用神经点云模拟机器人操控软体，实现高精度真实到虚拟的仿真。
SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation
- 基于学习的高斯点云建模，统一处理软体、环境与机械臂动作。
- 在真实机器人任务上提升20%重演准确率和泛化能力。
- 适合需要复杂柔性物体操作仿真的机器人研发人员。
在真实到虚拟的机器人软体操控中，模拟复杂交互下的形变动态仍是一大挑战，其动力学由环境作用与机器人动作共同驱动。现有模拟器依赖预设物理模型或数据驱动动力学，缺乏对机器人动作的条件控制，限制了精度、稳定性与泛化性。本文提出SoMA，一种用于软体操控的3D高斯点云模拟器。SoMA在统一潜在神经空间中耦合可变形动态、环境力与机器人关节动作，实现端到端的真实到虚拟仿真。通过对学习到的高斯点云建模交互，实现可控、稳定且长时程的操控，并可在未观测轨迹外泛化，无需预设物理模型。SoMA在真实机器人操控任务上将重演准确率与泛化性能提升20%，支持如长时程布料折叠等复杂任务的稳定仿真。
原文摘要 · Abstract (English)
Simulating deformable objects under rich interactions remains a fundamental challenge for real-to-sim robot manipulation, with dynamics jointly driven by environmental effects and robot actions. Existing simulators rely on predefined physics or data-driven dynamics without robot-conditioned control, limiting accuracy, stability, and generalization. This paper presents SoMA, a 3D Gaussian Splat simulator for soft-body manipulation. SoMA couples deformable dynamics, environmental forces, and robot joint actions in a unified latent neural space for end-to-end real-to-sim simulation. Modeling interactions over learned Gaussian splats enables controllable, stable long-horizon manipulation and generalization beyond observed trajectories without predefined physical models. SoMA improves resimulation accuracy and generalization on real-world robot manipulation by 20%, enabling stable simulation of complex tasks such as long-horizon cloth folding.
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。