Learning motor control parameters for motion strategy analysis of Parkinson's disease patients

Abstract

Although the neurological impairments of Parkinson's disease (PD) patients are well known to go along with motor control deficits, e.g., tremor, rigidity, and reduced movement, not much is known about the motor control parameters affected by the disease. In this paper, we therefore present a novel approach to human motions analysis using motor control strategies with joint weight parameterization. We record the motions of healthy subjects and PD patients performing a hand coordination task with the whole-body XSens MVN motion capture system. For our motion strategy analysis we then follow a two step approach. First, we perform a complexity reduction by mapping the recorded human motions to a simplified kinematic model of the upper body. Second, we reproduce the recorded motions using a Jacobian weighted damped least squares controller with adaptive joint weights. We developed a method to iteratively learn the joint weights of the controller with the mapped human joint trajectories as reference input. Finally, we use the learned joint weights for a quantitative comparison between the motion control strategies of healthy subjects and PD patients. Other than expected from clinical experience, we found that the joint weights are almost evenly distributed along the arm in the PD group. In contrast to that, the proximal joint weights of the healthy subjects are notably larger than the distal ones.

Adaptive control of a wheelchair mounted robotic arm with neuromorphically integrated velocity readings and online-learning

“…Adaptive motor control is long known to be mediated by projection neurons involving the basal ganglia and the neocortex, providing vision and proprioception-driven real-time error-correcting adaptive signals with which a dynamic motor control could be efficiently realized ( Graybiel et al, 1994 ). Failure to generate these error-correcting signals can manifest as Parkinson’s ( Burget et al, 2015 ) or Huntington’s ( Smith et al, 2000 ) brain disorders. While adaptive control could be implemented in conventional neural computational frameworks ( Cong and Liang, 2009 ), spiking neuronal architectures were shown to provide increased performance with lower energy consumption ( DeWolf et al, 2020 ).…”

Correlations between Motor Symptoms across Different Motor Tasks, Quantified via Random Forest Feature Classification in Parkinson’s Disease

“…In that respect, we believe that JA is a more broadly applicable measure for abnormality than too small or too large movement amplitudes, velocities, or ranges with respect to the normal subjects. Using many velocity traces from different joints, JA-related findings could also cover abnormal multisegmental control strategies in comparison to healthy subjects ( 46 ).…”

Analysis on the Subdivision of Skilled Mowing Movements on Slopes

“…In addition to the research that focused on the use of camera-based motion-capture devices, several studies have applied motion-capture devices to human motion analysis in open environments. For example, Burget et al compared the similarities and differences between subjects performing hand-coordination tasks by asking healthy subjects and patients with Parkinson’s disease to use an acceleration sensor-based motion-capture device [ 23 ].…”