A new approach to plan manual assembly

ABSTRACT Today’s methods for planning manual assembly processes have been developed for many decades. Besides technical advances, organisational innovations such as concurrent engineering have made a major contribution to both cost and quality of the final product. However, mass customisation and personalisation of products have imposed additional requirements. Planning should be performed for many different product variants while at the same time planning cost and time to market should be kept at a minimum level. The objective of this paper is to present a new approach for planning of manual assembly processes that goes beyond established industry practices, which has the potential to provide planning teams with tools to evaluate different assembly process scenarios faster, eliminating the need for physical prototypes. The approach is based on controlled natural language textual descriptions of assembly tasks, automatic generation human motions from the textual descriptions based on data-driven, statistical motion models and interactive process optimisation. The proposed method is evaluated in a pilot case from automotive industry regarding ease of use, extensibility, adaptability, motion realism and motion diversity. Results suggest that while the approach addresses practical needs of production planning, technical challenges remain in order to make it ready to be implemented into digital planning environments.

[1]  Lucas Kovar,et al.  Automated methods for data-driven synthesis of realistic and controllable human motion , 2004 .

[2]  Martin Manns,et al.  Automated DHM Modeling for Integrated Alpha-Numeric and Geometric Assembly Planning , 2013 .

[3]  Glen Berseth,et al.  DeepLoco , 2017, ACM Trans. Graph..

[4]  Nicolas Pronost,et al.  Interactive Character Animation Using Simulated Physics: A State‐of‐the‐Art Review , 2012, Comput. Graph. Forum.

[5]  G. Norman.  Likert scales, levels of measurement and the “laws” of statistics , 2010, Advances in health sciences education : theory and practice.

[6]  Yann LeCun,et al.  Convolutional Learning of Spatio-temporal Features , 2010, ECCV.

[7]  George Chryssolouris,et al.  ErgoToolkit: an ergonomic analysis tool in a virtual manufacturing environment , 2013, Int. J. Comput. Integr. Manuf..

[8]  Mario Walther,et al.  Integration of time as a factor in ergonomic simulation. , 2012, Work.

[9]  Lin Feng,et al.  Underlying Semantic Annotation Method for Human Motion Capture Data , 2011 .

[10]  Geoffrey E. Hinton,et al.  Two Distributed-State Models For Generating High-Dimensional Time Series , 2011, J. Mach. Learn. Res..

[11]  Jitendra Malik,et al.  Recurrent Network Models for Human Dynamics , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[12]  Michael Gleicher,et al.  Parametric motion graphs , 2007, SI3D.

[13]  Klaus Fischer,et al.  Scaled functional principal component analysis for human motion synthesis , 2016, MIG.

[14]  Jian-Jun Zhang,et al.  Adaptive motion synthesis for virtual characters: a survey , 2014, The Visual Computer.

[15]  Denis Wohlfeld,et al.  Digital Shadow – From production to product , 2017 .

[16]  Taku Komura,et al.  Fast Neural Style Transfer for Motion Data , 2017, IEEE Computer Graphics and Applications.

[17]  Martin Manns,et al.  A vagueness measure for concurrent engineering of manual assembly lines , 2014, Prod. Eng..

[18]  Igor S. Pandzic,et al.  State of the Art in Example‐Based Motion Synthesis for Virtual Characters in Interactive Applications , 2010, Comput. Graph. Forum.

[19]  Dianliang Wu,et al.  Virtual human modeling for interactive assembly and disassembly operation in virtual reality environment , 2013, The International Journal of Advanced Manufacturing Technology.

[20]  Dong Zhou,et al.  A maintenance time prediction method considering ergonomics through virtual reality simulation , 2016, SpringerPlus.

[21]  Martin Manns,et al.  Measuring Motion Capture Data Quality for Data Driven Human Motion Synthesis , 2016 .

[22]  Lucas Kovar,et al.  Motion Graphs , 2002, ACM Trans. Graph..

[23]  Taku Komura,et al.  A Deep Learning Framework for Character Motion Synthesis and Editing , 2016, ACM Trans. Graph..

[24]  Alla Safonova,et al.  Human Motion Synthesis with Optimization‐based Graphs , 2010, Comput. Graph. Forum.

[25]  Joe Cecil,et al.  Virtual engineering approaches in product and process design , 2007 .

[26]  Philipp Slusallek,et al.  XML3D: interactive 3D graphics for the web , 2010, Web3D '10.

[27]  Klaus Fischer,et al.  Accelerating statistical human motion synthesis using space partitioning data structures , 2017, Comput. Animat. Virtual Worlds.

[28]  Michael F. Zäh,et al.  Systematic workplace and assembly redesign for aging workforces , 2007, Prod. Eng..

[29]  A Garg,et al.  Revised NIOSH equation for the design and evaluation of manual lifting tasks. , 1993, Ergonomics.

[30]  Lars Hanson,et al.  Introducing a Formal High-Level Language for Instructing Automated Manikins , 2013 .

[31]  Stefan Mengel,et al.  Experimental Effort of Data Driven Human Motion Simulation in Automotive Assembly , 2016 .

[32]  Andreas Seidl,et al.  Ramsis - The Leading Cad Tool for Ergonomic Analysis of Vehicles , 2007, HCI.

[33]  Jinxiang Chai,et al.  Motion graphs++ , 2012, ACM Trans. Graph..

[34]  C. Karen Liu,et al.  Online control of simulated humanoids using particle belief propagation , 2015, ACM Trans. Graph..

[35]  Dan Lämkull,et al.  Ergonomic Risk Assessment of a Manikin’s Wrist Movements - a Test Study in Manual Assembly , 2013 .

[36]  E. Occhipinti.  OCRA: a concise index for the assessment of exposure to repetitive movements of the upper limbs. , 1998, Ergonomics.

[37]  Tim J. Gallwey,et al.  Problems of human variability in work measurement , 1992 .

[38]  Lars Hanson,et al.  Automatic creation of virtual manikin motions maximizing comfort in manual assembly processes , 2012 .

[39]  Steven M. LaValle,et al.  Randomized Kinodynamic Planning , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[40]  Joaquim B. Cavalcante Neto,et al.  Tunable Robustness: An Artificial Contact Strategy with Virtual Actuator Control for Balance , 2017, Comput. Graph. Forum.

[41]  Nestor Rychtyckyj.  Standard Language at Ford Motors: A Case Study in Controlled Language Development and Deployment , 2006, CLAW.

[42]  H. ElMaraghy,et al.  Variety, Complexity and Value Creation , 2014 .

[43]  D B Chaffin,et al.  Improving digital human modelling for proactive ergonomics in design , 2005, Ergonomics.

[44]  Dan Högberg,et al.  Creating and shaping the DHM tool IMMA for ergonomic product and production design , 2016 .

[45]  Sebastian Bauer,et al.  Ergonomic assessment of automotive assembly tasks with digital human modelling and the 'ergonomics assessment worksheet' (EAWS) , 2012 .

[46]  Erik Brolin,et al.  Adaptive regression model for synthesizing anthropometric population data , 2017 .

[47]  Yong Du,et al.  Hierarchical recurrent neural network for skeleton based action recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[48]  Taku Komura,et al.  Learning motion manifolds with convolutional autoencoders , 2015, SIGGRAPH Asia Technical Briefs.

[49]  Emilio Frazzoli,et al.  Sampling-based algorithms for optimal motion planning , 2011, Int. J. Robotics Res..

[50]  Lydia E. Kavraki,et al.  Path planning using lazy PRM , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[51]  Yen-Lin Chen,et al.  Interactive generation of human animation with deformable motion models , 2009, TOGS.

[52]  Ziv Bar-Joseph,et al.  Modeling spatial and temporal variation in motion data , 2009, ACM Trans. Graph..