典型文献
Collaborative Pushing and Grasping of Tightly Stacked Objects via Deep Reinforcement Learning
文献摘要：
Directly grasping the tightly stacked objects may cause collisions and result in failures, degenerating the functionality of robotic arms. Inspired by the observation that first pushing objects to a state of mutual separation and then grasping them individually can effectively increase the success rate, we devise a novel deep Q-learning framework to achieve collaborative pushing and grasping. Specifically, an efficient non-maximum suppression policy (PolicyNMS) is proposed to dynamically evaluate pushing and grasping actions by enforcing a suppression constraint on unreasonable actions. Moreover, a novel data-driven pushing reward network called PR-Net is designed to effectively assess the degree of separation or aggregation between objects. To benchmark the proposed method, we establish a dataset containing common household items dataset (CHID) in both simulation and real scenarios. Although trained using simulation data only, experiment results validate that our method generalizes well to real scenarios and achieves a 97％ grasp success rate at a fast speed for object separation in the real-world environment.
文献关键词：
中图分类号：
作者姓名：
Yuxiang Yang
作者机构：
School of Electronics and Information,Hangzhou Dianzi University,Hangzhou;Zhejiang Provincial Key Laboratory of Equipment Electronics,Hangzhou 310018,China;School of Computer Science,Faculty of Engineering,University of Sydney,Darlington,NSW 2006,Australia;JD Explore Academy,JD.com,Beijing 101111,China
文献出处：
引用格式：
[1]Yuxiang Yang-.Collaborative Pushing and Grasping of Tightly Stacked Objects via Deep Reinforcement Learning)[J].自动化学报（英文版）,2022(01):135-145
A类：
degenerating,PolicyNMS,CHID
B类：
Collaborative,Pushing,Grasping,Tightly,Stacked,Objects,via,Deep,Reinforcement,Learning,Directly,grasping,tightly,stacked,objects,may,cause,collisions,failures,functionality,robotic,arms,Inspired,by,observation,that,first,pushing,state,mutual,separation,then,them,individually,can,effectively,increase,success,rate,devise,novel,deep,learning,framework,collaborative,Specifically,efficient,maximum,suppression,policy,proposed,dynamically,evaluate,actions,enforcing,constraint,unreasonable,Moreover,driven,reward,network,called,PR,Net,designed,assess,degree,aggregation,between,To,benchmark,method,establish,dataset,containing,common,household,items,both,simulation,real,scenarios,Although,trained,using,only,experiment,results,validate,our,generalizes,well,achieves,fast,speed,world,environment
AB值：
0.644434
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。
