Estimating Running Ground Reaction Forces from Plantar Pressure during Graded Running

Abstract

Ground reaction forces (GRFs) describe how runners interact with their surroundings and provide the basis for computing inverse dynamics. Wearable technology can predict time−continuous GRFs during walking and running; however, the majority of GRF predictions examine level ground locomotion. The purpose of this manuscript was to predict vertical and anterior–posterior GRFs across different speeds and slopes. Eighteen recreationally active subjects ran on an instrumented treadmill while we collected GRFs and plantar pressure. Subjects ran on level ground at 2.6, 3.0, 3.4, and 3.8 m/s, six degrees inclined at 2.6, 2.8, and 3.0 m/s, and six degrees declined at 2.6, 2.8, 3.0, and 3.4 m/s. We estimated GRFs using a set of linear models and a recurrent neural network, which used speed, slope, and plantar pressure as inputs. We also tested eliminating speed and slope as inputs. The recurrent neural network outperformed the linear model across all conditions, especially with the prediction of anterior–posterior GRFs. Eliminating speed and slope as model inputs had little effect on performance. We also demonstrate that subject−specific model training can reduce errors from 8% to 3%. With such low errors, researchers can use these wearable−based GRFs to understand running performance or injuries in real−world settings.

Evaluation of the Foot Center of Pressure Estimation from Pressure Insoles during Sidestep Cuts, Runs and Walks

“…In view of the use of pressure insoles in the inverse dynamics process, an evaluation of the estimation of the ground reaction force and the estimation of the CoP position is necessary. Recent studies presented methods to estimate ground reaction force from plantar pressure, considering CoP as the force application point [ 17 ]. The artificial neural network use involves a large amount of data [ 18 ].…”

Characterization of the Kinetyx SI Wireless Pressure-Measuring Insole during Benchtop Testing and Running Gait

“…In total, 13 runners (8 male, 5 female) participants were recruited, aged 19–40 years (mean: 28 ± 5 years). Participant height ranged from 1.55 to 1.93 m (mean: 1.73 ± 0.10 m) and body mass ranged from 52.0 to 87.5 kg (mean: 66.6 ± 10.3 kg) [ 6 ]. All participants were free from injury at the time of testing, were familiar with treadmill running, and were given a 10 min self-selected warm-up.…”

“…Traditionally, standard laboratory-based measurement equipment such as in-ground force plates, or force-instrumented treadmills have been used to quantify foot-ground interactions during running. Increasingly, however, researchers have recognized the importance of measuring running foot-ground interactions outside of the laboratory in the natural training and competition environments [ 3 , 6 ]. Plantar pressure measurement systems (PPMS) offer a unique solution to researchers interested in measuring foot-ground interactions during running or walking, as well as for many different activities [ 7 , 8 , 9 , 10 ].…”

“…Additionally, in-shoe PPMS have been shown to accurately capture important kinematic running gait metrics such as stance time, stride time, and stride rate [ 11 , 12 , 13 , 14 , 15 , 16 ]. Further, PPMS have shown promise to approximate kinetic characteristics of gait, such as path of center of pressure, and vertical ground reaction forces [ 6 , 10 , 14 , 17 , 18 , 19 , 20 , 21 ], although some research has shown inter-session force reliability is still inconsistent [ 22 ].…”

A Deep Learning Model for 3D Ground Reaction Force Estimation Using Shoes with Three Uniaxial Load Cells

“…Recent research [ 8 , 9 , 10 ] indicates that investigations outside the laboratory are required to fully comprehend walking. Like force plates, pressure mats can only be utilized in a laboratory setting, despite their portability.…”