MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has launched a new platform for testing and developing soft robots in a range of environments.

The team said the platform, Softzoo, is a “bio-inspired” tool for engineers to optimize robotic design.

Using 3D-renderings of animals such as pandas, bears, fish and caterpillars, Softzoo provides customizable simulations of different bodies, adaptable to meet a variety of tasks. The designs are then digitally tested in different terrains to find the best body for each use case.

“Our framework can help users find the best configuration for a robot’s shape, allowing them to design soft robotics algorithms that can do many different things,” said Tsun-Hsuan Wang, lead researcher of the project. “In essence, it helps us understand the best strategies for robots to interact with their environments, inspiring researchers to develop new breeds of soft robots.”

The platform was designed to accelerate the development time for robots, allowing researchers to run multiple simulations at once and rapidly optimize design.

Softzoo also looks to develop a robot’s situational and environmental awareness, aligning its “brain and body” simultaneously.

“This computational approach to co-designing the soft robot bodies and their brains (that is, their controllers) opens the door to rapidly creating customized machines that are designed for a specific task,” said Daniela Rus, MIT CSAIL director.

A remaining challenge is translating the simulated soft robots to life, with the fabrication and testing process still a time and cost consuming effort.

“Transferring from simulation to physical robot remains unsolved and requires further study,” said Wang. “The muscle models, spatially varying stiffness, and sensorization in Softzoo cannot be straightforwardly realized with current fabrication techniques, so we are working on these challenges.”