Advanced soft robots: data-driven development, modeling and control
Submitted to the Croatian Science Foundation
Over the past 15 years, the study of nature-inspired soft robots has grown exponentially. Compared to rigid robots, they have tremendously improved human-machine interaction safety. As a result, they have become increasingly attractive in various medical fields, including robotic rehabilitation. However, inherent nonlinearity and formally infinite degrees of freedom hinder their development, modeling, and control, limiting their use outside the laboratory. Building on the Principal Investigator’s previous study “Control of Soft Robots with Inertial Dynamics” published in Science Robotics (2-year IF: 26.1), the proposed project aims to address these challenges within a biomechatronic design framework by establishing a new interdisciplinary research group and the “Laboratory for Bioinspired Robotics.” Leveraging the Koopman operator framework, data-driven modeling and development of controllers applicable to soft rehabilitation robots will be carried out. Data will be acquired using a motion capture system, and a method for modeling and forecasting grip strength through electromyographic sensors will be developed. This approach will enable real-time adaptivity of the device, allowing for adjustment of output force to optimize patient recovery during rehabilitation. In addition, by leveraging an interdisciplinary approach and fostering collaboration between engineers and medical experts, the project will examine the critical prerequisites for developing soft robots suitable for rehabilitation purposes. This includes conducting kinematic analyses of motion, selecting appropriate materials, and refining design parameters. Numerical and analytical models will be developed to optimize the designs and to achieve better durability and reliability, with experimental analyses validating these designs. The project will culminate in the development of a proof-of-concept prototype of an innovative soft robotic glove designed to rehabilitate patients with reduced hand mobility (Bazina et al., 2024), (Haggerty et al., 2023).
Integration of EMG sensing devices and hand dynamometer into ROS
An example of the 3D printed tendon-driven rehabilitation glove made on traditional robotics principles [B. Stanić, K. Dangubić, T. Galić, University of Rijeka, Faculty of Engineering, Course: Control of mechatronics systems (E. Kamenar)]
References
2024
ArXiv
Koopman-driven grip force prediction through EMG sensing
Tomislav Bazina, Ervin Kamenar, Maria Fonoberova, and Igor Mezić
Loss of hand function due to conditions like stroke or multiple sclerosis significantly impacts daily activities. Robotic rehabilitation provides tools to restore hand function, while novel methods based on surface electromyography (sEMG) enable the adaptation of the device’s force output according to the user’s condition, thereby improving rehabilitation outcomes. This study aims to achieve accurate force estimations during medium wrap grasps using a single sEMG sensor pair, thereby addressing the challenge of escalating sensor requirements for precise predictions. We conducted sEMG measurements on 13 subjects at two forearm positions, validating results with a hand dynamometer. We established flexible signal-processing steps, yielding high peak cross-correlations between the processed sEMG signal (representing meaningful muscle activity) and grip force. Influential parameters were subsequently identified through sensitivity analysis. Leveraging a novel data-driven Koopman operator theory-based approach and problem-specific data lifting techniques, we devised a methodology for the estimation and short-term prediction of grip force from processed sEMG signals. A weighted mean absolute percentage error (wMAPE) of approx. 5.5% was achieved for the estimated grip force, whereas predictions with a 0.5-second prediction horizon resulted in a wMAPE of approx. 17.9%. The methodology proved robust regarding precise electrode positioning, as the effect of sensing position on error metrics was non-significant. The algorithm executes exceptionally fast, processing, estimating, and predicting a 0.5-second sEMG signal batch in just approx. 30 ms, facilitating real-time implementation.
@article{bazina2024koopman,title={Koopman-driven grip force prediction through EMG sensing},author={Bazina, Tomislav and Kamenar, Ervin and Fonoberova, Maria and Mezi{\'c}, Igor},journal={arXiv preprint arXiv:2409.17340},year={2024},}
2023
SciRobot
Control of soft robots with inertial dynamics
David A Haggerty, Michael J Banks, Ervin Kamenar, Alan B Cao, and 3 more authors
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.
@article{haggerty2023control,title={Control of soft robots with inertial dynamics},author={Haggerty, David A and Banks, Michael J and Kamenar, Ervin and Cao, Alan B and Curtis, Patrick C and Mezi{\'c}, Igor and Hawkes, Elliot W},journal={Science robotics},volume={8},number={81},pages={eadd6864},year={2023},publisher={American Association for the Advancement of Science},doi={10.1126/scirobotics.add6864},}
