A framework that integrates planning,monitoring and replanning techniques is proposed.It can devise the best solution based on the current state according to specific objectives and properly deal with the influence of...A framework that integrates planning,monitoring and replanning techniques is proposed.It can devise the best solution based on the current state according to specific objectives and properly deal with the influence of abnormity on the plan execution.The framework consists of three parts:the hierarchical task network(HTN)planner based on Monte Carlo tree search(MCTS),hybrid plan monitoring based on forward and backward and norm-based replanning method selection.The HTN planner based on MCTS selects the optimal method for HTN compound task through pre-exploration.Based on specific objectives,it can identify the best solution to the current problem.The hybrid plan monitoring has the capability to detect the influence of abnormity on the effect of an executed action and the premise of an unexecuted action,thus trigger the replanning.The norm-based replanning selection method can measure the difference between the expected state and the actual state,and then select the best replanning algorithm.The experimental results reveal that our method can effectively deal with the influence of abnormity on the implementation of the plan and achieve the target task in an optimal way.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
Modeling how military commanders carry out operations is considered complicated,requiring the capability of not only planning for multiple subordinates but also responding to unexpected events during execution.This p...Modeling how military commanders carry out operations is considered complicated,requiring the capability of not only planning for multiple subordinates but also responding to unexpected events during execution.This paper presents an Hierarchical Task Network(HTN)embedded planning and execution control architecture for small unit commander agents.To be adaptive to dynamic world state changes,the architecture employs a partial planning mechanism and generates actions only applicable to current situations.It is also able to coordinate subordinates’actions and handle execution failures at runtime.We demonstrate the architecture’s use with an infantry company scenario,where the commander orders three platoons assaulting a defined hill.Our approach shows the effectiveness to control multiple entities in dynamic environments,making the architecture well-suited to represent small unit commanders’behavior.展开更多
基金supported by the National Natural Science Foundation of China(61806221).
文摘A framework that integrates planning,monitoring and replanning techniques is proposed.It can devise the best solution based on the current state according to specific objectives and properly deal with the influence of abnormity on the plan execution.The framework consists of three parts:the hierarchical task network(HTN)planner based on Monte Carlo tree search(MCTS),hybrid plan monitoring based on forward and backward and norm-based replanning method selection.The HTN planner based on MCTS selects the optimal method for HTN compound task through pre-exploration.Based on specific objectives,it can identify the best solution to the current problem.The hybrid plan monitoring has the capability to detect the influence of abnormity on the effect of an executed action and the premise of an unexecuted action,thus trigger the replanning.The norm-based replanning selection method can measure the difference between the expected state and the actual state,and then select the best replanning algorithm.The experimental results reveal that our method can effectively deal with the influence of abnormity on the implementation of the plan and achieve the target task in an optimal way.
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the National Natural Science Foundation of China(Grant Nos.61374185 and 61403402).
文摘Modeling how military commanders carry out operations is considered complicated,requiring the capability of not only planning for multiple subordinates but also responding to unexpected events during execution.This paper presents an Hierarchical Task Network(HTN)embedded planning and execution control architecture for small unit commander agents.To be adaptive to dynamic world state changes,the architecture employs a partial planning mechanism and generates actions only applicable to current situations.It is also able to coordinate subordinates’actions and handle execution failures at runtime.We demonstrate the architecture’s use with an infantry company scenario,where the commander orders three platoons assaulting a defined hill.Our approach shows the effectiveness to control multiple entities in dynamic environments,making the architecture well-suited to represent small unit commanders’behavior.
