外观
论文arXiv 2610.2056014 天前
PhySGA：面向可泛化和交互式3D组合的物理空间扎根智能体框架
原文链接：PhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Composition（arXiv 2610.20560 · 发布日期：2026-10-14）
PhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Composition
PhySGA针对复杂3D物体组合难题，结合智能体探索与物理仿真，并在Isaac Sim中验证效果。
核心要点
- 现有LLM坐标预测或扩散先验方法依赖静态先验，难处理悬挂、沉降和隐藏包含。
- 框架通过智能体探索与物理仿真，支持刚体、关节体和可变形物体的交互式装配。
- Assembly Agent负责全局规划与粗调，Critic Agent诊断接触动力学并闭环细调。
- Isaac Sim实验显示，其在关系保真度、物理合理性和视觉质量上显著优于已有方法。
验证范围与局限：验证范围为Isaac Sim内的仿真实验。
英文摘要 (Abstract)
3D object composition is pivotal to digital content creation and robot simulation, while also serving as a critical testbed for physical intelligence in foundation models. Previous methods either leverage large language models to directly predict object coordinates, or utilize generative diffusion priors to synthesize composite images for visual alignment, both of which rely on static priors in digital spaces. However, these methods consistently struggle with complex compositions such as precise hanging, gravity-driven settling and hidden containment, as these tasks require interactive construction processes involving global planning, fine-grained alignment, and physical simulation. To address these challenges, we propose PhySGA, a Physics-Space Grounded Agentic Framework for 3D composition via agent exploration and physical simulation, enabling the universal interactive assembly of rigid, articulated, and deformable objects. Directly applying vanilla LLMs or VLMs to this task proves insufficient, as current models inherently lack grounded physical understanding and interactive construction experience. To overcome this limitation, we design a collaborative feedforward-feedback architecture: an Assembly Agent focuses on geometric and kinematic reasoning for global step planning and coarse adjustment, while a Critic Agent reasons over contact dynamics for simulator state diagnosis and fine-grained closed-loop correction. Furthermore, Action Routers map semantic planning and analysis onto executable physical primitives within the simulator, while a task-specific Self-Evolving Skill Library distills historical trial-and-error feedback into reusable experiences, boosting success rates and minimizing exploration attempts. Extensive experiments within Isaac Sim demonstrate that PhySGA significantly surpasses existing methods in relation fidelity, physical plausibility, and visual quality.
作者：Weichen Lyu, Chong Xia, Mingyu Dong, Long Xu, Shengjun Zhang, Yueqi Duan
来源
本页事实对应的公开页面，以原文为准。