FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
复制标题
DOI：
10.48550/arxiv.2303.02346
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Zhou Xian;Bo Zhu;Zhenjia Xu;H. Tung;A. Torralba;Katerina Fragkiadaki;Chuang Gan
中科院分区：
文献类型：
--
作者：
Zhou Xian;Bo Zhu;Zhenjia Xu;H. Tung;A. Torralba;Katerina Fragkiadaki;Chuang Gan
人类在日常生活中操纵各种流体：创建拿铁艺术，从水中舀起漂浮物，滚动冰淇淋蛋卷等。由于流体的多方面复杂性，使用机器人在这些日常环境中增加或取代人类劳动力仍然是一项具有挑战性的任务。机器人流体操作的先前研究主要考虑在简单任务设置中由理想牛顿模型控制的流体（例如，浇注）。然而，绝大多数现实世界的流体系统表现出其复杂性方面的流体的复杂的材料行为和多组分的相互作用，这两者都远远超出了现有文献的范围。为了评估机器人学习算法对理解和与这种复杂的流体系统进行交互，需要一个具有多功能仿真功能和完善任务的综合虚拟平台。在这项工作中，我们介绍了FluidLab，一个模拟环境，涉及复杂的流体动力学的操纵任务的不同集合。这些任务解决固体和流体之间以及多种流体之间的相互作用。我们平台的核心是一个完全可微分的物理模拟器FluidEngine，为各种材料类型及其耦合提供GPU加速模拟和梯度计算。我们通过在我们的平台上评估一组强化学习和轨迹优化方法，确定了流体操作学习的几个挑战。为了解决这些挑战，我们提出了几个特定领域的优化方案，再加上可微物理，这是经验证明是有效的，在解决流体系统的非凸和非光滑特性的优化问题。此外，我们展示了合理的模拟到真实的转移部署优化的轨迹在现实世界中的设置。
Humans manipulate various kinds of fluids in their everyday life: creating latte art, scooping floating objects from water, rolling an ice cream cone, etc. Using robots to augment or replace human labors in these daily settings remain as a challenging task due to the multifaceted complexities of fluids. Previous research in robotic fluid manipulation mostly consider fluids governed by an ideal, Newtonian model in simple task settings (e.g., pouring). However, the vast majority of real-world fluid systems manifest their complexities in terms of the fluid's complex material behaviors and multi-component interactions, both of which were well beyond the scope of the current literature. To evaluate robot learning algorithms on understanding and interacting with such complex fluid systems, a comprehensive virtual platform with versatile simulation capabilities and well-established tasks is needed. In this work, we introduce FluidLab, a simulation environment with a diverse set of manipulation tasks involving complex fluid dynamics. These tasks address interactions between solid and fluid as well as among multiple fluids. At the heart of our platform is a fully differentiable physics simulator, FluidEngine, providing GPU-accelerated simulations and gradient calculations for various material types and their couplings. We identify several challenges for fluid manipulation learning by evaluating a set of reinforcement learning and trajectory optimization methods on our platform. To address these challenges, we propose several domain-specific optimization schemes coupled with differentiable physics, which are empirically shown to be effective in tackling optimization problems featured by fluid system's non-convex and non-smooth properties. Furthermore, we demonstrate reasonable sim-to-real transfer by deploying optimized trajectories in real-world settings.