Janez Podobnik

Automated detection of gait initiation and termination using wearable sensors

This paper presents algorithms for detection of gait initiation and termination using wearable inertial measurement units and pressure-sensitive insoles. Body joint angles, joint angular velocities, ground reaction force and center of plantar pressure of each foot are obtained from these sensors and input into supervised machine learning algorithms. The proposed initiation detection method recognizes two events: gait onset (an anticipatory movement preceding foot lifting) and toe-off. The termination detection algorithm segments gait into steps, measures the signals over a buffer at the beginning of each step, and determines whether this measurement belongs to the final step. The approach is validated with 10 subjects at two gait speeds, using within-subject and subject-independent cross-validation. Results show that gait initiation can be detected timely and accurately, with few errors in the case of within-subject cross-validation and overall good performance in subject-independent cross-validation. Gait termination can be predicted in over 80% of trials well before the subject comes to a complete stop. Results also show that the two sensor types are equivalent in predicting gait initiation while inertial measurement units are generally superior in predicting gait termination. Potential use of the algorithms is foreseen primarily with assistive devices such as prostheses and exoskeletons.

Three-Axial Accelerometer Calibration Using Kalman Filter Covariance Matrix for Online Estimation of Optimal Sensor Orientation

Inexpensive inertial/magnetic measurement units can be found in numerous applications and are typically used to determine orientation. Due to the presence of nonidealities in measurement systems, the calibration of the sensor is thus needed to determine sensor parameters such as bias, misalignment, and gain/sensitivity. In this paper, an online automatic calibration method for a three-axial accelerometer is presented. Parameters are estimated using an unscented Kalman filter. The sensor is placed in a number of different orientations using a robotic arm. These orientations are calculated online from the parameter covariance matrix and represent estimated optimal sensor orientations for parameter estimation. Numerous simulations are run to evaluate the proposed calibration method, and a comparison is made with an offline least mean squares calibration method. The simulation results show that calibration with the proposed method results in higher accuracy of parameter estimation when using less than 100 iterations. The proposed calibration method is also applied to a real accelerometer using a low number of iterations. The results show only slight (less than 0.4%) changes in parameter values between different calibration runs. The proposed calibration method provides an accurate parameter estimation using a small number of iterations without the need for manually predefining orientations of the sensor, and the method can be used in combination with other offline calibration methods to achieve even higher accuracy.

Development and validation of a wearable inertial measurement system for use with lower limb exoskeletons

This paper presents a system of inertial measurement units, each consisting of an accelerometer, gyroscope and magnetometer. They are characterized by a small size, wireless transmission, and open architecture, with the purpose of either integration into lower limb exoskeletons or general human movement analysis. Kalman filtering and the factored quaternion algorithm are used to track the orientation of each unit, and angles of the human joints are calculated from multiple units. After calibration, the system was tested with a wooden leg mockup and an actual human. The Optotrak optical measurement system was used as a reference. Differences between the inertial measurement system and the Optotrak were less than 2 degrees for the wooden leg and less than 5 degrees for the human leg, suggesting that the system represents a promising possibility for wearable movement tracking and analysis.

Development of gait segmentation methods for wearable foot pressure sensors

We present an automated segmentation method based on the analysis of plantar pressure signals recorded from two synchronized wireless foot insoles. Given the strict limits on computational power and power consumption typical of wearable electronic components, our aim is to investigate the capability of a Hidden Markov Model machine-learning method, to detect gait phases with different levels of complexity in the processing of the wearable pressure sensors signals. Therefore three different datasets are developed: raw voltage values, calibrated sensor signals and a calibrated estimation of total ground reaction force and position of the plantar center of pressure. The method is tested on a pool of 5 healthy subjects, through a leave-one-out cross validation. The results show high classification performances achieved using estimated biomechanical variables, being on average the 96%. Calibrated signals and raw voltage values show higher delays and dispersions in phase transition detection, suggesting a lower reliability for online applications.

Toward Real-Time Automated Detection of Turns during Gait Using Wearable Inertial Measurement Units

Previous studies have presented algorithms for detection of turns during gait using wearable sensors, but those algorithms were not built for real-time use. This paper therefore investigates the optimal approach for real-time detection of planned turns during gait using wearable inertial measurement units. Several different sensor positions (head, back and legs) and three different detection criteria (orientation, angular velocity and both) are compared with regard to their ability to correctly detect turn onset. Furthermore, the different sensor positions are compared with regard to their ability to predict the turn direction and amplitude. The evaluation was performed on ten healthy subjects who performed left/right turns at three amplitudes (22, 45 and 90 degrees). Results showed that turn onset can be most accurately detected with sensors on the back and using a combination of orientation and angular velocity. The same setup also gives the best prediction of turn direction and amplitude. Preliminary measurements with a single amputee were also performed and highlighted important differences such as slower turning that need to be taken into account.

HEnRiE - Haptic environment for reaching and grasping exercise

Task-oriented repetitive movements can improve motor recovery in patients with neurological or orthopaedic lesions. HEnRiE is a robot based haptic environment for simultaneous training of reaching and grasping movements. It consists of a robot with three active and two passive degrees of freedom and a grasping device with one degree of freedom. A training scenario that includes a virtual physiotherapist is introduced. Presented are results of a preliminary study that requires reaching and grasping coordination.

Magnetometer Calibration Using Kalman Filter Covariance Matrix for Online Estimation of Magnetic Field Orientation

The inertial/magnetic measurement units are an affordable instrument for the determination of orientation. The sensors embedded in the system are affected by nonidealities that can be greatly compensated by proper calibration, by determining sensor parameters, such as bias, misalignment, and sensitivity/gain. This paper presents an online calibration method for a three-axial magnetometer using a 3-D Helmholtz coil. The magnetometer is exposed to different directions of the magnetic field created by the 3-D coil. The parameters are estimated by using an unscented Kalman filter. The directions are calculated online by using a sensor parameter covariance matrix. The method evaluation is achieved by first running numerous simulations, followed by experiments using a real magnetometer, finally resulting in better accuracy of parameter estimation with a low number of measurement iterations compared with the method where magnetic field directions are determined manually.

Intention detection during gait initiation using supervised learning

This paper presents a study of gait intention detection using force plates, inertial measurement units and an optical measurement system. The main goal is to detect gait initiation before heel-off and toe-off. Several established supervised machine learning methods are used to detect the onset of gait initiation, the first heel-off and the first toe-off. Events manually annotated by an expert serve as a reference. Results show that force plate signals are the most useful sensor, allowing gait onset to be detected with a mean absolute error of 0.12 seconds. Inertial measurement units are less accurate, with a mean absolute error for gait onset detection of 0.22 seconds. However, the decreased accuracy is primarily due to a small number of poorly detected outliers. The accuracy of the different supervised methods is also compared. For practical use, we recommend a combination of inertial measurement units and in-shoe pressure sensors, with different supervised methods used to detect different events.

Upper limb and grasp rehabilitation and evaluation of stroke patients using HenRiE device

This paper presents a case study with a HenRiE (Haptic environment for reaching and grasping exercises) device with two hemiparetic subjects. The HenRiE device is intended for use in a robot-aided neurorehabilitation for training of reaching and grasping in haptic environments. The goal of the study is to develop a single system that retrains both hand grasping and releasing movements (which are essential to perform activities of daily living) and arm movements. The system combines a haptic interface and a grasping device, which is mounted on the end-effector of the haptic interface. The paper focuses on experimental training sessions with two hemiparetic subjects. Results show favourable effect both on arm and grasping.

Haptic Interaction Stability With Respect to Grasp Force

This paper addresses the contact instability of admittance control of a haptic interface. A high level of rigidity of the grasp of a subject operating the haptic interface will result in unstable behavior of the haptic interaction. Experiments with a system dedicated to measuring grasp force were performed to explore the conditions when grasp force has reached the critical grasp force that destabilizes the haptic interface. The critical grasp force was quantified for various values of virtual environment parameters. The experimental results are compared to simulation results obtained with a model of haptic interaction. To improve stability, two methods were applied: one with virtual coupling, the other with a compensator filter. A model was used to define the structure of the compensator filter and to determine the parameters of the virtual coupling and the compensator filter. Experimental and simulation results confirmed an improvement of stability. Both methods allow higher grasp forces of the human operator, and experiments show that the compensator filter allows higher grasp forces than the virtual coupling.