Push-Placement: A Hybrid Approach Integrating Prehensile and Non-Prehensile Manipulation for Object Rearrangement

2026-02-14

AI Summary

This work addresses the challenge of object rearrangement on cluttered tabletops, where target poses are often occluded, necessitating frequent and inefficient buffering actions. To mitigate this, the authors propose a novel hybrid manipulation primitive—push-placement—that simultaneously places a target object while pushing aside obstructing items, thereby reducing the need for explicit intermediate buffering. This primitive uniquely unifies grasping and non-grasping actions into a single coordinated motion. It is integrated into a closed-loop Monte Carlo Tree Search (MCTS) planner operating within a PyBullet-based physics simulation framework. Experimental results demonstrate that the proposed approach reduces robotic arm movement cost by 11.12% compared to a baseline MCTS planner and by 8.56% relative to a dynamic stacking method, highlighting its efficacy in improving task efficiency.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Efficient tabletop rearrangement remains challenging due to collisions and the need for temporary buffering when target poses are obstructed. Prehensile pick-and-place provides precise control but often requires extra moves, whereas non-prehensile pushing can be more efficient but suffers from complex, imprecise dynamics. This paper proposes push-placement, a hybrid action primitive that uses the grasped object to displace obstructing items while being placed, thereby reducing explicit buffering. The method is integrated into a physics-in-the-loop Monte Carlo Tree Search (MCTS) planner and evaluated in the PyBullet simulator. Empirical results show push-placement reduces the manipulator travel cost by up to 11.12% versus a baseline MCTS planner and 8.56% versus dynamic stacking. These findings indicate that hybrid prehensile/non-prehensile action primitives can substantially improve efficiency in long-horizon rearrangement tasks.

Problem

• object rearrangement
• prehensile manipulation
• non-prehensile manipulation
• collision handling
• buffering

Innovation

• push-placement
• hybrid manipulation
• Monte Carlo Tree Search
• object rearrangement
• non-prehensile manipulation