Scholarlink

This paper presents an innovative control strategy based on reinforcement learning (RL) to tackle the attitude tracking control problem for unmanned aerial vehicles (UAVs), emphasizing both desired transient performance and an optimal long-term performance index. Firstly, a prescribed performance function along with a corresponding error transformation technique is introduced to meet the desired transient and steady-state performance requirements. Next, by incorporating the Actor-Critic Neural Network (NN), a model-free optimal attitude tracking controller is developed, which compensates for model uncertainties and external perturbations in real time. Finally, comparative numerical simulations are conducted to demonstrate the effectiveness and superiority of the proposed method.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Reinforcement Learning Based Attitude Tracking Control of Unmanned Aerial Vehicles with Prescribed Performance

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Weining Huang,
  • Dapeng Yang,
  • Man Zhang,
  • Xiaoye Wang

摘要

This paper presents an innovative control strategy based on reinforcement learning (RL) to tackle the attitude tracking control problem for unmanned aerial vehicles (UAVs), emphasizing both desired transient performance and an optimal long-term performance index. Firstly, a prescribed performance function along with a corresponding error transformation technique is introduced to meet the desired transient and steady-state performance requirements. Next, by incorporating the Actor-Critic Neural Network (NN), a model-free optimal attitude tracking controller is developed, which compensates for model uncertainties and external perturbations in real time. Finally, comparative numerical simulations are conducted to demonstrate the effectiveness and superiority of the proposed method.