Deep Learning Conceptual Design of Sit-to-Stand Parallel Motion Six-Bar Mechanisms

Abstract

The Sit-to-Stand (STS) motion is a crucial activity in the daily lives of individuals, and its impairment can significantly impact independence and mobility, particularly among disabled individuals. Addressing this challenge necessitates the design of mobility assist devices that can simultaneously satisfy multiple conflicting constraints. The effective design of such devices often involves the generation of numerous conceptual mechanism designs. This paper introduces an innovative single degree-of-freedom (DOF) mechanism synthesis process for developing a highly customizable Sit-to-Stand (STS) mechanical device by integrating rigid body kinematics with machine learning. Unlike traditional mechanism synthesis approaches that primarily focus on limited functional requirements, such as path or motion generation, our proposed design pipeline efficiently generates a large number of one-DOF mechanism geometries and their corresponding motion paths, known as coupler curves. Leveraging a generative Deep Neural Network (DNN), we establish a probabilistic distribution of coupler curves and their mapping to mechanism parameters. Additionally, we introduce novel metrics for quantitatively evaluating and prioritizing design concepts. The methodology yields a diverse set of viable conceptual design solutions that adhere to the specified constraints. We showcase various single-degree-of-freedom six-bar linkage mechanisms designed for STS motion, presenting them in a ranked order based on established criteria. While the primary focus is on the integration of STS motion into a versatile mobility assist device, the proposed approach holds broad applicability for addressing design challenges in various applications.