arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.40333cs.CV
收藏

RFW-A:面向500个类别的40万件关节资产的智能体程序化生成

RFW-A: Agentic Procedural Generation of 400K Articulated Assets over 500 Categories

Alibaba Group(阿里巴巴集团);Tsinghua University(清华大学);Peking University(北京大学);Nanyang Technological University(南洋理工大学);Nanjing University(南京大学);The Hong Kong University of Science and Technology(香港科技大学)
Yuanbo Lyu, Changjian Pan, Saining Zhang, Yi Yang, Peishuo Li, Zhiheng Li, Jialu Liu, Junhao Chen, Jiawei Weng, Yupeng Gao, Weiqing Xiao, Wenyi Li, Jiarui Guo, … 展开作者

Yuanbo Lyu, Changjian Pan, Saining Zhang, Yi Yang, Peishuo Li, Zhiheng Li, Jialu Liu, Junhao Chen, Jiawei Weng, Yupeng Gao, Weiqing Xiao, Wenyi Li, Jiarui Guo, Rui Zhang, Jingrun Du, Weiyi Lin, Zenan Meng, Hu Wei, Lin Qu, Zongzheng Zhang, Hao Zhao, Chaojian Li

AI总结:

提出RFW-A结合智能体合成与程序化生成构建关节资产,构建了含40万件资产的RFW-A-400K,降低成本且提升关节估计与策略迁移性能。

摘要:

高质量的关节资产对于具身感知、仿真和操作至关重要,但大规模构建这类资产仍然困难。手动标注和程序化建模需要大量人力。近期的智能体系统通过程序合成实现资产构建自动化,但会为每件新资产重复进行代价高昂的推理和优化。我们的核心发现是,同一类别内的资产尽管结构和外观存在差异,却可共享构建逻辑。因此,智能体合成与程序化生成具有互补性:智能体可构建可复用的程序,而程序化执行则可在多个样本中复用生成的逻辑。为此,我们提出RFW-A,它将二者结合形成新的关节资产生成范式。从现有关节程序出发,RFW-A将可复用组件及其依赖组织为类别级生成器。智能体在采样的配置和运动状态下测试并优化这些生成器。一旦生成器构建并验证完成,即可通过程序化执行生成多样化资产,无需额外模型调用或 token 费用。生成器创作的预估 API 成本平均为10.62美元,在200件资产上摊销后每件为0.05美元,而作为基准的逐件智能体合成则为每件1.24美元。利用RFW-A,我们构建了包含500多个类别的40万件可仿真关节资产的RFW-A-400K。实验表明,该资产在物理仿真器中具有较高的结构和运动学有效性及稳定的执行性能。除资产有效性外,使用RFW-A-400K训练可提升对可见和未见类别的部件级关节估计,而使用检索及程序编辑资产在仿真中训练的策略可零样本迁移到真实关节对象。

英文摘要:

High-quality articulated assets are essential for embodied perception, simulation, and manipulation, yet constructing them at scale remains difficult. Manual annotation and procedural modeling require substantial human effort. Recent agentic systems automate asset construction through program synthesis, but repeat costly reasoning and refinement for every new asset. Our key observation is that assets within a category can share construction logic despite variations in structure and appearance. Agentic synthesis and procedural generation are therefore complementary: agents can construct reusable programs, while procedural execution reuses the resulting logic across many samples. We therefore present RFW-A, which combines the two in a new articulated-asset generation paradigm. Starting from existing articulated programs, RFW-A organizes reusable components and their dependencies into category-level generators. Agents test and refine these generators across sampled configurations and motion states. Once constructed and validated, the generators produce diverse assets through procedural execution with no further model calls or token charges. The estimated API cost of generator authoring averages $10.62, amortizing to $0.05 per asset over 200 assets, versus $1.24 for the sampled per-asset agentic synthesis baseline. Using RFW-A, we built RFW-A-400K, containing over 400K sim-ready articulated assets across more than 500 categories. Experiments show high structural and kinematic validity and stable execution across physics simulators. Beyond asset validity, training with RFW-A-400K improves part-level articulation estimation on seen and unseen categories, while policies trained in simulation with retrieved and program-edited assets transfer zero-shot to real articulated objects.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

相关深度报道

↑