HSC-VLA: Hierarchical Scene-Clearing for Robust Bimanual Manipulation in Dense Clutter

TL;DR

HSC-VLA introduces a hierarchical approach to dense clutter manipulation, decoupling reasoning from execution, significantly improving success rates in complex, cluttered environments.

Contribution

The paper presents HSC-VLA, a hierarchical framework that enhances bimanual manipulation in cluttered scenes by scene clearing and task decomposition, outperforming monolithic models.

Findings

Achieves 86.7% success in dense clutter, surpassing baseline by 52.4%.

Demonstrates strong performance on long-horizon tasks like sorting and restocking.

Exhibits robustness and effective failure recovery in complex environments.

Abstract

Modern Vision--Language--Action models often suffer from critical instruction-following failures in high-density manipulation environments, where task-irrelevant visual clutter dilutes attention, corrupts grounding, and substantially degrades performance in complex long-horizon scenarios. To overcome the representation bottleneck of monolithic end-to-end architectures, we propose HSC-VLA, a hierarchical framework that decouples high-level visual-semantic reasoning from low-level, high-frequency sensorimotor execution through an explicit scene-clearing abstraction. HSC-VLA employs a high-level Brain to decompose long-horizon tasks and to generate task-specific scene masks that preserve task-relevant geometry while suppressing distractors. The filtered observations are then passed to a low-level Cerebellum, a diffusion-based policy that performs bimanual manipulation using only mask-filtered vision and proprioception. Extensive experiments in densely cluttered supermarket shelves demonstrate that HSC-VLA achieves 86.7\% aggregate success under high-density clutter, surpassing the best monolithic baseline ($\pi_0$-Full FT at 34.3\%) by 52.4\%. HSC-VLA also exhibits strong long-horizon performance, reaching 72\% on clutter sorting and 66\% on restocking, demonstrating strong robustness and effective failure recovery in complex cluttered manipulation.