提出SPARTA框架，让机器人学会捏碎、涂抹、切割等渐进式操作。
Mash, Spread, Slice! Learning to Manipulate Object States via Visual Spatial Progress
- 基于空间渐进变化的结构模式，用视觉分割识别可操作与已改变区域。
- 在10种真实物体上实现3项任务，训练速度和准确率显著优于基线方法。
- 适合需要精细控制或快速部署的机器人操作场景，如厨房或工厂应用。
多数机器人操作聚焦于改变物体的运动状态：抓取、放置、开启或旋转。然而，大量现实世界任务涉及另一类状态变化——如捏碎、涂抹或切割，其物理与视觉状态逐步演变，且不必然伴随位置移动。本文提出SPARTA，首个统一处理此类对象状态变化操作的框架。核心洞察是：这些任务共享一种结构模式——以对象为中心的空间渐进变化，可表示为区域从可操作状态向已改变状态的转化。基于此，SPARTA整合了空间渐进的对象变化分割图，构建视觉技能以感知特定任务中可操作与已改变区域，生成：a）剥离外观变化的结构化策略观测；b）捕捉时间增量进展的密集奖励。该框架支持两种策略变体：无需示范或仿真即可实现精细控制的强化学习，以及适用于快速轻量部署的贪心控制。我们在真实机器人上验证了SPARTA在10种不同实物上的三项挑战性任务，相比稀疏奖励与视觉目标条件基线，显著提升了训练效率与精度。结果表明，进度感知的视觉表征是更广泛对象状态操作任务的通用基础。项目主页：https://vision.cs.utexas.edu/projects/sparta-robot
原文摘要 · Abstract (English)
Most robot manipulation focuses on changing the kinematic state of objects: picking, placing, opening, or rotating them. However, a wide range of real-world manipulation tasks involve a different class of object state change--such as mashing, spreading, or slicing--where the object's physical and visual state evolve progressively without necessarily changing its position. We present SPARTA, the first unified framework for the family of object state change manipulation tasks. Our key insight is that these tasks share a common structural pattern: they involve spatially-progressing, object-centric changes that can be represented as regions transitioning from an actionable to a transformed state. Building on this insight, SPARTA integrates spatially progressing object change segmentation maps, a visual skill to perceive actionable vs. transformed regions for specific object state change tasks, to generate a) structured policy observations that strip away appearance variability, and b) dense rewards that capture incremental progress over time. These are leveraged in two SPARTA policy variants: reinforcement learning for fine-grained control without demonstrations or simulation; and greedy control for fast, lightweight deployment. We validate SPARTA on a real robot for three challenging tasks across 10 diverse real-world objects, achieving significant improvements in training time and accuracy over sparse rewards and visual goal-conditioned baselines. Our results highlight progress-aware visual representations as a versatile foundation for the broader family of object state manipulation tasks. Project website: https://vision.cs.utexas.edu/projects/sparta-robot
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。