Underwater Soft Robot Modeling and Control With Differentiable Simulation

Abstract

Underwater soft robots are challenging to model and control because of their high degrees of freedom and their intricate coupling with water. In this paper, we present a method that leverages the recent development in differentiable simulation coupled with a differentiable, analytical hydrodynamic model to assist with the modeling and control of an underwater soft robot. We apply this method to Starfish, a customized soft robot design that is easy to fabricate and intuitive to manipulate. Our method starts with data obtained from the real robot and alternates between simulation and experiments. Specifically, the simulation step uses gradients from a differentiable simulator to run system identification and trajectory optimization, and the experiment step executes the optimized trajectory on the robot to collect new data to be fed into simulation. Our demonstration on Starfish shows that proper usage of gradients from a differentiable simulator not only narrows down its simulation-to-reality gap but also improves the performance of an open-loop controller in real experiments.

Modeling of Soft Pneumatic Actuators with Different Orientation Angles Using Echo State Networks for Irregular Time Series Data

“…However, this process requires intensive computation power and is very lengthy. New research proposes the use of differentiable simulation as a method of modeling soft robots and bridging the simulation-to-reality gap [21].…”

Robust Counterexample-guided Optimization for Planning from Differentiable Temporal Logic

“…However, exact gradients can be difficult to derive symbolically for complex optimization problems. Instead, recent works have turned to automatic differentiation using differentiable programming to automatically compute gradients in problems such as 3D shape optimization [18], aircraft design optimization [19], robot design optimization [20], [21], and machine learning [22].…”

Follow the Gradient: Crossing the Reality Gap using Differentiable Physics (RealityGrad)

“…In the past this would require black-box optimisation or calculation of numerical gradients but can now be achieved using gradients calculated using autodiff libraries. Examples of real2sim systemID include the optimisation of a pendulum start state and parameters [13], soft robot properties [14] and frictional properties [15]. However, one of the limiting factors for systemID using a differentiable simulator is the simulation time which has to be on the order of seconds or less.…”

“…Extending upon their earlier work Heiden et al [17] demonstrated the transference of a quadrupedal walking policy from simulation to a real quadruped using a large number of optimal trajectories generated from simulation. Another sim2real investigation conducted using differentiable simulators is work by Du et al where the authors implemented a sim2real approach for a underactuated underwater robot [14].…”