An efficient reinforcement learning scheme for the confinement escape problem

V Gurumurthy, N Mohanty, S Sundaram… - Applied Soft …, 2024 - Elsevier
Crucial real-world problems in robotics like trajectory planning during convoy missions and
autonomous rescue missions can be framed as a confinement escape problem (CEP)(a type …

A transfer learning model for cognitive electronic reconnaissance of unmanned aerial vehicle: Experiments

Y Zhang, S You, Y Yan, Q Ou, X Gao, F Jiang - Engineering Applications of …, 2024 - Elsevier
Abstract Applying Deep Reinforcement Learning (DRL) technologies to Unmanned Aerial
Vehicle (UAV) electronic reconnaissance is one of the current research hotspots. However …

Pursuit Winning Strategies for Reach-Avoid Games with Polygonal Obstacles

R Yan, S Mi, X Duan, J Chen, X Ji - arXiv preprint arXiv:2403.06202, 2024 - arxiv.org
This paper studies a multiplayer reach-avoid differential game in the presence of general
polygonal obstacles that block the players' motions. The pursuers cooperate to protect a …

Control Strategies in the Problem of Approach of Conflict-Controlled Objects

AA Chikrii, IS Rappoport - Cybernetics and Systems Analysis, 2024 - Springer
The authors propose a new approach to generating control strategies in the problem of
approach of conflict-controlled objects. Modifications of the first direct method are developed …

Sufficient Convergence Conditions for Conflict Controlled Objects with Different Inertia

AA Chikrii, IS Rappoport - Cybernetics and Systems Analysis, 2024 - Springer
The problem of approach of controlled objects with different inertia in dynamic game
problems is considered. For such controlled objects, it is characteristic that the Pontryagin …

Combining Dense and Sparse Rewards to Improve Deep Reinforcement Learning Policies in Reach-Avoid Games with Faster Evaders in Two vs. One Scenarios

J Silveira, K McCloskey, CA Rabbath… - … on Control, Decision …, 2024 - ieeexplore.ieee.org
This paper investigates a variation of the reach-avoid game, a multi-agent pursuit and
evasion scenario applicable to aerial defense, with faster evaders. Using Deep …

Multiple Equal-Speed Players in Reach-Avoid Differential Games: Non-point Capture

J Wang, Y Tang - Chinese Conference on Swarm Intelligence and …, 2023 - Springer
This paper investigates multi-player reach-avoid differential games with non-point capture
scenarios. The objective of the attackers' team is to reach a specific edge of the game …

ДОСТАТНІ УМОВИ ЗБЛИЖЕННЯ КОНФЛІКТНО-КЕРОВАНИХ ОБ'ЄКТІВ З РІЗНОЮ ІНЕРЦІЙНІСТЮ.

АО Чикрій, ЙС Раппопорт - Cybernetics & Systems Analysis …, 2024 - search.ebscohost.com
Розглянуто проблему зближення керованих обmектів з різною інерційністю в ігрових
задачах динаміки. Для таких керованих обmектів характерним е невиконання умови …

СТРАТЕГІЇ КЕРУВАННЯ У ПРОБЛЕМІ ЗБЛИЖЕННЯ КОНФЛІКТНО-КЕРОВАНИХ ОБ'ЄКТІВ.

АО ЧИКРІЙ, ЙС РАППОПОРТ - Cybernetics & Systems …, 2024 - search.ebscohost.com
Запропоновано новий підхід до формування стратегій керування в проблемі зближення
конфліктноrкерованих обmектів. Розроблено модифікаці¿ першого прямого меr тоду …