Abstract
Deep Reinforcement Learning (RL) has resulted in impressive results when applied in creating virtual character animation control agents capable of responsive behaviour. However, current state-of-the-art methods are heavily dependant on physics-driven feedback to learn character behaviours and are not transferable to portraying behaviour such as social interactions and gestures. In this paper, we present a novel approach to data-driven character animation; we introduce model-based RL animation control agents that learn character dynamics models that are applicable to a range of behaviours. Animation tasks are expressed as meta-objectives, and online planning is used to generate animation within a beta-distribution parameterised space that substantially improves agent efficiency. Purely through self-exploration and learned dynamics, agents created within our framework are able to output animations to successfully complete gaze and pointing tasks robustly while maintaining smoothness of motion, using minimal training epochs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Normoyle, A., Jörg, S.: The effect of animation controller and avatar on player perceptions. Comput. Animat. Virtual Worlds 29(6) (2018)
Lee, J.C., Peters, C., Küster, D., Castellano, G.: Engagement perception and generation for social robots and virtual agents. In: Toward Robotic Socially Believable Behaving Systems, vol. I, pp. 29–51. Springer (2016)
Gamage, V., Ennis, C.: Examining the effects of a virtual character on learning and engagement in serious games. In: Proceedings of the 11th Annual International Conference on Motion, Interaction, and Games, MIG ’18, New York, NY, USA, 2018. Association for Computing Machinery
Holden, D., Komura, T., Saito, J.: Phase-functioned neural networks for character control. ACM Trans. Graphics (TOG) 36(4), 42 (2017)
Klein, A., Yumak, Z., Beij, A., Frank van der Stappen, A.: Data-driven gaze animation using recurrent neural networks. In: Proceedings of the 12th Annual International Conference on Motion, Interaction, and Games, MIG ’19, New York, NY, USA, 2019. Association for Computing Machinery
Peng, X.B., Abbeel, P., Levine, S., van de Panne, M.: Deepmimic: example-guided deep reinforcement learning of physics-based character skills. ACM Trans. Graphics (TOG) 37(4), 1–14 (2018)
Aristidou, A., Lasenby, J.: Fabrik: a fast, iterative solver for the inverse kinematics problem. Graph. Models 73(5), 243–260 (2011)
Caserman, P., Achenbach, P., Göbel, S.: Analysis of inverse kinematics solutions for full-body reconstruction in virtual reality. In: 2019 IEEE 7th International Conference on Serious Games and Applications for Health (SeGAH), pp. 1–8. IEEE (2019)
Goslin, M., Mine, M.R.: The panda3d graphics engine. Computer 37(10), 112–114 (2004)
Adobe. Mixamo, 2020. http://www.mixamo.com. Last accessed 15 Feb 2021
Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807–814 (2010)
Savi’ć, S.: pyfabrik, 2020. https://pypi.org/project/pyfabrik/, Version 0.3.0. Last accessed 15 Feb 2021
Skocir, P., Kusek, M., Jezic, G.: Energy-efficient task allocation for service provisioning in machine-to-machine systems. Concurr. Comput. Pract. Exper. 29(23), e4269 (2017)
Precup, R.-E., Teban, T.-A., de Oliveira, T.E.A., Petriu, E.M.: Evolving fuzzy models for myoelectric-based control of a prosthetic hand. In: 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 72–77. IEEE (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Gamage, V., Ennis, C., Ross, R. (2021). Learned Dynamics Models and Online Planning for Model-Based Animation Agents. In: Jezic, G., Chen-Burger, J., Kusek, M., Sperka, R., Howlett, R.J., Jain, L.C. (eds) Agents and Multi-Agent Systems: Technologies and Applications 2021. Smart Innovation, Systems and Technologies, vol 241. Springer, Singapore. https://doi.org/10.1007/978-981-16-2994-5_3
Download citation
DOI: https://doi.org/10.1007/978-981-16-2994-5_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2993-8
Online ISBN: 978-981-16-2994-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)