University of Twente Student Theses


A general optimization framework for soft robotic actuators with analytical gradients

Wilmes, Daniel (2022) A general optimization framework for soft robotic actuators with analytical gradients.

[img] PDF
Abstract:The following thesis A general optimization framework for pressure-driven soft robotic actuators with analytical gradients is aimed at developing a system that allows defining an arbitrary loss functions in a soft actuators simulation, and optimize towards any parameter in the simulation using analytical gradients. This is motivated by inherent difficulties in modelling and development of both soft robots and their controllers due to the non-linear and time variant properties of the forces acting on them. Furthermore, solutions from comparable literature tend to lack generality and restrict themselves to certain use-cases or offer methods to work around the issues but are more time consuming in return. A literature study is first conducted related to soft body simulation and optimization procedures to find valid approaches in modelling soft robotic actuators and perform autodifferentiation. After an approach is chosen and implemented, a verification of the simulation is performed by comparing multiple simulations to an established FEMsolver. Afterwards the issue of exploding gradients for auto-differentiation is adressed by analysing the mathematical background of the problem and proposing a solution. To demonstrate the use of the developed 3D optimization framework for controller synthesis, a small neural network feedforward controller is set-up for a pneumatic endoscope actuator model with three pressure chambers and trained using the derived gradients from the simulation. Furthermore, a metaoptimization scheme is presented, where the damping factor of the simulation is split into 50ms time-windows and optimized with the intention of shortening the time until the deformation of the actuator reaches its final state. The developed system is shown to be able to derive meaningful gradients that can be used to optimize different components of the simulation. The proposed scaling scheme to avoid exploding gradients requires the user to fine-tune a few parameters to get optimal results. The scheme has been shown to produce useful gradients for an exemplary pressure optimization and controller synthesis. In comparison to reinforcement learning, the controller synthesis requires about 1 order of magnitude less iterations steps to converge in addition to more smooth and reduced loss fluctuation over the course of training. The meta-optimization managed to reduce the required number of time-steps by approximately 25% with some caveats. The loss function showed strong signs of being ill-defined but the optimization still succeeded based on the gradients and changes in the damping factors, which implies that more complex and well-behaved formulations have the potential to give better results.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:53 electrotechnology, 54 computer science
Programme:Electrical Engineering MSc (60353)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page