Learned Dynamics of Electrothermally-Actuated Soft Robot Limbs Using LSTM Neural Networks

11/08/2021
by   Rohan K. Mehta, et al.
0

Modeling the dynamics of soft robot limbs with electrothermal actuators is generally challenging due to thermal and mechanical hysteresis and the complex physical interactions that can arise during robot operation. This article proposes a neural network based on long short-term memory (LSTM) to address these challenges in actuator modeling. A planar soft limb, actuated by a pair of shape memory alloy (SMA) coils and containing embedded sensors for temperature and angular deflection, is used as a test platform. Data from this robot are used to train LSTM neural networks, using different combinations of sensor data, to model both unidirectional (one SMA) and bidirectional (both SMAs) motion. Open-loop rollout results show that the learned model is able to predict motions over extraordinarily long open-loop timescales (10 minutes) with little drift. Prediction errors are on the order of the soft deflection sensor's accuracy, even when using only the actuator's pulse width modulation inputs for learning. These LSTM models can be used in-situ, without extensive sensing, helping to bring soft electrothermally-actuated robots into practical application.

READ FULL TEXT

page 1

page 2

research
10/16/2020

Predicting Playa Inundation Using a Long Short-Term Memory Neural Network

In the Great Plains, playas are critical wetland habitats for migratory ...
research
02/13/2023

Soft Continuum Actuator Tip Position and Contact Force Prediction, Using Electrical Impedance Tomography and Recurrent Neural Networks

Enabling dexterous manipulation and safe human-robot interaction, soft r...
research
10/18/2021

Trajectory Optimization for Thermally-Actuated Soft Planar Robot Limbs

Practical use of robotic manipulators made from soft materials will requ...
research
01/04/2021

High-bandwidth nonlinear control for soft actuators with recursive network models

We present a high-bandwidth, lightweight, and nonlinear output tracking ...
research
11/10/2021

Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word

With the rapid development of AI technology in recent years, there have ...
research
07/31/2020

Predicting heave and surge motions of a semi-submersible with neural networks

Real-time motion prediction of a vessel or a floating platform can help ...
research
05/22/2022

Toward smart composites: small-scale, untethered prediction and control for soft sensor/actuator systems

We present a suite of algorithms and tools for model-predictive control ...

Please sign up or login with your details

Forgot password? Click here to reset