Probabilistic Slide-support Manipulation Planning in Clutter

TL;DR

This paper introduces a neural network-based bimanual manipulation planner that efficiently extracts objects from clutter by sliding and supporting objects, reducing motion sequences and enhancing safety.

Contribution

It presents a novel approach combining neural network predictions with Monte Carlo tree search for safe, efficient clutter object retrieval using bimanual robots.

Findings

Reduced number of motion sequences in object retrieval

Improved safety during manipulation

Effective bimanual planning in clutter environments

Abstract

To safely and efficiently extract an object from the clutter, this paper presents a bimanual manipulation planner in which one hand of the robot is used to slide the target object out of the clutter while the other hand is used to support the surrounding objects to prevent the clutter from collapsing. Our method uses a neural network to predict the physical phenomena of the clutter when the target object is moved. We generate the most efficient action based on the Monte Carlo tree search.The grasping and sliding actions are planned to minimize the number of motion sequences to pick the target object. In addition, the object to be supported is determined to minimize the position change of surrounding objects. Experiments with a real bimanual robot confirmed that the robot could retrieve the target object, reducing the total number of motion sequences and improving safety.