Active Inference for Integrated State-Estimation, Control, and Learning
Active Inference for Integrated State-Estimation, Control, and Learning
复制标题
DOI：
10.1109/icra48506.2021.9562009
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Mohamed Baioumy;Paul Duckworth;Bruno Lacerda;Nick Hawes
中科院分区：
文献类型：
--
作者：
Mohamed Baioumy;Paul Duckworth;Bruno Lacerda;Nick Hawes
这项工作提出了一种用于机器人操纵器的控制、状态估计和学习模型（超）参数的方法。它基于主动推理框架，该框架在计算神经科学中作为大脑理论而突出，其中行为是通过最小化变分自由能而产生的。首先，我们证明主动推理控制器与 PID 控制等经典方法之间存在直接关系。我们展示了其在机器人操纵器的自适应和鲁棒行为方面的应用，可与最先进的技术相媲美。此外，我们表明，通过学习特定的超参数，我们的方法可以处理未建模的动态、阻尼振荡，并且对于较差的初始参数具有鲁棒性。该方法在“Franka Emika Panda”7 DoF 机械臂上得到了验证。最后，我们强调机器人系统主动推理控制器的局限性。
This work presents an approach for control, state-estimation and learning model (hyper)parameters for robotic manipulators. It is based on the active inference framework, prominent in computational neuroscience as a theory of the brain, where behaviour arises from minimizing variational free-energy. First, we show there is a direct relationship between active inference controllers, and classic methods such as PID control. We demonstrate its application for adaptive and robust behaviour of a robotic manipulator that rivals state-of-the-art. Additionally, we show that by learning specific hyperparameters, our approach can deal with unmodeled dynamics, damps oscillations, and is robust against poor initial parameters. The approach is validated on the ‘Franka Emika Panda’ 7 DoF manipulator. Finally, we highlight limitations of active inference controllers for robotic systems.