English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper considers the problem of retrieving an object from many tightlypacked objects using a combination of robotic pushing and grasping actions.Object retrieval in dense clutter is an important skill for robots to operatein households and everyday environments effectively. The proposed solution,Visual Foresight Trees (VFT), intelligently rearranges the clutter surroundinga target object so that it can be grasped easily. Rearrangement with nestednonprehensile actions is challenging as it requires predicting complex objectinteractions in a combinatorially large configuration space of multipleobjects. We first show that a deep neural network can be trained to accuratelypredict the poses of the packed objects when the robot pushes one of them. Thepredictive network provides visual foresight and is used in a tree search as astate transition function in the space of scene images. The tree search returnsa sequence of consecutive push actions yielding the best arrangement of theclutter for grasping the target object. Experiments in simulation and using areal robot and objects show that the proposed approach outperforms model-freetechniques as well as model-based myopic methods both in terms of success ratesand the number of executed actions, on several challenging tasks. A videointroducing VFT, with robot experiments, is accessible athttps://youtu.be/7cL-hmgvyec. The full source code is available athttps://github.com/arc-l/vft.

Visual Foresight Trees for Object Retrieval From Clutter With Nonprehensile Rearrangement