Design optimization platform for assistive wearable devices applied to a knee damper exoskeleton

Abstract

Designing optimal assistive wearable devices is a complex task, often addressed using human-in-the-loop optimization and biomechanical modeling approaches. However, as the number of design parameters increases, the growing complexity and dimensionality of the design space make identifying optimal solutions more challenging. Predictive simulation, which models movement without relying on experimental data, provides a powerful tool for anticipating the effects of assistive devices on the human body and guiding the design process. This study aims to introduce a design optimization platform that leverages predictive simulation of movement to identify the optimal parameters for assistive wearable devices. The proposed approach is specifically capable of dealing with the challenges posed by high-dimensional design spaces. The proposed framework employs a two-layered optimization approach, with the inner loop solving the predictive simulation of movement and the outer loop identifying the optimal design parameters of the device. It is utilized for designing a knee exoskeleton with a damper to assist level-ground and downhill gait, achieving a significant reduction in normalized knee load peak value by for level-ground and by for downhill walking, along with a decrease in the cost of transport. The results indicate that the optimal device applies damping torques to the knee joint during the Stance phase of both movement scenarios, with different optimal damping coefficients. The optimization framework also demonstrates its capability to reliably and efficiently identify the optimal solution. It offers valuable insight for the initial design of assistive wearable devices and supports designers in efficiently determining the optimal parameter set.

Keywords: biomechanics; design; exoskeletons; human motor control; optimisation.

Figure 1.

Overview of the optimization framework for designing assistive wearable devices. The inner loop, implemented in the SCONE software, solves the predictive simulation of movement and includes the device and neuromuscular models and controllers, a cost function, and the CMA-ES optimizer for optimizing the neuromuscular controller parameters. The outer loop, implemented in Python, employs a Bayesian optimizer to identify the optimal design parameters of the assistive device by minimizing a cost function derived from the inner loop’s simulation results.

Figure 2.

Illustration of the gait cycle divided into five phases based on SCONE definitions Scone Software (2024): Early Stance, Late Stance, Lift Off, Swing, and Landing. Each phase is depicted by a still photo of the neuromuscular model at the onset of the corresponding phase. The knee exoskeleton structure, adapted from a previously developed design (Mahmoudi et al., 2025), is integrated into the neuromuscular model. Unlike the original design, which featured a Pneumatic Artificial Muscle (PAM) as its actuator, this exoskeleton incorporates a damper and clutch mechanism at the knee joint. The damper, highlighted in the figure, applies resistive torques during specific gait phases.

Figure 3.

Kinematics and kinetics results of predictive simulation of baseline conditions (movement without exoskeleton) in level-ground (dashed black line) and downhill slope (solid blue line) gait. The results are normalized for each gait cycle (from touchdown of the right leg to the next touchdown of the same leg) and averaged over the gait cycles of one full movement for each condition. The shaded area around each curve indicates the standard deviation values. Stance and Swing phases are separated by the respective vertical lines, indicating the Toe Off events.

Figure 4.

(a) Heat-map of the cost function values for the knee exoskeleton design in level-ground and downhill ( ) gait. The design space comprises the damping coefficient ( ) of the linear knee damper and the clutch mechanism that determines damper engagement across the five gait phases: Early Stance (ES), Late Stance (LS), Lift Off (LO), Swing (SW), and Landing (LN). The cost function, combining knee load and estimated cost of transport, is calculated for 1271 simulated design configurations, covering the entire design space. Green diamonds represent the iterations explored by the optimizer from the best of five optimization runs and blue diamonds indicate their optimal solutions. Purple diamonds mark the best solutions from the brute-force search of the entire design space. The best solution of the optimizer and the brute-force search in the downhill gait condition are the same. (b) The exploration order of the optimizer in each movement scenario. The abbreviations, shapes, and colors of indicated points are consistent with the heat-map.

Figure 5.

The median, 25th and 75th percentiles, maximum, minimum, and the kernel density estimate of the cost function values for the optimal results of multiple implementations of the optimization platform for the level-ground (first two graphs on the left side) and downhill (first two graphs on the right side) gait scenarios. The five runs of the optimizer used for the design of the device are also presented separately from the 20 runs used for investigation of the optimization platform’s performance.

Figure 6.

Knee kinematics, kinetics, and the metabolic cost of movement for the assisted scenario with the optimal knee exoskeleton design (solid blue lines) compared to the baseline condition without an exoskeleton (dashed black lines). The red dashed lines show the contribution of the exoskeleton joint. The results are normalized for each gait cycle (between two sequential touchdowns of the right leg) and averaged over all gait cycles of the entire movement for each condition. The shaded area around the lines indicates the standard deviation values. The Stance and Swing phases are separated by the respective vertical lines indicating the Toe Off event. The shaded blue area highlights the damper engagement phases.

Figure 7.

Normalized Muscle Tendon Unit (MTU) forces in the (a) level-ground, and (b) downhill slope gait, for the optimal knee exoskeleton design (solid blue lines) compared to the baseline condition, when the movement is simulated without an exoskeleton (dashed black lines). The results are normalized in each gait cycle (from touchdown of the right leg to the next touchdown of the same leg) and averaged over the gait cycles of one movement for each condition. The shaded area around the graphs illustrates the standard deviations. The Stance and Swing phases are separated by the respective vertical lines indicating the Toe-off events. The shaded area indicates the phases of the gait in which the damper is engaged.