A Virtual Character Learns to Defend Himself in Sword Fighting Based on Q-Network
Wang YM(王雨萌)1,2; Li E(李尔)1; Wang F(王丰); Xu B(徐波)1
2016-11
会议名称The 28th IEEE International Conference on Tools with Artificial Intelligence (ICTAI2016)
页码291-298
会议日期2016-11-6
会议地点San Jose, CA, USA
摘要In this paper, we create a virtual character that interacts with human player in a sword-fighting task. The data taken from a human player waving a stick as the 'sword' is mapped into the virtual environment; and the result of the collision detection during the virtual interaction is used as a reward for the reinforcement learning. We train a Q-network that animates the virtual character by rotating its joints toward the blocking the incoming attacks in each individual frame base on the current state. The trained virtual character makes quick and accurate blockings to 'sword' attacks coming in various forms. Further, a human-body dynamic model is used to predict the movements of the task irrelevant joints of the virtual character to create a more human like behavior. Experiment results demonstrate that this method can inspirit a virtual character with an automatic, human-like animation that interacts with human player in real time.
关键词Human-computer Interaction Reinforcement Learning Q-network Character Animation
URL查看原文
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14538
专题数字内容技术与服务研究中心_听觉模型与认知计算
作者单位1.中国科学院自动化研究所
2.中国科学院大学
推荐引用方式
GB/T 7714
Wang YM,Li E,Wang F,et al. A Virtual Character Learns to Defend Himself in Sword Fighting Based on Q-Network[C],2016:291-298.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
A Virtual Character (23634KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang YM(王雨萌)]的文章
[Li E(李尔)]的文章
[Wang F(王丰)]的文章
百度学术
百度学术中相似的文章
[Wang YM(王雨萌)]的文章
[Li E(李尔)]的文章
[Wang F(王丰)]的文章
必应学术
必应学术中相似的文章
[Wang YM(王雨萌)]的文章
[Li E(李尔)]的文章
[Wang F(王丰)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: A Virtual Character Learns to Defend Himself in Sword Fighting Based on Q-Network.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。