Efficient Object Manipulation to an Arbitrary Goal Pose: Learning-based Anytime Prioritized Planning

TL;DR

This paper introduces a learning-based anytime prioritized planning method for object manipulation tasks, enabling robots to efficiently find feasible paths to arbitrary goal poses with reduced time and cost.

Contribution

It presents a hierarchical learning framework with a cost estimator and refined training to improve planning efficiency in object manipulation tasks.

Findings

Achieves faster planning with lower path costs in simulation and real-world tests.

Outperforms baseline methods in success rate and efficiency.

Effective in handling reorientation and complex object placements.

Abstract

We focus on the task of object manipulation to an arbitrary goal pose, in which a robot is supposed to pick an assigned object to place at the goal position with a specific orientation. However, limited by the execution space of the manipulator with gripper, one-step picking, moving and releasing might be failed, where a reorientation object pose is required as a transition. In this paper, we propose a learning-driven anytime prioritized search-based solver to find a feasible solution with low path cost in a short time. In our work, the problem is formulated as a hierarchical learning problem, with the high level finding a reorientation object pose, and the low level planning paths between adjacent grasps. We learn an offline-training path cost estimator to predict approximate path planning costs, which serve as pseudo rewards to allow for pre-training the high-level planner without interacting with the simulator. To deal with the problem of distribution mismatch of the cost net and the actual execution cost space, a refined training stage is conducted with simulation interaction. A series of experiments carried out in simulation and real world indicate that our system can achieve better performances in the object manipulation task with less time and less cost.