用图像数据训练动态系统模型，让机器人更好理解世界变化。
Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive Architectures
- 结合序列嵌入与神经微分方程构建连续时间状态空间。
- 通过收缩嵌入和李普希茨约束使隐状态空间结构更有序。
- 仅用图像就能建模摆动系统，适合机器人控制与估计任务。
随着联合嵌入预测架构（JEPAs）展现出比重建类方法更强的能力，本文提出一种新方法，从任意观测数据中构建连续时间动态系统的世界模型。该方法将序列嵌入与神经常微分方程（neural ODEs）结合，采用强制嵌入收缩性与状态转移李普希茨常数的损失函数，构建结构良好的隐状态空间。实验表明，仅使用图像数据即可生成单摆系统的结构化隐状态空间模型。这一方法为开发更通用的控制算法与估计技术提供了新路径，在机器人领域具有广泛应用前景。
原文摘要 · Abstract (English)
With the advent of Joint Embedding Predictive Architectures (JEPAs), which appear to be more capable than reconstruction-based methods, this paper introduces a novel technique for creating world models using continuous-time dynamic systems from arbitrary observation data. The proposed method integrates sequence embeddings with neural ordinary differential equations (neural ODEs). It employs loss functions that enforce contractive embeddings and Lipschitz constants in state transitions to construct a well-organized latent state space. The approach's effectiveness is demonstrated through the generation of structured latent state-space models for a simple pendulum system using only image data. This opens up a new technique for developing more general control algorithms and estimation techniques with broad applications in robotics.
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。