HSC-VLA: Hierarchical Scene-Clearing for Robust Bimanual Manipulation in Dense Clutter
This work provides a significant improvement in robust bimanual manipulation for robots operating in densely cluttered environments, such as supermarket shelves, by improving instruction-following and reducing attention dilution.
This paper addresses the problem of instruction-following failures in high-density manipulation environments for Vision-Language-Action models. The proposed HSC-VLA framework achieves 86.7% aggregate success in dense clutter, outperforming the best monolithic baseline by 52.4%, and demonstrates strong long-horizon performance with 72% on clutter sorting and 66% on restocking.
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 ($π_0$-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.