STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation
STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation
复制标题
STORM：反应操纵的快速联合空间模型预测控制的集成框架
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Byron Boots
中科院分区：
文献类型：
--
作者：
M. Bhardwaj;Balakumar Sundaralingam;Arsalan Mousavian;Nathan D. Ratliff;D. Fox;Fabio Ramos;Byron Boots
基于采样的模型预测控制（MPC）是一种很有前途的工具，用于具有复杂、非光滑动力学和成本函数的机器人的反馈控制。然而，基于采样的MPC算法对计算量的要求一直是其在现实世界中应用于高维机器人操作问题的关键瓶颈。以前的方法通过在任务空间中运行MPC，同时依赖于低级操作空间控制器进行联合控制来解决这个问题。然而，由于在MPC公式中没有使用机器人的关节空间，现有的方法不能直接考虑与任务空间无关的约束，如避免关节限制、奇异构型和链路碰撞。在本文中，我们开发了一个快速的、基于关节空间采样的机械手MPC系统，该系统使用gpu有效地并行化。我们的方法可以处理任务和关节空间约束，同时计算下一个控制命令的时间小于8ms~（125Hz）。此外，我们的方法可以利用从原始传感器数据中学习到的成本函数，将感知紧密地集成到控制问题中。我们通过将其部署在Franka Panda机器人上以执行各种动态操作任务来验证我们的方法。我们研究了不同的成本公式和MPC参数对综合行为的影响，并提供了关键的见解，为基于采样的MPC在机械手中的应用铺平了道路。我们还提供高度优化的开源代码，供更广泛的机器人学习和控制社区使用。实验视频可以在https://sites.google.com/view/manipulation-mpc上找到
Sampling-based model-predictive control (MPC) is a promising tool for feedback control of robots with complex, non-smooth dynamics, and cost functions. However, the computationally demanding nature of sampling-based MPC algorithms has been a key bottleneck in their application to high-dimensional robotic manipulation problems in the real world. Previous methods have addressed this issue by running MPC in the task space while relying on a low-level operational space controller for joint control. However, by not using the joint space of the robot in the MPC formulation, existing methods cannot directly account for non-task space related constraints such as avoiding joint limits, singular configurations, and link collisions. In this paper, we develop a system for fast, joint space sampling-based MPC for manipulators that is efficiently parallelized using GPUs. Our approach can handle task and joint space constraints while taking less than 8ms~(125Hz) to compute the next control command. Further, our method can tightly integrate perception into the control problem by utilizing learned cost functions from raw sensor data. We validate our approach by deploying it on a Franka Panda robot for a variety of dynamic manipulation tasks. We study the effect of different cost formulations and MPC parameters on the synthesized behavior and provide key insights that pave the way for the application of sampling-based MPC for manipulators in a principled manner. We also provide highly optimized, open-source code to be used by the wider robot learning and control community. Videos of experiments can be found at: https://sites.google.com/view/manipulation-mpc
DOI：
10.15607/rss.2019.xv.033
发表时间：
2019-02
期刊：
ArXiv
影响因子：
--
作者：
Nolan Wagener;Ching-An Cheng;Jacob Sacks;Byron Boots
通讯作者：
Nolan Wagener;Ching-An Cheng;Jacob Sacks;Byron Boots