An official website of the United States government
Aggressive and accurate control of complex dynamical systems, such as soft robots, is especially challenging due to the difficulty of obtaining an accurate and tractable model for real-time control. Learned dynamic models are incredibly useful because they do not require derivation of an analytical model, they can represent complex, nonlinear behavior directly from data, and they can be evaluated quickly on graphics-processing units (GPUs). In this paper, we present an open-source Python library to further current research in model-based control of soft robot systems. Our library for Modeling of Learned Dynamics (MoLDy), is designed to generate learned forward models of complex systems through a data-driven approach to hyperparameter optimization and learned model training. Included in the MoLDy library, we present an open-source version of NEMPC (Nonlinear Evolutionary Model Predictive Control), a previously published control algorithm validated on soft robots. We demonstrate the ability of MoLDy and NEMPC to accurately perform modelbased control on a physical pneumatic continuum joint. We also present a benchmarking study on the effect of the loss metric used in model training on control performance. The results of this paper serve to guide other researchers in creating learned dynamic models of novel systems and using them in closed-loop control tasks.
more »
« less
Using First Principles for Deep Learning and Model-Based Control of Soft Robots
Model-based optimal control of soft robots may enable compliant, underdamped platforms to operate in a repeatable fashion and effectively accomplish tasks that are otherwise impossible for soft robots. Unfortunately, developing accurate analytical dynamic models for soft robots is time-consuming, difficult, and error-prone. Deep learning presents an alternative modeling approach that only requires a time history of system inputs and system states, which can be easily measured or estimated. However, fully relying on empirical or learned models involves collecting large amounts of representative data from a soft robot in order to model the complex state space–a task which may not be feasible in many situations. Furthermore, the exclusive use of empirical models for model-based control can be dangerous if the model does not generalize well. To address these challenges, we propose a hybrid modeling approach that combines machine learning methods with an existing first-principles model in order to improve overall performance for a sampling-based non-linear model predictive controller. We validate this approach on a soft robot platform and demonstrate that performance improves by 52% on average when employing the combined model.
more »
« less
- Award ID(s):
- 1935312
- PAR ID:
- 10310963
- Date Published:
- Journal Name:
- Frontiers in Robotics and AI
- Volume:
- 8
- ISSN:
- 2296-9144
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Underactuation is a core challenge associated with controlling soft and continuum robots, which possess theoretically infinite degrees of freedom, but few actuators. However, m actuators may still be used to control a dynamic soft robot in an m-dimensional output task space. In this paper we develop a task-space control approach for planar continuum robots that is robust to modeling error and requires very little sensor information. The controller is based on a highly underactuated discrete rod mechanics model in maximal coordinates and does not require conversion to a classical robot dynamics model form. This promotes straightforward control design, implementation and efficiency. We perform input-output feedback linearization on this model, apply sliding mode control to increase robustness, and formulate an observer to estimate the full state from sparse output measurements. Simulation results show exact task-space reference tracking behavior can be achieved even in the presence of significant modeling error, inaccurate initial conditions, and output-only sensing.more » « less
-
Because of the complex nature of soft robots, formulating dynamic models that are simple, efficient, and sufficiently accurate for simulation or control is a difficult task. This paper introduces an algorithm based on a recursive Newton-Euler (RNE) approach that enables an accurate and tractable lumped parameter dynamic model. This model scales linearly in computational complexity with the number of discrete segments. We validate this model by comparing it to actual hardware data from a three-joint continuum soft robot (with six degrees of freedom represented in a constant curvature kinematic model). The results show that this RNE-based model can be computed faster than real-time. We also show that with minimal system identification, a simulation performed using the dynamic model matches the real robot data with a median error of 3.15 degrees.more » « less
-
Soft robots have recently drawn extensive attention thanks to their unique ability of adapting to complicated environments. Soft robots are designed in a variety of shapes of aiming for many different applications. However, accurate modelling and control of soft robots is still an open problem due to the complex robot structure and uncertain interaction with the environment. In fact, there is no unified framework for the modeling and control of generic soft robots. In this paper, we present a novel data-driven machine learning method for modeling a cable-driven soft robot. This machine learning algorithm, named deterministic learning (DL), uses soft robot motion data to train a radial basis function neural network (RBFNN). The soft robot motion dynamics are then guaranteed to be accurately identified, represented, and stored as an RBFNN model with converged constant neural network weights. To validate our method, We have built a simulated soft robot almost identical to our real inchworm soft robot, and we have tested the DL algorithm in simulation. Furthermore, a neural network weight combining technique is used which can extract and combine useful dynamics information from multiple robot motion trajectories.more » « less
-
Soft robots promise improved safety and capability over rigid robots when deployed near humans or in complex, delicate, and dynamic environments. However, infinite degrees of freedom and the potential for highly nonlinear dynamics severely complicate their modeling and control. Analytical and machine learning methodologies have been applied to model soft robots but with constraints: quasi-static motions, quasi-linear deflections, or both. Here, we advance the modeling and control of soft robots into the inertial, nonlinear regime. We controlled motions of a soft, continuum arm with velocities 10 times larger and accelerations 40 times larger than those of previous work and did so for high-deflection shapes with more than 110° of curvature. We leveraged a data-driven learning approach for modeling, based on Koopman operator theory, and we introduce the concept of the static Koopman operator as a pregain term in optimal control. Our approach is rapid, requiring less than 5 min of training; is computationally low cost, requiring as little as 0.5 s to build the model; and is design agnostic, learning and accurately controlling two morphologically different soft robots. This work advances rapid modeling and control for soft robots from the realm of quasi-static to inertial, laying the groundwork for the next generation of compliant and highly dynamic robots.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3389/frobt.2021.654398
