Model Free Control of a Soft Pneumatic Segment
This video complements the article García-Samartín, J.F. et al, "Model-Free Control of a Soft Pneumatic Segment".
This video presents the steps required to achieve closed-loop control of one of the segments of PAUL, a robot previously featured on • PtP control of Pneumatic Soft Robot PAUL .
The first step is to study the behaviour of the piezoresistive sensors inserted in the robot, which exhibit highly non-linear behaviour. The goal is to model the relationship between inflation times and robot positions using a neural network. The video's third part shows the robot in operation.
Abstract: SSoft Robotics faces challenges in attaining control methods that ensure precision from hard-to-model actuators and sensors. This study focuses on closed-chain control of a segment of PAUL, a modular pneumatic soft arm, using elastomeric-based resistive sensors with negative piezoresistive behaviour irrespective of ambient temperature. PAUL's performance relies on bladder inflation and deflation times. The control approach employs two neural networks: the first translates position references into valve inflation times, and the second acts as a state observer to estimate bladder inflation times using sensor data. Following training, the system achieves position errors of 4.59mm, surpassing results from other soft robots presented in the literature. The study also explores system modularity, assessing performance under external loads from non-actuated segments.
Cite: García-Samartín, J.F.; Molina-Gómez, R.; Barrientos, A. Model-Free Control of a Soft Pneumatic Segment. Biomimetics, 2024