COMBO-Grasp: Learning Constraint-Based Manipulation for Bimanual Occluded Grasping

Jun Yamada, Alexander Luis Mitchell, Jack Collins, Ingmar Posner

Keywords: Occluded Grasping, Bimanual Manipulation, Reinforcement Learning

TL;DR: We propose COMBO-Grasp, a bimanual learning-based framework combining self-supervised and RL policies to tackle occluded robotic grasping tasks.

Abstract: This paper addresses the challenge of occluded robot grasping, i.e. grasping in situations where the desired grasp poses are kinematically infeasible due to environmental constraints such as surface collisions. Existing RL methods struggle with task complexity, and collecting expert demonstrations is often impractical. Instead, inspired by human bimanual manipulation strategies, where two hands coordinate to stabilise and reorient objects, we focus on a bimanual robotic setup to tackle this challenge. In particular, we introduce Constraint-based Manipulation for Bimanual Occluded Grasping (COMBO-Grasp), an approach which leverages two coordinated policies: a constraint policy trained using self-supervised datasets to generate stabilising poses and a grasping policy trained using RL that reorients and grasps the target object. A key contribution lies in value function-guided policy coordination, where gradients from a jointly trained value function refine the constraint policy during RL training to improve bimanual coordination and task performance. Lastly, COMBO-Grasp employs teacher-student policy distillation to effectively deploy vision-based policies in real-world environments. Experiments show that COMBO-Grasp significantly outperforms baselines and generalises to unseen objects in both simulation and real environments.

Submission Number: 356