Key points are not available for this paper at this time.
When a specific, relatively simple motion must be executed with high precision and high speed, simple mechanisms like the four-bar linkage are often the first choice. Combined with control of the crank speed, these systems are able to move the end-effector with any changing speed. Designing a certain mechanism for a pre-defined trajectory, however, usually requires an expert, which is why automatic design by a design assistant system is desirable. Modern AI methods may support such an automatic design, which shall function only based on hand drawings of the desired path and a corresponding velocity profile. For a planar four-bar mechanism, which serves only as an example, this article proposes a general data-driven procedure where first the geometry of a mechanism is synthesized by machine learning such that the track point follows approximately the desired trajectory. Then, the kinematic relation between the track point’s velocity profile and the crank’s angular velocity is learned. This learned inverse kinematics model may be applied to an arbitrary user-defined velocity profile of the track point. Finally, a controller governing the crank torque is designed purely based on data to track the resulting angular crank velocity. Not every drawn motion can necessarily be realized with a mechanism; however, the goal is to identify a mechanism that approximates the drawn curve as accurately as possible. While various design toolboxes already exist, especially for the design of four-bar linkages, this article presents a design pipeline using data-driven approaches that solely learn from forward simulation data. This nurtures the hope that presented approach is also applicable to more complex systems where analytic formulations cannot be easily derived.
Röder et al. (Mon,) studied this question.