BiNoMaP: Learning Category-Level Bimanual Non-Prehensile Manipulation Primitives

Huayi Zhou, Kui Jia

Keywords: Non-Prehensile Manipulation, Bimanual Robotic Manipulation, Motion Trajectory Optimization

TL;DR: We propose BiNoMaP, a dual-arm, RL-free framework that learns generalizable bimanual non-prehensile manipulation primitives from hand demonstrations, enabling robust instance- and category-level generalization across diverse tasks.

Abstract: Non-prehensile manipulation, encompassing ungraspable actions such as pushing, poking, and pivoting, represents a critical yet underexplored domain in robotics due to its contact-rich and analytically intractable nature. In this work, we revisit this problem from two novel perspectives. First, we move beyond the usual single-arm setup and the strong assumption of favorable external dexterity such as walls, ramps, or edges. Instead, we advocate a generalizable dual-arm configuration and establish a suite of Bimanual Non-prehensile Manipulation Primitives (BiNoMaP). Second, we depart from the prevailing RL-based paradigm and propose a three-stage, RL-free framework to learn non-prehensile skills. Specifically, we begin by extracting bimanual hand motion trajectories from video demonstrations. Due to visual inaccuracies and morphological gaps, these coarse trajectories are difficult to transfer directly to robotic end-effectors. To address this, we propose a geometry-aware post-optimization algorithm that refines raw motions into executable manipulation primitives that conform to specific motion patterns. Beyond instance-level reproduction, we further enable category-level generalization by parameterizing the learned primitives with object-relevant geometric attributes, particularly size, resulting in adaptable and general parameterized manipulation primitives. We validate BiNoMaP across a range of representative bimanual tasks and diverse object categories, demonstrating its effectiveness, efficiency, and superior generalization capability.

Primary Area: applications to robotics, autonomy, planning

Submission Number: 2567