A fuzzy logic based terrain identification approach to prosthesis control using multi-sensor fusion

Abstract

This paper presents a fuzzy logic based terrain identification method using multi-sensor fusion for powered prosthesis control. Five locomotion features including rising time of ground reaction force, sequence of foot strike on ground, foot inclination angle during stance, shank inclination angle at toe-off and maximal shank inclination angle during swing are selected to identify different terrains. These features are measured by fusion of two gyroscopes, two accelerometers, two force sensitive resistors and a timer. Based on the features, a fuzzy logic identification method is developed to identify level-ground, stair ascent, stair descent, upslope and downslope online in real time. Average identification accuracy higher than 97.5% is obtained in experiments of five able-bodied subjects and a transtibial amputee. Continuous identification results show the prospect of using the proposed method to realize real-time terrain identification of powered prostheses.

Motion control of a robotic transtibial prosthesis during transitions between level ground and stairs

“…The two membership values calculated from two feature values are added together to get the membership of a specific terrain, and the target terrain is the one with the largest membership value. For detailed information, see [23].…”

“…Based on our previous work [23], a simplified fuzzy-logic based terrain identification method is proposed to identify level ground, stair ascent, and stair descent. Two features are used to calculate membership values of different terrains.…”

Optimizing Support Vector Machine with Genetic Algorithm for Capacitive Sensing-Based Locomotion Mode Recognition

“…To solve this problem, several different sensing systems [8][9][10][11][12][13] have been proposed for locomotion mode recognition (LMR). Electromyography (EMG)-based systems and inertial sensor-based methods are the two main ways.…”

Detection of Gait Modes Using an Artificial Neural Network during Walking with a Powered Ankle-Foot Orthosis

“…In summary, existing gait mode recognition schemes have shortcomings of not being autonomous [4, 5], delay in detection of a new mode until the next step [16, 18], difficulty of implementation in real-time [6–10, 17], dependency on trained stair heights [16], or need for a large number of sensors [12–15, 19, 20]. There are currently no reliable gait mode recognition algorithms available which can detect all of the modes without long delays and without the use of a large number of sensors.…”