Symbolic State Space Optimization for Long Horizon Mobile Manipulation Planning

TL;DR

This paper introduces S3O, a method for automatically optimizing symbolic state spaces in long-horizon mobile manipulation tasks, improving planning efficiency and success rates.

Contribution

We propose Symbolic State Space Optimization (S3O) to automatically generate abstracted locations and groundings, reducing manual effort in task space design.

Findings

S3O outperforms TAMP baselines in simulation.

S3O improves task completion rate.

S3O reduces execution time.

Abstract

In existing task and motion planning (TAMP) research, it is a common assumption that experts manually specify the state space for task-level planning. A well-developed state space enables the desirable distribution of limited computational resources between task planning and motion planning. However, developing such task-level state spaces can be non-trivial in practice. In this paper, we consider a long horizon mobile manipulation domain including repeated navigation and manipulation. We propose Symbolic State Space Optimization (S3O) for computing a set of abstracted locations and their 2D geometric groundings for generating task-motion plans in such domains. Our approach has been extensively evaluated in simulation and demonstrated on a real mobile manipulator working on clearing up dining tables. Results show the superiority of the proposed method over TAMP baselines in task completion rate and execution time.