Leveraging Geometric Modeling-Based Computer Vision for Context Aware Control in a Hip Exosuit

Abstract

Human beings adapt their motor patterns in response to their surroundings, utilizing sensory modalities such as visual inputs. This context-informed adaptive motor behavior has increased interest in integrating computer vision algorithms into robotic assistive technologies, marking a shift towards <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">context aware control</i>. However, such integration has rarely been achieved so far, with current methods mostly relying on data-driven approaches. In this study, we introduce a novel control framework for a soft hip exosuit, employing instead a physics-informed computer vision method grounded on geometric modeling of the captured scene for assistance tuning during stairs and level walking. This approach promises to provide a viable solution that is more computationally efficient and does not depend on training examples. Evaluating the controller with six subjects on a path comprising level walking and stairs, we achieved an overall detection accuracy of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$93.0\pm 1.1\%$</tex-math></inline-formula>. Computer vision-based assistance provided significantly greater metabolic benefits compared to non-vision-based assistance, with larger energy reductions relative to being unassisted during stair ascent (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$-18.9 \pm 4.1\%$</tex-math></inline-formula> vs. <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$-5.2 \pm 4.1\%$</tex-math></inline-formula>) and descent (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$-10.1 \pm 3.6\%$</tex-math></inline-formula> vs. <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$-4.7 \pm 4.8\%$</tex-math></inline-formula>). Such a result is a consequence of the adaptive nature of the device, enabled by the context aware controller, that allowed for more effective walking support: i.e. the assistive torque showed a significant increase while ascending stairs (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$+33.9\pm 8.8\%$</tex-math></inline-formula>) and decrease while descending stairs (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$-17.4\pm 6.0\%$</tex-math></inline-formula>) compared to a condition without assistance modulation enabled by vision. These results highlight the potential of the approach, promoting effective real-time embedded applications in assistive robotics.