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

Abstract

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.

arXiv commentAccepted to RAS - 18 pages

References in corpus (8)

• Sequence to Sequence Learning with Neural Networks
• Recurrent Neural Network Regularization
• Sharp Minima Can Generalize For Deep Nets
• Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes
• Identifying Object States in Cooking-Related Images
• Manipulation Motion Taxonomy and Coding for Robots
• Accurate Robotic Pouring for Serving Drinks
• Estimating Motion Codes from Demonstration Videos