In project C6, we will investigate if the movement primitive / sensorimotor primitive models (SMPs) from the previous funding periods can be hierarchically extended to enable the perception, prediction and control of activities composed of sequential actions, which are composed of movements. Our best SMP models from the previous funding periods will be hierarchically composed in space and time by imbuing our sequencing approaches with semantic constraints. Steering such a model requires attentional control in naturalistic environments, which we will model jointly with project B3. Trained models will be evaluated with respect to their ability to generate believable activities, predict movement sequence continuations and respond human-like to sensory signal degradation.
former project-related publications
Chiovetto, E., Curio, C., Endres, D., & Giese, M. (2018). Perceptual integration of kinematic components in the recognition of emotional facial expressions. Journal of vision
, 18(4), 13-13. find paper
Clever, D., Harant, M., Koch, K. H., Mombaur, K. and Endres, D. (2016). A novel approach for the generation of complex humanoid walking sequences based on a combination of optimal control and learning of movement primitives. Robotics and Autonomous Systems
, Volume 83, 287–298.
Clever, D., Harant, M., Mombaur, K., Naveau, M., Stasse, O. and Endres, D. (2017). COCoMoPL: A Novel Approach for Humanoid Walking Generation Combining Optimal Control, Movement Primitives and Learning and its transfer to the real robot HRP-2. IEEE Robotics and Automation Letters
,2(2):977 – 984.
Junker, M., Endres, D., Sun, Z. P., Dicke, P. W., Giese, M., & Thier, P. (2018). Learning from the past: A reverberation of past errors in the cerebellar climbing fiber signal. PLoS biology
, 16(8), e2004344. find paper
Khoozani, P. A., Schrater, P. R., Endres, D., Fiehler, K., & Blohm, G. (2019). Models of allocentric coding for reaching in naturalistic visual scenes. In Proceedings of the 2019 Conference on
Cognitive Computational Neuroscience, 4 pages.
Knopp, B., Velychko, D., Dreibrodt, J., & Endres, D. (2019). Predicting Perceived Naturalness of Human Animations Based on Generative Movement Primitive Models. ACM Transactions on Applied Perception (TAP)
, 16(3), 1-18.
Knopp, B., Velychko, D., Dreibrodt, J., Schütz, A. C., & Endres, D. (2020). Evaluating perceptual predictions based on movement primitive models in VR- and online-experiments. In ACM
32 Symposium on Applied Perception
2020, SAP ·20, New York, NY, USA. Association for Computing Machinery.
Mukovskiy, A., Taubert, N., Endres, D., Vassallo, C., Naveau, M., Stasse, O., Souères, P. and Giese, M. A. (2017). Modeling of coordinated human body motion by learning of structured dynamic representations. In J.-P. Laumond, N. Mansard, and J.-B. Lasserre, editors, Geometric and Numerical Foundations of Movements, volume 117 of STAR Series, pages 1–26. Springer.
Quaglio, P., Yegenoglu, A., Torre, E., Endres, D. M., & Grün, S. (2017). Detection and Evaluation of Spatio-Temporal Spike Patterns in Massively Parallel Spike Train Data with SPADE. Frontiers in Computational Neuroscience
Schubert, M., & Endres, D. (2018). Empirically Evaluating the Similarity Model of Geist, Lengnink and Wille. In International Conference on Conceptual Structures
(pp. 88-95). Springer, Cham. find paper
Serr, A., Schubert, M., & Endres, D. (2019, July). Mathematical Similarity Models: Do We Need Incomparability to Be Precise? In International Conference on Conceptual Structures
(pp. 257-261). Springer, Cham.
Velychko, D., Endres , D., Taubert, N., and Giese, M. A. (2014). Coupling Gaussian process dynamical models with product-of-experts kernels. In Proceeding of the 24th International Conference on Artificial Neural Networks
, LNCS 8681, pages 603–610. Springer.
Velychko, D., Knopp, B. and Endres D. (2017). The coupled variational Gaussian process dynamical model. In Proceedings of the 27th
International Conference on Artificial Neural Networks
Velychko, D., Knopp, B. and Endres, D. (2016). The variational coupled Gaussian process dynamical model (Abstract). NIPS Workshop on Neurorobotics
Velychko, D., Knopp, B., & Endres, D (2018). Making the Coupled Gaussian Process Dynamical Model Modular and Scalable with Variational Approximations. Entropy,