移动机器人的路径规划基于改进的双深Q网络算法
Zhenggang Wang1, Shuhong Song1, Shenghui Cheng1
1College of Electrical Engineering, Anhui Polytechnic University, Wuhu, China.
Frontiers in neurorobotics
|February 28, 2025
概括
本研究介绍了BiLSTM-D3QN算法,用于改进路径规划. 与传统的深度强化学习方法相比,它提高了网络的融合,稳定性和效率.
科学领域:
- 机器人和人工智能 机器人和人工智能
- 机器学习 机器学习
- 路径规划算法 路径规划算法
背景情况:
- 传统的深度强化学习算法面临着缓慢的网络融合,不稳定的奖励融合和低效的路径规划等挑战.
- 现有的方法在复杂的环境中经常遇到困难,导致路径长度低于最佳,规划时间增加.
研究的目的:
- 提出一种先进的路径规划算法,BiLSTM-D3QN (双向长期和短期记忆决斗双深Q网络),它解决了传统深度强化学习的局限性.
- 提高网络收速度,奖励收稳定性和整体路径规划效率.
主要方法:
- 整合双向长期短期记忆 (BiLSTM) 网络,以提高记忆和决策稳定性.
- 整合了对决网络架构,以减轻Q值的高估和加速网络更新.
- 实现适应体验重复,并具有频率惩罚功能,以有效提取数据.
- 引入适应性行动选择机制以优化勘探.
主要成果:
- 与传统的深度强化学习相比,BiLSTM-D3QN在简单的环境中展示了优越的网络融合速度,规划效率,奖励融合稳定性和成功率.
- 在复杂的环境中,BiLSTM-D3QN比改进的ERDDQN算法实现了20米更短的路径长度,7个更少的转折点,0.54秒更快的规划时间和10.4%更高的成功率.
结论:
- 拟议的BiLSTM-D3QN算法在融合速度和路径规划性能方面明显优于现有方法.
- 在强化学习中,BiLSTM-D3QN为复杂的路径规划任务提供了更稳定,更有效的解决方案.
相关概念视频
01:24One-Degree-of-Freedom System
In mechanical engineering, one-degree-of-freedom systems form the basis of a wide range of electrical and mechanical components. Using these models, engineers can predict the behavior of various parts in a larger system, which gives them insight into how different forces interact with each other.
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
01:30Vector Functions and Motion: Problem Solving
Accurate position tracking is fundamental to the safe and effective operation of unmanned aerial vehicles (UAVs), particularly during precision maneuvers near complex structures. In this scenario, a drone is programmed to perform a high-precision inspection of a vertical structure, starting at position ((x, y, z) = (3, 0, 0)), with an initial velocity oriented in the positive z-direction. The trajectory of the drone is governed by a time-dependent acceleration function a(t), which is predefined...