FLEX : A Framework for Learning Robot-Agnostic Force-based Skills Involving Sustained Contact Object Manipulation


*Denotes Equal Contribution; Names in alphabetical order

FLEX: Learning Robot-Agnostic Force-based Skills for Sustained Contact Object Manipulation
This paper presents our work on developing a force-based learning framework for manipulating objects in force space. Our method decouples the robot from the object, simplifying the action space and reducing unnecessary exploration. We demonstrate the effectiveness of our framework on a diverse set of objects in simulation and a real robotic platform.

Abstract

Learning to manipulate objects efficiently, particularly those involving sustained contact (e.g., pushing, sliding) and articulated parts (e.g., drawers, doors), presents significant challenges. Traditional methods, such as robot-centric reinforcement learning (RL), imitation learning, and hybrid techniques, require massive training and often struggle to generalize across different objects and robot platforms. We propose a novel framework for learning object-centric manipulation policies in force space, decoupling the robot from the object. By directly applying forces to selected regions of the object, our method simplifies the action space, reduces unnecessary exploration, and decreases simulation overhead. This approach, trained in simulation on a small set of representative objects, captures object dynamics—such as joint configurations—allowing policies to generalize effectively to new, unseen objects. Decoupling these policies from robot-specific dynamics enables direct transfer to different robotic platforms (e.g., Kinova, Panda, UR5) without retraining. Our evaluations demonstrate that the method significantly outperforms baselines, achieving over an order of magnitude improvement in training efficiency compared to other state-of-the-art methods. Additionally, operating in force space enhances policy transferability across diverse robot platforms and object types. We further showcase the applicability of our method in a real-world robotic setting.

Video Demonstration

Real Robot Demonstration

BibTeX

<\!-- Trigger rebuild to ensure all LFS files are pulled -->