Learning Deep Dynamical Systems using Stable Neural ODEs
CoRR(2024)
摘要
Learning complex trajectories from demonstrations in robotic tasks has been
effectively addressed through the utilization of Dynamical Systems (DS).
State-of-the-art DS learning methods ensure stability of the generated
trajectories; however, they have three shortcomings: a) the DS is assumed to
have a single attractor, which limits the diversity of tasks it can achieve, b)
state derivative information is assumed to be available in the learning process
and c) the state of the DS is assumed to be measurable at inference time. We
propose a class of provably stable latent DS with possibly multiple attractors,
that inherit the training methods of Neural Ordinary Differential Equations,
thus, dropping the dependency on state derivative information. A diffeomorphic
mapping for the output and a loss that captures time-invariant trajectory
similarity are proposed. We validate the efficacy of our approach through
experiments conducted on a public dataset of handwritten shapes and within a
simulated object manipulation task.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要