相关实验视频

Updated: Jun 11, 2026

Insect-controlled Robot: A Mobile Robot Platform to Evaluate the Odor-tracking Capability of an Insect

Insect-controlled Robot: A Mobile Robot Platform to Evaluate the Odor-tracking Capability of an Insect

Published on: December 19, 2016

移动机器人用于动态室内环境的路径规划基于SAC-LSTM算法

Yongchao Zhang¹, Pengzhan Chen¹

¹School of Intelligent Manufacturing, Taizhou University, Taizhou 318000, China.

Sensors (Basel, Switzerland)

|December 23, 2023

概括

本研究介绍了一种改进的软演员-关键长短期记忆 (SAC-LSTM) 算法,用于移动机器人路径规划. 增强的算法实现了更快的融合和更高的成功率,特别是在动态环境中.

科学领域:

机器人技术机器人技术机器人技术
人工智能的人工智能
机器学习机器学习

背景情况:

在动态环境中的移动机器人导航由于不可预测的变化而带来挑战.
现有的路径规划算法可能会在连续运动和记忆保留方面扎.
软演员-关键 (SAC) 是一种强化学习算法,适用于连续控制任务.

研究的目的:

为快速和高效的路径规划提出一个改进的软演员-关键长短期记忆 (SAC-LSTM) 算法.
通过使用LSTM整合历史和当前状态来增强决策能力.
解决记忆减值问题,提高训练效率.

主要方法:

将长短期记忆 (LSTM) 网络集成到软行动者-关键 (SAC) 算法中.
实施燃烧训练方法以减轻LSTM隐藏状态重置问题.
采用优先级经验重复机制,以提高抽样效率和更快的趋同.
为Turtlebot3开发运动模型,包括状态/动作空间,奖励功能和计划过程.
在无障碍,静态和动态环境中使用ROS和Gazebo9.9进行模拟实验.

主要成果:

与标准SAC算法相比,SAC-LSTM算法在所有测试环境中显示出更快的融合率.
在动态障碍环境中,在路径规划成功率上有显著的10.5个百分点的改善.
该SAC-LSTM算法导致更短的路径规划时间和更简洁的计划路径.
在处理连续运动和整合历史状态信息方面提高了性能.

结论:

拟议的SAC-LSTM算法为移动机器人路径规划提供了卓越的性能,特别是在复杂和动态的环境中.
集成LSTM,内燃培训和优先级经验重复有效地提高了路径规划效率和成功率.
这种方法为移动机器人面临的实时导航挑战提供了强大的解决方案.

关键词:

在 SAC-LSTM 算法中.燃烧机制的内燃机制移动机器人移动机器人路径规划路径规划路径规划优先级经验重播机制重播机制

更多相关视频

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

Robotic Sensing and Stimuli Provision for Guided Plant Growth

Robotic Sensing and Stimuli Provision for Guided Plant Growth

Published on: July 1, 2019

相关概念视频

Vector Functions and Motion: Problem Solving

Vector 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...