arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.09178cs.RO
收藏

一种融合物理信息的示范引导学习框架用于颗粒材料操控

A Physics-informed Demonstration-guided Learning Framework for Granular Material Manipulation

School of Engineering, Cardiff University(工程学院,卡迪夫大学);School of Computer Science and Informatics, Cardiff University(计算机科学与信息学学院,卡迪夫大学)

Minglun Wei, Xintong Yang, Yu-Kun Lai, Seyed Amir Tafrishi, Ze Ji

AI总结:

本文提出一种融合物理信息的示范引导学习框架,通过可微分模拟器和梯度优化生成示范,实现高效学习颗粒材料操控任务。

摘要:

由于颗粒材料复杂的物理特性,机器人学习操控此类材料的研究大多要么忽视其物理特性,要么使用替代模型来近似其物理特性。基于精确建模获得的物理信息学习操控颗粒材料仍是一个未解决的问题。本文提出通过Taichi编程语言构建可微分的基于物理的模拟器,并开发一种由梯度优化生成的示范引导学习框架来加速学习过程,从而消除传统方法中昂贵的数据收集和模型训练。实验结果表明,我们的方法通过灵活的设计,训练出能够执行在模拟和真实环境中运输颗粒材料任务的稳健策略,超越了标准强化学习、模仿学习和先前特定任务的颗粒操控方法。

英文摘要:

Due to the complex physical properties of granular materials, research on robot learning for manipulating such materials predominantly either disregards the consideration of their physical characteristics or uses surrogate models to approximate their physical properties. Learning to manipulate granular materials based on physical information obtained through precise modelling remains an unsolved problem. In this paper, we propose to address this challenge by constructing a differentiable physics-based simulator for granular materials using the Taichi programming language and developing a learning framework accelerated by demonstrations generated through gradient-based optimisation on non-granular materials within our simulator, eliminating the costly data collection and model training of prior methods. Experimental results show that our method, with its flexible design, trains robust policies that are capable of executing the task of transporting granular materials in both simulated and real-world environments, beyond the capabilities of standard reinforcement learning, imitation learning, and prior task-specific granular manipulation methods.

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。

↑