# Robot Gaining Accurate Pouring Skills through Self-Supervised Learning and Generalization

arXiv: https://arxiv.org/abs/2011.10150 · HTML: https://mlsanity.com/paper/2011.10150/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [Imitation Learning for Nonprehensile Manipulation through Self-Supervised Learning Considering Motion Speed](https://mlsanity.com/paper/2206.10289/) (2022)
- [Research Challenges and Progress in Robotic Grasping and Manipulation Competitions](https://mlsanity.com/paper/2108.01483/) (2021)
- [From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Network](https://mlsanity.com/paper/2309.09181/) (2023)
- [Manipulation of Granular Materials by Learning Particle Interactions](https://mlsanity.com/paper/2111.02274/) (2021)
- [Consolidating Trees of Robotic Plans Generated Using Large Language Models to Improve Reliability](https://mlsanity.com/paper/2401.07868/) (2024)
- [The Sound of Water: Inferring Physical Properties from Pouring Liquids](https://mlsanity.com/paper/2411.11222/) (2024)
- [Vision-based robot manipulation of transparent liquid containers in a laboratory setting](https://mlsanity.com/paper/2404.16529/) (2024)
- [Pouring Dynamics Estimation Using Gated Recurrent Units](https://mlsanity.com/paper/2105.12828/) (2021)
- [Enabling robots to follow abstract instructions and complete complex dynamic tasks](https://mlsanity.com/paper/2406.11231/) (2024)

## Abstract (arXiv)

Pouring is one of the most commonly executed tasks in humans' daily lives, whose accuracy is affected by multiple factors, including the type of material to be poured and the geometry of the source and receiving containers. In this work, we propose a self-supervised learning approach that learns the pouring dynamics, pouring motion, and outcomes from unsupervised demonstrations for accurate pouring. The learned pouring model is then generalized by self-supervised practicing to different conditions such as using unaccustomed pouring cups. We have evaluated the proposed approach first with one container from the training set and four new but similar containers. The proposed approach achieved better pouring accuracy than a regular human with a similar pouring speed for all five cups. Both the accuracy and pouring speed outperform state-of-the-art works. We have also evaluated the proposed self-supervised generalization approach using unaccustomed containers that are far different from the ones in the training set. The self-supervised generalization reduces the pouring error of the unaccustomed containers to the desired accuracy level.