Publications by authors named "Nathaniel Goldfarb"

2 Publications

  • Page 1 of 1

Control of a lower limb exoskeleton using Learning from Demonstration and an iterative Linear Quadratic Regulator Controller: A simulation study.

Annu Int Conf IEEE Eng Med Biol Soc 2021 11;2021:4687-4693

Lower limb exoskeletons have complex dynamics that mimic human motion. They need to be able to replicate lower limb motion such as walking. The trajectory of the exoskeleton joints and the control signal generated are essential to the system's operation. Current learning from demonstration methods has only been combined with linear quadratic regulators; this limits the applicability of processes since most robotic systems have non-linear dynamics. The Asynchronous Multi-Body Framework simulates the dynamics and allows for real-time control. Eleven gait cycle demonstrations were recorded from volunteers using motion capture and encoded using Task Parameterized Gaussian mixture models. An iterative linear quadratic regulator is used to find an optimal control signal to drive the exoskeleton joints through the desired trajectories. A PD controller is added as a feed-forward control component for unmodeled dynamics and optimized using the Bayesian Information Criterion. We show how the trajectory is learned, and the control signal is optimized by reducing the required bins for learning. The framework presented produces optimal control signals to allow the exoskeleton's legs to follow human motion demonstrations.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/EMBC46164.2021.9630810DOI Listing
November 2021

Open source Vicon Toolkit for motion capture and Gait Analysis.

Comput Methods Programs Biomed 2021 Nov 29;212:106414. Epub 2021 Sep 29.

The Department of Robotics Engineering, Worcester Polytechnic Institute, 85 Prescott St, Worcester, MA 01609, United States. Electronic address:

Background And Objective: The Vicon motion capture system is a popular tool for biomechanics, gait analysis, and robotics. The ASCII files produced are large and complex, making them difficult to read and analyze.

Methods: This paper presents two packages, the Vicon Toolkit Package and the Gait Analysis Toolkit Package. They use an open-source framework for ingesting, parsing, and analyzing Vicon mocap data and performing gait analysis. The package that handles the Vicon analysis is separated from the Gait Analysis package to allow for abstraction and expansion, and is not specific only to the Vicon system.

Results: Our Vicon Toolkit provides tools to work directly with the marker data and other Vicon Nexus system outputs. The Gait Toolkit provides tools for performing gait analysis, EMG filtering, and learning trajectories. The packages are built upon a core library, GaitCore, that provides unified objects to perform operations and store data.

Conclusion: This paper will show how to use the packages' tools and the expected outputs. All the tools are open-source and written in Python3.x for ease of use and access to other powerful libraries.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.cmpb.2021.106414DOI Listing
November 2021
-->