Dynamic Buffers: Cost-Efficient Planning for Tabletop Rearrangement with Stacking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Barghi, Arman, Hosseini, Hamed, Ghasemi, Seraj, Masouleh, Mehdi Tale, Kalhor, Ahmad
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909810383912960
author Barghi, Arman
Hosseini, Hamed
Ghasemi, Seraj
Masouleh, Mehdi Tale
Kalhor, Ahmad
author_facet Barghi, Arman
Hosseini, Hamed
Ghasemi, Seraj
Masouleh, Mehdi Tale
Kalhor, Ahmad
contents Rearranging objects in cluttered tabletop environments remains a long-standing challenge in robotics. Classical planners often generate inefficient, high-cost plans by shuffling objects individually and using fixed buffers--temporary spaces such as empty table regions or static stacks--to resolve conflicts. When only free table locations are used as buffers, dense scenes become inefficient, since placing an object can restrict others from reaching their goals and complicate planning. Allowing stacking provides extra buffer capacity, but conventional stacking is static: once an object supports another, the base cannot be moved, which limits efficiency. To overcome these issues, a novel planning primitive called the Dynamic Buffer is introduced. Inspired by human grouping strategies, it enables robots to form temporary, movable stacks that can be transported as a unit. This improves both feasibility and efficiency in dense layouts, and it also reduces travel in large-scale settings where space is abundant. Compared with a state-of-the-art rearrangement planner, the approach reduces manipulator travel cost by 11.89% in dense scenarios with a stationary robot and by 5.69% in large, low-density settings with a mobile manipulator. Practicality is validated through experiments on a Delta parallel robot with a two-finger gripper. These findings establish dynamic buffering as a key primitive for cost-efficient and robust rearrangement planning.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22828
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dynamic Buffers: Cost-Efficient Planning for Tabletop Rearrangement with Stacking
Barghi, Arman
Hosseini, Hamed
Ghasemi, Seraj
Masouleh, Mehdi Tale
Kalhor, Ahmad
Robotics
Artificial Intelligence
I.2.9; I.2.8
Rearranging objects in cluttered tabletop environments remains a long-standing challenge in robotics. Classical planners often generate inefficient, high-cost plans by shuffling objects individually and using fixed buffers--temporary spaces such as empty table regions or static stacks--to resolve conflicts. When only free table locations are used as buffers, dense scenes become inefficient, since placing an object can restrict others from reaching their goals and complicate planning. Allowing stacking provides extra buffer capacity, but conventional stacking is static: once an object supports another, the base cannot be moved, which limits efficiency. To overcome these issues, a novel planning primitive called the Dynamic Buffer is introduced. Inspired by human grouping strategies, it enables robots to form temporary, movable stacks that can be transported as a unit. This improves both feasibility and efficiency in dense layouts, and it also reduces travel in large-scale settings where space is abundant. Compared with a state-of-the-art rearrangement planner, the approach reduces manipulator travel cost by 11.89% in dense scenarios with a stationary robot and by 5.69% in large, low-density settings with a mobile manipulator. Practicality is validated through experiments on a Delta parallel robot with a two-finger gripper. These findings establish dynamic buffering as a key primitive for cost-efficient and robust rearrangement planning.
title Dynamic Buffers: Cost-Efficient Planning for Tabletop Rearrangement with Stacking
topic Robotics
Artificial Intelligence
I.2.9; I.2.8
url https://arxiv.org/abs/2509.22828