Soft robotic grippers designed for general use by diverse task optimization
Graph-Based Design of Soft Grippers with Multi-Objective Quality-Diversity Optimisation
Robotics
Summary
Picking up different types of objects is hard for robots because each object might need a special kind of grab. The authors propose a way to design soft robot hands that can handle many things by using a clever graph-based structure and searching for many good designs at once. By testing these designs on a variety of grasping tasks, the designs become better at handling new objects they have not seen before. This helps make soft robotic hands more adaptable and useful across lots of jobs without needing to redesign for each task.
What this means in practice
- •For robotics engineers: Create soft robotic grippers that work well on a wide variety of objects by optimizing designs across diverse grasping tasks.
- •For agricultural automation teams: Implement robust soft grippers that adapt to different crops and shapes without redesign, improving harvest automation reliability.
Authors
Andre Farinha, Ge Shi, Harry Bowman, Brendan Tidd, David Howard, Josh Pinskier
Abstract
Effective manipulation across diverse objects is critical for applications ranging from agricultural harvesting to laboratory and domestic automation. While the inherent compliance of soft robotics is well suited to this challenge, designing grippers that generalize across tasks remains difficult due to the vast design space of continuum mechanics and the risk of overfitting to specific scenarios. We propose a graph-based design space for representing soft structures and mechanisms, coupled with a multi-objective, diversity-driven genetic optimization framework that explicitly promotes solution variety throughout the design process. Using multiple grasping scenarios during optimization, we study how task diversity influences the emergence of generalization to unseen objects and contact conditions. Our results show that optimization over a sufficiently diverse set of grasping cases leads to designs with emergent generalization, exhibiting improved robustness compared to task-specific solutions on novel scenarios. These findings suggest that diversity-driven optimization offers a principled pathway toward general-purpose soft grippers, aligned with the adaptable nature of soft robotics.