用低成本数据提升机器人抓取模型泛化能力，零样本场景成功率最高提升41%。
Boosting Robotic Manipulation Generalization with Minimal Costly Data
- 将操作轨迹拆解为阶段，用易获取的空间推理阶段数据增强模型
- 在少量昂贵物理交互数据中加入大量低成本空间推理数据，成功率提升41%
- 适合需要低成本扩展机器人泛化能力的研究者与开发者
视觉-语言-动作（VLA）模型在具身智能中的应用日益广泛，对多样化操作示范数据的需求也持续增长。然而，数据采集成本高昂，导致各类场景覆盖不足，限制了模型性能。研究发现，大工作空间下的空间推理阶段（SRP）是失败的主要原因，而该阶段数据可低成本获取，具有重要利用价值。本文提出RoboTron-Craft，一种分阶段、低成本的现实操作生成管道；在此基础上，提出RoboTron-Platter框架，将训练轨迹解耦为不同任务阶段，利用大量易收集的SRP数据提升VLA模型的泛化能力。分析表明，以适当比例引入子任务特定的SRP数据可显著促进机器人操作性能，最大化昂贵物理交互阶段（PIP）数据的利用效率。实验显示，在有限的PIP数据中融入大量低成本SRP轨迹，可在零样本场景下将成功率最高提升41%，并实现对新目标的技能迁移。
原文摘要 · Abstract (English)
The growing adoption of Vision-Language-Action (VLA) models in embodied AI intensifies the demand for diverse manipulation demonstrations. However, high costs associated with data collection often result in insufficient data coverage across all scenarios, which limits the performance of the models. It is observed that the spatial reasoning phase (SRP) in large workspace dominates the failure cases. Fortunately, this data can be collected with low cost, underscoring the potential of leveraging inexpensive data to improve model performance. In this paper, we introduce the RoboTron-Craft, a stage-divided and cost-effective pipeline for realistic manipulation generation. Base on this, the RoboTron-Platter method is introduced, a framework that decouples training trajectories into distinct task stages and leverages abundant easily collectible SRP data to enhance VLA model's generalization. Through analysis we demonstrate that sub-task-specific training with additional SRP data with proper proportion can act as a performance catalyst for robot manipulation, maximizing the utilization of costly physical interaction phase (PIP) data. Experiments show that through introducing large proportion of cost-effective SRP trajectories into a limited set of PIP data, we can achieve a maximum improvement of 41\% on success rate in zero-shot scenes, while with the ability to transfer manipulation skill to novel targets. Project available at https://github.com/ notFoundThisPerson/RoboTron-Craft.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。