Towards Reactive Robot Applications in Dynamic Environments

Traditionally, industrial robots have been deployed in fairly static environments, to perform highly dedicated tasks. These robots perform with very high precision and throughput. However, nowadays there is an increasing demand for utilizing robots in more dynamic environments, also performing more flexible and less specialized operations — high mix/low volume. Both traditional industrial robots and force-limited robots are used in collaborative, dynamic environments. Such robot applications introduce new challenges when it comes to efficiency and robustness. In this paper, we propose an architecture for reactive multi-robot applications in the context of dynamic environments, and we analyze the main research challenges that must be tackled for its realization. A logistics use case, with robots picking customer orders from the shelves of a warehouse, is used as a running example to support the description of the key challenges.

[1]  Klas Nilsson,et al.  Declarative-knowledge-based reconfiguration of automation systems using a blackboard architecture , 2011, SCAI.

[2]  Gianni Ferretti,et al.  Generation of human walking paths , 2013, IROS.

[3]  Aaron M. Dollar,et al.  Learning the post-contact reconfiguration of the hand object system for adaptive grasping mechanisms , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[4]  Erann Gat,et al.  Experiences with an architecture for intelligent, reactive agents , 1997, J. Exp. Theor. Artif. Intell..

[5]  Stefan Schaal,et al.  Real-Time Perception Meets Reactive Motion Generation , 2017, IEEE Robotics and Automation Letters.

[6]  Nils J. Nilsson,et al.  Teleo-Reactive Programs for Agent Control , 1993, J. Artif. Intell. Res..

[7]  Oliver Brock,et al.  Analysis and Observations From the First Amazon Picking Challenge , 2016, IEEE Transactions on Automation Science and Engineering.

[8]  Loredana Zollo,et al.  Slippage Detection with Piezoresistive Tactile Sensors , 2017, Sensors.

[9]  Kazuhiro Kosuge,et al.  Progress and prospects of the human–robot collaboration , 2017, Autonomous Robots.

[10]  Anthony Stentz,et al.  An auction-based approach to complex task allocation for multirobot teams , 2006 .

[11]  Brahim Bouzouia,et al.  Multi-agent Architecture Model for Driving Mobile Manipulator Robots , 2008 .

[12]  Baran Çürüklü,et al.  Extended Colored Traveling Salesperson for Modeling Multi-Agent Mission Planning Problems , 2019, ICORES.

[13]  Y. Shen,et al.  A design approach for incorporating task coordination for human-robot-coexistence within assembly systems , 2015, 2015 Annual IEEE Systems Conference (SysCon) Proceedings.

[14]  Andreas Pichler,et al.  Towards robot systems for small batch manufacturing , 2011, 2011 IEEE International Symposium on Assembly and Manufacturing (ISAM).

[15]  Qing Liu,et al.  A Hybrid Prediction Model for Moving Objects , 2008, 2008 IEEE 24th International Conference on Data Engineering.

[16]  Christos Faloutsos,et al.  Prediction and indexing of moving objects with unknown motion patterns , 2004, SIGMOD '04.

[17]  Andrea Maria Zanchettin,et al.  Reactive Task Adaptation Based on Hierarchical Constraints Classification for Safe Industrial Robots , 2015, IEEE/ASME Transactions on Mechatronics.

[18]  Aaron M. Dollar,et al.  Post-contact, in-hand object motion compensation for compliant and underactuated hands , 2016, 2016 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).