摘要
为了在复杂舞台环境下使用移动机器人实现物品搬运或者载人演出,提出了一种基于深度强化学习的动态路径规划算法;首先通过构建全局地图获取移动机器人周围的障碍物信息,将演员和舞台道具分别分类成动态障碍物和静态障碍物;然后建立局部地图,通过LSTM网络编码动态障碍物信息,使用社会注意力机制计算每个动态障碍物的重要性来实现更好的避障效果;通过构建新的奖励函数来实现对动静态障碍物的不同躲避动作;最后通过模仿学习和优先级经验回放技术来提高网络的收敛速度,从而实现在舞台复杂环境下的移动机器人的动态路径规划;实验结果表明,该网络的收敛速度明显提高,在不同障碍物环境下都能够表现出好的动态避障效果。
In order to realize that mobile robot carries goods or performs manned performances in complex stage environment, a dynamic path planning algorithm based on deep reinforcement learning is proposed. Firstly, the obstacle information around the mobile robot is obtained by constructing a global map, and the actors and stage props are classified into dynamic obstacles and static obstacles respectively. Then a local map is established to acquire the dynamic obstacle information through LSTM network, and the importance of each dynamic obstacle is calculated to achieve better obstacle avoidance effect through social attention mechanism. Different avoidance situations of dynamic and static obstacles are realized by constructing a new reward function. Finally, the simulation learning and priority experience playback technology are used to improve the convergence speed of the network, so as to realize the dynamic path planning of the mobile robot in the complex stage environment. The experimental results show that the convergence speed of the network is significantly improved, and it can show the good dynamic effect in different obstacle environments.
作者
张柏鑫
杨毅镔
朱华中
刘安东
倪洪杰
ZHANG Baixin;YANG Yibin;ZHU Huazhong;LIU Andong;NI Hongjie(College of Information Engineering,Zhejiang University of Technology,Hangzhou 310012,China)
出处
《计算机测量与控制》
2023年第1期153-159,166,共8页
Computer Measurement &Control
基金
国家自然科学基金项目(61973275)
浙江省省属高校基本科研业务(RF-A2020004)。
关键词
移动机器人
LSTM
深度强化学习
动态路径规划
实时避障
mobile robot
LSTM
deep reinforcement learning
dynamic path planning
real time obstacle avoidance
