CASIA OpenIR

Browse/Search Results:  1-10 of 133 Help

Selected(0)Clear Items/Page:    Sort:
智能机器人共享控制与操作技能学习方法研究 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2020
Authors:  席宝
Adobe PDF(9051Kb)  |  Favorite  |  View/Download:45/6  |  Submit date:2021/02/01
位姿检测  共享控制  强化学习  策略梯度  示教引导  
深度神经网络结构搜索与优化方法研究 学位论文
, 中科院自动化所: 中国科学院大学, 2020
Authors:  陈玉康
Adobe PDF(15079Kb)  |  Favorite  |  View/Download:91/5  |  Submit date:2020/06/09
深度学习  神经网络  结构搜索  目标检测  
数据驱动的温室生产管理与环境控制 学位论文
, 北京: 中国科学院自动化研究所, 2020
Authors:  翁宇琛
Adobe PDF(1684Kb)  |  Favorite  |  View/Download:50/0  |  Submit date:2020/06/09
价格预测  温室生产管理  lightGBM算法  温室环境控制  
基于自适应动态规划的智能空调能源系统自学习最优控制 学位论文
工程硕士, 中国科学院自动化研究所: 中国科学院大学, 2020
Authors:  廖泽华
Adobe PDF(2277Kb)  |  Favorite  |  View/Download:50/0  |  Submit date:2020/06/26
冰蓄冷空调  空调冷负荷预测  自适应动态规划  执行依赖启发式动态规划  平行自适应动态规划  
基于混合更新Q值的深度强化学习方法研究 学位论文
工程硕士, 中国科学院自动化研究所: 中国科学院大学, 2020
Authors:  李主南
Adobe PDF(3839Kb)  |  Favorite  |  View/Download:63/2  |  Submit date:2020/06/10
深度强化学习  Q 学习算法  过估计  欠估计  Actor-Critic  凸组合  混合更新  
Real-Sim-Real Transfer for Real-World Robot Control Policy Learning with Deep Reinforcement Learning 期刊论文
APPLIED SCIENCES-BASEL, 2020, 卷号: 10, 期号: 5, 页码: 16
Authors:  Liu, Naijun;  Cai, Yinghao;  Lu, Tao;  Wang, Rui;  Wang, Shuo
View  |  Adobe PDF(6287Kb)  |  Favorite  |  View/Download:27/4  |  Submit date:2020/06/02
robot  policy learning  reality gap  simulated environment  deep reinforcement learning  
Computational modeling of Emotion-motivated Decisions for Continuous Control of Mobile Robots 期刊论文
IEEE Transactions on Cognitive and Developmental Systems, 2020, 期号: 2020, 页码: 1-14
Authors:  Huang, Xiao;  Wu, Wei;  Qiao, Hong
View  |  Adobe PDF(5970Kb)  |  Favorite  |  View/Download:51/26  |  Submit date:2020/06/09
Brain-inspired Computing  Emotion-motivated Learning  Emotion-memory Interactions  Decision-making  Reinforcement Learning  
Manipulation Skill Learning on Multi-step Complex Task Based on Explicit and Implicit Curriculum Learning 期刊论文
SCIENCE CHINA Information Sciences, 2020, 卷号: 0, 期号: 0, 页码: 0-0
Authors:  Liu, Naijun;  Lu, Tao;  Cai, Yinghao;  Wang, Rui;  Wang, Shuo
View  |  Adobe PDF(2456Kb)  |  Favorite  |  View/Download:22/11  |  Submit date:2020/09/27
robot  manipulation skill learning  multi-step complex task  curriculum learning  
Bounded Evaluation: Querying Big Data with Bounded Resources 期刊论文
International Journal of Automation and Computing, 2020, 卷号: 17, 期号: 4, 页码: 502-526
Authors:  Yang Cao;  Wen-Fei Fan;  Teng-Fei Yuan
View  |  Adobe PDF(2149Kb)  |  Favorite  |  View/Download:0/0  |  Submit date:2021/02/22
Bounded evaluation  resource-bounded query processing  effective syntax  access schema  boundedness.  
Adversarial Attacks and Defenses in Images, Graphs and Text: A Review 期刊论文
International Journal of Automation and Computing, 2020, 卷号: 17, 期号: 2, 页码: 151-178
Authors:  Han Xu;  Yao Ma;  Hao-Chen Liu;  Debayan Deb;  Hui Liu;  Ji-Liang Tang;  Anil K. Jain
View  |  Adobe PDF(2155Kb)  |  Favorite  |  View/Download:0/0  |  Submit date:2021/02/22
Adversarial example  model safety  robustness  defenses  deep learning.