A Task-Motion Planning Framework Using Iteratively Deepened AND/OR Graph Networks

TL;DR

This paper introduces TMP-IDAN, a novel task-motion planning framework that uses iteratively deepened AND/OR graph networks to efficiently handle complex cluttered object retrieval tasks with online graph growth.

Contribution

The paper proposes a new online growing AND/OR graph network approach for task-motion planning, improving scalability and computational efficiency in cluttered environments.

Findings

Faster computation compared to traditional planners

Scalable to increasing objects and clutter

Validated on real robot and simulator in complex scenarios

Abstract

We present an approach for Task-Motion Planning (TMP) using Iterative Deepened AND/OR Graph Networks (TMP-IDAN) that uses an AND/OR graph network based novel abstraction for compactly representing the task-level states and actions. While retrieving a target object from clutter, the number of object re-arrangements required to grasp the target is not known ahead of time. To address this challenge, in contrast to traditional AND/OR graph-based planners, we grow the AND/OR graph online until the target grasp is feasible and thereby obtain a network of AND/OR graphs. The AND/OR graph network allows faster computations than traditional task planners. We validate our approach and evaluate its capabilities using a Baxter robot and a state-of-the-art robotics simulator in several challenging non-trivial cluttered table-top scenarios. The experiments show that our approach is readily scalable to increasing number of objects and different degrees of clutter.