Abstract
Trajectory generation for a dynamic task, where the outcome of the task is not ensured by simple repetition of a motion, is a complex problem. In this paper we explore a methodology for motion generation that retains the correspondence of the executed dynamic task. Throwing, which is not explored in this paper, is a very illustrative example. If we just imitate human throwing motion with a robot, the outcome of the throw with a robot will most likely not be very similar to the demonstrated one. In this paper we explore a deep encode-decode architecture, combined with ProDMP trajectory encoding in order to actively predict the behavior of the dynamic task and execute the motion such that the task is observed. Our example is based on the task of dragging a box across a surface. Guided by future work on transferability, in this paper we explore the parameters of the approach and the requirements for effective task transfer to a new domain.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Calinon, S., Alizadeh, T., Caldwell, D.G.: On improving the extrapolation capability of task-parameterized movement models. In: International Conference on Intelligent Robots and Systems, pp. 610–616 (2013)
Dillmann, R.: Teaching and learning of robot tasks via observation of human performance. Robot. Auton. Syst. 47(2–3), 109–116 (2004). https://doi.org/10.1016/j.robot.2004.03.005
Eysenbach, B., Levine, S.: Maximum entropy RL (provably) solves some robust RL problems (2021). https://doi.org/10.48550/ARXIV.2103.06257
Ijspeert, A., Nakanishi, J., Pastor, P., Hoffmann, H., Schaal, S.: Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput. 25(2), 328–373 (2013)
Ijspeert, A.J., Nakanishi, J., Hoffmann, H., Pastor, P., Schaal, S.: Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput. 25(2), 328–373 (2013)
Li, G., Jin, Z., Volpp, M., Otto, F., Lioutikov, R., Neumann, G.: ProDMPs: a unified perspective on dynamic and probabilistic movement primitives (2022). https://doi.org/10.48550/ARXIV.2210.01531
Lončarević, Z., Simonič, M., Ude, A., Gams, A.: Combining reinforcement learning and lazy learning for faster few-shot transfer learning. In: 21st International Conference on Humanoid Robots (Humanoids), pp. 285–290 (2022)
Pahič, R., Lončarević, Z., Ude, A., Nemec, B., Gams, A.: User feedback in latent space robotic skill learning. In: 18th International Conference on Humanoid Robots (Humanoids), pp. 270–276 (2018)
Pahič, R., Lončarević, Z., Gams, A., Ude, A.: Robot skill learning in latent space of a deep autoencoder neural network. Robot. Auton. Syst. 135, 103690 (2021)
Paraschos, A., Daniel, C., Peters, J., Neumann, G.: Probabilistic movement primitives. In: Neural Information Processing Systems, pp. 2616–2624 (2013)
Ude, A., Gams, A., Asfour, T., Morimoto, J.: Task-specific generalization of discrete and periodic dynamic movement primitives. Trans. Robot. 26(5), 800–815 (2010)
Volpp, M., Flürenbrock, F., Grossberger, L., Daniel, C., Neumann, G.: Bayesian context aggregation for neural processes. In: International Conference on Learning Representations (2021)
Acknowledgement
This research was funded by ARRS research grant Robot Textile and Fabric Inspection and Manipulation - RTFM (J2-4457), ARRS program group Automation, Robotics, and Biocybernetics (P2-0076) and DAAD Grant 57588366.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lončarević, Z., Li, G., Neumann, G., Gams, A. (2023). An Encoder-Decoder Architecture for Smooth Motion Generation. In: Petrič, T., Ude, A., Žlajpah, L. (eds) Advances in Service and Industrial Robotics. RAAD 2023. Mechanisms and Machine Science, vol 135. Springer, Cham. https://doi.org/10.1007/978-3-031-32606-6_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-32606-6_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-32605-9
Online ISBN: 978-3-031-32606-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)