# Overcoming Some Drawbacks of Dynamic Movement Primitives

arXiv: https://arxiv.org/abs/1908.10608 · HTML: https://mlsanity.com/paper/1908.10608/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2019.

## Built on by (most cited first, 5 of 5)

- [Unsupervised identification of surgical robotic actions from small non homogeneous datasets](https://mlsanity.com/paper/2105.08488/) (2021)
- [Towards Surgical Context Inference and Translation to Gestures](https://mlsanity.com/paper/2302.14237/) (2023)
- [Inductive Learning of Robot Task Knowledge from Raw Data and Online Expert Feedback](https://mlsanity.com/paper/2501.07507/) (2025)
- [Generalization of Auto-Regressive Hidden Markov Models to Non-Linear Dynamics and Unit Quaternion Observation Space](https://mlsanity.com/paper/2302.11834/) (2023)
- [Obstacle Avoidance using Dynamic Movement Primitives and Reinforcement Learning](https://mlsanity.com/paper/2510.09254/) (2025)

## Abstract (arXiv)

Dynamic Movement Primitives (DMPs) is a framework for learning a point-to-point trajectory from a demonstration. Despite being widely used, DMPs still present some shortcomings that may limit their usage in real robotic applications. Firstly, at the state of the art, mainly Gaussian basis functions have been used to perform function approximation. Secondly, the adaptation of the trajectory generated by the DMP heavily depends on the choice of hyperparameters and the new desired goal position. Lastly, DMPs are a framework for `one-shot learning', meaning that they are constrained to learn from a unique demonstration. In this work, we present and motivate a new set of basis functions to be used in the learning process, showing their ability to accurately approximate functions while having both analytical and numerical advantages w.r.t. Gaussian basis functions. Then, we show how to use the invariance of DMPs w.r.t. affine transformations to make the generalization of the trajectory robust against both the choice of hyperparameters and new goal position, performing both synthetic tests and experiments with real robots to show this increased robustness. Finally, we propose an algorithm to extract a common behavior from multiple observations, validating it both on a synthetic dataset and on a dataset obtained by performing a task on a real robot.