Contact-Rich Manipulation of a Flexible Object based on Deep Predictive Learning using Vision and Tactility

TL;DR

This paper presents a deep predictive learning approach combining vision and tactility for contact-rich manipulation of flexible objects, significantly improving success rates in unzipping tasks.

Contribution

It introduces a novel model integrating vision and tactile data with attention mechanisms and CNNs for real-time flexible object manipulation.

Findings

Tactile information increased success rate from 56.7% to 93.3%.

The method effectively responds to deformation during manipulation.

Real-time prediction reduces load on the zipper.

Abstract

We achieved contact-rich flexible object manipulation, which was difficult to control with vision alone. In the unzipping task we chose as a validation task, the gripper grasps the puller, which hides the bag state such as the direction and amount of deformation behind it, making it difficult to obtain information to perform the task by vision alone. Additionally, the flexible fabric bag state constantly changes during operation, so the robot needs to dynamically respond to the change. However, the appropriate robot behavior for all bag states is difficult to prepare in advance. To solve this problem, we developed a model that can perform contact-rich flexible object manipulation by real-time prediction of vision with tactility. We introduced a point-based attention mechanism for extracting image features, softmax transformation for predicting motions, and convolutional neural network for extracting tactile features. The results of experiments using a real robot arm revealed that our method can realize motions responding to the deformation of the bag while reducing the load on the zipper. Furthermore, using tactility improved the success rate from 56.7% to 93.3% compared with vision alone, demonstrating the effectiveness and high performance of our method.