Machine learning helps robots handle flexible cables with control
Manipulation of Deformable Linear Objects Using Model Predictive Path Integral Control with Bidirectional Long Short-Term Memory Learning
Robotics
Summary
Cables and similar flexible objects are hard for robots to manage because they bend and stretch in complicated ways. The paper presents a method where a type of neural network called a bidirectional Long Short-Term Memory is trained using simulated data to predict how these objects move. Then, a control technique called Model Predictive Path Integral (MPPI) control uses these predictions to guide the robot in handling cables accurately. The authors tested this approach both in simulation and with real experiments, showing it works well.
What this means in practice
- •For robotics engineers: Enable robots to manipulate flexible cables more accurately and efficiently by integrating learned dynamics with advanced control methods.
- •For manufacturing automation teams: Automate cable handling tasks such as wiring and assembly with improved reliability using a model-based learning control approach.
Authors
Lukas Zeh, Johannes Meiwaldt, Zexu Zhou, Armin Lechler, Alexander Verl
Abstract
The manipulation of Deformable Linear Objects (DLOs) such as cables poses a significant challenge for automation due to their infinite degrees of freedom and non-linear dynamics. In this paper we present a machine learning based optimal control approach for the manipulation of DLOs. This approach is divided into two main components: modeling and control. For modeling the dynamics of the DLO, we propose a learning based approach using a bidirectional Long Short-Term Memory (biLSTM) network. The biLSTM network is trained on synthetic data generated by the MuJoCo physics engine. For manipulating the DLO, a model predictive control strategy that employs Model Predictive Path Integral (MPPI) control is selected. The proposed approach is evaluated through simulation and experiments. The results demonstrate the effectiveness of the proposed method in achieving accurate and efficient manipulation of DLOs.