arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.15469cs.RO
收藏

学习上下文感知的神经ODE动力学用于自适应机器人控制

Learning Context-Aware Neural ODE Dynamics for Adaptive Robotic Control

University of California, Berkeley(加州大学伯克利分校);Aalto University(阿尔托大学);YaiYai Ltd(YaiYai有限公司)

Shao-Yi Yu, Jen-Wei Wang, Maya Horii, Masayoshi Tomizuka, Vikas Garg

AI总结:

提出基于神经ODE的上下文感知动力学模型,通过两阶段训练从状态-动作历史推断环境因素,实现模型预测控制下的自适应,在四旋翼、Sphero BOLT和Fanuc机械臂上验证了时空变化环境下的有效性。

摘要:

部署在不确定和动态变化环境中的机器人系统经常面临接触条件、空气动力学效应和外部干扰的变化,这些挑战了可靠的控制。为了在基于模型的控制下保持有效性,这些系统需要能够适应此类变化的动力学模型,特别是在直接获取完整环境信息受限的情况下。为了实现适应性并促进与模型预测控制的集成,我们提出了一种基于神经常微分方程的上下文感知动力学模型,该模型使用两阶段训练过程从状态-动作历史推断环境因素。我们在多种机器人平台上验证了该方法,包括仿真中的四旋翼,以及真实世界实验中的Sphero BOLT机器人和Fanuc机械臂。结果表明,我们的方法有效地适应了不同任务中时间和空间变化的环境变化。视频可在https://youtu.be/PY0sNyF2rqE 获取,源代码可在https://github.com/syyu410-yu/context-aware-neural-ode-control.git 获取。

英文摘要:

Robotic systems deployed in uncertain and dynamically changing environments often face variations in contact conditions, aerodynamic effects, and external disturbances that challenge reliable control. To remain effective under model-based control, these systems require dynamics models that can adapt to such changes, especially when direct access to complete environmental information is limited. To enable adaptability and facilitate integration with model predictive control, we propose a context-aware dynamics model based on neural ordinary differential equations, which infers environmental factors from state-action histories using a two-phase training procedure. We validate the approach across diverse robotic platforms, including a quadrotor in simulation, as well as a Sphero BOLT robot and a Fanuc manipulator in real-world experiments. The results demonstrate that our method effectively adapts to temporally and spatially varying environmental changes across different tasks. Videos are available at https://youtu.be/PY0sNyF2rqE , and the source code is available at https://github.com/syyu410-yu/context-aware-neural-ode-control.git .

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。

↑