A Dynamically Feasible Fast Replanning Strategy with Deep Reinforcement Learning

Hasanzade, Mehmet; Koyuncu, Emre

doi:10.1007/s10846-020-01274-1

Cited by 6 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The development of artificial intelligence provides alternative ways to address this challenge. Reinforcement learning (RL) as the representative of intelligent algorithms can interact with the environment in real time and obtains the optimal control of the maximum reward through data training [21,22]. RL has been widely employed to solve PE problems in the field of unmanned aerial vehicle (UAV) [23][24][25].…”

Section: Introductionmentioning

confidence: 99%

Two-Stage Pursuit Strategy for Incomplete-Information Impulsive Space Pursuit-Evasion Mission Using Reinforcement Learning

et al. 2021

View full text Add to dashboard Cite

This paper presents a novel and robust two-stage pursuit strategy for the incomplete-information impulsive space pursuit-evasion missions considering the J2 perturbation. The strategy firstly models the impulsive pursuit-evasion game problem into a far-distance rendezvous stage and a close-distance game stage according to the perception range of the evader. For the far-distance rendezvous stage, it is transformed into a rendezvous trajectory optimization problem and a new objective function is proposed to obtain the pursuit trajectory with the optimal terminal pursuit capability. For the close-distance game stage, a closed-loop pursuit approach is proposed using one of the reinforcement learning algorithms, i.e., the deep deterministic policy gradient algorithm, to solve and update the pursuit trajectory for the incomplete-information impulsive pursuit-evasion missions. The feasibility of this novel strategy and its robustness to different initial states of the pursuer and evader and to the evasion strategies are demonstrated for the sun-synchronous orbit pursuit-evasion game scenarios. The results of the Monte Carlo tests show that the successful pursuit ratio of the proposed method is over 91% for all the given scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%

Two-Stage Pursuit Strategy for Incomplete-Information Impulsive Space Pursuit-Evasion Mission Using Reinforcement Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

Constrained path planning for manned–unmanned rotorcraft teaming in emergency medical service missions

Roncolini,

Galante,

Quaranta

et al. 2024

CEAS Aeronaut J

View full text Add to dashboard Cite

This paper investigates the path-planning problem applied to an innovative Unmanned Air Vehicle teaming with a helicopter to increase safety during Helicopter Emergency Medical Services operations. The unmanned vehicle, a drone that optionally can be launched from the helicopter, has the mission to explore the area of operation to determine the meteorological and environmental conditions and to detect physical obstacles. It is initially found that the combination of probabilistically optimal Rapidly-exploring Random Tree (RRT$$^{*}$$ ∗ ) as the global planner and of Bidirectional Rapidly-exploring Random Tree (BiRRT) as the local planner provides a nearly optimal global path and a rapid replanning in case new obstacles are detected. Adopting a Savitzky–Golay filter in an optional post-processing phase enables trajectory smoothing, thus improving its practicability. The feasibility of the identified trajectory for a rigid-body helicopter model is assessed by computing a first estimate of attitude, forces, control inputs, and rotor power from the trajectory points and curvature. This assessment shows that the RRT$$^{*}$$ ∗ used as a local planner provides replanned trajectories more feasible than BiRRT with comparable computational times.

show abstract

A differential evolution with autonomous strategy selection and its application in remote sensing image denoising

Cao,

Jia,

Wang

et al. 2024

Expert Systems with Applications

View full text Add to dashboard Cite

A Dynamically Feasible Fast Replanning Strategy with Deep Reinforcement Learning

Cited by 6 publications

References 20 publications

Two-Stage Pursuit Strategy for Incomplete-Information Impulsive Space Pursuit-Evasion Mission Using Reinforcement Learning

Two-Stage Pursuit Strategy for Incomplete-Information Impulsive Space Pursuit-Evasion Mission Using Reinforcement Learning

Constrained path planning for manned–unmanned rotorcraft teaming in emergency medical service missions

A differential evolution with autonomous strategy selection and its application in remote sensing image denoising

Contact Info

Product

Resources

About