Near-optimal interception strategy for orbital pursuit-evasion using deep reinforcement learning

Zhang, Jingrui; Zhang, Xiaoying; Zhang, Yao; Shi, Heng; Tang, Liang; Li, Mou

doi:10.1016/j.actaastro.2022.05.057

Cited by 25 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method involves using deep reinforcement learning (DRL) to generate a capture zone (CZ) embedding strategy and a barrier inverse solution neural network (BISNN) to determine an approximately optimal guidance law within the CZ. This approach was described in detail in their paper [21] . dos Santos et al developed a parallel optimization algorithm to minimize the capture time in the capture and escape problem.…”

Section: Introductionmentioning

confidence: 99%

A collaborative siege method of multiple unmanned vehicles based on reinforcement learning

Su,

Pu,

Wang

et al. 2024

Intelligence & Robotics

View full text Add to dashboard Cite

A method based on multi-agent reinforcement learning is proposed to tackle the challenges to capture escaping Target by Unmanned Ground Vehicles (UGVs). Initially, this study introduces environment and motion models tailored for cooperative UGV capture, along with clearly defined success criteria for direct capture. An attention mechanism integrated into the Soft Actor-Critic (SAC) is leveraged, directing focus towards pivotal state features pertinent to the task while effectively managing less relevant aspects. This allows capturing agents to concentrate on the whereabouts and activities of the target agent, thereby enhancing coordination and collaboration during pursuit. This focus on the target agent aids in refining the capture process and ensures precise estimation of value functions. The reduction in superfluous activities and unproductive scenarios amplifies efficiency and robustness. Furthermore, the attention weights dynamically adapt to environmental shifts. To address constrained incentives arising in scenarios with multiple vehicles capturing targets, the study introduces a revamped reward system. It divides the reward function into individual and cooperative components, thereby optimizing both global and localized incentives. By facilitating cooperative collaboration among capturing UGVs, this approach curtails the action space of the target UGV, leading to successful capture outcomes. The proposed technique demonstrates enhanced capture success compared to previous SAC algorithms. Simulation trials and comparisons with alternative learning methodologies validate the effectiveness of the algorithm and the design approach of the reward function.

show abstract

Section: Introductionmentioning

confidence: 99%

A collaborative siege method of multiple unmanned vehicles based on reinforcement learning

Su,

Pu,

Wang

et al. 2024

Intelligence & Robotics

View full text Add to dashboard Cite

show abstract

“…Additionally, the two cutters and the escape ship are studied, as well as the differential pursuit-evasion games of active target defense. Furthermore, the works [7][8][9][10][11][12][13] are dedicated to various differential pursuit and evasion games.…”

Section: Introductionmentioning

confidence: 99%

Multi-Pursuer and One-Evader Evasion Differential Game with Integral Constraints for an Infinite System of Binary Differential Equations

Kazimirova,

Ibragimov,

Pansera

et al. 2024

Mathematics

View full text Add to dashboard Cite

In the Hilbert space l2, a differential evasion game involving multiple pursuers is considered. Integral constraints are imposed on player control functions. The pursuers are tasked with bringing the state of a system back to the origin of l2, while the evader simultaneously tries to avoid it. It is assumed that the energy of the evader is greater than the total energy of the pursuers. In this paper, we contribute to the solution of the differential evasion game with multiple pursuers by building an exact strategy for the evader.

show abstract

“…A hypersonic vehicle (HV) refers to a vehicle that flies through the atmosphere between 20 km and 100 km at a speed above Mach 5, which possesses the characteristics of special flight airspace and high flight speed [1]. In recent years, with the continuous development of anti-hypersonic technology, it has become necessary for the HV to solve the pursuitevasion (PE) problem [2][3][4] between itself and the interceptor.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Maneuver Strategy for a Hypersonic Pursuit-Evasion Game Based on Deep Reinforcement Learning

Guo,

Jiang,

Huang

et al. 2023

Aerospace

View full text Add to dashboard Cite

In order to improve the problem of overly relying on situational information, high computational power requirements, and weak adaptability of traditional maneuver methods used by hypersonic vehicles (HV), an intelligent maneuver strategy combining deep reinforcement learning (DRL) and deep neural network (DNN) is proposed to solve the hypersonic pursuit–evasion (PE) game problem under tough head-on situations. The twin delayed deep deterministic (TD3) gradient strategy algorithm is utilized to explore potential maneuver instructions, the DNN is used to fit to broaden application scenarios, and the intelligent maneuver strategy is generated with the initial situation of both the pursuit and evasion sides as the input and the maneuver game overload of the HV as the output. In addition, the experience pool classification strategy is proposed to improve the training convergence and rate of the TD3 algorithm. A set of reward functions is designed to achieve adaptive adjustment of evasion miss distance and energy consumption under different initial situations. The simulation results verify the feasibility and effectiveness of the above intelligent maneuver strategy in dealing with the PE game problem of HV under difficult situations, and the proposed improvement strategies are validated as well.

show abstract

Near-optimal interception strategy for orbital pursuit-evasion using deep reinforcement learning

Cited by 25 publications

References 24 publications

A collaborative siege method of multiple unmanned vehicles based on reinforcement learning

A collaborative siege method of multiple unmanned vehicles based on reinforcement learning

Multi-Pursuer and One-Evader Evasion Differential Game with Integral Constraints for an Infinite System of Binary Differential Equations

Intelligent Maneuver Strategy for a Hypersonic Pursuit-Evasion Game Based on Deep Reinforcement Learning

Contact Info

Product

Resources

About