Artículos

 

A Motion Capture based Planner for Virtual Characters Navigating in 3D Environments

 

Un planificador basado en capturas de movimiento para personajes virtuales desplazándose en ambientes 3D

 

Juan Carlos Arenas-Mena¹, Jean-Bernard Hayet¹, and Claudia Esteves²

 

¹ Centro de Investigación en Matemáticas, Guanajuato, Gto., México. Correo: jcarenas@cimat.mx, jbhayet@cimat.mx

² Departamento de Matemáticas, Universidad de Guanajuato, Gto., México. Correo: cesteves@cimat.mx

 

Article received on 09/02/2011.
Accepted on 03/11/2011.

 

Abstract

In this work, a strategy to automatically generate eye-believable motions for a virtual character that navigates in a 3D environment is presented. The overall approach consists of four components as follows. (1) A state-of-the-art path planner that computes a collision-free reference path for the character's center of mass (COM). For this planner, a simplified model that bounds the character's geometry is proposed. (2) A segmentation algorithm that divides the path into behaviors. (3) A classifier that compares each behavior with the corresponding motion capture segments previously analyzed and stored in a database. (4) A whole-body motion generator that synthesizes the appropriate behavior determined by the classifier. The main contribution of this work is to produce a sampling-based global motion planner that generates different behaviors (in addition to locomotion) issued from environmental constraints. Several results of our algorithm in different environments are shown and its current limitations are discussed.

Keywords: I.3.7 computing methodologies, computer graphics, three-dimensional graphics and realism, motion planning, character animation, motion-capture classification.

 

Resumen

En este trabajo se presenta una estrategia para generar automáticamente movimientos visualmente creíbles para un personaje virtual que navega en un ambiente 3D. Esta estrategia consta de 4 componentes: (1) Un planificador de movimientos que calcula un camino sin colisiones para el centro de masa (COM) del personaje. Para esto, se propone un modelo simplificado que envuelve la geometría del personaje. (2) Un algoritmo de segmentación que divide el camino en comportamientos. (3) Un clasificador que compara cada comportamiento con segmentos de captura de movimiento para identificar el tipo de comportamiento correspondiente. (4) Un controlador local de movimientos para todas las articulaciones del personaje que genera los comportamientos determinados por el clasificador. La contribución principal de este trabajo es producir un planificador de movimientos global basado en muestreos que genera diferentes comportamientos (además de locomoción) a partir de las restricciones del ambiente. Se muestran algunos resultados de aplicar esta estrategia en varios ambientes de prueba de para el personaje virtual y se discuten las limitantes del trabajo.

Palabras clave: I.3.7 metodologías computacionales, gráficas por computadora, gráficas tridimensionales y realismo, planificación de movimientos, animación de personajes, clasificación de comportamientos.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

References

1. Arechavaleta, G., Laumond, J-P., Hicheur, H. & Berthoz, A. (2008). On the nonholonomic nature of human locomotion. Autonomous Robots, 25(1), 25-35.         [ Links ]

2. Arikan, O. & Forsyth, D.A. (2002). Interactive motion generation from examples. ACM Transactions on Graphics, 21(3), 483-490.         [ Links ]

3. Barbic, J., Safonova, A., Pan, J., Faloutsos, C., Hodgins, J. & Pollard, N. (2004). Segmenting motion capture data into distinct behaviors. Graphics Interface, 1,185-194.         [ Links ]

4. Bishop, C.M., (2007). Pattern Recognition and Machine Learning. Springer.         [ Links ]

5. Choi, M.G., Lee, J., & Shin, S.Y. (2003). Planning biped locomotion using motion capture data and probabilistic roadmaps. ACM Transactions on Graphics, 22(2), 182-203.         [ Links ]

6. Choi, M.G., Kim, M., Hyun, K., & Lee, J. (2011). Deformable motion: squeezing into cluttered environments. Computer Graphics Forum (Eurographics), 30(2), 445-453.         [ Links ]

7. CMU's Motion capture database. (2003). Retrieved from http://mocap.cs.cmu.edu.         [ Links ]

8. Esteves C., Arechavaleta, G., Pettré, J., & Laumond, J-P (2006). Animation planning for virtual characters cooperation. ACM Transactions on Graphics, 25(2), 319-339.         [ Links ]

9. Gibson, S. (1997). 3D Chainmail: a fast algorithm for deforming volumetric objects. International Symposium on Interactive 3D Graphics. 149-154.         [ Links ]

10. Kavraki, L., Svetska, P., Latombe, J-C. & Overmars, M. (1996). Probabilistic roadmaps for path planning in high dimensional configuration spaces. IEEE Transactions on Robotics and Automation, 12(4), 566-580.         [ Links ]

11. Kovar, L., Gleicher, M. & Pighin, F. (2002). Motion graphs. ACM Transactions on Graphics. 21(3), 473-482.         [ Links ]

12. Kuffner, J.J. & LaValle, S. (2000). RRT-Connect: an efficient approach to single-query path planning. IEEE International Conference on Robotics and Automation. 995-1001.         [ Links ]

13. Lau, M. & Kuffner, J.J. (2005). Behavior planning for character animation. ACM SIGGRAPH/Eurographics Symposium on Computer Animation. 271-280.         [ Links ]

14. Li, L., McCann, J., Faloutsos, C. & Pollard, N. (2008). Laziness is a virtue: motion stitching using effort minimization. Short Papers Proceedings of Eurographics.         [ Links ]

15. Pettré, J. & Laumond, J-P. (2006). A motion capture-based control-space approach for walking mannequins. Computer Animation and Virtual Worlds. 17(2), 109-126.         [ Links ]

16. Pettré, J., Laumond, J-P. & Siméon, T. A 2-stages locomotion planner for digital actors. ACM SIGGRAPH/Eurographics Symposium on Computer Animation. 258-264.         [ Links ]

17. Pettré, J., Siméon, T. & Laumond, J-P. (2002). Planning human walk in virtual environments. IEEE/RSJ International Conference on Intelligent Robots and Systems. 3048-3053.         [ Links ]

18. Schiller, Z., Yamane, K. & Nakamura, Y. (2001). Planning motion patterns of human figures using a multi-layered grid and the dynamics filter. IEEE International Conference on Robotics and Automation. 1-8.         [ Links ]

19. Zhou, F., De la Torre, F. & Hodgins, J.K. (2011). Hierarchical aligned cluster analysis for temporal clustering of human motion. Accepted for publication at IEEE PAMI 2012.         [ Links ]