動的システム間の対応関係を学習する手法
Learning to Correspond Dynamical Systems
2つの動的システムの軌道データから共有潜在状態空間と潜在ダイナミクスを学習し、一方のシミュレーションから他方の動きを生成できる対応付け手法を提案。
著者: Nam Hee Kim, Zhaoming Xie, Michiel van de Panne
分類: cs.LG, cs.RO, stat.ML
原文アブストラクト
Many dynamical systems exhibit similar structure, as often captured by hand-designed simplified models that can be used for analysis and control. We develop a method for learning to correspond pairs of dynamical systems via a learned latent dynamical system. Given trajectory data from two dynamical systems, we learn a shared latent state space and a shared latent dynamics model, along with an encoder-decoder pair for each of the original systems. With the learned correspondences in place, we can use a simulation of one system to produce an imagined motion of its counterpart. We can also simulate in the learned latent dynamics and synthesize the motions of both corresponding systems, as a form of bisimulation. We demonstrate the approach using pairs of controlled bipedal walkers, as well as by pairing a walker with a controlled pendulum.
