RODec 15, 2019

Multi-Object Rearrangement with Monte Carlo Tree Search:A Case Study on Planar Nonprehensile Sorting

arXiv:1912.07024v362 citations
Originality Synthesis-oriented
AI Analysis

This addresses a specific robotic manipulation task for sorting objects, but it appears incremental as it applies an existing method (Monte Carlo tree search) to a new domain with a custom heuristic.

The paper tackled the problem of planar non-prehensile sorting for robots by using Monte Carlo tree search with a task-specific heuristic, achieving reliable sorting of large numbers of convex and non-convex objects, including in the presence of immovable obstacles.

In this work, we address a planar non-prehensile sorting task. Here, a robot needs to push many densely packed objects belonging to different classes into a configuration where these classes are clearly separated from each other. To achieve this, we propose to employ Monte Carlo tree search equipped with a task-specific heuristic function. We evaluate the algorithm on various simulated and real-world sorting tasks. We observe that the algorithm is capable to reliably sort large numbers of convex and non-convex objects, as well as convex objects in the presence of immovable obstacles.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes