Lazy-MOSAIC:用学习到的技能效果世界模型加速机器人操作规划
Lazy-MOSAIC: Accelerating Skill-Centric Manipulation Planning with Learned Skill-Effect World Models
如果你的机器人要在长时程任务里从技能库中挑动作,这篇论文给了一条提速路子:用学习型世界模型毫秒级预筛候选技能,仿真只花在刀刃上,比 MOSAIC 全量仿真省得多,成功率还不掉。做操作规划的工程团队可以看看。
论文提出 Lazy-MOSAIC,一个面向长时程机器人操作的懒规划框架,是对先前 MOSAIC 方法的加速改进。MOSAIC 让参数化技能引导非序列化搜索,但每个候选技能都要付出完整物理仿真成本。Lazy-MOSAIC 改为先用一个廉价的学习型技能效果世界模型,在不到一毫秒内预测技能的可行性与执行后的世界状态,再把昂贵的仿真集中在少数有希望的候选技能上。
当某个假设被仿真推翻时,系统只修复搜索中受影响的部分,而返回计划中的每个技能仍保证在仿真中验证过,兼顾速度与正确性。研究团队在难度递增的杂乱货架取物任务上评测,并在真实物理机器人上做了演示。
结果显示,Lazy-MOSAIC 的规划速度显著快于基线,仿真查询次数更少,同时在所有设置中成功率持平或超过基线。对做机器人操作与任务规划的开发者,这个“先廉价预测、后昂贵验证”的思路可以借鉴到自己的技能库搜索问题中。
Lazy-MOSAIC: Accelerating Skill-Centric Manipulation Planning with Learned Skill-Effect World Models
Long-horizon manipulation tasks require a robot to perform a sequence of physical interactions with its environment, typically combining several different skills. Planning such behaviors efficiently is challenging: given a library of parameterized skills, solutions lie in a vast hybrid space of skill sequences and their parameters, and evaluating each candidate skill's feasibility and effect with a high-fidelity world model such as a physics simulator is computationally expensive. MOSAIC, a recent skill-centric approach, lets the skills guide a non-sequential search toward the regions of this space where they are likely to succeed; however, it pays the full cost of simulation for every parameterized skill it considers. In this work, we introduce Lazy-MOSAIC, a lazy planning framework that instead searches over hypothesized skill outcomes. A cheap learned skill-effect world model predicts, in a fraction of a millisecond, a skill's feasibility and the world state it produces. Lazy-MOSAIC then uses these predictions to focus expensive simulation on promising candidate skills and, when a hypothesis is invalidated, repairs only the affected part of the search, while ensuring that every skill in a returned plan is validated in simulation. We evaluate Lazy-MOSAIC on cluttered-shelf retrieval tasks of increasing difficulty and demonstrate it on a physical robot, showing that it plans substantially faster than baselines with fewer simulator queries, while matching or exceeding their success rate in every setting. Visit skill-mosaic.github.io.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:Lazy-MOSAIC、机器人操作、世界模型、任务规划,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Itamar Mishani, Mukund Krishnakumar, Oren Salzman, Maxim Likhachev),经 AITOP 多维评分管线结构化提炼。