Designing the ideal soft gripper for diverse functionalities

Figure 1: Emulation of a wine-pouring scenario using a robotic arm and a soft gripper. The vacuum-actuated hybrid soft gripper comprises two main components: soft fingers and a palm (Subramaniam et al., 2020). The soft fingers employ a multi-material design with stiff wedges encapsulated by a softer, thin skin. Vacuum actuation induces finger bending as the thin skin collapses between the wedges. The soft gripper palm shares a similar multi-material design, using vacuum actuation to collapse thin skin between stiffer wedges. This active palm enhances the gripper’s payload capacity while offering precise aperture control. The gripper prototype evolved from this baseline design to meet specifications and address the challenges presented in each competition. The design table summarizes the design features added to the gripper depending on tasks that could be handled (Table 2).
Credit: SUTD

Robotic automation has become a game-changer in addressing labour shortages. While traditional rigid grippers have effectively automated various routine tasks, boosting efficiency and productivity in industries that deal with objects of well-defined specifications, they fall short in sectors like the food industry, where delicate objects of varying sizes and shapes need to be handled. In these cases, a more specialised type of gripper is required.

“Bioinspired soft robotics seeks to develop technologies that draw inspiration from nature and leverage advanced materials and fabrication processes,” said Dr Pablo Valdivia y Alvarado, Associate Professor at the Singapore University of Technology and Design (SUTD). Soft grippers inspired by the natural dexterity and control of human hands are particularly well-suited for the food industry. They can adapt to objects of varying sizes and shapes while distributing forces more evenly, making them ideal for handling delicate items.

Image 1
Figure 2: RoboSoft Layouts: (A) Layout of RoboSoft 2021 with four tasks of lifting a heavy, smooth-skinned fruit – watermelon, handling a small, delicate fruit – berry, picking up a coin on a hard surface, inserting the coin into the coin slot; (B) Gripper used in RoboSoft 2021 consisting of active palm for aperture control, suction cup for increased payload capacity and nails at fingertips for flat items; (C) Layout of RoboSoft 2022 for sorting items in Subspace A to Subspace B with three tasks of picking of three objects (grape, coke can, marshmallow) from Subspace A and placing them in a collecting basket in Subspace B; picking of two plant pots from Subspace A and placing them on two shelves in Subspace B; picking a wine bottle from Subspace A and pouring a dram of liquid into the glass in Subspace B along with picking up the glass and placing it on a coaster after safely placing the bottle back on the table; (D) Gripper used in RoboSoft 2022 consisting of 3D printed rigid palm with fixed aperture to avoid vibrations and spillage while handling wine and a suction cup for stable grasps; (E) Layout of RoboSoft 2023 with the task of assembling two food trays by picking the food items on shelves and bottle of orange juice from a source table to specific containers on the trays kept on an assembly table; (F) Gripper used in RoboSoft 2023 consisting of smaller fingers and active palm for fitting into limited shelf space, sensors integrated at finger tips for force control and slip detection and a hook shaped nail for scooping noodles. Credit: SUTD

Various competitions are organised to test and challenge the capabilities of soft grippers in performing real-world tasks. A leading event in this field is the annual IEEE RoboSoft Manipulation Competition, where Associate Professor Valdivia y Alvarado and his team secured the grand prize in both 2022 and 2023. In their paper “Applications of a vacuum-actuated multi-material hybrid soft gripper: lessons learnt from RoboSoft manipulation challenge” published in Frontiers in Robotics and AI, they share valuable insights and lessons from their participation in these competitions.

The group’s baseline gripper design was pivotal, providing a solid foundation for subsequent refinements. Given that certain competition details were often disclosed at the last minute, versatility was essential. The team chose a three-finger gripper design, capable of adapting to a wide variety of shapes and grasping modes.

In crafting the prototype, Assoc Prof Valdivia y Alvarado and his group prioritised materials that were durable, resistant to wear and tear, food- and skin-safe, and highly elastic, ensuring the gripper could effortlessly conform to different objects. Rather than using the more common positive pressure-based actuation, the team opted for vacuum actuation to avoid the inherent risk of pressure overload associated with positive pressure systems.

The team’s vacuum-actuated hybrid soft gripper was designed with two key components: soft composite fingers and a palm. The fingers, inspired by human anatomy, featured stiff wedges covered in a soft, thin skin. When activated by vacuum, the skin collapses, causing the fingers to bend and grasp objects. The palm, similarly designed, enhanced the gripper’s weight capacity and control.

This robust baseline design allowed for additional features and capabilities in later iterations. Associate Professor Valdivia y Alvarado highlighted the gripper’s wide grasping potential compared to other soft grippers. The team further enhanced the design by adding a suction cup to increase payload capacity and a curved nail that functions as a hook. This adaptability to specific competition challenges was crucial to their success in the RoboSoft competitions.

When reflecting on key lessons from the experience, Associate Professor Valdivia y Alvarado emphasised the importance of foresight and versatility. He stressed the value of opting for simpler, more efficient solutions over complex engineering that may slow down processing time. Additionally, he highlighted the need for a versatile and modular design, allowing for regular updates as competition details emerged. Adaptability was crucial.

The RoboSoft competition scenarios, grounded in real-world applications, demonstrated the potential of the team’s vacuum-actuated hybrid soft gripper for tasks such as food handling, high-mix packaging, waste segregation, and urban farming. With two technology commercialisation grants already secured, the team is advancing product development and pilot testing.

This project exemplifies SUTD’s approach of integrating design and technology in research. The gripper, which earned the prestigious Iron A’ Design Award, was designed to accommodate diverse functionalities across various industries. Associate Professor Valdivia y Alvarado noted that their methodology of incorporating constant industry feedback ensures that research remains relevant, facilitating the transition from lab prototypes to commercial products ready for end users.

Journal: Frontiers in Robotics and AI
DOI: 10.3389/frobt.2024.1356692

Media Contact

Melissa Koh
Singapore University of Technology and Design
melissa_koh@sutd.edu.sg
Office: 65-649-98742

www.sutd.edu.sg

Media Contact

Melissa Koh
Singapore University of Technology and Design

All latest news from the category: Materials Sciences

Materials management deals with the research, development, manufacturing and processing of raw and industrial materials. Key aspects here are biological and medical issues, which play an increasingly important role in this field.

innovations-report offers in-depth articles related to the development and application of materials and the structure and properties of new materials.

Back to home

Comments (0)

Write a comment

Newest articles

First-of-its-kind study uses remote sensing to monitor plastic debris in rivers and lakes

Remote sensing creates a cost-effective solution to monitoring plastic pollution. A first-of-its-kind study from researchers at the University of Minnesota Twin Cities shows how remote sensing can help monitor and…

Laser-based artificial neuron mimics nerve cell functions at lightning speed

With a processing speed a billion times faster than nature, chip-based laser neuron could help advance AI tasks such as pattern recognition and sequence prediction. Researchers have developed a laser-based…

Optimising the processing of plastic waste

Just one look in the yellow bin reveals a colourful jumble of different types of plastic. However, the purer and more uniform plastic waste is, the easier it is to…