典型文献
A deep Q-learning network based active ob ject detection model with a novel training algorithm for service robots
文献摘要：
This paper focuses on the problem of active object detection (AOD). AOD is important for service robots to complete tasks in the family environment, and leads robots to approach the target object by taking appropriate moving actions. Most of the current AOD methods are based on reinforcement learning with low training e?ciency and testing accuracy. Therefore, an AOD model based on a deep Q-learning network (DQN) with a novel training algorithm is proposed in this paper. The DQN model is designed to fi t the Q-values of various actions, and includes state space, feature extraction, and a multilayer perceptron. In contrast to existing research, a novel training algorithm based on memory is designed for the proposed DQN model to improve training e?ciency and testing accuracy. In addition, a method of generating the end state is presented to judge when to stop the AOD task during the training process. Su?cient comparison experiments and ablation studies are performed based on an AOD dataset, proving that the presented method has better performance than the comparable methods and that the proposed training algorithm is more effective than the raw training algorithm.
文献关键词：
中图分类号：
作者姓名：
Shaopeng LIU;Guohui TIAN;Yongcheng CUI;Xuyang SHAO
作者机构：
School of Control Science and Engineering,Shandong University,Jinan 250061,China
文献出处：
引用格式：
[1]Shaopeng LIU;Guohui TIAN;Yongcheng CUI;Xuyang SHAO-.A deep Q-learning network based active ob ject detection model with a novel training algorithm for service robots)[J].信息与电子工程前沿（英文）,2022(11):1673-1683
A类：
B类：
deep,learning,network,active,detection,model,novel,training,algorithm,service,robots,This,paper,focuses,problem,object,AOD,important,complete,tasks,family,environment,leads,approach,target,by,taking,appropriate,moving,actions,Most,current,methods,are,reinforcement,low,ciency,testing,accuracy,Therefore,DQN,proposed,this,designed,fi,values,various,includes,state,space,feature,extraction,multilayer,perceptron,In,contrast,existing,research,memory,improve,addition,generating,end,presented,judge,when,stop,during,process,Su,cient,comparison,experiments,ablation,studies,performed,dataset,proving,that,has,better,performance,than,comparable,more,effective,raw
AB值：
0.505406
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
