Researchers’ algorithm designs soft robots that sense

MIT News  March 22, 2021
Unlike rigid robots which operate with compact degrees of freedom, soft robots must reason about an infinite dimensional state space. This continuum state space presents
significant challenges when working with a finite set of discrete sensors. Sensor location has a profound downstream impact on the richness of learned models for robotic tasks. Researchers at MIT present a novel representation for co-learning sensor placement and complex tasks. They developed a neural architecture which processes on-board sensor information to learn a salient and sparse selection of placements for optimal task performance. They evaluated their model and learning algorithm on six soft robot morphologies for various supervised learning tasks, including tactile sensing and proprioception. Their method demonstrates superior performance in task learning to algorithmic and human baselines while also learning sensor placements and latent spaces that are semantically meaningful. Video…read more. Open Access TECHNICAL ARTICLE