Arena-Rosnav: Towards Deployment of Deep-Reinforcement-Learning-Based Obstacle Avoidance into Conventional Autonomous Navigation Systems

被引:20
作者
Kaestner, Linh [1 ]
Buiyan, Teham [1 ]
Jiao, Lei [1 ]
Tuan Anh Le [1 ]
Zhao, Xinlin [1 ]
Shen, Zhengcheng [1 ]
Lambrecht, Jens [1 ]
机构
[1] Berlin Inst Technol, Fac Elect Engn & Comp Sci, Chair Ind Grade Networks & Clouds, Berlin, Germany
来源
2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) | 2021年
关键词
ROBOT NAVIGATION; SAFETY;
D O I
10.1109/IROS51168.2021.9636226
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recently, mobile robots have become important tools in various industries, especially in logistics. Deep reinforcement learning emerged as an alternative planning method to replace overly conservative approaches and promises more efficient and flexible navigation. However, deep reinforcement learning approaches are not suitable for long-range navigation due to their proneness to local minima and lack of long term memory, which hinders its widespread integration into industrial applications of mobile robotics. In this paper, we propose a navigation system incorporating deep-reinforcement-learning-based local planners into conventional navigation stacks for long-range navigation. Therefore, a framework for training and testing the deep reinforcement learning algorithms along with classic approaches is presented. We evaluated our deep-reinforcement-learning-enhanced navigation system against various conventional planners and found that our system outperforms them in terms of safety, efficiency and robustness.
引用
收藏
页码:6456 / 6463
页数:8
相关论文
empty
未找到相关数据