Researchers from the Massachusetts Institute of Technology (MIT) have developed a deep learning neural network that mainly aims to aid soft-bodied robots' design. Soft-bodied robots like iterations of robotic elephants can easily interact with people more safely or can slip into tight spaces with ease. But their programmed duties are a critical part that needs fine detailing, crucial data, and a logical, algorithmic base.
Keeping the things mentioned above in mind, MIT researchers have developed an algorithm that will help engineers design soft robots precisely to collect more helpful information about their surroundings. The deep-learning algorithm will suggest an optimized placement of sensors within the robot itself, which will allow the engineers to model them in a better way to interact with its environment and complete assigned tasks.
The researchers have stated that the research work will be presented during April's IEEE international conference on soft robotics. The data will be published in the journal IEEE Robotics and Automation Letters. The research also includes novel neural network architecture that will optimize the sensor placement and allows the robot to complete its task efficiently. At the same time, the network will keep track of particles used to complete the task.