PhyScensis: 基于物理的LLM代理用于复杂物理场景布置
PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement
AI总结：
PhyScensis通过物理引擎驱动的LLM代理框架，生成复杂物理场景布局，提升机器人操作中的场景复杂性和物理准确性。
摘要：
自动生成交互式3D环境对于扩大模拟中的机器人数据收集至关重要。尽管先前的工作主要集中在3D资产放置上，但往往忽略了物体之间的物理关系（例如接触、支撑、平衡和包容），这对于创建复杂的、逼真的操作场景如桌面布置、书架整理或箱子打包至关重要。与经典的3D布局生成相比，生成复杂的物理场景引入了额外的挑战：（a）更高的物体密度和复杂性（例如，一个小型书架可能存放几十本书），（b）更丰富的支撑关系和紧凑的空间布局，以及（c）需要准确建模空间放置和物理属性。为了解决这些挑战，我们提出了PhyScensis，一个由物理引擎驱动的LLM代理框架，用于生成具有高复杂性的物理场景配置。具体而言，我们的框架由三个主要组件组成：一个LLM代理迭代地提出带有空间和物理谓词的资产；一个求解器，配备物理引擎，将这些谓词转化为3D场景；以及求解器的反馈指导代理进一步完善和丰富配置。此外，我们的框架通过概率编程实现对细粒度文本描述和数值参数（例如相对位置、场景稳定性）的强可控性。实验结果表明，我们的方法在场景复杂性、视觉质量和物理准确性方面均优于先前的方法，提供了一个统一的管道，用于为机器人操作生成复杂的物理场景布局。
英文摘要：
Automatically generating interactive 3D environments is crucial for scaling up robotic data collection in simulation. While prior work has primarily focused on 3D asset placement, it often overlooks the physical relationships between objects (e.g., contact, support, balance, and containment), which are essential for creating complex and realistic manipulation scenarios such as tabletop arrangements, shelf organization, or box packing. Compared to classical 3D layout generation, producing complex physical scenes introduces additional challenges: (a) higher object density and complexity (e.g., a small shelf may hold dozens of books), (b) richer supporting relationships and compact spatial layouts, and (c) the need to accurately model both spatial placement and physical properties. To address these challenges, we propose PhyScensis, an LLM agent-based framework powered by a physics engine, to produce physically plausible scene configurations with high complexity. Specifically, our framework consists of three main components: an LLM agent iteratively proposes assets with spatial and physical predicates; a solver, equipped with a physics engine, realizes these predicates into a 3D scene; and feedback from the solver informs the agent to refine and enrich the configuration. Moreover, our framework preserves strong controllability over fine-grained textual descriptions and numerical parameters (e.g., relative positions, scene stability), enabled through probabilistic programming for stability and a complementary heuristic that jointly regulates stability and spatial relations. Experimental results show that our method outperforms prior approaches in scene complexity, visual quality, and physical accuracy, offering a unified pipeline for generating complex physical scene layouts for robotic manipulation.
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。
