DeepAI AI Chat
Log In Sign Up

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

by   Yongqiang Huang, et al.

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.


page 6

page 7

page 10

page 12


How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?

Despite the recent success of video self-supervised learning, there is m...

Leveraging Hidden Structure in Self-Supervised Learning

This work considers the problem of learning structured representations f...

Using Multiple Self-Supervised Tasks Improves Model Robustness

Deep networks achieve state-of-the-art performance on computer vision ta...

Imitation Learning for Nonprehensile Manipulation through Self-Supervised Learning Considering Motion Speed

Robots are expected to replace menial tasks such as housework. Some of t...

Feature diversity in self-supervised learning

Many studies on scaling laws consider basic factors such as model size, ...

Learning what is above and what is below: horizon approach to monocular obstacle detection

A novel approach is proposed for monocular obstacle detection, which rel...

Embodied Self-supervised Learning by Coordinated Sampling and Training

Self-supervised learning can significantly improve the performance of do...