A Cyber Expert System for Auto-Tuning Powered Prosthesis Impedance Control Parameters

Abstract

Typically impedance control parameters (e.g., stiffness and damping) in powered lower limb prostheses are fine-tuned by human experts (HMEs), which is time and resource intensive. Automated tuning procedures would make powered prostheses more practical for clinical use. In this study, we developed a novel cyber expert system (CES) that encoded HME tuning decisions as computer rules to auto-tune control parameters for a powered knee (passive ankle) prosthesis. The tuning performance of CES was preliminarily quantified on two able-bodied subjects and two transfemoral amputees. After CES and HME tuning, we observed normative prosthetic knee kinematics and improved or slightly improved gait symmetry and step width within each subject. Compared to HME, the CES tuning procedure required less time and no human intervention. Hence, using CES for auto-tuning prosthesis control was a sound concept, promising to enhance the practical value of powered prosthetic legs. However, the tuning goals of CES might not fully capture those of the HME. This was because we observed that HME tuning reduced trunk sway, while CES sometimes led to slightly increased trunk motion. Additional research is still needed to identify more appropriate tuning objectives for powered prosthetic legs to improve amputees' walking function.

Extremum Seeking Control for Model-Free Auto-Tuning of Powered Prosthetic Legs

“…is used to enforce the continuous-phase gait in (6). The proportional and the damping gains in (7) are given by…”

“…been made in real-time automatic selection of control parameters. In [6], [7], rule-based fuzzy logic inference schemes, which are based on subjects' walking data, were developed in order to automate the tuning process of the knee joint control parameters. As noted by the authors in [8], this approach relies heavily on the knowledge and the experience of the human experts to formulate fuzzy rules.…”

“…However, it is unclear whether either of these approaches can simultaneously tune the impedance parameters of multiple joints, where the dynamics of one joint affects the other. The presented results in [6], [7] are also limited to a single walking speed (0.6 ms -1 ). Apart from tuning impedance control parameters in powered prostheses, efforts have been made in the field of exoskeletons to tune the ankle joint parameters in real-time in order to improve the metabolic cost of the subject [9]- [11].…”

“…With respect to the automatically tuned impedance-based controllers in the literature, our adaptation algorithm enjoys a unique combination of several features. First, we demonstrate the effectiveness of our adaptation algorithm across different walking speeds as opposed to carrying out adaptation at a fixed walking speed [6], [7]. Our algorithm takes approximately one minute to track real-time changes in the optimal proportional gains, which is sufficiently fast compared to prior approaches that take 1-2 hours for adaptation [9]- [11].…”

Automatic tuning of virtual constraint-based control algorithms for powered knee-ankle prostheses

“…In order to reduce the burden of clinicians, approaches such as rule-based fuzzy logic inference [7], model-based methods [8], and cyber expert systems [9] have been used to automatically find an optimum set of parameters for prosthetic impedance controllers. These approaches, however, have two main limitations: (i) they do not simultaneously tune multiple joints; and (ii) they have not demonstrated the ability to learn different parameters for subjects/models with different physical attributes.…”