Inertial measurement unit (IMU)-based 3D joint angle estimation have a wide range of important applications, among them, in gait analysis and exoskeleton robot control. Conventionally, the joint angle was determined via the estimation of 3D orientation of each body segment using 9-axis IMUs including 3-axis magnetometers. However, a magnetometer is limited by magnetic disturbance in the vicinity of the sensor, which highly affects the accuracy of the joint angle. Accordingly, this study aims to estimate the joint angle using the 6-axis IMU signals composed of a 3-axis accelerometer and a 3-axis gyroscope without a magnetometer. This paper proposes a recurrent neural network (RNN) model, which indirectly utilizes the joint kinematic constraint and thus estimates joint angles based on 6-axis IMUs without using a magnetometer signal. The performance of the proposed model was validated for a mechanical joint and human elbow joint, under magnetically disturbed environments. Experimental results showed that the proposed RNN approach outperformed the conventional approach based on a Kalman filter (KF), i.e., RNN 3.48° vs. KF 10.01° for the mechanical joint and RNN 7.39° vs. KF 21.27° for the elbow joint.

In the case of dynamic sports activities such as skiing and sprints, it is difficult to apply optical motion capture systems because of measurement volume limitation. Alternatively, the use of inertial measurement unit (IMU) as a motion sensor has gained attention. This paper proposes a drift reduction method in the IMU-based joint angle estimation for dynamic motion-involved sports applications. To resolve the problem of conventional IMU-based methods significantly reducing performance under highly dynamic conditions, the proposed method applies a correction method using joint constraint. The proposed method is the complementary filter based on the previous drift reduction technique using the joint constraint, but performs in real time. The proposed method was validated by comparing the estimation accuracy with conventional methods under various dynamic conditions. The results showed that the proposed method was superior to the methods that did not use the constraint. While the proposed method was 0.19° less accurate than the non-realtime method of the reference, it is more practical due to its realtime correction capability.

Displacement estimation based on inertial sensor signals is usually performed in aid of global positioning systems or barometers. However, due to low accuracy estimation capabilities of such aiding sensors, inertial sensor-based displacement estimation is difficult to achieve high accuracy. This paper will show that it is possible to determine the vertical displacement of a link connected by a joint with higher accuracy while only using the inertial sensor. The proposed method utilizes a predetermined position vector from the joint center to the sensor and link orientation. By combining the joint constraint, accuracy of the orientation estimation is ensured even in highly dynamic conditions, and thus, the vertical displacement estimation with high accuracy can be achieved. Experimental results show that the proposed method outperformed the method by fusing inertial sensor and barometer signals as well as the method using inertial sensor signals only without constraint combination.