Multi-Modal Planning on Regrasping for Stable Manipulation

TL;DR

This paper introduces a multi-modal planning approach based on Markov Decision Processes to enable robots to re-grasp objects for stable manipulation, addressing workspace limitations and improving pick-and-place success rates.

Contribution

It presents a novel multi-modal planner that re-arranges objects for stable grasping, combining re-grasping and transfer actions within a Markov Decision Process framework.

Findings

Enhanced success rate in simulation and real-world tasks

Effective handling of workspace constraints for grasping

Improved robustness in multi-modal manipulation scenarios

Abstract

Nowadays, a number of grasping algorithms have been proposed, that can predict a candidate of grasp poses, even for unseen objects. This enables a robotic manipulator to pick-and-place such objects. However, some of the predicted grasp poses to stably lift a target object may not be directly approachable due to workspace limitations. In such cases, the robot will need to re-grasp the desired object to enable successful grasping on it. This involves planning a sequence of continuous actions such as sliding, re-grasping, and transferring. To address this multi-modal problem, we propose a Markov-Decision Process-based multi-modal planner that can rearrange the object into a position suitable for stable manipulation. We demonstrate improved performance in both simulation and the real world for pick-and-place tasks.