Scholarlink

A global sliding mode guidance law (GSMG) incorporating reinforcement learning (RL) is proposed to handle guidance tasks with intersection angle constraints. Firstly, the connection between the desired intersection angle and the line-of-sight (LOS) angle is established. A GSMG law is constructed, ensuring system stability, with an adjustable coefficient introduced for further refinement. Secondly, RL is leveraged to optimize this coefficient while reducing the number of observation variables. A deep deterministic policy gradient (DDPG) algorithm is employed for training, with a specifically designed network structure and reward function. Thirdly, the agent learns to output optimized coefficients, and comparative simulations validate the effectiveness of the guidance strategy.

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

Global Sliding Mode Guidance Law with Intersection Angle Constraint Based on Reinforcement Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Changhai Wang,
  • Rongqi Zhang,
  • Qingdong Li,
  • Jianglong Yu,
  • Xiwang Dong,
  • Zhang Ren

摘要

A global sliding mode guidance law (GSMG) incorporating reinforcement learning (RL) is proposed to handle guidance tasks with intersection angle constraints. Firstly, the connection between the desired intersection angle and the line-of-sight (LOS) angle is established. A GSMG law is constructed, ensuring system stability, with an adjustable coefficient introduced for further refinement. Secondly, RL is leveraged to optimize this coefficient while reducing the number of observation variables. A deep deterministic policy gradient (DDPG) algorithm is employed for training, with a specifically designed network structure and reward function. Thirdly, the agent learns to output optimized coefficients, and comparative simulations validate the effectiveness of the guidance strategy.