Semi-automatic task planning of virtual humans in digital factory settings

被引：1

作者：

Winter M. ^{[1
]}

Kronfeld T. ^{[1
]}

Brunnett G. ^{[1
]}

机构：

[1] Technische Universität Chemnitz, Germany

来源：

Computer-Aided Design and Applications | 2019年 / 16卷 / 04期

关键词：

Digital factory; Human factors; Knowledge modeling; Process planning; State space search; Virtual humans; Virtual prototyping;

D O I：

10.14733/cadaps.2019.688-702

中图分类号：

学科分类号：

摘要：

In commercial software systems for production planning the movements of digital humans have to be programmed manually. To improve the usability of digital humans in such simulations, methods are needed that create work plans, actions and movements for digital humans at least semi-automatically. The "Smart Virtual Worker" (SVW) is an experimental software platform for the development of such methods. For given descriptions of transport or assembly tasks the SVW computes action sequences and movements to fulfill these tasks. An optimization procedure is used to find solutions that balance the requirements of effciency and ergonomics according to the specifications of Method Time Measurement (MTM) and Rapid Upper Limb Assessment (RULA). Since these scores can only be computed as we traverse the state space, learning methods must be used to compute the solution. In this paper we present a way to systematically implement world knowledge in the form of an action pre-selection mechanism to enhance the performance of such strategies. To show the effectiveness of our method we demonstrate that even with a complete random action selection our method is capable of solving non-trivial planning problems. © 2019 CAD Solutions, LLC.

引用

页码：688 / 702

页数：14

共 16 条

[1]

Choi S., Kim B.H., Do Noh S., A diagnosis and evaluation method for strategic planning and systematic design of a virtual factory in smart manufacturing systems, International Journal of Precision Engineering and Manufacturing, 16, 6, pp. 1107-1115, (2015)

[2]

Devedzic V., Knowledge modeling-state of the art, Integrated Computer-Aided Engineering, 8, 3, pp. 257-281, (2001)

[3]

Kronfeld T., Fankhanel J., Brunnett G., Representation of motion spaces using spline functions and fourier series, Proceedings of the MMCS 2012, LNCS (Lecture Notes in Computer Science), pp. 265-282, (2014)

[4]

Kunz A., Zank M., Fjeld M., Nescher T., Real Walking in Virtual Environments for Factory Planning and Evaluation, Procedia CIRP, 44, pp. 257-262, (2016)

[5]

Lu Y., Li Q., Zhou Z., Deng Y., Ontology-based knowledge modeling for automated construction safety checking, Safety Science, 79, pp. 11-18, (2015)

[6]

Maynard H., Stegemerten G., Schwab J., Methods-time measurement, Proc. of the Sixth Intl. Conf. on Epigenetic Robotics, (1948)

[7]

McAtamney L., Corlett E.N., Rula: A survey method for the investigation of work-related upper limb disorder, Applied Ergonomics, 24, 2, pp. 91-93, (1993)

[8]

Papudesi V., Huber M., Learning behaviorally grounded state representations for reinforcement learning agents, Proc. of the Sixth Intl. Conf. on Epigenetic Robotics, (2006)

[9]

Petnga L., Austin M., An ontological framework for knowledge modeling and decision support in cyber-physical systems, Advanced Engineering Informatics, 30, 1, pp. 77-94, (2016)

[10]

Polasek P., Bures M., Simon M., Comparison of digital tools for ergonomics in practice, Procedia Engineering, 100, pp. 1277-1285, (2015)

← 1 2 →