Multimodal sensor-based whole-body control for human-robot collaboration in industrial settings

被引:48
作者
Fernandez, Jose de Gea [1 ]
Mronga, Dennis [1 ]
Guenther, Martin [1 ]
Knobloch, Tobias [4 ]
Wirkus, Malte [1 ]
Schroeer, Martin [2 ]
Trampler, Mathias [1 ]
Stiene, Stefan [1 ]
Kirchner, Elsa [1 ,2 ]
Bargsten, Vinzenz [2 ]
Baenziger, Timo [3 ]
Teiwes, Johannes [3 ]
Krueger, Thomas [3 ]
Kirchner, Frank [1 ,2 ]
机构
[1] German Res Ctr Artificial Intelligence DFKI, Robot Innovat Ctr, Robert Hooke Str 1, D-28359 Bremen, Germany
[2] Univ Bremen, Robot Grp, Robert Hooke Str 1, D-28359 Bremen, Germany
[3] Volkswagen AG, Berliner Ring 2, D-38436 Wolfsburg, Germany
[4] Hsch Aschaffenburg, Wurzburger Str 45, D-63743 Aschaffenburg, Germany
关键词
Whole-body control; Human-robot collaboration; Intuitive interfaces; Gesture recognition; Collision avoidance; Modular software;
D O I
10.1016/j.robot.2017.04.007
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper describes the development of a dual-arm robotic system for industrial human robot collaboration. The robot demonstrator described here possesses multiple sensor modalities for the monitoring of the shared human robot workspace and is equipped with the ability for real-time collision-free dual arm manipulation. A whole-body control framework is used as a key control element which generates a coherent output signal for the robot's joints given the multiple controller inputs, tasks' priorities, physical constraints, and current situation. Furthermore, sets of controller-constraints combinations of the whole body controller constitute the basic building blocks that describe actions of a high-level action plan to be sequentially executed. In addition, the robotic system can be controlled in an intuitive manner via human gestures. These individual robotic capabilities are combined into an industrial demonstrator which is validated in a gearbox assembly station of a Volkswagen factory. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码:102 / 119
页数:18
相关论文
共 29 条
[1]  
[Anonymous], 2012, EUROPEAN PROJECT ROS
[2]  
[Anonymous], 2016, FRANKA ROBOT KBEE AG
[3]  
[Anonymous], 2016, MOTOMAN HC10 COLLABO
[4]  
[Anonymous], 2009, P 2009 IEEE C EMERGI
[5]  
Argyros AA, 2004, LECT NOTES COMPUT SC, V3023, P368
[6]  
Benbasat Ari Y., 2002, GEST SIGN LANG HUM C, P9
[7]  
Blodow Nico, 2014, MANAGING BELIEF STAT
[8]  
de Fernandez Jose Gea, 2015, 2015 SPAC ROB S SPAC
[9]  
Hirzinger G, 2002, 2002 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS, P1710, DOI 10.1109/ROBOT.2002.1014788
[10]  
Joyeux S., 2011, 6 NAT C CONTR ARCH R