“Responsive characters from motion fragments” by McCann and Pollard

In game environments, animated character motion must rapidly adapt to changes in player input – for example, if a directional signal from the player’s gamepad is not incorporated into the character’s trajectory immediately, the character may blithely run off a ledge. Traditional schemes for data-driven character animation lack the split-second reactivity required for this direct control; while they can be made to work, motion artifacts will result. We describe an on-line character animation controller that assembles a motion stream from short motion fragments, choosing each fragment based on current player input and the previous fragment. By adding a simple model of player behavior we are able to improve an existing reinforcement learning method for precalculating good fragment choices. We demonstrate the efficacy of our model by comparing the animation selected by our new controller to that selected by existing methods and to the optimal selection, given knowledge of the entire path. This comparison is performed over real-world data collected from a game prototype. Finally, we provide results indicating that occasional low-quality transitions between motion segments are crucial to high-quality on-line motion generation; this is an important result for others crafting animation systems for directly-controlled characters, as it argues against the common practice of transition thresholding.

1. Abe, Y., Liu, C. K., and Popović, Z. 2004. Momentum-based parameterization of dynamic character motion. In SCA ’04: Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation, Eurographics Association, Aire-la-Ville, Switzerland, Switzerland, 173–182. Google ScholarDigital Library
2. Arikan, O., and Forsyth, D. A. 2002. Interactive motion generation from examples. ACM Press, New York, NY, USA, vol. 21, 483–490. Google ScholarDigital Library
3. Bellman, R. 1957. Dynamic Programming. Princeton University Press, Princeton, NJ. Google ScholarDigital Library
4. Chai, J., and Hodgins, J. K. 2005. Performance animation from low-dimensional control signals. ACM Transactions on Graphics 24, 3, 686–696. Google ScholarDigital Library
5. CMU, 2001. http://mocap.cs.cmu.edu.Google Scholar
6. Dontcheva, M., Yngve, G., and Popović, Z. 2003. Layered acting for character animation. ACM Transactions on Graphics 22, 3, 409–416. Google ScholarDigital Library
7. Faloutsos, P., van de Panne, M., and Terzopoulos, D. 2001. Composable controllers for physics-based character animation. In Proceedings of ACM SIGGRAPH 2001, ACM Press, New York, NY, USA, 251–260. Google ScholarDigital Library
8. Gleicher, M., Shin, H. J., Kovar, L., and Jepsen, A. 2003. Snap-together motion: Assembling run-time animations. In SCA ’03: Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation, ACM Press, New York, NY, USA. Google ScholarDigital Library
9. Grzeszczuk, R., and Terzopoulos, D. 1995. Automated learning of muscle-actuated locomotion through control abstraction. In Proceedings of ACM SIGGRAPH 1995, ACM Press, New York, NY, USA, 63–70. Google ScholarDigital Library
10. Heck, R., and Gleicher, M., 2006. Parametric motion graphs. ACM SIGGRAPH / Eurographics Symposium on Computer Animation (Poster), August.Google Scholar
11. Hsu, E., Gentry, S., and Popović, J. 2004. Example-based control of human motion. In SCA ’04: Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation, ACM Press, New York, NY, USA, 69–77. Google ScholarDigital Library
12. Ikemoto, L. K. M., Arikan, O., and Forsyth, D. A. 2005. Learning to move autonomously in a hostile world. Tech. Rep. UCB/CSD-05-1395, EECS Department, University of California, Berkeley.Google Scholar
13. Ikemoto, L. K. M., Arikan, O., and Forsyth, D. 2006. Quick motion transitions with cached multi-way blends. Tech. Rep. UCB/EECS-2006-14, EECS Department, University of California, Berkeley, February 13.Google Scholar
14. James, D. L., and Fatahalian, K. 2003. Precomputing interactive dynamic deformable scenes. ACM Transactions on Graphics 22, 3 (July), 879–887. Google ScholarDigital Library
15. James, D. L., Twigg, C. D., Cove, A., and Wang, R. Y. 2006. Mesh ensemble motion graphs. In SIGGRAPH ’06: ACM SIGGRAPH 2006 Sketches, ACM Press, New York, NY, USA, 69. Google ScholarDigital Library
16. Kaelbling, L. P., Littman, M. L., and Moore, A. P. 1996. Reinforcement learning: A survey. Journal of Artificial Intelligence Research 4, 237–285. Google ScholarCross Ref
17. Kovar, L., Gleicher, M., and Pighin, F. 2002. Motion graphs. ACM Press, New York, NY, USA, vol. 21, 473–482. Google ScholarDigital Library
18. Laszlo, J., van de Panne, M., and Fiume, E. 2000. Interactive control for physically-based animation. In Proceedings of ACM SIGGRAPH 2001, ACM Press, New York, NY, USA. Google ScholarDigital Library
19. Lee, J., and Lee, K. H. 2004. Precomputing avatar behavior from human motion data. In ACM SIGGRAPH / Eurographics Symposium on Computer Animation, 79–87. Google ScholarDigital Library
20. Lee, J., and Lee, K. H. 2006. Precomputing avatar behavior from human motion data. Graph. Models 68, 2, 158–174. Google ScholarDigital Library
21. Lee, J., Chai, J., Reitsma, P. S. A., Hodgins, J. K., and Pollard, N. S. 2002. Interactive control of avatars animated with human motion data. ACM Press, New York, NY, USA, vol. 21, 491–500. Google ScholarDigital Library
22. Levin, E., Pieraccini, R., and Eckert, W. 2000. A stochastic model of human-machine interaction for learning dialog strategies. IEEE Transactions on Speech and Audio Processing 8, 1, 11–23.Google ScholarCross Ref
23. Moore, A., and Atkeson, C. 1995. The parti-game algorithm for variable resolution reinforcement learning in multidimensional state-spaces. Machine Learning 21. Google ScholarDigital Library
24. Reitsma, P. S. A., and Pollard, N. S. 2004. Evaluating motion graphs for character navigation. In SCA ’04: Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation, ACM Press, New York, NY, USA, 89–98. Google ScholarDigital Library
25. Reitsma, P. S. A., and Pollard, N. S. (in press). Evaluating motion graphs for character animation. ACM Transactions on Graphics. in press. Google ScholarDigital Library
26. RenderWare, 2001. http://www.renderware.com.Google Scholar
27. Safonova, A., and Hodgins, J. 2007. Construction and optimal search of interpolated motion graphs. ACM Transactions on Graphics 26, 3 (Aug.). Google ScholarDigital Library
28. Safonova, A. 2006. Reducing the search space for physically realistic human motion synthesis. PhD thesis, Carnegie Mellon University, Pittsburgh, PA. Google ScholarDigital Library
29. Schödl, A., and Essa, I. A. 2000. Machine learning for video-based rendering. Tech. Rep. GIT-GVU-00-11, Georgia Institute of Technology.Google Scholar
30. Shin, H. J., and Oh, H. S. 2006. Fat graphs: Constructing an interactive character with continuous controls. In ACM SIGGRAPH/Eurographics Symposium on Computer Animation, 291–298. Google ScholarDigital Library
31. Shin, H. J., Lee, J., Shin, S. Y., and Gleicher, M. 2001. Computer puppetry: An importance-based approach. ACM Transactions on Graphics 20, 2, 67–94. Google ScholarDigital Library
32. Sutton, R. S., and Barto, A. G. 1998. Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA, ch. 4.4. Google ScholarDigital Library
33. Torque, 2000. http://www.garagegames.com/products/torque/tge/.Google Scholar
34. Treuille, A., Lee, Y., and Popović, Z. 2007. Character animation with continuous user control. ACM Transactions on Graphics 26, 3 (Aug.). Google ScholarDigital Library
35. van de Panne, M., and Lee, C. 2003. Ski stunt simulator: Experiments with interactive dynamics. In Proceedings of the 14th Western Computer Graphics Symposium.Google Scholar
36. Zhao, P., and van de Panne, M. 2005. User interfaces for interactive control of physics-based 3d characters. In SI3D ’05: Proceedings of the 2005 symposium on Interactive 3D graphics and games, ACM Press, New York, NY, USA, 87–94. Google ScholarDigital Library