# Learning Periodic Tasks from Human Demonstrations

arXiv: https://arxiv.org/abs/2109.14078 · HTML: https://mlsanity.com/paper/2109.14078/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2021.

## Built on by (most cited first, 10 of 10)

- [Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation](https://mlsanity.com/paper/2401.02117/) (2024)
- [DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation](https://mlsanity.com/paper/2403.07788/) (2024)
- [EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning](https://mlsanity.com/paper/2407.01479/) (2024)
- [Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction](https://mlsanity.com/paper/2409.18121/) (2024)
- [K-VIL: Keypoints-based Visual Imitation Learning](https://mlsanity.com/paper/2209.03277/) (2022)
- [Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulation](https://mlsanity.com/paper/2203.09749/) (2022)
- [A Survey on Imitation Learning for Contact-Rich Tasks in Robotics](https://mlsanity.com/paper/2506.13498/) (2025)
- [Learning Robot Manipulation from Cross-Morphology Demonstration](https://mlsanity.com/paper/2304.03833/) (2023)
- [PhyPlan: Compositional and Adaptive Physical Task Reasoning with Physics-Informed Skill Networks for Robot Manipulators](https://mlsanity.com/paper/2402.15767/) (2024)
- [PhyPlan: Generalizable and Rapid Physical Task Planning with Physics Informed Skill Networks for Robot Manipulators](https://mlsanity.com/paper/2406.00001/) (2024)

## Abstract (arXiv)

We develop a method for learning periodic tasks from visual demonstrations. The core idea is to leverage periodicity in the policy structure to model periodic aspects of the tasks. We use active learning to optimize parameters of rhythmic dynamic movement primitives (rDMPs) and propose an objective to maximize the similarity between the motion of objects manipulated by the robot and the desired motion in human video demonstrations. We consider tasks with deformable objects and granular matter whose states are challenging to represent and track: wiping surfaces with a cloth, winding cables/wires, and stirring granular matter with a spoon. Our method does not require tracking markers or manual annotations. The initial training data consists of 10-minute videos of random unpaired interactions with objects by the robot and human. We use these for unsupervised learning of a keypoint model to get task-agnostic visual correspondences. Then, we use Bayesian optimization to optimize rDMPs from a single human video demonstration within few robot trials. We present simulation and hardware experiments to validate our approach.