MOMA-Force: Visual-Force Imitation for Real-World Mobile Manipulation

In this paper, we present a novel method for mobile manipulators to perform multiple contact-rich manipulation tasks. While learning-based methods have the potential to generate actions in an end-to-end manner, they often suffer from insufficient action accuracy and robustness against noise. On the other hand, classical control-based methods can enhance system robustness, but at the cost of extensive parameter tuning. To address these challenges, we present MOMA-Force, a visual-force imitation method that seamlessly combines representation learning for perception, imitation learning for complex motion generation, and admittance whole-body control for system robustness and controllability. MOMA-Force enables a mobile manipulator to learn multiple complex contact-rich tasks with high success rates and small contact forces. In a real household setting, our method outperforms baseline methods in terms of task success rates. Moreover, our method achieves smaller contact forces and smaller force variances compared to baseline methods without force imitation. Overall, we offer a promising approach for efficient and robust mobile manipulation in the real world. Videos and more details can be found on https://visual-force-imitation.github.io.

I. Introduction

Mobile manipulation combines two fundamental robot capabilities: mobility and manipulation. These two capabilities substantially extend robot applications in the real world compared to static manipulation [1]. For example, mobile manipulation enables robots to complete tasks involving manipulations with large workspaces (e.g., opening closet doors). However, mobile manipulation poses significant challenges when it comes to real-world tasks. The challenges are mainly twofold. First, uncertainties caused by localization and control can lead to potential safety issues, especially in contact-rich tasks. Second, the high-dimensional configuration space makes motion generation and control complex.