Research on Virtual Path Planning Based on Improved DQN

计算机科学 运动规划 路径(计算) 人工智能 机器人
作者
Cheng Yi,Meng Qi
出处
期刊:IEEE International Conference on Real-time Computing and Robotics 卷期号:: 387-392
标识
DOI:10.1109/rcar49640.2020.9303290
摘要

An end-to-end approach based on the theory of Deep Reinforcement Learning has been proven to be able to meet or exceed human-level strategic capabilities. Applying this learning algorithm to path planning methods can make robots self-contained learning ability and environment interaction ability, and increased generalization ability. In this paper, Deep Q Network (DQN) as the typical Deep Reinforcement Learning method is improved. Improvement points can be divided into two steps. Firstly, the two steps of the selection of actions in the current network and how to calculate the target Q value are decoupled to eliminate overestimation caused by the rapid optimization of Q value in the possible direction. Then, considering that the action value function can bring benefits in addition to the action with the greatest value made by the agent, the static environment also has certain influence, the final result is a linear combination of two parts, which is to estimate the value functions of the upper, lower, left and right actions of the neural network output and the value of the environment state itself. Under the same experimental conditions, the improved DQN network is compared with the original DQN network, the result shows that the estimated final target value function of improved DQN network is more accurate and effective for virtual path planning tasks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
wwww完成签到,获得积分10
刚刚
大个应助思睿拜采纳,获得10
刚刚
澡雪发布了新的文献求助10
刚刚
蓓蓓发布了新的文献求助30
1秒前
1秒前
wtt发布了新的文献求助10
1秒前
Star完成签到,获得积分10
2秒前
小豆豆应助科研通管家采纳,获得10
3秒前
彭于晏应助科研通管家采纳,获得10
3秒前
JamesPei应助科研通管家采纳,获得10
4秒前
Ava应助科研通管家采纳,获得10
4秒前
大个应助科研通管家采纳,获得10
4秒前
田様应助科研通管家采纳,获得10
4秒前
赘婿应助科研通管家采纳,获得10
4秒前
科研通AI2S应助科研通管家采纳,获得10
4秒前
ll应助科研通管家采纳,获得10
4秒前
4秒前
思源应助科研通管家采纳,获得10
4秒前
4秒前
11发布了新的文献求助10
4秒前
chx完成签到,获得积分10
5秒前
zwk发布了新的文献求助30
5秒前
略略略应助可爱绮采纳,获得20
7秒前
布丁完成签到,获得积分10
7秒前
研友_VZG7GZ应助孙成成采纳,获得10
8秒前
8秒前
Ava应助欣慰的乌冬面采纳,获得10
9秒前
风为裳完成签到,获得积分10
9秒前
9秒前
10秒前
一碗鱼完成签到,获得积分10
10秒前
ty发布了新的文献求助10
10秒前
45发布了新的文献求助10
10秒前
清爽乐菱应助可爱思山采纳,获得40
10秒前
11秒前
勤劳茗发布了新的文献求助10
12秒前
无限曲奇发布了新的文献求助10
13秒前
糜轩完成签到,获得积分10
14秒前
独特大米完成签到,获得积分20
14秒前
红色鼻涕虫完成签到,获得积分20
15秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3975543
求助须知:如何正确求助?哪些是违规求助? 3519971
关于积分的说明 11200248
捐赠科研通 3256311
什么是DOI,文献DOI怎么找? 1798213
邀请新用户注册赠送积分活动 877446
科研通“疑难数据库(出版商)”最低求助积分说明 806338