The problem of collision avoidance for non-cooperative targets has received significant attention from researchers in recent years.Non-cooperative targets exhibit uncertain states and unpredictable behaviors,making co...The problem of collision avoidance for non-cooperative targets has received significant attention from researchers in recent years.Non-cooperative targets exhibit uncertain states and unpredictable behaviors,making collision avoidance significantly more challenging than that for space debris.Much existing research focuses on the continuous thrust model,whereas the impulsive maneuver model is more appropriate for long-duration and long-distance avoidance missions.Additionally,it is important to minimize the impact on the original mission while avoiding noncooperative targets.On the other hand,the existing avoidance algorithms are computationally complex and time-consuming especially with the limited computing capability of the on-board computer,posing challenges for practical engineering applications.To conquer these difficulties,this paper makes the following key contributions:(A)a turn-based(sequential decision-making)limited-area impulsive collision avoidance model considering the time delay of precision orbit determination is established for the first time;(B)a novel Selection Probability Learning Adaptive Search-depth Search Tree(SPL-ASST)algorithm is proposed for non-cooperative target avoidance,which improves the decision-making efficiency by introducing an adaptive-search-depth mechanism and a neural network into the traditional Monte Carlo Tree Search(MCTS).Numerical simulations confirm the effectiveness and efficiency of the proposed method.展开更多
This paper investigates impulsive orbital attack-defense(AD)games under multiple constraints and victory conditions,involving three spacecraft:attacker,target,and defender.In the AD scenario,the attacker aims to breac...This paper investigates impulsive orbital attack-defense(AD)games under multiple constraints and victory conditions,involving three spacecraft:attacker,target,and defender.In the AD scenario,the attacker aims to breach the defender's interception to rendezvous with the target,while the defender seeks to protect the target by blocking or actively pursuing the attacker.Four different maneuvering constraints and five potential game outcomes are incorporated to more accurately model AD game problems and increase complexity,thereby reducing the effectiveness of traditional methods such as differential games and game-tree searches.To address these challenges,this study proposes a multiagent deep reinforcement learning solution with variable reward functions.Two attack strategies,Direct attack(DA)and Bypass attack(BA),are developed for the attacker,each focusing on different mission priorities.Similarly,two defense strategies,Direct interdiction(DI)and Collinear interdiction(CI),are designed for the defender,each optimizing specific defensive actions through tailored reward functions.Each reward function incorporates both process rewards(e.g.,distance and angle)and outcome rewards,derived from physical principles and validated via geometric analysis.Extensive simulations of four strategy confrontations demonstrate average defensive success rates of 75%for DI vs.DA,40%for DI vs.BA,80%for CI vs.DA,and 70%for CI vs.BA.Results indicate that CI outperforms DI for defenders,while BA outperforms DA for attackers.Moreover,defenders achieve their objectives more effectively under identical maneuvering capabilities.Trajectory evolution analyses further illustrate the effectiveness of the proposed variable reward function-driven strategies.These strategies and analyses offer valuable guidance for practical orbital defense scenarios and lay a foundation for future multi-agent game research.展开更多
Optimal,many-revolution spacecraft trajectories are challenging to solve.A connection is made for a class of models between optimal direct and indirect solutions.For transfers that minimize thrust-acceleration-squared...Optimal,many-revolution spacecraft trajectories are challenging to solve.A connection is made for a class of models between optimal direct and indirect solutions.For transfers that minimize thrust-acceleration-squared,primer vector theory maps direct,many-impulsive-maneuver trajectories to the indirect,continuous-thrust-acceleration equivalent.The mapping algorithm is independent of how the direct solution is obtained and requires only a solver for a boundary value problem and its partial derivatives.A Lambert solver is used for the two-body problem in this work.The mapping is simple because the impulsive maneuvers and co-states share the same linear space around an optimal trajectory.For numerical results,the direct coast-impulse solutions are demonstrated to converge to the indirect continuous solutions as the number of impulses and segments increases.The two-body design space is explored with a set of three many-revolution,many-segment examples changing semimajor axis,eccentricity,and inclination.The first two examples involve a small change to either semimajor axis or eccentricity,and the third example is a transfer to geosynchronous orbit.Using a single processor,the optimization runtime is seconds to minutes for revolution counts of 10 to 100,and on the order of one hour for examples with up to 500 revolutions.Any of these thrust-acceleration-squared solutions are good candidates to start a homotopy to a higher-fidelity minimization problem with practical constraints.展开更多
基金co-supported by the Foundation of Shanghai Astronautics Science and Technology Innovation,China(No.SAST2022-114)the National Natural Science Foundation of China(No.62303378),the National Natural Science Foundation of China(Nos.124B2031,12202281)the Foundation of China National Key Laboratory of Science and Technology on Test Physics&Numerical Mathematics,China(No.08-YY-2023-R11)。
文摘The problem of collision avoidance for non-cooperative targets has received significant attention from researchers in recent years.Non-cooperative targets exhibit uncertain states and unpredictable behaviors,making collision avoidance significantly more challenging than that for space debris.Much existing research focuses on the continuous thrust model,whereas the impulsive maneuver model is more appropriate for long-duration and long-distance avoidance missions.Additionally,it is important to minimize the impact on the original mission while avoiding noncooperative targets.On the other hand,the existing avoidance algorithms are computationally complex and time-consuming especially with the limited computing capability of the on-board computer,posing challenges for practical engineering applications.To conquer these difficulties,this paper makes the following key contributions:(A)a turn-based(sequential decision-making)limited-area impulsive collision avoidance model considering the time delay of precision orbit determination is established for the first time;(B)a novel Selection Probability Learning Adaptive Search-depth Search Tree(SPL-ASST)algorithm is proposed for non-cooperative target avoidance,which improves the decision-making efficiency by introducing an adaptive-search-depth mechanism and a neural network into the traditional Monte Carlo Tree Search(MCTS).Numerical simulations confirm the effectiveness and efficiency of the proposed method.
基金supported by National Key R&D Program of China:Gravitational Wave Detection Project(Grant Nos.2021YFC22026,2021YFC2202601,2021YFC2202603)National Natural Science Foundation of China(Grant Nos.12172288 and 12472046)。
文摘This paper investigates impulsive orbital attack-defense(AD)games under multiple constraints and victory conditions,involving three spacecraft:attacker,target,and defender.In the AD scenario,the attacker aims to breach the defender's interception to rendezvous with the target,while the defender seeks to protect the target by blocking or actively pursuing the attacker.Four different maneuvering constraints and five potential game outcomes are incorporated to more accurately model AD game problems and increase complexity,thereby reducing the effectiveness of traditional methods such as differential games and game-tree searches.To address these challenges,this study proposes a multiagent deep reinforcement learning solution with variable reward functions.Two attack strategies,Direct attack(DA)and Bypass attack(BA),are developed for the attacker,each focusing on different mission priorities.Similarly,two defense strategies,Direct interdiction(DI)and Collinear interdiction(CI),are designed for the defender,each optimizing specific defensive actions through tailored reward functions.Each reward function incorporates both process rewards(e.g.,distance and angle)and outcome rewards,derived from physical principles and validated via geometric analysis.Extensive simulations of four strategy confrontations demonstrate average defensive success rates of 75%for DI vs.DA,40%for DI vs.BA,80%for CI vs.DA,and 70%for CI vs.BA.Results indicate that CI outperforms DI for defenders,while BA outperforms DA for attackers.Moreover,defenders achieve their objectives more effectively under identical maneuvering capabilities.Trajectory evolution analyses further illustrate the effectiveness of the proposed variable reward function-driven strategies.These strategies and analyses offer valuable guidance for practical orbital defense scenarios and lay a foundation for future multi-agent game research.
文摘Optimal,many-revolution spacecraft trajectories are challenging to solve.A connection is made for a class of models between optimal direct and indirect solutions.For transfers that minimize thrust-acceleration-squared,primer vector theory maps direct,many-impulsive-maneuver trajectories to the indirect,continuous-thrust-acceleration equivalent.The mapping algorithm is independent of how the direct solution is obtained and requires only a solver for a boundary value problem and its partial derivatives.A Lambert solver is used for the two-body problem in this work.The mapping is simple because the impulsive maneuvers and co-states share the same linear space around an optimal trajectory.For numerical results,the direct coast-impulse solutions are demonstrated to converge to the indirect continuous solutions as the number of impulses and segments increases.The two-body design space is explored with a set of three many-revolution,many-segment examples changing semimajor axis,eccentricity,and inclination.The first two examples involve a small change to either semimajor axis or eccentricity,and the third example is a transfer to geosynchronous orbit.Using a single processor,the optimization runtime is seconds to minutes for revolution counts of 10 to 100,and on the order of one hour for examples with up to 500 revolutions.Any of these thrust-acceleration-squared solutions are good candidates to start a homotopy to a higher-fidelity minimization problem with practical constraints.
