Multi-objective Generative Design Framework and Realization for Quasi-serial Manipulator: Considering Kinematic and Dynamic Performance

TL;DR

The paper tackles task-based design of a quasi-serial manipulator by jointly optimizing its kinematic workspace $η$ and dynamic joint torques $τ_1$, $τ_2$. It introduces a four-stage framework that generates a large pool of 4-bar mechanisms, trains an MLP surrogate to predict $η$, $τ_1$, and $τ_2$, and applies NSGA-II to obtain Pareto-optimal designs under crank-rocker and other constraints, aided by topology optimization and 3D-printed realization. Design-rule extraction using Sobol sensitivity, decision trees, and correlation analysis yields practical guidance for initial design and rapid exploration. The results demonstrate feasibility for real-world applications, showing substantial gains in design efficiency and providing a validated path from concept to payload-tested realization.

Abstract

This paper proposes a framework that optimizes the linkage mechanism of the quasi-serial manipulator for target tasks. This process is explained through a case study of 2-degree-of-freedom linkage mechanisms, which significantly affect the workspace of the quasi-serial manipulator. First, a vast quasi-serial mechanism is generated with a workspace satisfying a target task and it converts it into a 3D CAD model. Then, the workspace and required torque performance of each mechanism are evaluated through kinematic and dynamic analysis. A deep learning-based surrogate model is leveraged to efficiently predict mechanisms and performance during the optimization process. After model training, a multi-objective optimization problem is formulated under the mechanical and dynamic conditions of the manipulator. The design goal of the manipulator is to recommend quasi-serial mechanisms with optimized kinematic (workspace) and dynamic (joint torque) performance that satisfies the target task. To investigate the underlying physics from the obtained Pareto solutions, various data mining techniques are performed to extract design rules that can provide practical design guidance. Finally, the manipulator was designed in detail for realization with 3D printed parts, including topology optimization. Also, the task-based optimized manipulator is verified through a payload test. Based on these results, the proposed framework has the potential for other real applications as realized cases and provides a reasonable design plan through the design rule extraction.

Figures (15)

• Figure 1: Multi-objective generative mechanism design framework
• Figure 2: Example of target task
• Figure 3: Quasi-serial manipulator generation process
• Figure 4: Dynamic simulation automation process
• Figure 5: Validation of MLP model using test data: ground truth as x-axis and prediction of MLP as y-axis