Centre of Pressure Estimation during Walking Using Only Inertial-Measurement Units and End-To-End Statistical Modelling

Center of Mass Estimation for Impaired Gait Assessment Using Inertial Measurement Units

Injury or disease often compromise walking dynamics and negatively impact quality of life and independence. Assessing methods to restore or improve pathological gait can be expedited by examining a global parameter that reflects overall musculoskeletal control. Center of mass (CoM) kinematics follow well-defined trajectories during unimpaired gait, and change predictably with various gait pathologies. We propose a method to estimate CoM trajectories from inertial measurement units (IMUs) using a bidirectional Long Short-Term Memory neural network to evaluate rehabilitation interventions and outcomes. Five non-disabled volunteers participated in a single session of various dynamic walking trials with IMUs mounted on various body segments. A neural network trained with data from four of the five volunteers through a leave-one-subject out cross validation estimated the CoM with average root mean square errors (RMSEs) of 1.44cm, 1.15cm, and 0.40cm in the mediolateral (ML), anteroposterior (AP), and inferior/superior (IS) directions respectively. The impact of number and location of IMUs on network prediction accuracy was determined via principal component analysis. Comparing across all configurations, three to five IMUs located on the legs and medial trunk were the most promising reduced sensor sets for achieving CoM estimates suitable for outcome assessment. Lastly, the networks were tested on data from an individual with hemiparesis with the greatest error increase in the ML direction, which could stem from asymmetric gait. These results provide a framework for assessing gait deviations after disease or injury and evaluating rehabilitation interventions intended to normalize gait pathologies.

Peak Tibiofemoral Contact Forces Estimated Using IMU-Based Approaches Are Not Significantly Different from Motion Capture-Based Estimations in Patients with Knee Osteoarthritis

Altered tibiofemoral contact forces represent a risk factor for osteoarthritis onset and progression, making optimization of the knee force distribution a target of treatment strategies. Musculoskeletal model-based simulations are a state-of-the-art method to estimate joint contact forces, but they typically require laboratory-based input and skilled operators. To overcome these limitations, ambulatory methods, relying on inertial measurement units, have been proposed to estimated ground reaction forces and, consequently, knee contact forces out-of-the-lab. This study proposes the use of a full inertial-capture-based musculoskeletal modelling workflow with an underlying probabilistic principal component analysis model trained on 1787 gait cycles in patients with knee osteoarthritis. As validation, five patients with knee osteoarthritis were instrumented with 17 inertial measurement units and 76 opto-reflective markers. Participants performed multiple overground walking trials while motion and inertial capture methods were synchronously recorded. Moderate to strong correlations were found for the inertial capture-based knee contact forces compared to motion capture with root mean square error between 0.15 and 0.40 of body weight. The results show that our workflow can inform and potentially assist clinical practitioners to monitor knee joint loading in physical therapy sessions and eventually assess long-term therapeutic effects in a clinical context.

Joint Torque Prediction via Hybrid Neuromusculoskeletal Modelling during Gait Using Statistical Ground Reaction Estimates: An Exploratory Study

Joint torques of lower extremity are important clinical indicators of gait capability. This parameter can be quantified via hybrid neuromusculoskeletal modelling that combines electromyography-driven modelling and static optimisation. The simulations rely on kinematics and external force measurements, for example, ground reaction forces (GRF) and the corresponding centres of pressure (COP), which are conventionally acquired using force plates. This bulky equipment, however, hinders gait analysis in real-world environments. While this portability issue could potentially be solved by estimating the parameters through machine learning, the effect of the estimation errors on joint torque prediction with biomechanical models remains to be investigated. This study first estimated GRF and COP through feedforward artificial neural networks, and then leveraged them to predict lower-limb sagittal joint torques via (i) inverse dynamics and (ii) hybrid modelling. The approach was evaluated on five healthy subjects, individually. The predicted torques were validated with the measured torques, showing that hip was the most sensitive whereas ankle was the most resistive to the GRF/COP estimates for both models, with average metrics values being 0.70 < R2 < 0.97 and 0.069 < RMSE < 0.15 (Nm/kg). This study demonstrated the feasibility of torque prediction based on personalised (neuro)musculoskeletal modelling using statistical ground reaction estimates, thus providing insights into potential real-world mobile joint torque quantification.

INS Error Estimation Based on an ANFIS and Its Application in Complex and Covert Surroundings

Inertial navigation is a crucial part of vehicle navigation systems in complex and covert surroundings. To address the low accuracy of vehicle inertial navigation in multifaced and covert surroundings, in this study, we proposed an inertial navigation error estimation based on an adaptive neuro fuzzy inference system (ANFIS) which can quickly and accurately output the position error of a vehicle end-to-end. The new system was tested using both single-sequence and multi-sequence data collected from a vehicle by the KITTI dataset. The results were compared with an inertial navigation system (INS) position solution method, artificial neural networks (ANNs) method, and a long short-term memory (LSTM) method. Test results indicated that the accumulative position errors in single sequence and multi-sequences experiments decreased from 9.83% and 4.14% to 0.45% and 0.61% by using ANFIS, respectively, which were significantly less than those of the other three approaches. This result suggests that the ANFIS can considerably improve the positioning accuracy of inertial navigation, which has significance for vehicle inertial navigation in complex and covert surroundings.

Performance Evaluation of IMU and DVL Integration in Marine Navigation

Global navigation satellite system (GNSS) spoofing poses a significant threat to maritime logistics. Many maritime electronic devices rely on GNSS time, positioning, and speed for safe vessel operation. In this study, inertial measurement unit (IMU) and Doppler velocity log (DVL) devices, which are important in the event of GNSS spoofing or outage, are considered in conventional navigation. A velocity integration method using IMU and DVL in terms of dead-reckoning is investigated in this study. GNSS has been widely used for ship navigation, but IMU, DVL, or combined IMU and DVL navigation have received little attention. Military-grade sensors are very expensive and generally cannot be utilized in smaller vessels. Therefore, this study focuses on the use of consumer-grade sensors. First, the performance of a micro electromechanical system (MEMS)-based yaw rate angle with DVL was evaluated using 60 min of raw data for a 50 m-long ship located in Tokyo Bay. Second, the performance of an IMU-MEMS using three gyroscopes and three accelerometers with DVL was evaluated using the same dataset. A gyrocompass, which is equipped on the ship, is used as a heading reference. The results proved that both methods could achieve less than 1 km horizontal error in 60 min.