![[2506.00494] Multi-Objective Neural Network-Assisted Design Optimization of Soft Fin-Ray Fingers for Enhanced Grasping Performance](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2506.00494] Multi-Objective Neural Network-Assisted Design Optimization of Soft Fin-Ray Fingers for Enhanced Grasping Performance
Summary
This article presents a multi-objective optimization approach using neural networks to enhance the design of soft Fin-Ray fingers for improved grasping performance.
Why It Matters
The research addresses the challenge of balancing rigidity and delicacy in soft robotic grippers, which is crucial for applications in automation and robotics. By optimizing design parameters, the study contributes to advancements in robotic manipulation, potentially impacting industries such as manufacturing and healthcare.
Key Takeaways
- The internal structure of Fin-Ray fingers significantly affects their grasping capabilities.
- A dataset of 120 simulations was created to model grasp force and deformation behavior.
- The study employs a multilayer perceptron to predict contact force and tip displacement.
- The optimization process reveals a trade-off between force exertion and delicate handling.
- Results indicate that the proposed methodology can enhance the design of soft grippers for varied applications.
Computer Science > Robotics arXiv:2506.00494 (cs) [Submitted on 31 May 2025 (v1), last revised 15 Feb 2026 (this version, v2)] Title:Multi-Objective Neural Network-Assisted Design Optimization of Soft Fin-Ray Fingers for Enhanced Grasping Performance Authors:Ali Ghanizadeh, Ali Ahmadi, Arash Bahrami View a PDF of the paper titled Multi-Objective Neural Network-Assisted Design Optimization of Soft Fin-Ray Fingers for Enhanced Grasping Performance, by Ali Ghanizadeh and 2 other authors View PDF HTML (experimental) Abstract:The internal structure of the Fin-Ray fingers plays a significant role in their adaptability and grasping performance. However, modeling the grasp force and deformation behavior for design purposes is challenging. When the Fin-Ray finger becomes more rigid and capable of exerting higher forces, it becomes less delicate in handling objects. The contrast between these two gives rise to a multi-objective optimization problem. We employ the finite element method to estimate the deflections and contact forces of the Fin-Ray fingers grasping cylindrical objects, generating a dataset of 120 simulations. This dataset includes three input variables: the thickness of the front and support beams, the thickness of the crossbeams, and the equal spacing between the crossbeams, which are the design variables in the optimization. This dataset is then used to construct a multilayer perceptron (MLP) with four output neurons predicting the contact force and tip displacement ...
