'Body-in-the-Loop' Optimization of Assistive Robotic Devices: A Validation Study

Abstract

Abstract-Physiological measures, such as pain, anxiety, effort, or energy consumption, play a crucial role in the evaluation and development of assistive robotic devices. Physiological data are collected and analyzed by researchers and clinicians, and are often used to inform an iterative tuning process of a device and its controller. Currently, these data are collected then analyzed offline such that they are only evaluated after the experiment has ended. This makes any iterative design process tedious and time consuming since tuning must be done on a subject-by-subject basis and for a variety of tasks that the device is intended to be used for. To overcome these drawbacks, we are proposing a new type of human-machine interaction that is based on measuring and using physiological measurements in real-time. By continuously monitoring a physiological objective through a set of suitable sensors, we propose conducting an optimization of a set of controller parameters that shape the assistance provided by the device. In other words, we pose an optimization that includes the human body in the loop. This Body-in-the-Loop optimization allows for optimal subject specific control and has the potential to be used for controller adaptation to changing environments. We validated this concept in an extensive human subject study where we autonomously optimized the actuation onset of a pair of bilateral ankle exoskeletons to minimize user's metabolic effort.

Considering passive mechanical properties and patient user motor performance in lower limb prosthesis design optimization to enhance rehabilitation outcomes

“…In this scenario, devices are constrained to explore a defined range of some parameter to populate the experimental map of relationships. A subsequent optimization routine then “pushes” the user toward their optimal device tuning in a gradient-descent or semi-automated co-adaptation fashion 127–129 . Using such approaches, the patient’s motor performance is theoretically accounted for as the optimization operates on the combined human-prosthesis system.…”

Human-in-the-loop optimization of exoskeleton assistance during walking

“…Control laws that are general enough to approximate globally optimal assistance strategies are likely to require multiple parameters per assisted joint (10), resulting in high-dimensional optimization problems. Initial efforts in this domain have demonstrated the ability to optimize a single gait or device parameter using line search (24) or gradient descent (25), but these methods are inefficient, being sensitive to drift and noise, and scale poorly, requiring many more evaluations for each new parameter to be optimized, particularly in the presence of parametric interactions (26). Many optimization methods that work well in simulation (27 ) are subject to these limitations; building an approximation of the system takes time, and the human changes during that time.…”

Shortcomings of human-in-the-loop optimization for an ankle-foot prosthesis: a case series

“…It is also not biased due to changes as a result of adaptation over time because it does not use information from previous generations. Other optimization strategies such as gradient descent 22,23 or Bayesian optimization 25 have also been used successfully for HILO of exoskeletons. However, these strategies have only been used to optimize one or two parameters simultaneously.…”

“…result in high reductions in metabolic cost [22][23][24][25][26] . This technique involves choosing the parameters of a control architecture based on the human response to changes in control parameters.…”