dexterous robot and proposes a task planning method.This method proceeds into three steps:task allocation,base position search,and sequence planning.To allocate the task regions,this method calculates the tool work matrix and proposes a criterion to evaluate a sub-region.And then all tasks contained in the sub-region are considered globally to search the base positions.Lastly,we apply an improved ant colony algorithm for base sequence planning and determine the inspection orders according to the planned path.We validated the optimized algorithm by conducting task planning experiments using our robot on a tube sheet.The results show that the proposed method can accomplish full task coverage with few repetitive or redundant inspections and it increases the efficiency by 33.31% compared to the traditional planning algorithms.展开更多
In this paper,a resource mobility aware two-stage hybrid task planning algorithm is proposed to reduce the resource conflict between emergency tasks and the common tasks,so as to improve the overall performance of spa...In this paper,a resource mobility aware two-stage hybrid task planning algorithm is proposed to reduce the resource conflict between emergency tasks and the common tasks,so as to improve the overall performance of space information networks.Specifically,in the common task planning stage,a resource fragment avoidance task planning algorithm is proposed,which reduces the contention between emergency tasks and the planned common tasks in the next stage by avoiding the generation of resource fragments.For emergency tasks,we design a metric to quantify the revenue of the candidate resource combination of emergency tasks,which considers both the priority of the tasks and the impact on the planned common tasks.Based on this,a resource mobility aware emergency task planning algorithm is proposed,which strikes a good balance between improving the sum priority and avoiding disturbing the planned common tasks.Finally,simulation results show that the proposed algorithm is superior to the existing algorithms in both the sum task priority and the task completion rate.展开更多
Recently, crowdsourcing platforms have attracted a number of citizens to perform a variety of location- specific tasks. However, most existing approaches consider the arrangement of a set of tasks for a set of crowd w...Recently, crowdsourcing platforms have attracted a number of citizens to perform a variety of location- specific tasks. However, most existing approaches consider the arrangement of a set of tasks for a set of crowd workers, while few consider crowd workers arriving in a dynamic manner. Therefore, how to arrange suitable location-specific tasks to a set of crowd workers such that the crowd workers obtain maximum satisfaction when arriving sequentially represents a challenge. To address the limitation of existing approaches, we first identify a more general and useful model that considers not only the arrangement of a set of tasks to a set of crowd workers, but also all the dynamic arrivals of all crowd workers. Then, we present an effective crowd-task model which is applied to offiine and online settings, respectively. To solve the problem in an offiine setting, we first observe the characteristics of task planning （CTP） and devise a CTP algorithm to solve the problem. We also propose an effective greedy method and integrated simulated annealing （ISA） techniques to improve the algorithm performance. To solve the problem in an online setting, we develop a greedy algorithm for task planning. Finally, we verify the effectiveness and efficiency of the proposed solutions through extensive experiments using real and synthetic datasets.展开更多
interaction pipelines while maintaining interfaces for task-specific customization.The Structural-BT framework supports the modular design of structure functionalities and allows easy extensibility of the inner planni...interaction pipelines while maintaining interfaces for task-specific customization.The Structural-BT framework supports the modular design of structure functionalities and allows easy extensibility of the inner planning flows between BT components.With the Structural-BT framework,software engineers can develop robotic software by flexibly composing BT structures to formulate the skeleton software architecture and implement task-specific algorithms when necessary.In the experiment,this paper develops robotic software for diverse task scenarios and selects the baseline approaches of Robot Operating System(ROS)and classical BT development frameworks for comparison.By quantitatively measuring the reuse frequencies and ratios of BT structures,the Structural-BT framework has been shown to be more efficient than the baseline approaches for robotic software development.展开更多
Learning is widely used in intelligent planning to shorten the planning process or improve the plan quality. This paper aims at introducing learning and fatigue into the classical hierarchical task network （HTN） pla...Learning is widely used in intelligent planning to shorten the planning process or improve the plan quality. This paper aims at introducing learning and fatigue into the classical hierarchical task network （HTN） planning process so as to create better high- quality plans quickly. The process of HTN planning is mapped during a depth-first search process in a problem-solving agent, and the models of learning in HTN planning is conducted similar to the learning depth-first search （LDFS）. Based on the models, a learning method integrating HTN planning and LDFS is presented, and a fatigue mechanism is introduced to balance exploration and exploitation in learning. Finally, experiments in two classical do- mains are carried out in order to validate the effectiveness of the proposed learning and fatigue inspired method.展开更多
In multi-satellite mission scheduling,an integrated space-ground architecture is typically employed,seamlessly integrating the brain-like ground-based offline planning(satellite-terrestrial collaboration)with the cere...In multi-satellite mission scheduling,an integrated space-ground architecture is typically employed,seamlessly integrating the brain-like ground-based offline planning(satellite-terrestrial collaboration)with the cerebellum-like onboard realtime coordination(multi-satellite collaboration).Within this framework,this survey comprehensively reviews cooperative task planning and resource allocation for embodied multi-satellite systems,leveraging cutting-edge artificial intelligence(AI),particularly reinforcement learning(RL)and large language models(LLMs),to overcome complex coordination challenges in strategic decision-making,synchronization across subsystems,and constrained resource optimization.First,a taxonomy of cooperative scheduling models,covering task scheduling and resource allocation,is presented for key mission profiles(disaster response,onorbit servicing,deep-space exploration),highlighting pervasive spatial,temporal,and resource constraints.Then,AI-enhanced optimization algorithms in centralized,decentralized,and hybrid architectures are reviewed,classified as:(1)multi-objective offline optimization for mission deployment and strategic decisions,(2)online multi-objective optimization adapting to dynamic demands,and(3)explainable AI-driven scheduling ensuring trust in autonomous operations.Methodologies are validated via a high-fidelity simulation platform using digital twins and physics-informed neural networks for realistic emulation and benchmarking.Finally,future directions target fully autonomous AI agent swarms with collective reasoning,human-AI collaborative planning with enhanced interpretability,space autonomy,and multimodal LLM.展开更多
There are multiple ways to control a robotic system. Most of them require the users to have prior knowledge about robots or get trained before using them. Natural language based control attracts increasing attention d...There are multiple ways to control a robotic system. Most of them require the users to have prior knowledge about robots or get trained before using them. Natural language based control attracts increasing attention due to its versatility and less requirements for users. Since natural language instructions from users cannot be understood by the robots directly, the linguistic input has to be processed into a formal representation which captures the task specification and removes the ambiguity inherent in natural language. For most of existing natural language controlled robotic system, they assume the given language instructions are already in correct orders. However, it is very likely for untrained users to give commands in a mixed order based on their direct observation and intuitive thinking. Simply following the order of the commands can lead to failures of tasks. To provide a remedy for the problem, we propose a novel framework named dependency relation matrix （DRM） to model and organize the semantic information extracted from language input, in order to figure out an executable sequence of subtasks for later execution. In addition, the proposed approach projects abstract language input and detailed sensory information into the same space, and uses the difference between the goal specification and temporal status of the task under implementation to monitor the progress of task execution. In this paper, we describe the DRM framework in detail, and illustrate the utility of this approach with experiment results.展开更多
基金co-supported by the National Natural Science Foundation of China(Nos.61906203,61876187)the National Key Laboratory of Science and Technology on UAV,Northwestern Polytechnical University,China(No.614230110080817)。
文摘Unmanned Aerial Vehicles(UAVs)are useful in dangerous and dynamic tasks such as search-and-rescue,forest surveillance,and anti-terrorist operations.These tasks can be solved better through the collaboration of multiple UAVs under human supervision.However,it is still difficult for human to monitor,understand,predict and control the behaviors of the UAVs due to the task complexity as well as the black-box machine learning and planning algorithms being used.In this paper,the coactive design method is adopted to analyze the cognitive capabilities required for the tasks and design the interdependencies among the heterogeneous teammates of UAVs or human for coherent collaboration.Then,an agent-based task planner is proposed to automatically decompose a complex task into a sequence of explainable subtasks under constrains of resources,execution time,social rules and costs.Besides,a deep reinforcement learning approach is designed for the UAVs to learn optimal policies of a flocking behavior and a path planner that are easy for the human operator to understand and control.Finally,a mixed-initiative action selection mechanism is used to evaluate the learned policies as well as the human’s decisions.Experimental results demonstrate the effectiveness of the proposed methods.
文摘Traditionally, heuristic re-planning algorithms are used to tackle the problem of dynamic task planning for multiple satellites. However, the traditional heuristic strategies depend on the concrete tasks, which often affect the result’s optimality. Noticing that the historical information of cooperative task planning will impact the latter planning results, we propose a hybrid learning algorithm for dynamic multi-satellite task planning, which is based on the multi-agent reinforcement learning of policy iteration and the transfer learning. The reinforcement learning strategy of each satellite is described with neural networks. The policy neural network individuals with the best topological structure and weights are found by applying co-evolutionary search iteratively. To avoid the failure of the historical learning caused by the randomly occurring observation requests, a novel approach is proposed to balance the quality and efficiency of the task planning, which converts the historical learning strategy to the current initial learning strategy by applying the transfer learning algorithm. The simulations and analysis show the feasibility and adaptability of the proposed approach especially for the situation with randomly occurring observation requests.
文摘Task planning and collaboration of multiple robots have broad application prospects and value in the field of robotics.To improve the performance and working efficiency of our Spherical Underwater Robot(SUR),we propose a multi-robot control strategy that can realize the task planning and collaboration of multiple robots.To complete real-time information sharing of multiple robots,we first build an acoustic communication system with excellent communication performance under low noise ratio conditions.Then,the task planning and collaboration control strategy adjust the SURs so that they maintain their positions in the desired formation when the formation moves.Multiple SURs can move along desired trajectories in the expected formation.The control strategy of each SUR uses only its information and limited information of its neighboring SURs.Finally,based on theoretical analysis and experiments,we evaluate the validity and reliability of the proposed strategy.In comparison to the traditional leader–follower method,it is not necessary to designate a leader and its followers explicitly in our system;thus,important advantages,such as fault tolerance,are achieved.
基金the National Natural Science Foundation of China(72001212).
文摘With the new development trend of multi-resource coordinated Earth observation and the new goal of Earth observation application of“short response time,high observation accuracy,and wide coverage”,space-aeronautics cooperative complex task planning problem has become an urgent problem to be solved.The focus of this problem is to use multiple resources to perform collaborative observations on complex tasks.By analyzing the process from task assignment to receiving task observation results,we propose a multi-layer interactive task planning framework which is composed of a preprocessing method for complex tasks,a task allocation layer,a task planning layer,and a task coordination layer.According to the characteristics of the framework,a hybrid genetic parallel tabu(HGPT)algorithm is proposed on this basis.The algorithm uses genetic annealing algorithm(GAA),parallel tabu(PT)algorithm,and heuristic rules to achieve task allocation,task planning,and task coordination.At the same time,coding improvements,operator design,annealing operations,and parallel calculations are added to the algorithm.In order to verify the effectiveness of the algorithm,simulation experiments under complex task scenarios of different scales are carried out.Experimental results show that this method can effectively solve the problems of observing complex tasks.Meanwhile,the optimization effect and convergence speed of the HGPT is better than that of the related algorithms.
基金supported by the Natural Science Foundation of China under Grants U19B2025,62121001,and 62001347in part by Key Research and Development Program of Shaanxi(ProgramNo.2022ZDLGY05-02)in part by Young Talent Support Program of Xi’an Association for Science and Technology(No.095920221337).
文摘The unreasonable observation arrangements in the satellite operation control center(SOCC)may result in the observation data cannot be downloaded as scheduled.Meanwhile,if the operation instructions released by the satellite telemetry tracking center(STTC)for the on-board payloads are not injected on the specific satellites in time,the corresponding satellites cannot perform the observation operations as planned.Therefore,there is an urgent need to design an integrated instruction release,and observation task planning(I-IRO-TP)scheme by efficiently collaborating the SOCC and STTC.Motivated by this fact,we design an interaction mechanism between the SOCC and the STTC,where we first formulate the I-IRO-TP problem as a constraint satisfaction problem aiming at maximizing the number of completed tasks.Furthermore,we propose an interactive imaging task planning algorithm based on the analysis of resource distribution in the STTC during the previous planning periods to preferentially select the observation arcs that not only satisfy the requirements in the observation resource allocation phase but also facilitate the arrangement of measurement and control instruction release.We conduct extensive simulations to demonstrate the effectiveness of the proposed algorithm in terms of the number of completed tasks.
基金supported by the National Science Foundation for Young Scholars of China(6130123471401175)
文摘Multiple earth observing satellites need to communicate with each other to observe plenty of targets on the Earth together. The factors, such as external interference, result in satellite information interaction delays, which is unable to ensure the integrity and timeliness of the information on decision making for satellites. And the optimization of the planning result is affected. Therefore, the effect of communication delay is considered during the multi-satel ite coordinating process. For this problem, firstly, a distributed cooperative optimization problem for multiple satellites in the delayed communication environment is formulized. Secondly, based on both the analysis of the temporal sequence of tasks in a single satellite and the dynamically decoupled characteristics of the multi-satellite system, the environment information of multi-satellite distributed cooperative optimization is constructed on the basis of the directed acyclic graph（DAG）. Then, both a cooperative optimization decision making framework and a model are built according to the decentralized partial observable Markov decision process（DEC-POMDP）. After that, a satellite coordinating strategy aimed at different conditions of communication delay is mainly analyzed, and a unified processing strategy on communication delay is designed. An approximate cooperative optimization algorithm based on simulated annealing is proposed. Finally, the effectiveness and robustness of the method presented in this paper are verified via the simulation.
文摘In an Internet based multi-operator and multi-robot system (IMOMR), operators have to work collaboratively to overcome the constraints of space and time. Inherently, the activities among them can be defined as a computer-supported cooperative work (CSCW). As a practical application of CSCW, a collaborative task planning system (CTPS) for IMOMR is proposed in this paper on the basis of Petri nets. Its definition, components design, and concrete implementation are given in detail, respectively. As a result, a clear collaboration mechanism of multiple operators in an IMOMR is obtained to guarantee their task planning.
文摘The results of analyzing the managerial characteristics and complexity of product cooperative development suggest that task planning is an important aspect for process management of product cooperative development and the method for planning tasks should be able to model the dependency between tasks and iterations during the development process. In this paper, a DSM-based method and its corresponding optimization algorithms are developed. At first the coupled task sets and uncoupled task sets are identified, and the tasks are then optimized by the corresponding algorithms. The optimal tasks plan will reduce the development time and cost. Considering the practical requirements in real world, a Multilayer DSM is proposed, and its information communication techniques between DSM and traversing principle are described in details.
基金supported by the National Natural Science Foundation of China(No.61903036)。
文摘In response to the uncertainty of information of the injured in post disaster situations,considering constraints such as random chance and the quantity of rescue resource,the split deliv-ery vehicle routing problem with stochastic demands(SDVRPSD)model and the multi-depot split delivery heterogeneous vehicle routing problem with stochastic demands(MDSDHVRPSD)model are established.A two-stage hybrid variable neighborhood tabu search algorithm is designed for unmanned vehicle task planning to minimize the path cost of rescue plans.Simulation experiments show that the solution obtained by the algorithm can effectively reduce the rescue vehicle path cost and the rescue task completion time,with high optimization quality and certain portability.
基金supported by the National Natural Science Foundation of China(Nos.T2121003,U24B20156)Open Fund of the National Key Laboratory of Helicopter Aeromechanics(No.2024-ZSJ-LB-02-06)。
文摘In dynamic and uncertain reconnaissance missions,effective task assignment and path planning for multiple unmanned aerial vehicles(UAVs)present significant challenges.A stochastic multi-UAV reconnaissance scheduling problem is formulated as a combinatorial optimization task with nonlinear objectives and coupled constraints.To solve the non-deterministic polynomial(NP)-hard problem efficiently,a novel learning-enhanced pigeon-inspired optimization(L-PIO)algorithm is proposed.The algorithm integrates a Q-learning mechanism to dynamically regulate control parameters,enabling adaptive exploration–exploitation trade-offs across different optimization phases.Additionally,geometric abstraction techniques are employed to approximate complex reconnaissance regions using maximum inscribed rectangles and spiral path models,allowing for precise cost modeling of UAV paths.The formal objective function is developed to minimize global flight distance and completion time while maximizing reconnaissance priority and task coverage.A series of simulation experiments are conducted under three scenarios:static task allocation,dynamic task emergence,and UAV failure recovery.Comparative analysis with several updated algorithms demonstrates that L-PIO exhibits superior robustness,adaptability,and computational efficiency.The results verify the algorithm's effectiveness in addressing dynamic reconnaissance task planning in real-time multi-UAV applications.
基金supported in part by the National Natural Science Foundation of China under Grant Nos.62576349 and 61876187
文摘Although large language models(LLMs)have succeeded in natural language understanding,there are still many challenges in converting natural language instructions into understandable and executable action plans for UAVs while generalizing across different missions.This paper introduces MUTP-LLM,a novel hybrid framework that addresses this gap by integrating the semantic flexibility of LLMs with the formal rigor of traditional planners through a structured,multi-stage architecture.Specifically,our framework first employs an large language model(LLM)to translate ambiguous human commands into a structured symbolic task sequence.A hierarchical planner then generates a high-level plan by allocating and sequencing these tasks.Subsequently,another LLM instance grounds the abstract plan into concrete navigational waypoints.Crucially,a two-stage validation mechanism verifies the plan's logical coherence and physical safety before it is dispatched for execution.Simulation experiments demonstrate that MUTP-LLM achieves superior performance in task success,planning robustness,and safety compared to end-to-end LLM or purely traditional approaches.
基金supported in part by the National Key R&D Program(2018AAA0101501)of Chinathe science and technology project of SGCC(State Grid Corporation of China).
文摘The complexity and uncertainty in power systems cause great challenges to controlling power grids.As a popular data-driven technique,deep reinforcement learning(DRL)attracts attention in the control of power grids.However,DRL has some inherent drawbacks in terms of data efficiency and explainability.This paper presents a novel hierarchical task planning(HTP)approach,bridging planning and DRL,to the task of power line flow regulation.First,we introduce a threelevel task hierarchy to model the task and model the sequence of task units on each level as a task planning-Markov decision processes(TP-MDPs).Second,we model the task as a sequential decision-making problem and introduce a higher planner and a lower planner in HTP to handle different levels of task units.In addition,we introduce a two-layer knowledge graph that can update dynamically during the planning procedure to assist HTP.Experimental results conducted on the IEEE 118-bus and IEEE 300-bus systems demonstrate our HTP approach outperforms proximal policy optimization,a state-of-the-art deep reinforcement learning(DRL)approach,improving efficiency by 26.16%and 6.86%on both systems.
基金supported in part by the NSF China under Grant(61701365,61801365,62001347)in part by Natural Science Foundation of Shaanxi Province(2020JQ-686)+4 种基金in part by the China Postdoctoral Science Foundation under Grant(2018M643581,2019TQ0210,2019TQ0241,2020M673344)in part by Young Talent fund of University Association for Science and Technology in Shaanxi,China(20200112)in part by Key Research and Development Program in Shaanxi Province of China(2021GY066)in part by Postdoctoral Foundation in Shaanxi Province of China(2018BSHEDZZ47)the Fundamental Research Funds for the Central Universities。
文摘This paper studies the coordinated planning of transmission tasks in the heterogeneous space networks to enable efficient sharing of ground stations cross satellite systems.Specifically,we first formulate the coordinated planning problem into a mixed integer liner programming(MILP)problem based on time expanded graph.Then,the problem is transferred and reformulated into a consensus optimization framework which can be solved by satellite systems parallelly.With alternating direction method of multipliers(ADMM),a semi-distributed coordinated transmission task planning algorithm is proposed,in which each satellite system plans its own tasks based on local information and limited communication with the coordination center.Simulation results demonstrate that compared with the centralized and fully-distributed methods,the proposed semi-distributed coordinated method can strike a better balance among task complete rate,complexity,and the amount of information required to be exchanged.
基金supported by the National Natural Science Foundation of China(Grant No.U2013214)the Self-Planned Task of the State Key Laboratory of Robotics and System(HIT),China(Grant No.SKLRS202001A03).
文摘Many heat transfer tubes are distributed on the tube plates of a steam generator that requires periodic inspection by robots.Existing inspection robots are usually involved in issues:Robots with manipulators need complicated installation due to their fixed base;tube mobile robots suffer from low running efficiency because of their structural restricts.Since there are thousands of tubes to be checked,task planning is essential to guarantee the precise,orderly,and efficient inspection process.Most in-service robots check the task tubes using row-by-row and column-bycolumn planning.This leads to unnecessary inspections,resulting in a long shutdown and affecting the regular operation of a nuclear power plant.Therefore,this paper introduces the structure and control system of a dexterous robot and proposes a task planning method.This method proceeds into three steps:task allocation,base position search,and sequence planning.To allocate the task regions,this method calculates the tool work matrix and proposes a criterion to evaluate a sub-region.And then all tasks contained in the sub-region are considered globally to search the base positions.Lastly,we apply an improved ant colony algorithm for base sequence planning and determine the inspection orders according to the planned path.We validated the optimized algorithm by conducting task planning experiments using our robot on a tube sheet.The results show that the proposed method can accomplish full task coverage with few repetitive or redundant inspections and it increases the efficiency by 33.31% compared to the traditional planning algorithms.
基金supported by the National Natural Science Foundation of China(61701365,61801365 and 91638202)China Postdoctoral Science Foundation(2018M643581,2019TQ0241)+2 种基金National Natural Science Foundation of Shaanxi Province(2019JQ-152)Postdoctoral Foundation in Shaanxi Province of Chinathe Fundamental Research Funds for the Central Universities.
文摘In this paper,a resource mobility aware two-stage hybrid task planning algorithm is proposed to reduce the resource conflict between emergency tasks and the common tasks,so as to improve the overall performance of space information networks.Specifically,in the common task planning stage,a resource fragment avoidance task planning algorithm is proposed,which reduces the contention between emergency tasks and the planned common tasks in the next stage by avoiding the generation of resource fragments.For emergency tasks,we design a metric to quantify the revenue of the candidate resource combination of emergency tasks,which considers both the priority of the tasks and the impact on the planned common tasks.Based on this,a resource mobility aware emergency task planning algorithm is proposed,which strikes a good balance between improving the sum priority and avoiding disturbing the planned common tasks.Finally,simulation results show that the proposed algorithm is superior to the existing algorithms in both the sum task priority and the task completion rate.
基金supported by the National High-Tech R&D Program(863) of China(No.2014AA015203)
文摘Recently, crowdsourcing platforms have attracted a number of citizens to perform a variety of location- specific tasks. However, most existing approaches consider the arrangement of a set of tasks for a set of crowd workers, while few consider crowd workers arriving in a dynamic manner. Therefore, how to arrange suitable location-specific tasks to a set of crowd workers such that the crowd workers obtain maximum satisfaction when arriving sequentially represents a challenge. To address the limitation of existing approaches, we first identify a more general and useful model that considers not only the arrangement of a set of tasks to a set of crowd workers, but also all the dynamic arrivals of all crowd workers. Then, we present an effective crowd-task model which is applied to offiine and online settings, respectively. To solve the problem in an offiine setting, we first observe the characteristics of task planning （CTP） and devise a CTP algorithm to solve the problem. We also propose an effective greedy method and integrated simulated annealing （ISA） techniques to improve the algorithm performance. To solve the problem in an online setting, we develop a greedy algorithm for task planning. Finally, we verify the effectiveness and efficiency of the proposed solutions through extensive experiments using real and synthetic datasets.
文摘interaction pipelines while maintaining interfaces for task-specific customization.The Structural-BT framework supports the modular design of structure functionalities and allows easy extensibility of the inner planning flows between BT components.With the Structural-BT framework,software engineers can develop robotic software by flexibly composing BT structures to formulate the skeleton software architecture and implement task-specific algorithms when necessary.In the experiment,this paper develops robotic software for diverse task scenarios and selects the baseline approaches of Robot Operating System(ROS)and classical BT development frameworks for comparison.By quantitatively measuring the reuse frequencies and ratios of BT structures,the Structural-BT framework has been shown to be more efficient than the baseline approaches for robotic software development.
文摘Learning is widely used in intelligent planning to shorten the planning process or improve the plan quality. This paper aims at introducing learning and fatigue into the classical hierarchical task network （HTN） planning process so as to create better high- quality plans quickly. The process of HTN planning is mapped during a depth-first search process in a problem-solving agent, and the models of learning in HTN planning is conducted similar to the learning depth-first search （LDFS）. Based on the models, a learning method integrating HTN planning and LDFS is presented, and a fatigue mechanism is introduced to balance exploration and exploitation in learning. Finally, experiments in two classical do- mains are carried out in order to validate the effectiveness of the proposed learning and fatigue inspired method.
基金supported by the National Natural Science Foundation of China(Grant Nos.62573197,62233005,U2441245,62273195)Shanghai Science and Intelligence“Hundred Teams,Hundred Projects”Program(Grant No.RZ-RGZN-01-25-0951)+5 种基金the CNPC Innovation Fund(Grant No.2024DQ02-0507)the Shanghai Natural Science Foundation Project(Grant No.24ZR1416400)the Shanghai Baiyulan Talent Program Pujiang Project(Grant No.24PJD020)the Industry-Academia-Research Collaboration Fund of the Eighth Academy of China Aerospace Science and Technology Corporation(Grant No.SAST2024-060)the Beijing Natural Science Foundation(Grant No.L252095)the Programme of Introducing Talents of Discipline to Universities(the 111 Project)(Grant No.B17017)。
文摘In multi-satellite mission scheduling,an integrated space-ground architecture is typically employed,seamlessly integrating the brain-like ground-based offline planning(satellite-terrestrial collaboration)with the cerebellum-like onboard realtime coordination(multi-satellite collaboration).Within this framework,this survey comprehensively reviews cooperative task planning and resource allocation for embodied multi-satellite systems,leveraging cutting-edge artificial intelligence(AI),particularly reinforcement learning(RL)and large language models(LLMs),to overcome complex coordination challenges in strategic decision-making,synchronization across subsystems,and constrained resource optimization.First,a taxonomy of cooperative scheduling models,covering task scheduling and resource allocation,is presented for key mission profiles(disaster response,onorbit servicing,deep-space exploration),highlighting pervasive spatial,temporal,and resource constraints.Then,AI-enhanced optimization algorithms in centralized,decentralized,and hybrid architectures are reviewed,classified as:(1)multi-objective offline optimization for mission deployment and strategic decisions,(2)online multi-objective optimization adapting to dynamic demands,and(3)explainable AI-driven scheduling ensuring trust in autonomous operations.Methodologies are validated via a high-fidelity simulation platform using digital twins and physics-informed neural networks for realistic emulation and benchmarking.Finally,future directions target fully autonomous AI agent swarms with collective reasoning,human-AI collaborative planning with enhanced interpretability,space autonomy,and multimodal LLM.
文摘There are multiple ways to control a robotic system. Most of them require the users to have prior knowledge about robots or get trained before using them. Natural language based control attracts increasing attention due to its versatility and less requirements for users. Since natural language instructions from users cannot be understood by the robots directly, the linguistic input has to be processed into a formal representation which captures the task specification and removes the ambiguity inherent in natural language. For most of existing natural language controlled robotic system, they assume the given language instructions are already in correct orders. However, it is very likely for untrained users to give commands in a mixed order based on their direct observation and intuitive thinking. Simply following the order of the commands can lead to failures of tasks. To provide a remedy for the problem, we propose a novel framework named dependency relation matrix （DRM） to model and organize the semantic information extracted from language input, in order to figure out an executable sequence of subtasks for later execution. In addition, the proposed approach projects abstract language input and detailed sensory information into the same space, and uses the difference between the goal specification and temporal status of the task under implementation to monitor the progress of task execution. In this paper, we describe the DRM framework in detail, and illustrate the utility of this approach with experiment results.
