Visual Foresight Trees for Object Retrieval from Clutter with Nonprehensile Rearrangement

TL;DR

This paper introduces Visual Foresight Trees (VFT), a method that uses deep learning and tree search to rearrange cluttered objects for easier robotic grasping, improving success rates in dense environments.

Contribution

The paper presents VFT, a novel approach combining neural network predictions with tree search for nonprehensile rearrangement in cluttered object retrieval tasks.

Findings

VFT outperforms model-free and myopic methods in success rate.

VFT reduces the number of actions needed for successful retrieval.

The approach is effective in both simulation and real robot experiments.

Abstract

This paper considers the problem of retrieving an object from many tightly packed objects using a combination of robotic pushing and grasping actions. Object retrieval in dense clutter is an important skill for robots to operate in households and everyday environments effectively. The proposed solution, Visual Foresight Trees (VFT), intelligently rearranges the clutter surrounding a target object so that it can be grasped easily. Rearrangement with nested nonprehensile actions is challenging as it requires predicting complex object interactions in a combinatorially large configuration space of multiple objects. We first show that a deep neural network can be trained to accurately predict the poses of the packed objects when the robot pushes one of them. The predictive network provides visual foresight and is used in a tree search as a state transition function in the space of scene images. The tree search returns a sequence of consecutive push actions yielding the best arrangement of the clutter for grasping the target object. Experiments in simulation and using a real robot and objects show that the proposed approach outperforms model-free techniques as well as model-based myopic methods both in terms of success rates and the number of executed actions, on several challenging tasks. A video introducing VFT, with robot experiments, is accessible at https://youtu.be/7cL-hmgvyec. The full source code is available at https://github.com/arc-l/vft.