Slope estimation during normal walking using a shank-mounted inertial sensor

Abstract

In this paper we propose an approach for the estimation of the slope of the walking surface during normal walking using a body-worn sensor composed of a biaxial accelerometer and a uniaxial gyroscope attached to the shank. It builds upon a state of the art technique that was successfully used to estimate the walking velocity from walking stride data, but did not work when used to estimate the slope of the walking surface. As claimed by the authors, the reason was that it did not take into account the actual inclination of the shank of the stance leg at the beginning of the stride (mid stance). In this paper, inspired by the biomechanical characteristics of human walking, we propose to solve this issue by using the accelerometer as a tilt sensor, assuming that at mid stance it is only measuring the gravity acceleration. Results from a set of experiments involving several users walking at different inclinations on a treadmill confirm the feasibility of our approach. A statistical analysis of slope estimations shows in first instance that the technique is capable of distinguishing the different slopes of the walking surface for every subject. It reports a global RMS error (per-unit difference between actual and estimated inclination of the walking surface for each stride identified in the experiments) of 0.05 and this can be reduced to 0.03 with subject-specific calibration and post processing procedures by means of averaging techniques.

Keywords: gait; inertial sensors; shank; slope estimation; tilt.

Figure 1.

Sensor placement (left). Normal and tangential accelerations ( ${\mathit{\text{a}}}_{\mathit{\text{n}}}^{\mathit{\text{s}}}(\mathit{\text{t}}),{\mathit{\text{a}}}_{\mathit{\text{t}}}^{\mathit{\text{s}}}(\mathit{\text{t}})$) and rotation speed (ω(t)) are sampled from an inertial sensor attached to the external face of the shank, at an intermediate point between the knee and the ankle. Local maxima of lower lobes of shank rotation speed are used to segment the whole signal into single strides (right). MS stands for Mid Stance.

Figure 2.

Raw estimations of the slope of the walking surface for the six subjects at the seven treadmill inclinations (0.14, 0.1, 0.06, 0.02, −0.02, −0.05, −0.09, from left to right for each subject). Big dots show the actual inclination of the treadmill for each experiment.

Figure 3.

Corrected estimations for the six subjects at the inclinations (0.14, 0.06, 0.02, −0.02, −0.09, from left to right for each subject) using a linear model for each user defined from experiments at 0.1 and −0.05 and applying a moving average filter to raw estimations. Big dots show the actual inclination of the treadmill for each experiment.